From 89fc77a0017ff14131f5a4871eeeadb1c8f81e16 Mon Sep 17 00:00:00 2001 From: Aaron W Chen Date: Wed, 8 May 2024 10:18:47 -0700 Subject: [PATCH] Close out open notebooks, update old NLTK code --- .gitconfig | 11 + nbs/01_initial_eda.ipynb | 8 +- nbs/04_word_lists_combine_features.ipynb | 5 + nbs/07_bertopic_testing.ipynb | 47 +- nbs/11_sklearn_mlfow_model_testing.ipynb | 151 +- nbs/13_new_preproc_test.ipynb | 2486 +++++++++++++++++++++- src/nltk/dish_predictor.py | 485 +++-- src/nltk/ohe_dish_predictor.py | 491 +++-- src/nltk/prepare_ohe_database.py | 179 +- 9 files changed, 3106 insertions(+), 757 deletions(-) create mode 100644 .gitconfig diff --git a/.gitconfig b/.gitconfig new file mode 100644 index 0000000..9054574 --- /dev/null +++ b/.gitconfig @@ -0,0 +1,11 @@ +# Generated by nbdev_install_hooks +# +# If you need to disable this instrumentation do: +# git config --local --unset include.path +# +# To restore: +# git config --local include.path ../.gitconfig +# +[merge "nbdev-merge"] + name = resolve conflicts with nbdev_fix + driver = nbdev_merge %O %A %B %P diff --git a/nbs/01_initial_eda.ipynb b/nbs/01_initial_eda.ipynb index df28015..620ee2c 100644 --- a/nbs/01_initial_eda.ipynb +++ b/nbs/01_initial_eda.ipynb @@ -3059,7 +3059,13 @@ "source": [] } ], - "metadata": {}, + "metadata": { + "kernelspec": { + "display_name": "python3", + "language": "python", + "name": "python3" + } + }, "nbformat": 4, "nbformat_minor": 2 } diff --git a/nbs/04_word_lists_combine_features.ipynb b/nbs/04_word_lists_combine_features.ipynb index eacce42..e4cbfb9 100644 --- a/nbs/04_word_lists_combine_features.ipynb +++ b/nbs/04_word_lists_combine_features.ipynb @@ -1547,6 +1547,11 @@ "filtered_df.head()" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + }, { "cell_type": "markdown", "metadata": {}, diff --git a/nbs/07_bertopic_testing.ipynb b/nbs/07_bertopic_testing.ipynb index 58ea557..505f9ab 100644 --- a/nbs/07_bertopic_testing.ipynb +++ b/nbs/07_bertopic_testing.ipynb @@ -132,54 +132,13 @@ "metadata": {}, "outputs": [ { - "data": { - "text/html": [ - "
                                       ❗❗❗ AUTHORIZATION REQUIRED ❗❗❗                                        \n",
-       "
\n" - ], - "text/plain": [ - " \u001b[1m❗❗❗ AUTHORIZATION REQUIRED ❗❗❗\u001b[0m \n" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "084490be36a047529096776bcb49e6de", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "Output()" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", + "name": "stderr", "output_type": "stream", "text": [ - "\n", - "\n", - "Open the following link in your browser to authorize the client:\n", - "https://dagshub.com/login/oauth/authorize?state=1bf46b97-13cb-4873-9c57-af8141828675&client_id=32b60ba385aa7cecf24046d8195a71c07dd345d9657977863b52e7748e0f0f28&middleman_request_id=b534b316020d1f4e499a4a24567fc8ff36a49714fc1a4e01f004354ef9e20587\n", - "\n", - "\n" + "Token Dagshub OAuth token, valid until 2023-03-15 05:42:01.541960+00:00 does not exist in the storage\n", + "Token Dagshub OAuth token, valid until 2023-07-27 17:31:38.987842+00:00 does not exist in the storage\n" ] }, - { - "data": { - "text/html": [ - "
\n"
-      ],
-      "text/plain": []
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
     {
      "data": {
       "text/html": [
diff --git a/nbs/11_sklearn_mlfow_model_testing.ipynb b/nbs/11_sklearn_mlfow_model_testing.ipynb
index 85645c8..b6393e6 100644
--- a/nbs/11_sklearn_mlfow_model_testing.ipynb
+++ b/nbs/11_sklearn_mlfow_model_testing.ipynb
@@ -242,149 +242,14 @@
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5c7f9ca7c04d4d61a1d93d784e67a1e8",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.6.0.json:   0%|   …"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-13 11:12:24 INFO: Downloading default packages for language: en (English) ...\n",
-      "2024-02-13 11:12:24 INFO: File exists: /home/awchen/stanza_resources/en/default.zip\n",
-      "2024-02-13 11:12:27 INFO: Finished downloading models and saved to /home/awchen/stanza_resources.\n",
-      "2024-02-13 11:12:27 INFO: Checking for updates to resources.json in case models have been updated.  Note: this behavior can be turned off with download_method=None or download_method=DownloadMethod.REUSE_RESOURCES\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "341eed1075774bfaa7c7873d53723222",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.6.0.json:   0%|   …"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-13 11:12:28 INFO: Loading these models for language: en (English):\n",
-      "======================================\n",
-      "| Processor    | Package             |\n",
-      "--------------------------------------\n",
-      "| tokenize     | combined            |\n",
-      "| pos          | combined_charlm     |\n",
-      "| lemma        | combined_nocharlm   |\n",
-      "| constituency | ptb3-revised_charlm |\n",
-      "| depparse     | combined_charlm     |\n",
-      "| sentiment    | sstplus             |\n",
-      "| ner          | ontonotes_charlm    |\n",
-      "======================================\n",
-      "\n",
-      "2024-02-13 11:12:28 INFO: Using device: cpu\n",
-      "2024-02-13 11:12:28 INFO: Loading: tokenize\n",
-      "2024-02-13 11:12:28 INFO: Loading: pos\n",
-      "2024-02-13 11:12:28 INFO: Loading: lemma\n",
-      "2024-02-13 11:12:29 INFO: Loading: constituency\n",
-      "2024-02-13 11:12:29 INFO: Loading: depparse\n",
-      "2024-02-13 11:12:29 INFO: Loading: sentiment\n",
-      "2024-02-13 11:12:29 INFO: Loading: ner\n",
-      "2024-02-13 11:12:29 INFO: Done loading processors!\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "--------------\n",
-      "Raw Dataframe:\n",
-      "                         id  \\\n",
-      "0  54a2b6b019925f464b373351   \n",
-      "1  54a408a019925f464b3733bc   \n",
-      "2  54a408a26529d92b2c003631   \n",
-      "3  54a408a66529d92b2c003638   \n",
-      "4  54a408a719925f464b3733cc   \n",
-      "\n",
-      "                                                 dek  \\\n",
-      "0  How does fried chicken achieve No. 1 status? B...   \n",
-      "1                                Spinaci all'Ebraica   \n",
-      "2  This majestic, moist, and richly spiced honey ...   \n",
-      "3  The idea for this sandwich came to me when my ...   \n",
-      "4  In 1930, Simon Agranat, the chief justice of t...   \n",
-      "\n",
-      "                                     hed                   pubDate  \\\n",
-      "0            Pickle-Brined Fried Chicken  2014-08-19T04:00:00.000Z   \n",
-      "1                   Spinach Jewish Style  2008-09-09T04:00:00.000Z   \n",
-      "2                  New Year’s Honey Cake  2008-09-10T04:00:00.000Z   \n",
-      "3  The B.L.A.—Bagel with Lox and Avocado  2008-09-08T04:00:00.000Z   \n",
-      "4        Shakshuka a la Doktor Shakshuka  2008-09-09T04:00:00.000Z   \n",
-      "\n",
-      "                             author    type  \\\n",
-      "0                                []  recipe   \n",
-      "1  [{'name': 'Edda Servi Machlin'}]  recipe   \n",
-      "2       [{'name': 'Marcy Goldman'}]  recipe   \n",
-      "3           [{'name': 'Faye Levy'}]  recipe   \n",
-      "4         [{'name': 'Joan Nathan'}]  recipe   \n",
-      "\n",
-      "                                                 url  \\\n",
-      "0  /recipes/food/views/pickle-brined-fried-chicke...   \n",
-      "1    /recipes/food/views/spinach-jewish-style-350152   \n",
-      "2  /recipes/food/views/majestic-and-moist-new-yea...   \n",
-      "3  /recipes/food/views/the-b-l-a-bagel-with-lox-a...   \n",
-      "4  /recipes/food/views/shakshuka-a-la-doktor-shak...   \n",
-      "\n",
-      "                                           photoData  \\\n",
-      "0  {'id': '54a2b64a6529d92b2c003409', 'filename':...   \n",
-      "1  {'id': '56746182accb4c9831e45e0a', 'filename':...   \n",
-      "2  {'id': '55e85ba4cf90d6663f728014', 'filename':...   \n",
-      "3  {'id': '5674617e47d1a28026045e4f', 'filename':...   \n",
-      "4  {'id': '56746183b47c050a284a4e15', 'filename':...   \n",
-      "\n",
-      "                                                 tag  aggregateRating  \\\n",
-      "0  {'category': 'ingredient', 'name': 'Chicken', ...             3.11   \n",
-      "1  {'category': 'cuisine', 'name': 'Italian', 'ur...             3.22   \n",
-      "2  {'category': 'cuisine', 'name': 'Jewish', 'url...             3.62   \n",
-      "3  {'category': 'cuisine', 'name': 'Jewish', 'url...             4.00   \n",
-      "4  {'category': 'cuisine', 'name': 'Jewish', 'url...             2.71   \n",
-      "\n",
-      "                                         ingredients  \\\n",
-      "0  [1 tablespoons yellow mustard seeds, 1 tablesp...   \n",
-      "1  [3 pounds small-leaved bulk spinach, Salt, 1/2...   \n",
-      "2  [3 1/2 cups all-purpose flour, 1 tablespoon ba...   \n",
-      "3  [1 small ripe avocado, preferably Hass (see No...   \n",
-      "4  [2 pounds fresh tomatoes, unpeeled and cut in ...   \n",
-      "\n",
-      "                                           prepSteps  reviewsCount  \\\n",
-      "0  [Toast mustard and coriander seeds in a dry me...             7   \n",
-      "1  [Remove the stems and roots from the spinach. ...             5   \n",
-      "2  [I like this cake best baked in a 9-inch angel...           105   \n",
-      "3  [A short time before serving, mash avocado and...             7   \n",
-      "4  [1. Place the tomatoes, garlic, salt, paprika,...             7   \n",
-      "\n",
-      "   willMakeAgainPct  dateCrawled  \n",
-      "0               100   1498547035  \n",
-      "1                80   1498547740  \n",
-      "2                88   1498547738  \n",
-      "3               100   1498547740  \n",
-      "4                83   1498547740  \n",
-      "(34756, 15)\n"
+     "ename": "NameError",
+     "evalue": "name 'stanza' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[1], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;66;03m# instantiate stanza pipeline\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m \u001b[43mstanza\u001b[49m\u001b[38;5;241m.\u001b[39mdownload(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124men\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m      3\u001b[0m nlp \u001b[38;5;241m=\u001b[39m stanza\u001b[38;5;241m.\u001b[39mPipeline(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124men\u001b[39m\u001b[38;5;124m'\u001b[39m, \n\u001b[1;32m      4\u001b[0m                     depparse_batch_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m50\u001b[39m, \n\u001b[1;32m      5\u001b[0m                     depparse_min_length_to_batch_separately\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m50\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m      8\u001b[0m                     batch_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m100\u001b[39m\n\u001b[1;32m      9\u001b[0m                     )\n\u001b[1;32m     11\u001b[0m \u001b[38;5;66;03m# load raw data and preprocess/clean\u001b[39;00m\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'stanza' is not defined"
      ]
     }
    ],
diff --git a/nbs/13_new_preproc_test.ipynb b/nbs/13_new_preproc_test.ipynb
index 9e207ff..7dea6f0 100644
--- a/nbs/13_new_preproc_test.ipynb
+++ b/nbs/13_new_preproc_test.ipynb
@@ -28,7 +28,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d7088c22cb4c4a2aa598d9fb700e8af0",
+       "model_id": "d85c6278f7234ed288c39189c62f316e",
        "version_major": 2,
        "version_minor": 0
       },
@@ -43,16 +43,16 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2024-03-27 20:57:40 INFO: Downloading default packages for language: en (English) ...\n",
-      "2024-03-27 20:57:41 INFO: File exists: /home/awchen/stanza_resources/en/default.zip\n",
-      "2024-03-27 20:57:44 INFO: Finished downloading models and saved to /home/awchen/stanza_resources.\n",
-      "2024-03-27 20:57:44 INFO: Checking for updates to resources.json in case models have been updated.  Note: this behavior can be turned off with download_method=None or download_method=DownloadMethod.REUSE_RESOURCES\n"
+      "2024-04-03 18:58:24 INFO: Downloading default packages for language: en (English) ...\n",
+      "2024-04-03 18:58:24 INFO: File exists: /home/awchen/stanza_resources/en/default.zip\n",
+      "2024-04-03 18:58:27 INFO: Finished downloading models and saved to /home/awchen/stanza_resources.\n",
+      "2024-04-03 18:58:27 INFO: Checking for updates to resources.json in case models have been updated.  Note: this behavior can be turned off with download_method=None or download_method=DownloadMethod.REUSE_RESOURCES\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f62ab630814a49449d6f0be2ac47e87e",
+       "model_id": "646c5253882946ff89f2460e06d236a4",
        "version_major": 2,
        "version_minor": 0
       },
@@ -67,7 +67,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2024-03-27 20:57:45 INFO: Loading these models for language: en (English):\n",
+      "2024-04-03 18:58:28 INFO: Loading these models for language: en (English):\n",
       "======================================\n",
       "| Processor    | Package             |\n",
       "--------------------------------------\n",
@@ -80,15 +80,15 @@
       "| ner          | ontonotes_charlm    |\n",
       "======================================\n",
       "\n",
-      "2024-03-27 20:57:45 INFO: Using device: cpu\n",
-      "2024-03-27 20:57:45 INFO: Loading: tokenize\n",
-      "2024-03-27 20:57:45 INFO: Loading: pos\n",
-      "2024-03-27 20:57:45 INFO: Loading: lemma\n",
-      "2024-03-27 20:57:45 INFO: Loading: constituency\n",
-      "2024-03-27 20:57:45 INFO: Loading: depparse\n",
-      "2024-03-27 20:57:45 INFO: Loading: sentiment\n",
-      "2024-03-27 20:57:46 INFO: Loading: ner\n",
-      "2024-03-27 20:57:46 INFO: Done loading processors!\n"
+      "2024-04-03 18:58:28 INFO: Using device: cpu\n",
+      "2024-04-03 18:58:28 INFO: Loading: tokenize\n",
+      "2024-04-03 18:58:28 INFO: Loading: pos\n",
+      "2024-04-03 18:58:28 INFO: Loading: lemma\n",
+      "2024-04-03 18:58:29 INFO: Loading: constituency\n",
+      "2024-04-03 18:58:29 INFO: Loading: depparse\n",
+      "2024-04-03 18:58:29 INFO: Loading: sentiment\n",
+      "2024-04-03 18:58:29 INFO: Loading: ner\n",
+      "2024-04-03 18:58:30 INFO: Done loading processors!\n"
      ]
     }
    ],
@@ -164,7 +164,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e03d339b07814cbc840d2f131a85f927",
+       "model_id": "7bd9eefff2a34d3dab46d8aa6564f18a",
        "version_major": 2,
        "version_minor": 0
       },
@@ -179,16 +179,16 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2024-03-27 20:57:46 INFO: Downloading default packages for language: en (English) ...\n",
-      "2024-03-27 20:57:47 INFO: File exists: /home/awchen/stanza_resources/en/default.zip\n",
-      "2024-03-27 20:57:50 INFO: Finished downloading models and saved to /home/awchen/stanza_resources.\n",
-      "2024-03-27 20:57:50 INFO: Checking for updates to resources.json in case models have been updated.  Note: this behavior can be turned off with download_method=None or download_method=DownloadMethod.REUSE_RESOURCES\n"
+      "2024-04-03 18:58:30 INFO: Downloading default packages for language: en (English) ...\n",
+      "2024-04-03 18:58:31 INFO: File exists: /home/awchen/stanza_resources/en/default.zip\n",
+      "2024-04-03 18:58:34 INFO: Finished downloading models and saved to /home/awchen/stanza_resources.\n",
+      "2024-04-03 18:58:34 INFO: Checking for updates to resources.json in case models have been updated.  Note: this behavior can be turned off with download_method=None or download_method=DownloadMethod.REUSE_RESOURCES\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c31d2969037c4ad1a79333ff34364488",
+       "model_id": "e2c669f0e57b433b9d1afce065617d0e",
        "version_major": 2,
        "version_minor": 0
       },
@@ -203,7 +203,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2024-03-27 20:57:51 INFO: Loading these models for language: en (English):\n",
+      "2024-04-03 18:58:35 INFO: Loading these models for language: en (English):\n",
       "======================================\n",
       "| Processor    | Package             |\n",
       "--------------------------------------\n",
@@ -216,15 +216,15 @@
       "| ner          | ontonotes_charlm    |\n",
       "======================================\n",
       "\n",
-      "2024-03-27 20:57:51 INFO: Using device: cuda\n",
