diff --git a/projects/NaturalLanguageProcessing/sentiment_analysis.ipynb b/projects/NaturalLanguageProcessing/sentiment_analysis.ipynb
index 70b008cb9..8b10868a2 100644
--- a/projects/NaturalLanguageProcessing/sentiment_analysis.ipynb
+++ b/projects/NaturalLanguageProcessing/sentiment_analysis.ipynb
@@ -78,12 +78,23 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 1,
"metadata": {
- "cellView": "form",
- "execution": {}
+ "cellView": "form"
},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
+ "torchvision 0.14.0 requires torch==1.13.0, but you have torch 2.3.1 which is incompatible.\u001b[0m\u001b[31m\n",
+ "\u001b[0m\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
+ "torchvision 0.14.0 requires torch==1.13.0, but you have torch 2.3.1 which is incompatible.\u001b[0m\u001b[31m\n",
+ "\u001b[0m"
+ ]
+ }
+ ],
"source": [
"# @title Install dependencies\n",
"!pip install pandas --quiet\n",
@@ -93,11 +104,20 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {
- "execution": {}