-      "2024-03-27 20:57:51 INFO: Loading: tokenize\n",
-      "2024-03-27 20:57:54 INFO: Loading: pos\n",
-      "2024-03-27 20:57:54 INFO: Loading: lemma\n",
-      "2024-03-27 20:57:54 INFO: Loading: constituency\n",
-      "2024-03-27 20:57:54 INFO: Loading: depparse\n",
-      "2024-03-27 20:57:54 INFO: Loading: sentiment\n",
-      "2024-03-27 20:57:55 INFO: Loading: ner\n",
-      "2024-03-27 20:57:55 INFO: Done loading processors!\n"
+      "2024-04-03 18:58:35 INFO: Using device: cuda\n",
+      "2024-04-03 18:58:35 INFO: Loading: tokenize\n",
+      "2024-04-03 18:58:38 INFO: Loading: pos\n",
+      "2024-04-03 18:58:38 INFO: Loading: lemma\n",
+      "2024-04-03 18:58:38 INFO: Loading: constituency\n",
+      "2024-04-03 18:58:39 INFO: Loading: depparse\n",
+      "2024-04-03 18:58:39 INFO: Loading: sentiment\n",
+      "2024-04-03 18:58:39 INFO: Loading: ner\n",
+      "2024-04-03 18:58:40 INFO: Done loading processors!\n"
      ]
     }
    ],
@@ -244,7 +244,88 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "--------------\n",
+      "Raw Dataframe:\n",
+      "                         id  \\\n",
+      "0  54a2b6b019925f464b373351   \n",
+      "1  54a408a019925f464b3733bc   \n",
+      "2  54a408a26529d92b2c003631   \n",
+      "3  54a408a66529d92b2c003638   \n",
+      "4  54a408a719925f464b3733cc   \n",
+      "\n",
+      "                                                 dek  \\\n",
+      "0  How does fried chicken achieve No. 1 status? B...   \n",
+      "1                                Spinaci all'Ebraica   \n",
+      "2  This majestic, moist, and richly spiced honey ...   \n",
+      "3  The idea for this sandwich came to me when my ...   \n",
+      "4  In 1930, Simon Agranat, the chief justice of t...   \n",
+      "\n",
+      "                                     hed                   pubDate  \\\n",
+      "0            Pickle-Brined Fried Chicken  2014-08-19T04:00:00.000Z   \n",
+      "1                   Spinach Jewish Style  2008-09-09T04:00:00.000Z   \n",
+      "2                  New Year’s Honey Cake  2008-09-10T04:00:00.000Z   \n",
+      "3  The B.L.A.—Bagel with Lox and Avocado  2008-09-08T04:00:00.000Z   \n",
+      "4        Shakshuka a la Doktor Shakshuka  2008-09-09T04:00:00.000Z   \n",
+      "\n",
+      "                             author    type  \\\n",
+      "0                                []  recipe   \n",
+      "1  [{'name': 'Edda Servi Machlin'}]  recipe   \n",
+      "2       [{'name': 'Marcy Goldman'}]  recipe   \n",
+      "3           [{'name': 'Faye Levy'}]  recipe   \n",
+      "4         [{'name': 'Joan Nathan'}]  recipe   \n",
+      "\n",
+      "                                                 url  \\\n",
+      "0  /recipes/food/views/pickle-brined-fried-chicke...   \n",
+      "1    /recipes/food/views/spinach-jewish-style-350152   \n",
+      "2  /recipes/food/views/majestic-and-moist-new-yea...   \n",
+      "3  /recipes/food/views/the-b-l-a-bagel-with-lox-a...   \n",
+      "4  /recipes/food/views/shakshuka-a-la-doktor-shak...   \n",
+      "\n",
+      "                                           photoData  \\\n",
+      "0  {'id': '54a2b64a6529d92b2c003409', 'filename':...   \n",
+      "1  {'id': '56746182accb4c9831e45e0a', 'filename':...   \n",
+      "2  {'id': '55e85ba4cf90d6663f728014', 'filename':...   \n",
+      "3  {'id': '5674617e47d1a28026045e4f', 'filename':...   \n",
+      "4  {'id': '56746183b47c050a284a4e15', 'filename':...   \n",
+      "\n",
+      "                                                 tag  aggregateRating  \\\n",
+      "0  {'category': 'ingredient', 'name': 'Chicken', ...             3.11   \n",
+      "1  {'category': 'cuisine', 'name': 'Italian', 'ur...             3.22   \n",
+      "2  {'category': 'cuisine', 'name': 'Jewish', 'url...             3.62   \n",
+      "3  {'category': 'cuisine', 'name': 'Jewish', 'url...             4.00   \n",
+      "4  {'category': 'cuisine', 'name': 'Jewish', 'url...             2.71   \n",
+      "\n",
+      "                                         ingredients  \\\n",
+      "0  [1 tablespoons yellow mustard seeds, 1 tablesp...   \n",
+      "1  [3 pounds small-leaved bulk spinach, Salt, 1/2...   \n",
+      "2  [3 1/2 cups all-purpose flour, 1 tablespoon ba...   \n",
+      "3  [1 small ripe avocado, preferably Hass (see No...   \n",
+      "4  [2 pounds fresh tomatoes, unpeeled and cut in ...   \n",
+      "\n",
+      "                                           prepSteps  reviewsCount  \\\n",
+      "0  [Toast mustard and coriander seeds in a dry me...             7   \n",
+      "1  [Remove the stems and roots from the spinach. ...             5   \n",
+      "2  [I like this cake best baked in a 9-inch angel...           105   \n",
+      "3  [A short time before serving, mash avocado and...             7   \n",
+      "4  [1. Place the tomatoes, garlic, salt, paprika,...             7   \n",
+      "\n",
+      "   willMakeAgainPct  dateCrawled  \n",
+      "0               100   1498547035  \n",
+      "1                80   1498547740  \n",
+      "2                88   1498547738  \n",
+      "3               100   1498547740  \n",
+      "4                83   1498547740  \n",
+      "(34756, 15)\n"
+     ]
+    }
+   ],
    "source": [
     "# load raw data and preprocess/clean\n",
     "data = dvc.api.read(\n",
@@ -262,7 +343,114 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "--------------\n",
+      "Preprocessed Dataframe:\n",
+      "                                                                        dek  \\\n",
+      "id                                                                            \n",
+      "54a4270b19925f464b37c1dc                                                      \n",
+      "54a42cde19925f464b3809d2  Green chiles pickled in soy sauce and vinegar ...   \n",
+      "54a433036529d92b2c015de3  This soup features the flavors of India: aroma...   \n",
+      "54a451926529d92b2c01eda8                                                      \n",
+      "54a430876529d92b2c013e2b  Brown sugar and molasses are balanced by fresh...   \n",
+      "\n",
+      "                                                                        hed  \\\n",
+      "id                                                                            \n",
+      "54a4270b19925f464b37c1dc  Grilled Hearts of Romaine with Blue Cheese Vin...   \n",
+      "54a42cde19925f464b3809d2                              Soy-Pickled Jalapeños   \n",
+      "54a433036529d92b2c015de3  Curried Potato and Spinach Soup with Onion Sal...   \n",
+      "54a451926529d92b2c01eda8                                       Chicken Soup   \n",
+      "54a430876529d92b2c013e2b                           Sweet-Hot Barbecue Sauce   \n",
+      "\n",
+      "                          aggregateRating  \\\n",
+      "id                                          \n",
+      "54a4270b19925f464b37c1dc             3.64   \n",
+      "54a42cde19925f464b3809d2             3.43   \n",
+      "54a433036529d92b2c015de3             3.00   \n",
+      "54a451926529d92b2c01eda8             3.19   \n",
+      "54a430876529d92b2c013e2b             0.00   \n",
+      "\n",
+      "                                                                ingredients  \\\n",
+      "id                                                                            \n",
+      "54a4270b19925f464b37c1dc  [1 1/2 cups white wine vinegar, 1/2 cup sugar,...   \n",
+      "54a42cde19925f464b3809d2  [3 large fresh jalapeños (4 inches), sliced 1/...   \n",
+      "54a433036529d92b2c015de3  [4 cups chopped red onions (about 2 large), 1 ...   \n",
+      "54a451926529d92b2c01eda8  [1 pound chicken parts, 2 stalks celery, inclu...   \n",
+      "54a430876529d92b2c013e2b  [2 tablespoons olive oil, 1 cup chopped onion,...   \n",
+      "\n",
+      "                                                                  prepSteps  \\\n",
+      "id                                                                            \n",
+      "54a4270b19925f464b37c1dc  [Combine first 5 ingredients and 1/4 teaspoon ...   \n",
+      "54a42cde19925f464b3809d2  [Combine all ingredients in a small heavy sauc...   \n",
+      "54a433036529d92b2c015de3  [Combine first 5 ingredients in heavy medium s...   \n",
+      "54a451926529d92b2c01eda8  [1. Pour 12 cups of cold water into a large st...   \n",
+      "54a430876529d92b2c013e2b  [Heat oil in large saucepan over medium-high h...   \n",
+      "\n",
+      "                          reviewsCount  willMakeAgainPct  \\\n",
+      "id                                                         \n",
+      "54a4270b19925f464b37c1dc             9               100   \n",
+      "54a42cde19925f464b3809d2             6               100   \n",
+      "54a433036529d92b2c015de3             6                67   \n",
+      "54a451926529d92b2c01eda8            32                87   \n",
+      "54a430876529d92b2c013e2b             0                 0   \n",
+      "\n",
+      "                                                      ingredients_lemmafied  \\\n",
+      "id                                                                            \n",
+      "54a4270b19925f464b37c1dc  cup white wine vinegar brk cup sugar brk cup w...   \n",
+      "54a42cde19925f464b3809d2  large fresh jalapeño inch slice inch thick brk...   \n",
+      "54a433036529d92b2c015de3  cup chop red onion large brk tablespoon sunflo...   \n",
+      "54a451926529d92b2c01eda8  pound chicken part brk stalk celery include le...   \n",
+      "54a430876529d92b2c013e2b  tablespoon olive oil brk cup chop onion brk cu...   \n",
+      "\n",
+      "                             cuisine_name  \\\n",
+      "id                                          \n",
+      "54a4270b19925f464b37c1dc  Missing Cuisine   \n",
+      "54a42cde19925f464b3809d2  Missing Cuisine   \n",
+      "54a433036529d92b2c015de3           Indian   \n",
+      "54a451926529d92b2c01eda8           Kosher   \n",
+      "54a430876529d92b2c013e2b  Missing Cuisine   \n",
+      "\n",
+      "                                               photo_filename  \\\n",
+      "id                                                              \n",
+      "54a4270b19925f464b37c1dc  EP_12162015_placeholders_casual.jpg   \n",
+      "54a42cde19925f464b3809d2  EP_12162015_placeholders_rustic.jpg   \n",
+      "54a433036529d92b2c015de3                           234125.jpg   \n",
+      "54a451926529d92b2c01eda8  EP_12162015_placeholders_formal.jpg   \n",
+      "54a430876529d92b2c013e2b  EP_12162015_placeholders_rustic.jpg   \n",
+      "\n",
+      "                                                               photo_credit  \\\n",
+      "id                                                                            \n",
+      "54a4270b19925f464b37c1dc  Photo by Chelsea Kyle, Prop Styling by Rhoda B...   \n",
+      "54a42cde19925f464b3809d2  Photo by Chelsea Kyle, Prop Styling by Anna St...   \n",
+      "54a433036529d92b2c015de3                                      Brian Leatart   \n",
+      "54a451926529d92b2c01eda8  Photo by Chelsea Kyle, Prop Styling by Rhoda B...   \n",
+      "54a430876529d92b2c013e2b  Photo by Chelsea Kyle, Prop Styling by Anna St...   \n",
+      "\n",
+      "                              author_name            date_published  \\\n",
+      "id                                                                    \n",
+      "54a4270b19925f464b37c1dc    Kate Higgins  2010-12-16 04:00:00+00:00   \n",
+      "54a42cde19925f464b3809d2     Lillian Chou 2009-02-19 04:00:00+00:00   \n",
+      "54a433036529d92b2c015de3     Peter Gordon 2006-03-07 04:00:00+00:00   \n",
+      "54a451926529d92b2c01eda8  Sharon Lebewohl 2004-08-20 04:00:00+00:00   \n",
+      "54a430876529d92b2c013e2b   Suzanne Tracht 2007-12-03 20:11:11+00:00   \n",
+      "\n",
+      "                                                                 recipe_url  \n",
+      "id                                                                           \n",
+      "54a4270b19925f464b37c1dc  https://www.epicurious.com/recipes/food/views/...  \n",
+      "54a42cde19925f464b3809d2  https://www.epicurious.com/recipes/food/views/...  \n",
+      "54a433036529d92b2c015de3  https://www.epicurious.com/recipes/food/views/...  \n",
+      "54a451926529d92b2c01eda8  https://www.epicurious.com/recipes/food/views/...  \n",
+      "54a430876529d92b2c013e2b  https://www.epicurious.com/recipes/food/views/...  \n",
+      "(50, 14)\n"
+     ]
+    }
+   ],
    "source": [
     "# take sample and train/test split \n",
     "subset_df = raw_df.sample(n=100, random_state=45)\n",
@@ -281,7 +469,35 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "fit_transform start: 2024-04-03 19:00:04.028764\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 50/50 [00:00<00:00, 8700.07it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "fit_transform end: 2024-04-03 19:00:04.049144\n",
+      "Index(['English', 'English hothouse', 'English hothouse cucumber', 'available',\n",
+      "       'baby', 'baking', 'baking powder', 'bay', 'bay leave', 'beef',\n",
+      "       ...\n",
+      "       'white', 'white vinegar', 'white wine', 'white wine vinegar', 'whole',\n",
+      "       'wine', 'wine vinegar', 'yukon', 'yukon gold', 'yukon gold potato'],\n",
+      "      dtype='object', length=283)\n"
+     ]
+    }
+   ],
    "source": [
     "# cv_params are parameters for the sklearn CountVectorizer or TFIDFVectorizer\n",
     "sklearn_transformer_params = {    \n",
@@ -315,7 +531,1661 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "
\n",
+       "\n",
+       "\n",
+       "  \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "  \n",
+       "  \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "  \n",
+       "
EnglishEnglish hothouseEnglish hothouse cucumberavailablebabybakingbaking powderbaybay leavebeef...whitewhite vinegarwhite winewhite wine vinegarwholewinewine vinegaryukonyukon goldyukon gold potato
id
54a4270b19925f464b37c1dc0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.1499950.1499950.000000...0.1881550.0000000.2811100.2811100.0000000.2413430.2526410.0000000.0000000.000000
54a42cde19925f464b3809d20.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a433036529d92b2c015de30.0000000.0000000.0000000.0000000.0896660.0000000.0000000.0896660.0896660.000000...0.0562390.0000000.0000000.0000000.0000000.0000000.0000000.0896660.0896660.089666
54a451926529d92b2c01eda80.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.4780390.0000000.0000000.0000000.0000000.000000
54a430876529d92b2c013e2b0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0758790.1209800.0000000.0000000.0000000.0973290.0000000.0000000.0000000.000000
54a453df6529d92b2c0206870.0000000.0000000.0000000.0000000.0000000.1344960.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.1154690.0000000.0000000.0000000.0000000.000000
55b0e7116284773353bf45800.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a42bab6529d92b2c00ffa70.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a4748f19925f464b399ef20.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0971410.0000000.0000000.0000000.0000000.0000000.0000000.1548790.1548790.154879
54a4356a19925f464b3875bb0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0984600.0000000.1471020.1471020.1262920.1262920.1322040.0000000.0000000.000000
54a4697e6529d92b2c0279d30.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a45e426529d92b2c02488f0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a452c96529d92b2c01f8890.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.252416...0.1583160.2524160.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a4323619925f464b384bcc0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a4259119925f464b37af9c0.0000000.0000000.0000000.0000000.1655440.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a431da6529d92b2c014ee90.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.1841320.1841320.184132
54a426fd19925f464b37c1250.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a47bb019925f464b39b9b70.0000000.0000000.0000000.0000000.0000000.2206190.2354370.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a434d819925f464b386e620.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a428116529d92b2c00d1a70.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a436036529d92b2c01859e0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a47edf19925f464b39c58d0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a419706529d92b2c0066500.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a4349619925f464b386b120.0000000.0000000.0000000.0000000.0000000.1257390.1341840.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.1079520.0000000.0000000.0000000.0000000.000000
54a4340f6529d92b2c016be80.0000000.0000000.0000000.0000000.0000000.0000000.0000000.1880890.1880890.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a40e546529d92b2c0046060.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a428b419925f464b37d5ce0.0000000.0000000.0000000.0000000.0000000.1202450.1283210.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.1032350.0000000.0000000.0000000.0000000.000000
54a453a519925f464b38fd160.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a41cb219925f464b376d820.1293530.1293530.1293530.1293530.0000000.0000000.0000000.0000000.0000000.000000...0.0811310.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a431896529d92b2c014b270.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.147772...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a423ab19925f464b3799f20.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.1323490.0000000.0000000.0000000.0000000.000000
54a47c1419925f464b39bb280.0000000.0000000.0000000.1468740.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
593ee3ba12c27b182380821f0.1083410.1083410.1083410.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0679520.0000000.1015220.1015220.0000000.0871600.0912400.0000000.0000000.000000
54a456366529d92b2c02235a0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.120817...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a452d419925f464b38f1b50.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.1119270.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a4659b6529d92b2c026a530.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a46d5d19925f464b3982d30.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.1110530.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a4582119925f464b3927a10.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a4205319925f464b377c9f0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a470cc19925f464b39906b0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.1689370.1768450.0000000.0000000.000000
54a44f4a6529d92b2c01de450.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.2592130.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
592ef494ae10ad089795ebfa0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0985600.0000000.1472520.1472520.0000000.1264210.1323390.0000000.0000000.000000
54a41f016529d92b2c00757d0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.1242630.1981220.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a436266529d92b2c01876e0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a428bd19925f464b37d63e0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a45a4f6529d92b2c0234d10.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a41ed76529d92b2c0074400.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a42c906529d92b2c010b740.0000000.0000000.0000000.1851290.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.1489370.0000000.0000000.0000000.0000000.000000
569519a6dc18ea6c22c9b9ab0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.4072260.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
54a438d56529d92b2c0196480.1511650.1511650.1511650.0000000.1511650.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.1216130.1273060.0000000.0000000.000000
\n",
+       "
50 rows × 283 columns
\n",
+       "
"
+      ],
+      "text/plain": [
+       "                           English  English hothouse  \\\n",
+       "id                                                     \n",
+       "54a4270b19925f464b37c1dc  0.000000          0.000000   \n",
+       "54a42cde19925f464b3809d2  0.000000          0.000000   \n",
+       "54a433036529d92b2c015de3  0.000000          0.000000   \n",
+       "54a451926529d92b2c01eda8  0.000000          0.000000   \n",
+       "54a430876529d92b2c013e2b  0.000000          0.000000   \n",
+       "54a453df6529d92b2c020687  0.000000          0.000000   \n",
+       "55b0e7116284773353bf4580  0.000000          0.000000   \n",
+       "54a42bab6529d92b2c00ffa7  0.000000          0.000000   \n",
+       "54a4748f19925f464b399ef2  0.000000          0.000000   \n",
+       "54a4356a19925f464b3875bb  0.000000          0.000000   \n",
+       "54a4697e6529d92b2c0279d3  0.000000          0.000000   \n",
+       "54a45e426529d92b2c02488f  0.000000          0.000000   \n",
+       "54a452c96529d92b2c01f889  0.000000          0.000000   \n",
+       "54a4323619925f464b384bcc  0.000000          0.000000   \n",
+       "54a4259119925f464b37af9c  0.000000          0.000000   \n",
+       "54a431da6529d92b2c014ee9  0.000000          0.000000   \n",
+       "54a426fd19925f464b37c125  0.000000          0.000000   \n",
+       "54a47bb019925f464b39b9b7  0.000000          0.000000   \n",
+       "54a434d819925f464b386e62  0.000000          0.000000   \n",
+       "54a428116529d92b2c00d1a7  0.000000          0.000000   \n",
+       "54a436036529d92b2c01859e  0.000000          0.000000   \n",
+       "54a47edf19925f464b39c58d  0.000000          0.000000   \n",
+       "54a419706529d92b2c006650  0.000000          0.000000   \n",
+       "54a4349619925f464b386b12  0.000000          0.000000   \n",
+       "54a4340f6529d92b2c016be8  0.000000          0.000000   \n",
+       "54a40e546529d92b2c004606  0.000000          0.000000   \n",
+       "54a428b419925f464b37d5ce  0.000000          0.000000   \n",
+       "54a453a519925f464b38fd16  0.000000          0.000000   \n",
+       "54a41cb219925f464b376d82  0.129353          0.129353   \n",
+       "54a431896529d92b2c014b27  0.000000          0.000000   \n",
+       "54a423ab19925f464b3799f2  0.000000          0.000000   \n",
+       "54a47c1419925f464b39bb28  0.000000          0.000000   \n",
+       "593ee3ba12c27b182380821f  0.108341          0.108341   \n",
+       "54a456366529d92b2c02235a  0.000000          0.000000   \n",
+       "54a452d419925f464b38f1b5  0.000000          0.000000   \n",
+       "54a4659b6529d92b2c026a53  0.000000          0.000000   \n",
+       "54a46d5d19925f464b3982d3  0.000000          0.000000   \n",
+       "54a4582119925f464b3927a1  0.000000          0.000000   \n",
+       "54a4205319925f464b377c9f  0.000000          0.000000   \n",
+       "54a470cc19925f464b39906b  0.000000          0.000000   \n",
+       "54a44f4a6529d92b2c01de45  0.000000          0.000000   \n",
+       "592ef494ae10ad089795ebfa  0.000000          0.000000   \n",
+       "54a41f016529d92b2c00757d  0.000000          0.000000   \n",
+       "54a436266529d92b2c01876e  0.000000          0.000000   \n",
+       "54a428bd19925f464b37d63e  0.000000          0.000000   \n",
+       "54a45a4f6529d92b2c0234d1  0.000000          0.000000   \n",
+       "54a41ed76529d92b2c007440  0.000000          0.000000   \n",
+       "54a42c906529d92b2c010b74  0.000000          0.000000   \n",
+       "569519a6dc18ea6c22c9b9ab  0.000000          0.000000   \n",
+       "54a438d56529d92b2c019648  0.151165          0.151165   \n",
+       "\n",
+       "                          English hothouse cucumber  available      baby  \\\n",
+       "id                                                                         \n",
+       "54a4270b19925f464b37c1dc                   0.000000   0.000000  0.000000   \n",
+       "54a42cde19925f464b3809d2                   0.000000   0.000000  0.000000   \n",
+       "54a433036529d92b2c015de3                   0.000000   0.000000  0.089666   \n",
+       "54a451926529d92b2c01eda8                   0.000000   0.000000  0.000000   \n",
+       "54a430876529d92b2c013e2b                   0.000000   0.000000  0.000000   \n",
+       "54a453df6529d92b2c020687                   0.000000   0.000000  0.000000   \n",
+       "55b0e7116284773353bf4580                   0.000000   0.000000  0.000000   \n",
+       "54a42bab6529d92b2c00ffa7                   0.000000   0.000000  0.000000   \n",
+       "54a4748f19925f464b399ef2                   0.000000   0.000000  0.000000   \n",
+       "54a4356a19925f464b3875bb                   0.000000   0.000000  0.000000   \n",
+       "54a4697e6529d92b2c0279d3                   0.000000   0.000000  0.000000   \n",
+       "54a45e426529d92b2c02488f                   0.000000   0.000000  0.000000   \n",
+       "54a452c96529d92b2c01f889                   0.000000   0.000000  0.000000   \n",
+       "54a4323619925f464b384bcc                   0.000000   0.000000  0.000000   \n",
+       "54a4259119925f464b37af9c                   0.000000   0.000000  0.165544   \n",
+       "54a431da6529d92b2c014ee9                   0.000000   0.000000  0.000000   \n",
+       "54a426fd19925f464b37c125                   0.000000   0.000000  0.000000   \n",
+       "54a47bb019925f464b39b9b7                   0.000000   0.000000  0.000000   \n",
+       "54a434d819925f464b386e62                   0.000000   0.000000  0.000000   \n",
+       "54a428116529d92b2c00d1a7                   0.000000   0.000000  0.000000   \n",
+       "54a436036529d92b2c01859e                   0.000000   0.000000  0.000000   \n",
+       "54a47edf19925f464b39c58d                   0.000000   0.000000  0.000000   \n",
+       "54a419706529d92b2c006650                   0.000000   0.000000  0.000000   \n",
+       "54a4349619925f464b386b12                   0.000000   0.000000  0.000000   \n",
+       "54a4340f6529d92b2c016be8                   0.000000   0.000000  0.000000   \n",
+       "54a40e546529d92b2c004606                   0.000000   0.000000  0.000000   \n",
+       "54a428b419925f464b37d5ce                   0.000000   0.000000  0.000000   \n",
+       "54a453a519925f464b38fd16                   0.000000   0.000000  0.000000   \n",
+       "54a41cb219925f464b376d82                   0.129353   0.129353  0.000000   \n",
+       "54a431896529d92b2c014b27                   0.000000   0.000000  0.000000   \n",
+       "54a423ab19925f464b3799f2                   0.000000   0.000000  0.000000   \n",
+       "54a47c1419925f464b39bb28                   0.000000   0.146874  0.000000   \n",
+       "593ee3ba12c27b182380821f                   0.108341   0.000000  0.000000   \n",
+       "54a456366529d92b2c02235a                   0.000000   0.000000  0.000000   \n",
+       "54a452d419925f464b38f1b5                   0.000000   0.000000  0.000000   \n",
+       "54a4659b6529d92b2c026a53                   0.000000   0.000000  0.000000   \n",
+       "54a46d5d19925f464b3982d3                   0.000000   0.000000  0.000000   \n",
+       "54a4582119925f464b3927a1                   0.000000   0.000000  0.000000   \n",
+       "54a4205319925f464b377c9f                   0.000000   0.000000  0.000000   \n",
+       "54a470cc19925f464b39906b                   0.000000   0.000000  0.000000   \n",
+       "54a44f4a6529d92b2c01de45                   0.000000   0.000000  0.000000   \n",
+       "592ef494ae10ad089795ebfa                   0.000000   0.000000  0.000000   \n",
+       "54a41f016529d92b2c00757d                   0.000000   0.000000  0.000000   \n",
+       "54a436266529d92b2c01876e                   0.000000   0.000000  0.000000   \n",
+       "54a428bd19925f464b37d63e                   0.000000   0.000000  0.000000   \n",
+       "54a45a4f6529d92b2c0234d1                   0.000000   0.000000  0.000000   \n",
+       "54a41ed76529d92b2c007440                   0.000000   0.000000  0.000000   \n",
+       "54a42c906529d92b2c010b74                   0.000000   0.185129  0.000000   \n",
+       "569519a6dc18ea6c22c9b9ab                   0.000000   0.000000  0.000000   \n",
+       "54a438d56529d92b2c019648                   0.151165   0.000000  0.151165   \n",
+       "\n",
+       "                            baking  baking powder       bay  bay leave  \\\n",
+       "id                                                                       \n",
+       "54a4270b19925f464b37c1dc  0.000000       0.000000  0.149995   0.149995   \n",
+       "54a42cde19925f464b3809d2  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a433036529d92b2c015de3  0.000000       0.000000  0.089666   0.089666   \n",
+       "54a451926529d92b2c01eda8  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a430876529d92b2c013e2b  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a453df6529d92b2c020687  0.134496       0.000000  0.000000   0.000000   \n",
+       "55b0e7116284773353bf4580  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a42bab6529d92b2c00ffa7  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a4748f19925f464b399ef2  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a4356a19925f464b3875bb  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a4697e6529d92b2c0279d3  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a45e426529d92b2c02488f  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a452c96529d92b2c01f889  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a4323619925f464b384bcc  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a4259119925f464b37af9c  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a431da6529d92b2c014ee9  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a426fd19925f464b37c125  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a47bb019925f464b39b9b7  0.220619       0.235437  0.000000   0.000000   \n",
+       "54a434d819925f464b386e62  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a428116529d92b2c00d1a7  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a436036529d92b2c01859e  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a47edf19925f464b39c58d  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a419706529d92b2c006650  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a4349619925f464b386b12  0.125739       0.134184  0.000000   0.000000   \n",
+       "54a4340f6529d92b2c016be8  0.000000       0.000000  0.188089   0.188089   \n",
+       "54a40e546529d92b2c004606  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a428b419925f464b37d5ce  0.120245       0.128321  0.000000   0.000000   \n",
+       "54a453a519925f464b38fd16  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a41cb219925f464b376d82  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a431896529d92b2c014b27  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a423ab19925f464b3799f2  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a47c1419925f464b39bb28  0.000000       0.000000  0.000000   0.000000   \n",
+       "593ee3ba12c27b182380821f  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a456366529d92b2c02235a  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a452d419925f464b38f1b5  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a4659b6529d92b2c026a53  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a46d5d19925f464b3982d3  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a4582119925f464b3927a1  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a4205319925f464b377c9f  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a470cc19925f464b39906b  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a44f4a6529d92b2c01de45  0.000000       0.000000  0.000000   0.000000   \n",
+       "592ef494ae10ad089795ebfa  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a41f016529d92b2c00757d  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a436266529d92b2c01876e  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a428bd19925f464b37d63e  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a45a4f6529d92b2c0234d1  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a41ed76529d92b2c007440  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a42c906529d92b2c010b74  0.000000       0.000000  0.000000   0.000000   \n",
+       "569519a6dc18ea6c22c9b9ab  0.000000       0.000000  0.000000   0.000000   \n",
+       "54a438d56529d92b2c019648  0.000000       0.000000  0.000000   0.000000   \n",
+       "\n",
+       "                              beef  ...     white  white vinegar  white wine  \\\n",
+       "id                                  ...                                        \n",
+       "54a4270b19925f464b37c1dc  0.000000  ...  0.188155       0.000000    0.281110   \n",
+       "54a42cde19925f464b3809d2  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a433036529d92b2c015de3  0.000000  ...  0.056239       0.000000    0.000000   \n",
+       "54a451926529d92b2c01eda8  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a430876529d92b2c013e2b  0.000000  ...  0.075879       0.120980    0.000000   \n",
+       "54a453df6529d92b2c020687  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "55b0e7116284773353bf4580  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a42bab6529d92b2c00ffa7  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a4748f19925f464b399ef2  0.000000  ...  0.097141       0.000000    0.000000   \n",
+       "54a4356a19925f464b3875bb  0.000000  ...  0.098460       0.000000    0.147102   \n",
+       "54a4697e6529d92b2c0279d3  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a45e426529d92b2c02488f  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a452c96529d92b2c01f889  0.252416  ...  0.158316       0.252416    0.000000   \n",
+       "54a4323619925f464b384bcc  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a4259119925f464b37af9c  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a431da6529d92b2c014ee9  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a426fd19925f464b37c125  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a47bb019925f464b39b9b7  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a434d819925f464b386e62  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a428116529d92b2c00d1a7  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a436036529d92b2c01859e  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a47edf19925f464b39c58d  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a419706529d92b2c006650  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a4349619925f464b386b12  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a4340f6529d92b2c016be8  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a40e546529d92b2c004606  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a428b419925f464b37d5ce  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a453a519925f464b38fd16  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a41cb219925f464b376d82  0.000000  ...  0.081131       0.000000    0.000000   \n",
+       "54a431896529d92b2c014b27  0.147772  ...  0.000000       0.000000    0.000000   \n",
+       "54a423ab19925f464b3799f2  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a47c1419925f464b39bb28  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "593ee3ba12c27b182380821f  0.000000  ...  0.067952       0.000000    0.101522   \n",
+       "54a456366529d92b2c02235a  0.120817  ...  0.000000       0.000000    0.000000   \n",
+       "54a452d419925f464b38f1b5  0.000000  ...  0.111927       0.000000    0.000000   \n",
+       "54a4659b6529d92b2c026a53  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a46d5d19925f464b3982d3  0.000000  ...  0.111053       0.000000    0.000000   \n",
+       "54a4582119925f464b3927a1  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a4205319925f464b377c9f  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a470cc19925f464b39906b  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a44f4a6529d92b2c01de45  0.000000  ...  0.259213       0.000000    0.000000   \n",
+       "592ef494ae10ad089795ebfa  0.000000  ...  0.098560       0.000000    0.147252   \n",
+       "54a41f016529d92b2c00757d  0.000000  ...  0.124263       0.198122    0.000000   \n",
+       "54a436266529d92b2c01876e  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a428bd19925f464b37d63e  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a45a4f6529d92b2c0234d1  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a41ed76529d92b2c007440  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "54a42c906529d92b2c010b74  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "569519a6dc18ea6c22c9b9ab  0.000000  ...  0.407226       0.000000    0.000000   \n",
+       "54a438d56529d92b2c019648  0.000000  ...  0.000000       0.000000    0.000000   \n",
+       "\n",
+       "                          white wine vinegar     whole      wine  \\\n",
+       "id                                                                 \n",
+       "54a4270b19925f464b37c1dc            0.281110  0.000000  0.241343   \n",
+       "54a42cde19925f464b3809d2            0.000000  0.000000  0.000000   \n",
+       "54a433036529d92b2c015de3            0.000000  0.000000  0.000000   \n",
+       "54a451926529d92b2c01eda8            0.000000  0.478039  0.000000   \n",
+       "54a430876529d92b2c013e2b            0.000000  0.000000  0.097329   \n",
+       "54a453df6529d92b2c020687            0.000000  0.115469  0.000000   \n",
+       "55b0e7116284773353bf4580            0.000000  0.000000  0.000000   \n",
+       "54a42bab6529d92b2c00ffa7            0.000000  0.000000  0.000000   \n",
+       "54a4748f19925f464b399ef2            0.000000  0.000000  0.000000   \n",
+       "54a4356a19925f464b3875bb            0.147102  0.126292  0.126292   \n",
+       "54a4697e6529d92b2c0279d3            0.000000  0.000000  0.000000   \n",
+       "54a45e426529d92b2c02488f            0.000000  0.000000  0.000000   \n",
+       "54a452c96529d92b2c01f889            0.000000  0.000000  0.000000   \n",
+       "54a4323619925f464b384bcc            0.000000  0.000000  0.000000   \n",
+       "54a4259119925f464b37af9c            0.000000  0.000000  0.000000   \n",
+       "54a431da6529d92b2c014ee9            0.000000  0.000000  0.000000   \n",
+       "54a426fd19925f464b37c125            0.000000  0.000000  0.000000   \n",
+       "54a47bb019925f464b39b9b7            0.000000  0.000000  0.000000   \n",
+       "54a434d819925f464b386e62            0.000000  0.000000  0.000000   \n",
+       "54a428116529d92b2c00d1a7            0.000000  0.000000  0.000000   \n",
+       "54a436036529d92b2c01859e            0.000000  0.000000  0.000000   \n",
+       "54a47edf19925f464b39c58d            0.000000  0.000000  0.000000   \n",
+       "54a419706529d92b2c006650            0.000000  0.000000  0.000000   \n",
+       "54a4349619925f464b386b12            0.000000  0.107952  0.000000   \n",
+       "54a4340f6529d92b2c016be8            0.000000  0.000000  0.000000   \n",
+       "54a40e546529d92b2c004606            0.000000  0.000000  0.000000   \n",
+       "54a428b419925f464b37d5ce            0.000000  0.103235  0.000000   \n",
+       "54a453a519925f464b38fd16            0.000000  0.000000  0.000000   \n",
+       "54a41cb219925f464b376d82            0.000000  0.000000  0.000000   \n",
+       "54a431896529d92b2c014b27            0.000000  0.000000  0.000000   \n",
+       "54a423ab19925f464b3799f2            0.000000  0.132349  0.000000   \n",
+       "54a47c1419925f464b39bb28            0.000000  0.000000  0.000000   \n",
+       "593ee3ba12c27b182380821f            0.101522  0.000000  0.087160   \n",
+       "54a456366529d92b2c02235a            0.000000  0.000000  0.000000   \n",
+       "54a452d419925f464b38f1b5            0.000000  0.000000  0.000000   \n",
+       "54a4659b6529d92b2c026a53            0.000000  0.000000  0.000000   \n",
+       "54a46d5d19925f464b3982d3            0.000000  0.000000  0.000000   \n",
+       "54a4582119925f464b3927a1            0.000000  0.000000  0.000000   \n",
+       "54a4205319925f464b377c9f            0.000000  0.000000  0.000000   \n",
+       "54a470cc19925f464b39906b            0.000000  0.000000  0.168937   \n",
+       "54a44f4a6529d92b2c01de45            0.000000  0.000000  0.000000   \n",
+       "592ef494ae10ad089795ebfa            0.147252  0.000000  0.126421   \n",
+       "54a41f016529d92b2c00757d            0.000000  0.000000  0.000000   \n",
+       "54a436266529d92b2c01876e            0.000000  0.000000  0.000000   \n",
+       "54a428bd19925f464b37d63e            0.000000  0.000000  0.000000   \n",
+       "54a45a4f6529d92b2c0234d1            0.000000  0.000000  0.000000   \n",
+       "54a41ed76529d92b2c007440            0.000000  0.000000  0.000000   \n",
+       "54a42c906529d92b2c010b74            0.000000  0.148937  0.000000   \n",
+       "569519a6dc18ea6c22c9b9ab            0.000000  0.000000  0.000000   \n",
+       "54a438d56529d92b2c019648            0.000000  0.000000  0.121613   \n",
+       "\n",
+       "                          wine vinegar     yukon  yukon gold  \\\n",
+       "id                                                             \n",
+       "54a4270b19925f464b37c1dc      0.252641  0.000000    0.000000   \n",
+       "54a42cde19925f464b3809d2      0.000000  0.000000    0.000000   \n",
+       "54a433036529d92b2c015de3      0.000000  0.089666    0.089666   \n",
+       "54a451926529d92b2c01eda8      0.000000  0.000000    0.000000   \n",
+       "54a430876529d92b2c013e2b      0.000000  0.000000    0.000000   \n",
+       "54a453df6529d92b2c020687      0.000000  0.000000    0.000000   \n",
+       "55b0e7116284773353bf4580      0.000000  0.000000    0.000000   \n",
+       "54a42bab6529d92b2c00ffa7      0.000000  0.000000    0.000000   \n",
+       "54a4748f19925f464b399ef2      0.000000  0.154879    0.154879   \n",
+       "54a4356a19925f464b3875bb      0.132204  0.000000    0.000000   \n",
+       "54a4697e6529d92b2c0279d3      0.000000  0.000000    0.000000   \n",
+       "54a45e426529d92b2c02488f      0.000000  0.000000    0.000000   \n",
+       "54a452c96529d92b2c01f889      0.000000  0.000000    0.000000   \n",
+       "54a4323619925f464b384bcc      0.000000  0.000000    0.000000   \n",
+       "54a4259119925f464b37af9c      0.000000  0.000000    0.000000   \n",
+       "54a431da6529d92b2c014ee9      0.000000  0.184132    0.184132   \n",
+       "54a426fd19925f464b37c125      0.000000  0.000000    0.000000   \n",
+       "54a47bb019925f464b39b9b7      0.000000  0.000000    0.000000   \n",
+       "54a434d819925f464b386e62      0.000000  0.000000    0.000000   \n",
+       "54a428116529d92b2c00d1a7      0.000000  0.000000    0.000000   \n",
+       "54a436036529d92b2c01859e      0.000000  0.000000    0.000000   \n",
+       "54a47edf19925f464b39c58d      0.000000  0.000000    0.000000   \n",
+       "54a419706529d92b2c006650      0.000000  0.000000    0.000000   \n",
+       "54a4349619925f464b386b12      0.000000  0.000000    0.000000   \n",
+       "54a4340f6529d92b2c016be8      0.000000  0.000000    0.000000   \n",
+       "54a40e546529d92b2c004606      0.000000  0.000000    0.000000   \n",
+       "54a428b419925f464b37d5ce      0.000000  0.000000    0.000000   \n",
+       "54a453a519925f464b38fd16      0.000000  0.000000    0.000000   \n",
+       "54a41cb219925f464b376d82      0.000000  0.000000    0.000000   \n",
+       "54a431896529d92b2c014b27      0.000000  0.000000    0.000000   \n",
+       "54a423ab19925f464b3799f2      0.000000  0.000000    0.000000   \n",
+       "54a47c1419925f464b39bb28      0.000000  0.000000    0.000000   \n",
+       "593ee3ba12c27b182380821f      0.091240  0.000000    0.000000   \n",
+       "54a456366529d92b2c02235a      0.000000  0.000000    0.000000   \n",
+       "54a452d419925f464b38f1b5      0.000000  0.000000    0.000000   \n",
+       "54a4659b6529d92b2c026a53      0.000000  0.000000    0.000000   \n",
+       "54a46d5d19925f464b3982d3      0.000000  0.000000    0.000000   \n",
+       "54a4582119925f464b3927a1      0.000000  0.000000    0.000000   \n",
+       "54a4205319925f464b377c9f      0.000000  0.000000    0.000000   \n",
+       "54a470cc19925f464b39906b      0.176845  0.000000    0.000000   \n",
+       "54a44f4a6529d92b2c01de45      0.000000  0.000000    0.000000   \n",
+       "592ef494ae10ad089795ebfa      0.132339  0.000000    0.000000   \n",
+       "54a41f016529d92b2c00757d      0.000000  0.000000    0.000000   \n",
+       "54a436266529d92b2c01876e      0.000000  0.000000    0.000000   \n",
+       "54a428bd19925f464b37d63e      0.000000  0.000000    0.000000   \n",
+       "54a45a4f6529d92b2c0234d1      0.000000  0.000000    0.000000   \n",
+       "54a41ed76529d92b2c007440      0.000000  0.000000    0.000000   \n",
+       "54a42c906529d92b2c010b74      0.000000  0.000000    0.000000   \n",
+       "569519a6dc18ea6c22c9b9ab      0.000000  0.000000    0.000000   \n",
+       "54a438d56529d92b2c019648      0.127306  0.000000    0.000000   \n",
+       "\n",
+       "                          yukon gold potato  \n",
+       "id                                           \n",
+       "54a4270b19925f464b37c1dc           0.000000  \n",
+       "54a42cde19925f464b3809d2           0.000000  \n",
+       "54a433036529d92b2c015de3           0.089666  \n",
+       "54a451926529d92b2c01eda8           0.000000  \n",
+       "54a430876529d92b2c013e2b           0.000000  \n",
+       "54a453df6529d92b2c020687           0.000000  \n",
+       "55b0e7116284773353bf4580           0.000000  \n",
+       "54a42bab6529d92b2c00ffa7           0.000000  \n",
+       "54a4748f19925f464b399ef2           0.154879  \n",
+       "54a4356a19925f464b3875bb           0.000000  \n",
+       "54a4697e6529d92b2c0279d3           0.000000  \n",
+       "54a45e426529d92b2c02488f           0.000000  \n",
+       "54a452c96529d92b2c01f889           0.000000  \n",
+       "54a4323619925f464b384bcc           0.000000  \n",
+       "54a4259119925f464b37af9c           0.000000  \n",
+       "54a431da6529d92b2c014ee9           0.184132  \n",
+       "54a426fd19925f464b37c125           0.000000  \n",
+       "54a47bb019925f464b39b9b7           0.000000  \n",
+       "54a434d819925f464b386e62           0.000000  \n",
+       "54a428116529d92b2c00d1a7           0.000000  \n",
+       "54a436036529d92b2c01859e           0.000000  \n",
+       "54a47edf19925f464b39c58d           0.000000  \n",
+       "54a419706529d92b2c006650           0.000000  \n",
+       "54a4349619925f464b386b12           0.000000  \n",
+       "54a4340f6529d92b2c016be8           0.000000  \n",
+       "54a40e546529d92b2c004606           0.000000  \n",
+       "54a428b419925f464b37d5ce           0.000000  \n",
+       "54a453a519925f464b38fd16           0.000000  \n",
+       "54a41cb219925f464b376d82           0.000000  \n",
+       "54a431896529d92b2c014b27           0.000000  \n",
+       "54a423ab19925f464b3799f2           0.000000  \n",
+       "54a47c1419925f464b39bb28           0.000000  \n",
+       "593ee3ba12c27b182380821f           0.000000  \n",
+       "54a456366529d92b2c02235a           0.000000  \n",
+       "54a452d419925f464b38f1b5           0.000000  \n",
+       "54a4659b6529d92b2c026a53           0.000000  \n",
+       "54a46d5d19925f464b3982d3           0.000000  \n",
+       "54a4582119925f464b3927a1           0.000000  \n",
+       "54a4205319925f464b377c9f           0.000000  \n",
+       "54a470cc19925f464b39906b           0.000000  \n",
+       "54a44f4a6529d92b2c01de45           0.000000  \n",
+       "592ef494ae10ad089795ebfa           0.000000  \n",
+       "54a41f016529d92b2c00757d           0.000000  \n",
+       "54a436266529d92b2c01876e           0.000000  \n",
+       "54a428bd19925f464b37d63e           0.000000  \n",
+       "54a45a4f6529d92b2c0234d1           0.000000  \n",
+       "54a41ed76529d92b2c007440           0.000000  \n",
+       "54a42c906529d92b2c010b74           0.000000  \n",
+       "569519a6dc18ea6c22c9b9ab           0.000000  \n",
+       "54a438d56529d92b2c019648           0.000000  \n",
+       "\n",
+       "[50 rows x 283 columns]"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "transformed_recipe"
    ]
@@ -324,7 +2194,300 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['English',\n",
+       " 'English hothouse',\n",
+       " 'English hothouse cucumber',\n",
+       " 'available',\n",
+       " 'baby',\n",
+       " 'baking',\n",
+       " 'baking powder',\n",
+       " 'bay',\n",
+       " 'bay leave',\n",
+       " 'beef',\n",
+       " 'bell',\n",
+       " 'bell pepper',\n",
+       " 'black',\n",
+       " 'black pepper',\n",
+       " 'bread',\n",
+       " 'brk',\n",
+       " 'broth',\n",
+       " 'brown',\n",
+       " 'brown sugar',\n",
+       " 'bunch',\n",
+       " 'butter',\n",
+       " 'can',\n",
+       " 'carrot',\n",
+       " 'cayenne',\n",
+       " 'cayenne pepper',\n",
+       " 'celery',\n",
+       " 'cheese',\n",
+       " 'cherry',\n",
+       " 'chicken',\n",
+       " 'chile',\n",
+       " 'chop',\n",
+       " 'chop fresh',\n",
+       " 'chop fresh cilantro',\n",
+       " 'chop onion',\n",
+       " 'chop red',\n",
+       " 'cilantro',\n",
+       " 'cinnamon',\n",
+       " 'clove',\n",
+       " 'clove mince',\n",
+       " 'coarse',\n",
+       " 'coarse kosher',\n",
+       " 'coarse kosher salt',\n",
+       " 'core',\n",
+       " 'core cut',\n",
+       " 'core cut inch',\n",
+       " 'coriander',\n",
+       " 'cream',\n",
+       " 'crosswise',\n",
+       " 'cube',\n",
+       " 'cucumber',\n",
+       " 'cumin',\n",
+       " 'cup',\n",
+       " 'cup chop',\n",
+       " 'cup chop onion',\n",
+       " 'cup dry',\n",
+       " 'cup fresh',\n",
+       " 'cup grate',\n",
+       " 'cup olive',\n",
+       " 'cup olive oil',\n",
+       " 'cup pack',\n",
+       " 'cup purpose',\n",
+       " 'cup purpose flour',\n",
+       " 'cup slice',\n",
+       " 'cup sour',\n",
+       " 'cup sour cream',\n",
+       " 'cup stick',\n",
+       " 'cup sugar',\n",
+       " 'cup tablespoon',\n",
+       " 'cup water',\n",
+       " 'curry',\n",
+       " 'curry powder',\n",
+       " 'cut',\n",
+       " 'cut inch',\n",
+       " 'cut inch cube',\n",
+       " 'cut inch thick',\n",
+       " 'dark',\n",
+       " 'dark brown',\n",
+       " 'dark brown sugar',\n",
+       " 'dijon',\n",
+       " 'dijon mustard',\n",
+       " 'distil',\n",
+       " 'distil white',\n",
+       " 'distil white vinegar',\n",
+       " 'divide',\n",
+       " 'drain',\n",
+       " 'dry',\n",
+       " 'egg',\n",
+       " 'equipment',\n",
+       " 'extra',\n",
+       " 'extra virgin',\n",
+       " 'extra virgin olive',\n",
+       " 'extra virgin olive oil',\n",
+       " 'extract',\n",
+       " 'fillet',\n",
+       " 'firm',\n",
+       " 'flour',\n",
+       " 'food',\n",
+       " 'food store',\n",
+       " 'fresh',\n",
+       " 'fresh cilantro',\n",
+       " 'fresh lemon',\n",
+       " 'fresh lemon juice',\n",
+       " 'fresh lime',\n",
+       " 'fresh lime juice',\n",
+       " 'fresh mint',\n",
+       " 'garlic',\n",
+       " 'garlic clove',\n",
+       " 'garlic clove mince',\n",
+       " 'garlic powder',\n",
+       " 'garnish',\n",
+       " 'ginger',\n",
+       " 'gold',\n",
+       " 'gold potato',\n",
+       " 'golden',\n",
+       " 'golden brown',\n",
+       " 'grain',\n",
+       " 'grate',\n",
+       " 'grate lemon',\n",
+       " 'green',\n",
+       " 'green onion',\n",
+       " 'ground',\n",
+       " 'ground black',\n",
+       " 'ground black pepper',\n",
+       " 'ground cinnamon',\n",
+       " 'ground cumin',\n",
+       " 'halve',\n",
+       " 'halve pit',\n",
+       " 'hot',\n",
+       " 'hothouse',\n",
+       " 'hothouse cucumber',\n",
+       " 'inch',\n",
+       " 'inch cube',\n",
+       " 'inch long',\n",
+       " 'inch piece',\n",
+       " 'inch thick',\n",
+       " 'jalape',\n",
+       " 'juice',\n",
+       " 'kosher',\n",
+       " 'kosher salt',\n",
+       " 'large',\n",
+       " 'large egg',\n",
+       " 'large garlic',\n",
+       " 'large garlic clove',\n",
+       " 'leave',\n",
+       " 'lemon',\n",
+       " 'lemon juice',\n",
+       " 'light',\n",
+       " 'lime',\n",
+       " 'lime juice',\n",
+       " 'liqueur',\n",
+       " 'long',\n",
+       " 'low',\n",
+       " 'low salt',\n",
+       " 'medium',\n",
+       " 'milk',\n",
+       " 'mince',\n",
+       " 'mint',\n",
+       " 'mustard',\n",
+       " 'oil',\n",
+       " 'olive',\n",
+       " 'olive oil',\n",
+       " 'onion',\n",
+       " 'onion chop',\n",
+       " 'onion slice',\n",
+       " 'orange',\n",
+       " 'other',\n",
+       " 'ounce',\n",
+       " 'ounce can',\n",
+       " 'pack',\n",
+       " 'pack dark',\n",
+       " 'pack dark brown',\n",
+       " 'pack dark brown sugar',\n",
+       " 'parsley',\n",
+       " 'paste',\n",
+       " 'peel',\n",
+       " 'pepper',\n",
+       " 'piece',\n",
+       " 'pinch',\n",
+       " 'pit',\n",
+       " 'potato',\n",
+       " 'pound',\n",
+       " 'powder',\n",
+       " 'purpose',\n",
+       " 'purpose flour',\n",
+       " 'red',\n",
+       " 'red bell',\n",
+       " 'red bell pepper',\n",
+       " 'red onion',\n",
+       " 'red wine',\n",
+       " 'rice',\n",
+       " 'roast',\n",
+       " 'romaine',\n",
+       " 'room',\n",
+       " 'room temperature',\n",
+       " 'rosemary',\n",
+       " 'salt',\n",
+       " 'salt ground',\n",
+       " 'sauce',\n",
+       " 'scallion',\n",
+       " 'seed',\n",
+       " 'sesame',\n",
+       " 'shallot',\n",
+       " 'slice',\n",
+       " 'small',\n",
+       " 'sour',\n",
+       " 'sour cream',\n",
+       " 'soy',\n",
+       " 'soy sauce',\n",
+       " 'special',\n",
+       " 'special equipment',\n",
+       " 'specialty',\n",
+       " 'specialty food',\n",
+       " 'sprig',\n",
+       " 'stem',\n",
+       " 'stick',\n",
+       " 'store',\n",
+       " 'strip',\n",
+       " 'style',\n",
+       " 'such',\n",
+       " 'sugar',\n",
+       " 'tablespoon',\n",
+       " 'tablespoon chop',\n",
+       " 'tablespoon chop fresh',\n",
+       " 'tablespoon chop fresh cilantro',\n",
+       " 'tablespoon extra',\n",
+       " 'tablespoon extra virgin',\n",
+       " 'tablespoon extra virgin olive',\n",
+       " 'tablespoon fresh',\n",
+       " 'tablespoon fresh lemon',\n",
+       " 'tablespoon fresh lemon juice',\n",
+       " 'tablespoon light',\n",
+       " 'tablespoon olive',\n",
+       " 'tablespoon olive oil',\n",
+       " 'tablespoon sugar',\n",
+       " 'tablespoon white',\n",
+       " 'tablespoon white wine',\n",
+       " 'tablespoon white wine vinegar',\n",
+       " 'taste',\n",
+       " 'teaspoon',\n",
+       " 'teaspoon baking',\n",
+       " 'teaspoon dry',\n",
+       " 'teaspoon grate',\n",
+       " 'teaspoon grate lemon',\n",
+       " 'teaspoon ground',\n",
+       " 'teaspoon ground cumin',\n",
+       " 'teaspoon salt',\n",
+       " 'teaspoon vanilla',\n",
+       " 'teaspoon vanilla extract',\n",
+       " 'temperature',\n",
+       " 'thick',\n",
+       " 'thick slice',\n",
+       " 'thyme',\n",
+       " 'to',\n",
+       " 'to taste',\n",
+       " 'toast',\n",
+       " 'tomato',\n",
+       " 'tomato halve',\n",
+       " 'trim',\n",
+       " 'unpeeled',\n",
+       " 'unsalt',\n",
+       " 'unsalt butter',\n",
+       " 'unsweetened',\n",
+       " 'use',\n",
+       " 'vanilla',\n",
+       " 'vanilla extract',\n",
+       " 'vegetable',\n",
+       " 'vegetable oil',\n",
+       " 'vinegar',\n",
+       " 'virgin',\n",
+       " 'virgin olive',\n",
+       " 'virgin olive oil',\n",
+       " 'water',\n",
+       " 'wedge',\n",
+       " 'white',\n",
+       " 'white vinegar',\n",
+       " 'white wine',\n",
+       " 'white wine vinegar',\n",
+       " 'whole',\n",
+       " 'wine',\n",
+       " 'wine vinegar',\n",
+       " 'yukon',\n",
+       " 'yukon gold',\n",
+       " 'yukon gold potato']"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "transformed_recipe.columns.tolist()"
    ]
@@ -333,7 +2496,254 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "
\n",
+       "\n",
+       "\n",
+       "  \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "  \n",
+       "  \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "    \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "      \n",
+       "    \n",
+       "  \n",
+       "
dekhedaggregateRatingingredientsprepStepsreviewsCountwillMakeAgainPctingredients_lemmafiedcuisine_namephoto_filenamephoto_creditauthor_namedate_publishedrecipe_url
id
54a4270b19925f464b37c1dcGrilled Hearts of Romaine with Blue Cheese Vin...3.64[1 1/2 cups white wine vinegar, 1/2 cup sugar,...[Combine first 5 ingredients and 1/4 teaspoon ...9100cup white wine vinegar brk cup sugar brk cup w...Missing CuisineEP_12162015_placeholders_casual.jpgPhoto by Chelsea Kyle, Prop Styling by Rhoda B...Kate Higgins2010-12-16 04:00:00+00:00https://www.epicurious.com/recipes/food/views/...
54a42cde19925f464b3809d2Green chiles pickled in soy sauce and vinegar ...Soy-Pickled Jalapeños3.43[3 large fresh jalapeños (4 inches), sliced 1/...[Combine all ingredients in a small heavy sauc...6100large fresh jalapeño inch slice inch thick brk...Missing CuisineEP_12162015_placeholders_rustic.jpgPhoto by Chelsea Kyle, Prop Styling by Anna St...Lillian Chou2009-02-19 04:00:00+00:00https://www.epicurious.com/recipes/food/views/...
54a433036529d92b2c015de3This soup features the flavors of India: aroma...Curried Potato and Spinach Soup with Onion Sal...3.00[4 cups chopped red onions (about 2 large), 1 ...[Combine first 5 ingredients in heavy medium s...667cup chop red onion large brk tablespoon sunflo...Indian234125.jpgBrian LeatartPeter Gordon2006-03-07 04:00:00+00:00https://www.epicurious.com/recipes/food/views/...
54a451926529d92b2c01eda8Chicken Soup3.19[1 pound chicken parts, 2 stalks celery, inclu...[1. Pour 12 cups of cold water into a large st...3287pound chicken part brk stalk celery include le...KosherEP_12162015_placeholders_formal.jpgPhoto by Chelsea Kyle, Prop Styling by Rhoda B...Sharon Lebewohl2004-08-20 04:00:00+00:00https://www.epicurious.com/recipes/food/views/...
54a430876529d92b2c013e2bBrown sugar and molasses are balanced by fresh...Sweet-Hot Barbecue Sauce0.00[2 tablespoons olive oil, 1 cup chopped onion,...[Heat oil in large saucepan over medium-high h...00tablespoon olive oil brk cup chop onion brk cu...Missing CuisineEP_12162015_placeholders_rustic.jpgPhoto by Chelsea Kyle, Prop Styling by Anna St...Suzanne Tracht2007-12-03 20:11:11+00:00https://www.epicurious.com/recipes/food/views/...
\n",
+       "
"
+      ],
+      "text/plain": [
+       "                                                                        dek  \\\n",
+       "id                                                                            \n",
+       "54a4270b19925f464b37c1dc                                                      \n",
+       "54a42cde19925f464b3809d2  Green chiles pickled in soy sauce and vinegar ...   \n",
+       "54a433036529d92b2c015de3  This soup features the flavors of India: aroma...   \n",
+       "54a451926529d92b2c01eda8                                                      \n",
+       "54a430876529d92b2c013e2b  Brown sugar and molasses are balanced by fresh...   \n",
+       "\n",
+       "                                                                        hed  \\\n",
+       "id                                                                            \n",
+       "54a4270b19925f464b37c1dc  Grilled Hearts of Romaine with Blue Cheese Vin...   \n",
+       "54a42cde19925f464b3809d2                              Soy-Pickled Jalapeños   \n",
+       "54a433036529d92b2c015de3  Curried Potato and Spinach Soup with Onion Sal...   \n",
+       "54a451926529d92b2c01eda8                                       Chicken Soup   \n",
+       "54a430876529d92b2c013e2b                           Sweet-Hot Barbecue Sauce   \n",
+       "\n",
+       "                          aggregateRating  \\\n",
+       "id                                          \n",
+       "54a4270b19925f464b37c1dc             3.64   \n",
+       "54a42cde19925f464b3809d2             3.43   \n",
+       "54a433036529d92b2c015de3             3.00   \n",
+       "54a451926529d92b2c01eda8             3.19   \n",
+       "54a430876529d92b2c013e2b             0.00   \n",
+       "\n",
+       "                                                                ingredients  \\\n",
+       "id                                                                            \n",
+       "54a4270b19925f464b37c1dc  [1 1/2 cups white wine vinegar, 1/2 cup sugar,...   \n",
+       "54a42cde19925f464b3809d2  [3 large fresh jalapeños (4 inches), sliced 1/...   \n",
+       "54a433036529d92b2c015de3  [4 cups chopped red onions (about 2 large), 1 ...   \n",
+       "54a451926529d92b2c01eda8  [1 pound chicken parts, 2 stalks celery, inclu...   \n",
+       "54a430876529d92b2c013e2b  [2 tablespoons olive oil, 1 cup chopped onion,...   \n",
+       "\n",
+       "                                                                  prepSteps  \\\n",
+       "id                                                                            \n",
+       "54a4270b19925f464b37c1dc  [Combine first 5 ingredients and 1/4 teaspoon ...   \n",
+       "54a42cde19925f464b3809d2  [Combine all ingredients in a small heavy sauc...   \n",
+       "54a433036529d92b2c015de3  [Combine first 5 ingredients in heavy medium s...   \n",
+       "54a451926529d92b2c01eda8  [1. Pour 12 cups of cold water into a large st...   \n",
+       "54a430876529d92b2c013e2b  [Heat oil in large saucepan over medium-high h...   \n",
+       "\n",
+       "                          reviewsCount  willMakeAgainPct  \\\n",
+       "id                                                         \n",
+       "54a4270b19925f464b37c1dc             9               100   \n",
+       "54a42cde19925f464b3809d2             6               100   \n",
+       "54a433036529d92b2c015de3             6                67   \n",
+       "54a451926529d92b2c01eda8            32                87   \n",
+       "54a430876529d92b2c013e2b             0                 0   \n",
+       "\n",
+       "                                                      ingredients_lemmafied  \\\n",
+       "id                                                                            \n",
+       "54a4270b19925f464b37c1dc  cup white wine vinegar brk cup sugar brk cup w...   \n",
+       "54a42cde19925f464b3809d2  large fresh jalapeño inch slice inch thick brk...   \n",
+       "54a433036529d92b2c015de3  cup chop red onion large brk tablespoon sunflo...   \n",
+       "54a451926529d92b2c01eda8  pound chicken part brk stalk celery include le...   \n",
+       "54a430876529d92b2c013e2b  tablespoon olive oil brk cup chop onion brk cu...   \n",
+       "\n",
+       "                             cuisine_name  \\\n",
+       "id                                          \n",
+       "54a4270b19925f464b37c1dc  Missing Cuisine   \n",
+       "54a42cde19925f464b3809d2  Missing Cuisine   \n",
+       "54a433036529d92b2c015de3           Indian   \n",
+       "54a451926529d92b2c01eda8           Kosher   \n",
+       "54a430876529d92b2c013e2b  Missing Cuisine   \n",
+       "\n",
+       "                                               photo_filename  \\\n",
+       "id                                                              \n",
+       "54a4270b19925f464b37c1dc  EP_12162015_placeholders_casual.jpg   \n",
+       "54a42cde19925f464b3809d2  EP_12162015_placeholders_rustic.jpg   \n",
+       "54a433036529d92b2c015de3                           234125.jpg   \n",
+       "54a451926529d92b2c01eda8  EP_12162015_placeholders_formal.jpg   \n",
+       "54a430876529d92b2c013e2b  EP_12162015_placeholders_rustic.jpg   \n",
+       "\n",
+       "                                                               photo_credit  \\\n",
+       "id                                                                            \n",
+       "54a4270b19925f464b37c1dc  Photo by Chelsea Kyle, Prop Styling by Rhoda B...   \n",
+       "54a42cde19925f464b3809d2  Photo by Chelsea Kyle, Prop Styling by Anna St...   \n",
+       "54a433036529d92b2c015de3                                      Brian Leatart   \n",
+       "54a451926529d92b2c01eda8  Photo by Chelsea Kyle, Prop Styling by Rhoda B...   \n",
+       "54a430876529d92b2c013e2b  Photo by Chelsea Kyle, Prop Styling by Anna St...   \n",
+       "\n",
+       "                              author_name            date_published  \\\n",
+       "id                                                                    \n",
+       "54a4270b19925f464b37c1dc    Kate Higgins  2010-12-16 04:00:00+00:00   \n",
+       "54a42cde19925f464b3809d2     Lillian Chou 2009-02-19 04:00:00+00:00   \n",
+       "54a433036529d92b2c015de3     Peter Gordon 2006-03-07 04:00:00+00:00   \n",
+       "54a451926529d92b2c01eda8  Sharon Lebewohl 2004-08-20 04:00:00+00:00   \n",
+       "54a430876529d92b2c013e2b   Suzanne Tracht 2007-12-03 20:11:11+00:00   \n",
+       "\n",
+       "                                                                 recipe_url  \n",
+       "id                                                                           \n",
+       "54a4270b19925f464b37c1dc  https://www.epicurious.com/recipes/food/views/...  \n",
+       "54a42cde19925f464b3809d2  https://www.epicurious.com/recipes/food/views/...  \n",
+       "54a433036529d92b2c015de3  https://www.epicurious.com/recipes/food/views/...  \n",
+       "54a451926529d92b2c01eda8  https://www.epicurious.com/recipes/food/views/...  \n",
+       "54a430876529d92b2c013e2b  https://www.epicurious.com/recipes/food/views/...  "
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "to_nlp_df.head()"
    ]
diff --git a/src/nltk/dish_predictor.py b/src/nltk/dish_predictor.py
index a0c1ffd..fb68b78 100644
--- a/src/nltk/dish_predictor.py
+++ b/src/nltk/dish_predictor.py
@@ -15,8 +15,9 @@
 import numpy as np
 from pandas.io.json import json_normalize
 import nltk
-nltk.download('wordnet')
-nltk.download('stopwords')
+
+nltk.download("wordnet")
+nltk.download("stopwords")
 from nltk.corpus import stopwords
 from nltk import word_tokenize, FreqDist
 from nltk.stem.wordnet import WordNetLemmatizer
@@ -28,235 +29,283 @@
 
 # Define all functions
 
+
 def import_stored_files():
-  # Load in the stored Epicurious database, TFIDF Vectorizer object to transform,
-  # the input, and the TFIDF word matrix from joblib and created by 
-  # prepare_database.py
-  with open("joblib/tfidf_recipe_dataframe.joblib", "rb") as fo:
-    prepped = joblib.load("joblib/tfidf_recipe_dataframe.joblib")
+    # Load in the stored Epicurious database, TFIDF Vectorizer object to transform,
+    # the input, and the TFIDF word matrix from joblib and created by
+    # prepare_database.py
+    with open("joblib/tfidf_recipe_dataframe.joblib", "rb") as fo:
+        prepped = joblib.load("joblib/tfidf_recipe_dataframe.joblib")
 
-  with open("joblib/recipe_tfidf.joblib", "rb") as fo:
-    ingred_tfidf = joblib.load("joblib/recipe_tfidf.joblib")
+    with open("joblib/recipe_tfidf.joblib", "rb") as fo:
+        ingred_tfidf = joblib.load("joblib/recipe_tfidf.joblib")
 
-  with open("joblib/recipe_word_matrix_tfidf.joblib", "rb") as fo:
-    ingred_word_matrix = joblib.load("joblib/recipe_word_matrix_tfidf.joblib")
+    with open("joblib/recipe_word_matrix_tfidf.joblib", "rb") as fo:
+        ingred_word_matrix = joblib.load("joblib/recipe_word_matrix_tfidf.joblib")
 
-  return prepped, ingred_tfidf, ingred_word_matrix
+    return prepped, ingred_tfidf, ingred_word_matrix
 
 
 def transform_tfidf(ingred_tfidf, recipe):
-  # This function takes in a TFIDF Vectorizer object and a recipe, then 
-  # creates/transforms the given recipe into a TFIDF form
-
-  ingreds = recipe['ingredients'].apply(" ".join).str.lower()
-  response = ingred_tfidf.transform(ingreds)
-  transformed_recipe = pd.DataFrame(response.toarray(),
-                                    columns=ingred_tfidf.get_feature_names(),
-                                    index=recipe.index)
-  return transformed_recipe
-
-
-def filter_out_cuisine(ingred_word_matrix, 
-                        X_df, 
-                        cuisine_name, 
-                        tfidf):
-  # This function takes in the ingredient word matrix (from joblib), a 
-  # dataframe made from the database (from joblib), the user inputted cuisine 
-  # name, and the ingredient TFIDF Vectorizer object (from joblib) and returns
-  # a word sub matrix that removes all recipes with the same cuisine as the 
-  # inputted recipe.
-
-  east_asian = ['Asian', 'Chinese', 'Japanese']
-
-  southeast_asian = ['Thai', 'Vietnamese']
-
-  euro_islands = ['English', 'Irish']
-
-  euro_continental = ['French', 'German', 'Eastern European']
-
-  mediterranean = ['Italian', 'Mediterranean', 'Kosher', 'Middle Eastern']
-
-  all_cuisines = ['African', 'American', 'Asian', 'Cajun/Creole', 'Chinese', 'Eastern European', 'English',
-                  'French', 'German', 'Indian', 'Irish', 'Italian', 'Japanese', 'Kosher', 'Latin American', 
-                  'Mediterranean', 'Mexican', 'Middle Eastern', 'Moroccan', 'Scandinavian', 'Southwestern', 
-                  'Thai', 'Vietnamese']
-
-  if cuisine_name in east_asian:
-    choices = [cuis for cuis in all_cuisines if cuis not in east_asian]
-  elif cuisine_name in southeast_asian:
-    choices = [cuis for cuis in all_cuisines if cuis not in southeast_asian]
-  elif cuisine_name in euro_islands:
-    choices = [cuis for cuis in all_cuisines if cuis not in euro_islands]
-  elif cuisine_name in euro_continental:
-    choices = [cuis for cuis in all_cuisines if cuis not in euro_continental]
-  elif cuisine_name in mediterranean:
-    choices = [cuis for cuis in all_cuisines if cuis not in mediterranean]
-  else:
-    choices = [cuis for cuis in all_cuisines if cuis != cuisine_name]
-
-  combo = pd.concat([ingred_word_matrix, X_df['imputed_label']], axis=1)
-  filtered_ingred_word_matrix = combo[combo['imputed_label'].isin(choices)].drop('imputed_label', 
-                                                                    axis=1)
-  return filtered_ingred_word_matrix
+    # This function takes in a TFIDF Vectorizer object and a recipe, then
+    # creates/transforms the given recipe into a TFIDF form
+
+    ingreds = recipe["ingredients"].apply(" ".join).str.lower()
+    response = ingred_tfidf.transform(ingreds)
+    transformed_recipe = pd.DataFrame(
+        response.toarray(), columns=ingred_tfidf.get_feature_names(), index=recipe.index
+    )
+    return transformed_recipe
+
+
+def filter_out_cuisine(ingred_word_matrix, X_df, cuisine_name, tfidf):
+    # This function takes in the ingredient word matrix (from joblib), a
+    # dataframe made from the database (from joblib), the user inputted cuisine
+    # name, and the ingredient TFIDF Vectorizer object (from joblib) and returns
+    # a word sub matrix that removes all recipes with the same cuisine as the
+    # inputted recipe.
+
+    east_asian = ["Asian", "Chinese", "Japanese"]
+
+    southeast_asian = ["Thai", "Vietnamese"]
+
+    euro_islands = ["English", "Irish"]
+
+    euro_continental = ["French", "German", "Eastern European"]
+
+    mediterranean = ["Italian", "Mediterranean", "Kosher", "Middle Eastern"]
+
+    all_cuisines = [
+        "African",
+        "American",
+        "Asian",
+        "Cajun/Creole",
+        "Chinese",
+        "Eastern European",
+        "English",
+        "French",
+        "German",
+        "Indian",
+        "Irish",
+        "Italian",
+        "Japanese",
+        "Kosher",
+        "Latin American",
+        "Mediterranean",
+        "Mexican",
+        "Middle Eastern",
+        "Moroccan",
+        "Scandinavian",
+        "Southwestern",
+        "Thai",
+        "Vietnamese",
+    ]
+
+    if cuisine_name in east_asian:
+        choices = [cuis for cuis in all_cuisines if cuis not in east_asian]
+    elif cuisine_name in southeast_asian:
+        choices = [cuis for cuis in all_cuisines if cuis not in southeast_asian]
+    elif cuisine_name in euro_islands:
+        choices = [cuis for cuis in all_cuisines if cuis not in euro_islands]
+    elif cuisine_name in euro_continental:
+        choices = [cuis for cuis in all_cuisines if cuis not in euro_continental]
+    elif cuisine_name in mediterranean:
+        choices = [cuis for cuis in all_cuisines if cuis not in mediterranean]
+    else:
+        choices = [cuis for cuis in all_cuisines if cuis != cuisine_name]
+
+    combo = pd.concat([ingred_word_matrix, X_df["imputed_label"]], axis=1)
+    filtered_ingred_word_matrix = combo[combo["imputed_label"].isin(choices)].drop(
+        "imputed_label", axis=1
+    )
+    return filtered_ingred_word_matrix
 
 
 def picture_placer(filename):
-  # This function takes in a filename and returns the relative location inside
-  # an HTML tag
-  location = f'photos/{filename}'
-  return location
+    # This function takes in a filename and returns the relative location inside
+    # an HTML tag
+    location = f"photos/{filename}"
+    return location
 
 
 def link_maker(recipe_link):
-  # This function takes in the incomplete recipe link from the dataframe and 
-  # returns the complete one.
-  full_link = f'https://www.epicurious.com{recipe_link}'
-  return full_link
-
-
-def find_closest_recipes(filtered_ingred_word_matrix, 
-                          recipe_tfidf, 
-                          X_df):
-  # This function takes in the filtered ingredient word matrix from function
-  # filter_out_cuisine, the TFIDF recipe from function transform_tfidf, and 
-  # a dataframe made from the database (from joblib) and returns a Pandas 
-  # DataFrame with the top five most similar recipes and a Pandas Series 
-  # containing the similarity amount
-
-  m2 = (recipe_tfidf != 0).any()
-  recipe_weights = recipe_tfidf.iloc[0][recipe_tfidf.iloc[0] != 0].to_dict()
-
-  ingreds_used = m2.index[m2].tolist()
-  search_vec = np.array(recipe_tfidf).reshape(1,-1)
-  res_cos_sim = cosine_similarity(filtered_ingred_word_matrix, search_vec)
-  top_five = np.argsort(res_cos_sim.flatten())[-5:][::-1]
-  top_five_list = top_five.tolist()
-  
-  recipe_ids = [filtered_ingred_word_matrix.iloc[idx].name for idx in top_five]
-
-  suggest_df = X_df.loc[recipe_ids]
-  proximity = pd.DataFrame(data=res_cos_sim[top_five], 
-                            columns=['cosine_similarity'], 
-                            index=suggest_df.index)
-  
-  full_df = pd.concat([suggest_df, proximity], axis=1)
-  expand_photo_df = pd.concat([full_df.drop(["photoData"], axis=1), 
-                                full_df["photoData"].apply(pd.Series)], axis=1)
-  reduced = expand_photo_df[['hed', 'recipe_url', 'filename', 'imputed_label', 'ingredients', 'cosine_similarity']].dropna(axis=1)
-  reduced['photo'] = reduced['filename'].apply(picture_placer)
-  reduced['fixed_url'] = reduced["recipe_url"].apply(link_maker)
-  reduced['rounded'] = reduced['cosine_similarity'].round(3)
-
-  reduced = reduced.drop('recipe_url', axis=1)
-
-  ingr_weights = [filtered_ingred_word_matrix.iloc[num][filtered_ingred_word_matrix.iloc[num] != 0].to_dict() for num in top_five_list]
-  reduced['ingred_weights'] = ingr_weights
-
-  return reduced, ingreds_used, recipe_weights
+    # This function takes in the incomplete recipe link from the dataframe and
+    # returns the complete one.
+    full_link = f"https://www.epicurious.com{recipe_link}"
+    return full_link
+
+
+def find_closest_recipes(filtered_ingred_word_matrix, recipe_tfidf, X_df):
+    # This function takes in the filtered ingredient word matrix from function
+    # filter_out_cuisine, the TFIDF recipe from function transform_tfidf, and
+    # a dataframe made from the database (from joblib) and returns a Pandas
+    # DataFrame with the top five most similar recipes and a Pandas Series
+    # containing the similarity amount
+
+    m2 = (recipe_tfidf != 0).any()
+    recipe_weights = recipe_tfidf.iloc[0][recipe_tfidf.iloc[0] != 0].to_dict()
+
+    ingreds_used = m2.index[m2].tolist()
+    search_vec = np.array(recipe_tfidf).reshape(1, -1)
+    res_cos_sim = cosine_similarity(filtered_ingred_word_matrix, search_vec)
+    top_five = np.argsort(res_cos_sim.flatten())[-5:][::-1]
+    top_five_list = top_five.tolist()
+
+    recipe_ids = [filtered_ingred_word_matrix.iloc[idx].name for idx in top_five]
+
+    suggest_df = X_df.loc[recipe_ids]
+    proximity = pd.DataFrame(
+        data=res_cos_sim[top_five],
+        columns=["cosine_similarity"],
+        index=suggest_df.index,
+    )
+
+    full_df = pd.concat([suggest_df, proximity], axis=1)
+    expand_photo_df = pd.concat(
+        [full_df.drop(["photoData"], axis=1), full_df["photoData"].apply(pd.Series)],
+        axis=1,
+    )
+    reduced = expand_photo_df[
+        [
+            "hed",
+            "recipe_url",
+            "filename",
+            "imputed_label",
+            "ingredients",
+            "cosine_similarity",
+        ]
+    ].dropna(axis=1)
+    reduced["photo"] = reduced["filename"].apply(picture_placer)
+    reduced["fixed_url"] = reduced["recipe_url"].apply(link_maker)
+    reduced["rounded"] = reduced["cosine_similarity"].round(3)
+
+    reduced = reduced.drop("recipe_url", axis=1)
+
+    ingr_weights = [
+        filtered_ingred_word_matrix.iloc[num][
+            filtered_ingred_word_matrix.iloc[num] != 0
+        ].to_dict()
+        for num in top_five_list
+    ]
+    reduced["ingred_weights"] = ingr_weights
+
+    return reduced, ingreds_used, recipe_weights
 
 
 def find_similar_dishes(dish_name, cuisine_name):
-  prepped, ingred_tfidf, ingred_word_matrix = import_stored_files()
-  # This function calls the Edamam API, stores the results as a JSON, and 
-  # stores the timestamp, dish name, and cuisine name/classification in a 
-  # separate csv.
-  now = datetime.now()
-  dt_string = now.strftime("%d_%m_%Y_%H_%M_%S")
-
-  api_base = "https://api.edamam.com/search?"
-
-  # Level up:
-  # Implement lemmatization using trained dataset on input in order to make 
-  # future database be less likely to have redundant entries 
-  # (e.g., taco vs tacos)
-
-  q = f"q={dish_name}"
-
-  # Level up:
-  # Check a database of dishes to see if this query has been asked for already
-  # If not, do an API call
-
-  # Currently, just does an API call, may hit API limit if continuing with this
-  # version
-  f = open("secrets/edamam.json","r")
-  cred = json.load(f)
-  f.close()
-
-  app_id = cred["id"]
-  app_id_s = f"&app_id={app_id}"
-
-  app_key = cred["key"]
-  app_key_s = f"&app_key={app_key}"
-  
-  # Level up: 
-  # Explicitly ask for a few recipes using limiter and make an "average version"
-  # of the input in order to get better results from the API call
-  # limiter = "&from=0&to=4"
-  # API currently defaults to returning 10
-
-  api_call = api_base + q+ app_id_s + app_key_s #+ limiter
-
-  resp = requests.get(api_call)
-
-  if resp.status_code == 200:
-    response_dict = resp.json()
-    resp_dict_hits = response_dict['hits']
-    
-    # Store the API result into a JSON and the cuisine type and dish name into a 
-    # csv
-    # Heroku does not save files to directory
-    # Can work with EC2
-    # with open(f"../write_data/{dt_string}_{dish_name}_edamam_api_return.json", "w") as f:
-    #   json.dump(resp_dict_hits, f)
-
-    # fields = [dt_string, dish_name, cuisine_name]
-    # with open("../write_data/user_requests.csv", "a", newline='') as f:
-    #   writer = csv.writer(f)
-    #   writer.writerow(fields)
-
-    urls = []
-    labels = []
-    sources = []
-    ingreds = []
-
-    for recipe in resp_dict_hits:
-        recipe_path = recipe['recipe']
-        urls.append(recipe_path['url'])
-        labels.append(recipe_path['label'])
-        sources.append(recipe_path['source'])
-        ingreds.append([item['text'] for item in recipe_path['ingredients']])
-        
-    all_recipes = {'url': urls,
-                  'label': labels, 
-                  'source': sources, 
-                  'ingredients': ingreds
-                  }
-
-    recipe_df = pd.DataFrame(all_recipes)
-
-    one_recipe = []
-
-    for listing in recipe_df['ingredients']:
-        for ingred in listing:
-            one_recipe.append(ingred.lower())
-        
-    one_recipe = list(set(one_recipe))
-
-    query_df = pd.DataFrame(data={'name': dish_name, 'ingredients': [one_recipe], 'cuisine': cuisine_name})
-
-    query_tfidf = transform_tfidf(ingred_tfidf=ingred_tfidf, recipe=query_df)
-    query_matrix = filter_out_cuisine(ingred_word_matrix=ingred_word_matrix, 
-                                      X_df=prepped, 
-                                      cuisine_name=cuisine_name, 
-                                      tfidf=ingred_tfidf)
-                                      
-    query_similar, ingreds_used, recipe_weights = find_closest_recipes(filtered_ingred_word_matrix=query_matrix, 
-                                          recipe_tfidf=query_tfidf, 
-                                          X_df=prepped)
-    
-    return query_similar.to_dict(orient='records'), ingreds_used, recipe_weights
-    
-    
-  else:
-    return("Error, unable to retrieve. Server response code is: ", 
-          resp.status_code)
+    prepped, ingred_tfidf, ingred_word_matrix = import_stored_files()
+    # This function calls the Edamam API, stores the results as a JSON, and
+    # stores the timestamp, dish name, and cuisine name/classification in a
+    # separate csv.
+    now = datetime.now()
+    dt_string = now.strftime("%d_%m_%Y_%H_%M_%S")
+
+    api_base = "https://api.edamam.com/search?"
+
+    # Level up:
+    # Implement lemmatization using trained dataset on input in order to make
+    # future database be less likely to have redundant entries
+    # (e.g., taco vs tacos)
+
+    q = f"q={dish_name}"
+
+    # Level up:
+    # Check a database of dishes to see if this query has been asked for already
+    # If not, do an API call
+
+    # Currently, just does an API call, may hit API limit if continuing with this
+    # version
+    f = open("secrets/edamam.json", "r")
+    cred = json.load(f)
+    f.close()
+
+    app_id = cred["id"]
+    app_id_s = f"&app_id={app_id}"
+
+    app_key = cred["key"]
+    app_key_s = f"&app_key={app_key}"
+
+    # Level up:
+    # Explicitly ask for a few recipes using limiter and make an "average version"
+    # of the input in order to get better results from the API call
+    # limiter = "&from=0&to=4"
+    # API currently defaults to returning 10
+
+    api_call = api_base + q + app_id_s + app_key_s  # + limiter
+
+    resp = requests.get(api_call)
+
+    if resp.status_code == 200:
+        response_dict = resp.json()
+        resp_dict_hits = response_dict["hits"]
+
+        # Store the API result into a JSON and the cuisine type and dish name into a
+        # csv
+        # Heroku does not save files to directory
+        # Can work with EC2
+        # with open(f"../write_data/{dt_string}_{dish_name}_edamam_api_return.json", "w") as f:
+        #   json.dump(resp_dict_hits, f)
+
+        # fields = [dt_string, dish_name, cuisine_name]
+        # with open("../write_data/user_requests.csv", "a", newline='') as f:
+        #   writer = csv.writer(f)
+        #   writer.writerow(fields)
+
+        urls = []
+        labels = []
+        sources = []
+        ingreds = []
+
+        for recipe in resp_dict_hits:
+            recipe_path = recipe["recipe"]
+            urls.append(recipe_path["url"])
+            labels.append(recipe_path["label"])
+            sources.append(recipe_path["source"])
+            ingreds.append([item["text"] for item in recipe_path["ingredients"]])
+
+        all_recipes = {
+            "url": urls,
+            "label": labels,
+            "source": sources,
+            "ingredients": ingreds,
+        }
+
+        recipe_df = pd.DataFrame(all_recipes)
+
+        one_recipe = []
+
+        for listing in recipe_df["ingredients"]:
+            for ingred in listing:
+                one_recipe.append(ingred.lower())
+
+        one_recipe = list(set(one_recipe))
+
+        query_df = pd.DataFrame(
+            data={
+                "name": dish_name,
+                "ingredients": [one_recipe],
+                "cuisine": cuisine_name,
+            }
+        )
+
+        query_tfidf = transform_tfidf(ingred_tfidf=ingred_tfidf, recipe=query_df)
+        query_matrix = filter_out_cuisine(
+            ingred_word_matrix=ingred_word_matrix,
+            X_df=prepped,
+            cuisine_name=cuisine_name,
+            tfidf=ingred_tfidf,
+        )
+
+        query_similar, ingreds_used, recipe_weights = find_closest_recipes(
+            filtered_ingred_word_matrix=query_matrix,
+            recipe_tfidf=query_tfidf,
+            X_df=prepped,
+        )
+
+        return query_similar.to_dict(orient="records"), ingreds_used, recipe_weights
+
+    else:
+        return (
+            "Error, unable to retrieve. Server response code is: ",
+            resp.status_code,
+        )
diff --git a/src/nltk/ohe_dish_predictor.py b/src/nltk/ohe_dish_predictor.py
index accbcf6..691820f 100644
--- a/src/nltk/ohe_dish_predictor.py
+++ b/src/nltk/ohe_dish_predictor.py
@@ -15,8 +15,9 @@
 import numpy as np
 from pandas.io.json import json_normalize
 import nltk
-nltk.download('wordnet')
-nltk.download('stopwords')
+
+nltk.download("wordnet")
+nltk.download("stopwords")
 from nltk.corpus import stopwords
 from nltk import word_tokenize, FreqDist
 from nltk.stem.wordnet import WordNetLemmatizer
@@ -28,239 +29,285 @@
 
 # Define all functions
 
+
 def import_stored_files():
-  # Load in the stored Epicurious database, OHE/CountVectorizer object to transform,
-  # the input, and the OHE/CountVectorizer word matrix from joblib and created by 
-  # prepare_database.py
-  with open("joblib/ohe_recipe_dataframe.joblib", "rb") as fo:
-    prepped = joblib.load("joblib/ohe_recipe_dataframe.joblib")
+    # Load in the stored Epicurious database, OHE/CountVectorizer object to transform,
+    # the input, and the OHE/CountVectorizer word matrix from joblib and created by
+    # prepare_database.py
+    with open("joblib/ohe_recipe_dataframe.joblib", "rb") as fo:
+        prepped = joblib.load("joblib/ohe_recipe_dataframe.joblib")
 
-  with open("joblib/recipe_ohe.joblib", "rb") as fo:
-    ingred_ohe = joblib.load("joblib/recipe_ohe.joblib")
+    with open("joblib/recipe_ohe.joblib", "rb") as fo:
+        ingred_ohe = joblib.load("joblib/recipe_ohe.joblib")
 
-  with open("joblib/recipe_word_matrix_ohe.joblib", "rb") as fo:
-    ingred_word_matrix = joblib.load("joblib/recipe_word_matrix_ohe.joblib")
+    with open("joblib/recipe_word_matrix_ohe.joblib", "rb") as fo:
+        ingred_word_matrix = joblib.load("joblib/recipe_word_matrix_ohe.joblib")
 
-  return prepped, ingred_ohe, ingred_word_matrix
+    return prepped, ingred_ohe, ingred_word_matrix
 
 
 def transform_ohe(ingred_ohe, recipe):
-  # This function takes in a OHE/CountVectorizer object and a recipe, then 
-  # creates/transforms the given recipe into a CountVectorizer form
-  pd.set_option('display.max_colwidth', 500)
-  print('Raw ingredients')
-  print(recipe['ingredients'])
-  ingreds = recipe['ingredients'].apply(" ".join).str.lower()
-  print(ingreds)
-  response = ingred_ohe.transform(ingreds)
-  transformed_recipe = pd.DataFrame(response.toarray(),
-                                    columns=ingred_ohe.get_feature_names(),
-                                    index=recipe.index)
-  return transformed_recipe
-
-
-def filter_out_cuisine(ingred_word_matrix, 
-                        X_df, 
-                        cuisine_name, 
-                        ohe):
-  # This function takes in the ingredient word matrix (from joblib), a 
-  # dataframe made from the database (from joblib), the user inputted cuisine 
-  # name, and the ingredient OHE/CountVectorizer object (from joblib) and returns
-  # a word sub matrix that removes all recipes with the same cuisine as the 
-  # inputted recipe.
-
-  east_asian = ['Asian', 'Chinese', 'Japanese']
-
-  southeast_asian = ['Thai', 'Vietnamese']
-
-  euro_islands = ['English', 'Irish']
-
-  euro_continental = ['French', 'German', 'Eastern European']
-
-  mediterranean = ['Italian', 'Mediterranean', 'Kosher', 'Middle Eastern']
-
-  all_cuisines = ['African', 'American', 'Asian', 'Cajun/Creole', 'Chinese', 'Eastern European', 'English',
-                  'French', 'German', 'Indian', 'Irish', 'Italian', 'Japanese', 'Kosher', 'Latin American', 
-                  'Mediterranean', 'Mexican', 'Middle Eastern', 'Moroccan', 'Scandinavian', 'Southwestern', 
-                  'Thai', 'Vietnamese']
-
-  if cuisine_name in east_asian:
-    choices = [cuis for cuis in all_cuisines if cuis not in east_asian]
-  elif cuisine_name in southeast_asian:
-    choices = [cuis for cuis in all_cuisines if cuis not in southeast_asian]
-  elif cuisine_name in euro_islands:
-    choices = [cuis for cuis in all_cuisines if cuis not in euro_islands]
-  elif cuisine_name in euro_continental:
-    choices = [cuis for cuis in all_cuisines if cuis not in euro_continental]
-  elif cuisine_name in mediterranean:
-    choices = [cuis for cuis in all_cuisines if cuis not in mediterranean]
-  else:
-    choices = [cuis for cuis in all_cuisines if cuis != cuisine_name]
-
-  combo = pd.concat([ingred_word_matrix, X_df['imputed_label']], axis=1)
-  filtered_ingred_word_matrix = combo[combo['imputed_label'].isin(choices)].drop('imputed_label', 
-                                                                    axis=1)
-  return filtered_ingred_word_matrix
+    # This function takes in a OHE/CountVectorizer object and a recipe, then
+    # creates/transforms the given recipe into a CountVectorizer form
+    pd.set_option("display.max_colwidth", 500)
+    print("Raw ingredients")
+    print(recipe["ingredients"])
+    ingreds = recipe["ingredients"].apply(" ".join).str.lower()
+    print(ingreds)
+    response = ingred_ohe.transform(ingreds)
+    transformed_recipe = pd.DataFrame(
+        response.toarray(), columns=ingred_ohe.get_feature_names(), index=recipe.index
+    )
+    return transformed_recipe
+
+
+def filter_out_cuisine(ingred_word_matrix, X_df, cuisine_name, ohe):
+    # This function takes in the ingredient word matrix (from joblib), a
+    # dataframe made from the database (from joblib), the user inputted cuisine
+    # name, and the ingredient OHE/CountVectorizer object (from joblib) and returns
+    # a word sub matrix that removes all recipes with the same cuisine as the
+    # inputted recipe.
+
+    east_asian = ["Asian", "Chinese", "Japanese"]
+
+    southeast_asian = ["Thai", "Vietnamese"]
+
+    euro_islands = ["English", "Irish"]
+
+    euro_continental = ["French", "German", "Eastern European"]
+
+    mediterranean = ["Italian", "Mediterranean", "Kosher", "Middle Eastern"]
+
+    all_cuisines = [
+        "African",
+        "American",
+        "Asian",
+        "Cajun/Creole",
+        "Chinese",
+        "Eastern European",
+        "English",
+        "French",
+        "German",
+        "Indian",
+        "Irish",
+        "Italian",
+        "Japanese",
+        "Kosher",
+        "Latin American",
+        "Mediterranean",
+        "Mexican",
+        "Middle Eastern",
+        "Moroccan",
+        "Scandinavian",
+        "Southwestern",
+        "Thai",
+        "Vietnamese",
+    ]
+
+    if cuisine_name in east_asian:
+        choices = [cuis for cuis in all_cuisines if cuis not in east_asian]
+    elif cuisine_name in southeast_asian:
+        choices = [cuis for cuis in all_cuisines if cuis not in southeast_asian]
+    elif cuisine_name in euro_islands:
+        choices = [cuis for cuis in all_cuisines if cuis not in euro_islands]
+    elif cuisine_name in euro_continental:
+        choices = [cuis for cuis in all_cuisines if cuis not in euro_continental]
+    elif cuisine_name in mediterranean:
+        choices = [cuis for cuis in all_cuisines if cuis not in mediterranean]
+    else:
+        choices = [cuis for cuis in all_cuisines if cuis != cuisine_name]
+
+    combo = pd.concat([ingred_word_matrix, X_df["imputed_label"]], axis=1)
+    filtered_ingred_word_matrix = combo[combo["imputed_label"].isin(choices)].drop(
+        "imputed_label", axis=1
+    )
+    return filtered_ingred_word_matrix
 
 
 def picture_placer(filename):
-  # This function takes in a filename and returns the relative location inside
-  # an HTML tag
-  location = f'photos/{filename}'
-  return location
+    # This function takes in a filename and returns the relative location inside
+    # an HTML tag
+    location = f"photos/{filename}"
+    return location
 
 
 def link_maker(recipe_link):
-  # This function takes in the incomplete recipe link from the dataframe and 
-  # returns the complete one.
-  full_link = f'https://www.epicurious.com{recipe_link}'
-  return full_link
-
-
-def find_closest_recipes(filtered_ingred_word_matrix, 
-                          recipe_ohe, 
-                          X_df):
-  # This function takes in the filtered ingredient word matrix from function
-  # filter_out_cuisine, the ohe recipe from function transform_ohe, and 
-  # a dataframe made from the database (from joblib) and returns a Pandas 
-  # DataFrame with the top five most similar recipes and a Pandas Series 
-  # containing the similarity amount
-
-  m2 = (recipe_ohe != 0).any()
-  recipe_ohe_weights = recipe_ohe.iloc[0][recipe_ohe.iloc[0] != 0].to_dict()
-
-  ingreds_used = m2.index[m2].tolist()
-  search_vec = np.array(recipe_ohe).reshape(1,-1)
-  res_cos_sim = cosine_similarity(filtered_ingred_word_matrix, search_vec)
-  top_five = np.argsort(res_cos_sim.flatten())[-5:][::-1]
-  
-  top_five_list = top_five.tolist()
-  
-  recipe_ids = [filtered_ingred_word_matrix.iloc[idx].name for idx in top_five]
-  
-  suggest_df = X_df.loc[recipe_ids]
-  proximity = pd.DataFrame(data=res_cos_sim[top_five], 
-                            columns=['cosine_similarity'], 
-                            index=suggest_df.index)
-  
-  full_df = pd.concat([suggest_df, proximity], axis=1)
-  expand_photo_df = pd.concat([full_df.drop(["photoData"], axis=1), 
-                                full_df["photoData"].apply(pd.Series)], axis=1)
-  reduced = expand_photo_df[['hed', 'recipe_url', 'filename', 'imputed_label', 'ingredients', 'cosine_similarity']].dropna(axis=1)
-  reduced['photo'] = reduced['filename'].apply(picture_placer)
-  reduced['fixed_url'] = reduced["recipe_url"].apply(link_maker)
-  reduced['rounded'] = reduced['cosine_similarity'].round(3)
-
-  reduced = reduced.drop('recipe_url', axis=1)
-
-  ingr_weights = [filtered_ingred_word_matrix.iloc[num][filtered_ingred_word_matrix.iloc[num] != 0].to_dict() for num in top_five_list]
-  reduced['ingred_weights'] = ingr_weights
-  print(ingr_weights)
-  return reduced, ingreds_used, recipe_ohe_weights
+    # This function takes in the incomplete recipe link from the dataframe and
+    # returns the complete one.
+    full_link = f"https://www.epicurious.com{recipe_link}"
+    return full_link
+
+
+def find_closest_recipes(filtered_ingred_word_matrix, recipe_ohe, X_df):
+    # This function takes in the filtered ingredient word matrix from function
+    # filter_out_cuisine, the ohe recipe from function transform_ohe, and
+    # a dataframe made from the database (from joblib) and returns a Pandas
+    # DataFrame with the top five most similar recipes and a Pandas Series
+    # containing the similarity amount
+
+    m2 = (recipe_ohe != 0).any()
+    recipe_ohe_weights = recipe_ohe.iloc[0][recipe_ohe.iloc[0] != 0].to_dict()
+
+    ingreds_used = m2.index[m2].tolist()
+    search_vec = np.array(recipe_ohe).reshape(1, -1)
+    res_cos_sim = cosine_similarity(filtered_ingred_word_matrix, search_vec)
+    top_five = np.argsort(res_cos_sim.flatten())[-5:][::-1]
+
+    top_five_list = top_five.tolist()
+
+    recipe_ids = [filtered_ingred_word_matrix.iloc[idx].name for idx in top_five]
+
+    suggest_df = X_df.loc[recipe_ids]
+    proximity = pd.DataFrame(
+        data=res_cos_sim[top_five],
+        columns=["cosine_similarity"],
+        index=suggest_df.index,
+    )
+
+    full_df = pd.concat([suggest_df, proximity], axis=1)
+    expand_photo_df = pd.concat(
+        [full_df.drop(["photoData"], axis=1), full_df["photoData"].apply(pd.Series)],
+        axis=1,
+    )
+    reduced = expand_photo_df[
+        [
+            "hed",
+            "recipe_url",
+            "filename",
+            "imputed_label",
+            "ingredients",
+            "cosine_similarity",
+        ]
+    ].dropna(axis=1)
+    reduced["photo"] = reduced["filename"].apply(picture_placer)
+    reduced["fixed_url"] = reduced["recipe_url"].apply(link_maker)
+    reduced["rounded"] = reduced["cosine_similarity"].round(3)
+
+    reduced = reduced.drop("recipe_url", axis=1)
+
+    ingr_weights = [
+        filtered_ingred_word_matrix.iloc[num][
+            filtered_ingred_word_matrix.iloc[num] != 0
+        ].to_dict()
+        for num in top_five_list
+    ]
+    reduced["ingred_weights"] = ingr_weights
+    print(ingr_weights)
+    return reduced, ingreds_used, recipe_ohe_weights
 
 
 def find_similar_dishes(dish_name, cuisine_name):
-  prepped, ingred_ohe, ingred_word_matrix = import_stored_files()
-  # This function calls the Edamam API, stores the results as a JSON, and 
-  # stores the timestamp, dish name, and cuisine name/classification in a 
-  # separate csv.
-  now = datetime.now()
-  dt_string = now.strftime("%d_%m_%Y_%H_%M_%S")
-
-  api_base = "https://api.edamam.com/search?"
-
-  # Level up:
-  # Implement lemmatization using trained dataset on input in order to make 
-  # future database be less likely to have redundant entries 
-  # (e.g., taco vs tacos)
-
-  q = f"q={dish_name}"
-
-  # Level up:
-  # Check a database of dishes to see if this query has been asked for already
-  # If not, do an API call
-
-  # Currently, just does an API call, may hit API limit if continuing with this
-  # version
-  f = open("secrets/edamam.json","r")
-  cred = json.load(f)
-  f.close()
-
-  app_id = cred["id"]
-  app_id_s = f"&app_id={app_id}"
-
-  app_key = cred["key"]
-  app_key_s = f"&app_key={app_key}"
-  
-  # Level up: 
-  # Explicitly ask for a few recipes using limiter and make an "average version"
-  # of the input in order to get better results from the API call
-  # limiter = "&from=0&to=4"
-  # API currently defaults to returning 10
-
-  api_call = api_base + q+ app_id_s + app_key_s #+ limiter
-
-  resp = requests.get(api_call)
-
-  if resp.status_code == 200:
-    response_dict = resp.json()
-    resp_dict_hits = response_dict['hits']
-    
-    # Store the API result into a JSON and the cuisine type and dish name into a 
-    # csv
-    # Heroku does not save files to directory
-    # Can work with EC2
-    # with open(f"../write_data/{dt_string}_{dish_name}_edamam_api_return.json", "w") as f:
-    #   json.dump(resp_dict_hits, f)
-
-    # fields = [dt_string, dish_name, cuisine_name]
-    # with open("../write_data/user_requests.csv", "a", newline='') as f:
-    #   writer = csv.writer(f)
-    #   writer.writerow(fields)
-
-    urls = []
-    labels = []
-    sources = []
-    ingreds = []
-
-    for recipe in resp_dict_hits:
-        recipe_path = recipe['recipe']
-        urls.append(recipe_path['url'])
-        labels.append(recipe_path['label'])
-        sources.append(recipe_path['source'])
-        ingreds.append([item['text'] for item in recipe_path['ingredients']])
-        
-    all_recipes = {'url': urls,
-                  'label': labels, 
-                  'source': sources, 
-                  'ingredients': ingreds
-                  }
-
-    recipe_df = pd.DataFrame(all_recipes)
-
-    one_recipe = []
-
-    for listing in recipe_df['ingredients']:
-        for ingred in listing:
-            one_recipe.append(ingred.lower())
-        
-    one_recipe = list(set(one_recipe))
-
-    query_df = pd.DataFrame(data={'name': dish_name, 'ingredients': [one_recipe], 'cuisine': cuisine_name})
-
-    query_ohe = transform_ohe(ingred_ohe=ingred_ohe, recipe=query_df)
-    query_matrix = filter_out_cuisine(ingred_word_matrix=ingred_word_matrix, 
-                                      X_df=prepped, 
-                                      cuisine_name=cuisine_name, 
-                                      ohe=ingred_ohe)
-                                      
-    query_similar, ingreds_used, rec_weights = find_closest_recipes(filtered_ingred_word_matrix=query_matrix, 
-                                          recipe_ohe=query_ohe, 
-                                          X_df=prepped)
-    
-    return query_similar.to_dict(orient='records'), ingreds_used, rec_weights
-    
-    
-  else:
-    return("Error, unable to retrieve. Server response code is: ", 
-          resp.status_code)
+    prepped, ingred_ohe, ingred_word_matrix = import_stored_files()
+    # This function calls the Edamam API, stores the results as a JSON, and
+    # stores the timestamp, dish name, and cuisine name/classification in a
+    # separate csv.
+    now = datetime.now()
+    dt_string = now.strftime("%d_%m_%Y_%H_%M_%S")
+
+    api_base = "https://api.edamam.com/search?"
+
+    # Level up:
+    # Implement lemmatization using trained dataset on input in order to make
+    # future database be less likely to have redundant entries
+    # (e.g., taco vs tacos)
+
+    q = f"q={dish_name}"
+
+    # Level up:
+    # Check a database of dishes to see if this query has been asked for already
+    # If not, do an API call
+
+    # Currently, just does an API call, may hit API limit if continuing with this
+    # version
+    f = open("secrets/edamam.json", "r")
+    cred = json.load(f)
+    f.close()
+
+    app_id = cred["id"]
+    app_id_s = f"&app_id={app_id}"
+
+    app_key = cred["key"]
+    app_key_s = f"&app_key={app_key}"
+
+    # Level up:
+    # Explicitly ask for a few recipes using limiter and make an "average version"
+    # of the input in order to get better results from the API call
+    # limiter = "&from=0&to=4"
+    # API currently defaults to returning 10
+
+    api_call = api_base + q + app_id_s + app_key_s  # + limiter
+
+    resp = requests.get(api_call)
+
+    if resp.status_code == 200:
+        response_dict = resp.json()
+        resp_dict_hits = response_dict["hits"]
+
+        # Store the API result into a JSON and the cuisine type and dish name into a
+        # csv
+        # Heroku does not save files to directory
+        # Can work with EC2
+        # with open(f"../write_data/{dt_string}_{dish_name}_edamam_api_return.json", "w") as f:
+        #   json.dump(resp_dict_hits, f)
+
+        # fields = [dt_string, dish_name, cuisine_name]
+        # with open("../write_data/user_requests.csv", "a", newline='') as f:
+        #   writer = csv.writer(f)
+        #   writer.writerow(fields)
+
+        urls = []
+        labels = []
+        sources = []
+        ingreds = []
+
+        for recipe in resp_dict_hits:
+            recipe_path = recipe["recipe"]
+            urls.append(recipe_path["url"])
+            labels.append(recipe_path["label"])
+            sources.append(recipe_path["source"])
+            ingreds.append([item["text"] for item in recipe_path["ingredients"]])
+
+        all_recipes = {
+            "url": urls,
+            "label": labels,
+            "source": sources,
+            "ingredients": ingreds,
+        }
+
+        recipe_df = pd.DataFrame(all_recipes)
+
+        one_recipe = []
+
+        for listing in recipe_df["ingredients"]:
+            for ingred in listing:
+                one_recipe.append(ingred.lower())
+
+        one_recipe = list(set(one_recipe))
+
+        query_df = pd.DataFrame(
+            data={
+                "name": dish_name,
+                "ingredients": [one_recipe],
+                "cuisine": cuisine_name,
+            }
+        )
+
+        query_ohe = transform_ohe(ingred_ohe=ingred_ohe, recipe=query_df)
+        query_matrix = filter_out_cuisine(
+            ingred_word_matrix=ingred_word_matrix,
+            X_df=prepped,
+            cuisine_name=cuisine_name,
+            ohe=ingred_ohe,
+        )
+
+        query_similar, ingreds_used, rec_weights = find_closest_recipes(
+            filtered_ingred_word_matrix=query_matrix, recipe_ohe=query_ohe, X_df=prepped
+        )
+
+        return query_similar.to_dict(orient="records"), ingreds_used, rec_weights
+
+    else:
+        return (
+            "Error, unable to retrieve. Server response code is: ",
+            resp.status_code,
+        )
diff --git a/src/nltk/prepare_ohe_database.py b/src/nltk/prepare_ohe_database.py
index 7ba5dce..7db9b2f 100644
--- a/src/nltk/prepare_ohe_database.py
+++ b/src/nltk/prepare_ohe_database.py
@@ -12,9 +12,10 @@
 import pandas as pd
 import numpy as np
 import nltk
-nltk.download('wordnet')
-nltk.download('stopwords')
-nltk.download('punkt')
+
+nltk.download("wordnet")
+nltk.download("stopwords")
+nltk.download("punkt")
 from nltk.corpus import stopwords
 from nltk.stem.wordnet import WordNetLemmatizer
 from nltk.tokenize import sent_tokenize, word_tokenize
@@ -39,12 +40,12 @@
 
 # Define functions
 def cuisine_namer(text):
-    """This function converts redundant and/or rare categories into more common 
-  ones/umbrella ones.
-  
-  In the future, there's a hope that this renaming mechanism will not have 
-  under sampled cuisine tags.
-  """
+    """This function converts redundant and/or rare categories into more common
+    ones/umbrella ones.
+
+    In the future, there's a hope that this renaming mechanism will not have
+    under sampled cuisine tags.
+    """
     if text == "Central American/Caribbean":
         return "Caribbean"
     elif text == "Jewish":
@@ -74,8 +75,8 @@ def cuisine_namer(text):
 
 
 def load_data(filepath, test_size=0.1, random_state=10):
-    """ This function uses a filepath, test_size, and random_state
-    to load the Epicurious JSON into a dataframe and then split into 
+    """This function uses a filepath, test_size, and random_state
+    to load the Epicurious JSON into a dataframe and then split into
     train/test sets."""
     with open(filepath, "r") as f:
         datastore = json.load(f)
@@ -87,121 +88,117 @@ def load_data(filepath, test_size=0.1, random_state=10):
 
 
 def prep_data(X):
-  """ This function takes a dataframe X, drops columns that will not be used,
-  expands the hierarchical column into the dataframe, renames the columns
-  to be more human-readable, and drops one column created during dataframe
-  expansion"""
-  X.drop(
-      [
-          "pubDate",
-          "author",
-          "type",
-          "aggregateRating",
-          "reviewsCount",
-          "willMakeAgainPct",
-          "dateCrawled",
-          'prepSteps'
-      ],
-      axis=1,
-      inplace=True,
-  )
-
-  X.rename({'url': 'recipe_url'}, axis=1, inplace=True)     
-  
-  concat = pd.concat([X.drop(["tag"], axis=1), X["tag"].apply(pd.Series)], axis=1)
-  concat.drop(
-      [
-          0,
-          "photosBadgeAltText",
-          "photosBadgeFileName",
-          "photosBadgeID",
-          "photosBadgeRelatedUri",
-          "url"
-      ],
-      axis=1,
-      inplace=True,
-  )
-  cuisine_only = concat[concat["category"] == "cuisine"]
-  cuisine_only.dropna(axis=0, inplace=True)
-  cuisine_only["imputed_label"] = cuisine_only["name"].apply(cuisine_namer)
-  cuisine_only.drop('name', axis=1, inplace=True)
-  return cuisine_only
+    """This function takes a dataframe X, drops columns that will not be used,
+    expands the hierarchical column into the dataframe, renames the columns
+    to be more human-readable, and drops one column created during dataframe
+    expansion"""
+    X.drop(
+        [
+            "pubDate",
+            "author",
+            "type",
+            "aggregateRating",
+            "reviewsCount",
+            "willMakeAgainPct",
+            "dateCrawled",
+            "prepSteps",
+        ],
+        axis=1,
+        inplace=True,
+    )
+
+    X.rename({"url": "recipe_url"}, axis=1, inplace=True)
+
+    concat = pd.concat([X.drop(["tag"], axis=1), X["tag"].apply(pd.Series)], axis=1)
+    concat.drop(
+        [
+            0,
+            "photosBadgeAltText",
+            "photosBadgeFileName",
+            "photosBadgeID",
+            "photosBadgeRelatedUri",
+            "url",
+        ],
+        axis=1,
+        inplace=True,
+    )
+    cuisine_only = concat[concat["category"] == "cuisine"]
+    cuisine_only.dropna(axis=0, inplace=True)
+    cuisine_only["imputed_label"] = cuisine_only["name"].apply(cuisine_namer)
+    cuisine_only.drop("name", axis=1, inplace=True)
+    return cuisine_only
 
 
 def fit_transform_ohe_matrix(X_df, stopwords_list):
-  ohe = CountVectorizer(
+    ohe = CountVectorizer(
         stop_words=stopwords_list,
         min_df=2,
         token_pattern=r"(?u)\b[a-zA-Z]{2,}\b",
         preprocessor=lemmatizer.lemmatize,
         binary=True,
     )
-  ingreds = X_df["ingredients"].apply(" ".join).str.lower()
-  ohe.fit(ingreds)
-  response = ohe.transform(ingreds)
-  ohe_matrix = pd.DataFrame(response.toarray(), 
-                              columns=ohe.get_feature_names(), 
-                              index=X_df.index
-                            )
-  return ohe, ohe_matrix
-  
+    ingreds = X_df["ingredients"].apply(" ".join).str.lower()
+    ohe.fit(ingreds)
+    response = ohe.transform(ingreds)
+    ohe_matrix = pd.DataFrame(
+        response.toarray(), columns=ohe.get_feature_names(), index=X_df.index
+    )
+    return ohe, ohe_matrix
+
 
 def transform_ohe(ohe, recipe):
-  ingreds = recipe['ingredients'].apply(" ".join).str.lower()
-  response = ohe.transform(ingreds)
+    ingreds = recipe["ingredients"].apply(" ".join).str.lower()
+    response = ohe.transform(ingreds)
 
-  ohe_transformed_recipe = pd.DataFrame(
-                                        response.toarray(),
-                                        columns=ohe.get_feature_names(),
-                                        index=recipe.index
-                                        )
-  return ohe_transformed_recipe
+    ohe_transformed_recipe = pd.DataFrame(
+        response.toarray(), columns=ohe.get_feature_names(), index=recipe.index
+    )
+    return ohe_transformed_recipe
 
 
 def transform_from_test_ohe(ohe, df, idx):
-  recipe = df['ingredients'].iloc[idx].apply(' '.join).str.lower()
-  response = ohe.transform(recipe)
-  ohe_transformed_test_recipe = pd.DataFrame(
-                                            response.toarray(), 
-                                            columns=ohe.get_feature_names()
-                                            )
+    recipe = df["ingredients"].iloc[idx].apply(" ".join).str.lower()
+    response = ohe.transform(recipe)
+    ohe_transformed_test_recipe = pd.DataFrame(
+        response.toarray(), columns=ohe.get_feature_names()
+    )
 
-  return ohe_transformed_test_recipe
+    return ohe_transformed_test_recipe
 
 
 def filter_out_cuisine(ingred_word_matrix, X_df, cuisine_name, ohe):
-  combo = pd.concat([ingred_word_matrix, X_df["imputed_label"]], axis=1)
-  filtered_ingred_word_matrix = combo[combo["imputed_label"] != cuisine_name].drop(
-      "imputed_label", axis=1
-  )
-  return filtered_ingred_word_matrix
+    combo = pd.concat([ingred_word_matrix, X_df["imputed_label"]], axis=1)
+    filtered_ingred_word_matrix = combo[combo["imputed_label"] != cuisine_name].drop(
+        "imputed_label", axis=1
+    )
+    return filtered_ingred_word_matrix
 
 
 def find_closest_recipes(filtered_ingred_word_matrix, recipe_ohe_transform, X_df):
-  search_vec = np.array(recipe_ohe_transform).reshape(1, -1)
-  res_cos_sim = cosine_similarity(filtered_ingred_word_matrix, search_vec)
-  top_five = np.argsort(res_cos_sim.flatten())[-5:][::-1]
-  proximity = res_cos_sim[top_five]
-  recipe_ids = [filtered_ingred_word_matrix.iloc[idx].name for idx in top_five]
-  suggest_df = X_df.loc[recipe_ids]
+    search_vec = np.array(recipe_ohe_transform).reshape(1, -1)
+    res_cos_sim = cosine_similarity(filtered_ingred_word_matrix, search_vec)
+    top_five = np.argsort(res_cos_sim.flatten())[-5:][::-1]
+    proximity = res_cos_sim[top_five]
+    recipe_ids = [filtered_ingred_word_matrix.iloc[idx].name for idx in top_five]
+    suggest_df = X_df.loc[recipe_ids]
 
-  return suggest_df, proximity
+    return suggest_df, proximity
 
 
 # Create the dataframe
 X_train, X_test = load_data(filename)
 
 with open("../joblib/ohe_test_subset.joblib", "wb") as fo:
-  joblib.dump(X_test, fo, compress=True)
+    joblib.dump(X_test, fo, compress=True)
 
 prepped = prep_data(X_train)
 with open("../joblib/ohe_recipe_dataframe.joblib", "wb") as fo:
-  joblib.dump(prepped, fo, compress=True)
+    joblib.dump(prepped, fo, compress=True)
 
 # Create the ingredients OHE matrix
 ingred_ohe, ingred_word_matrix = fit_transform_ohe_matrix(prepped, stopwords_list)
 with open("../joblib/recipe_ohe.joblib", "wb") as fo:
-  joblib.dump(ingred_ohe, fo, compress=True)
+    joblib.dump(ingred_ohe, fo, compress=True)
 
 with open("../joblib/recipe_word_matrix_ohe.joblib", "wb") as fo:
-  joblib.dump(ingred_word_matrix, fo, compress=True)
+    joblib.dump(ingred_word_matrix, fo, compress=True)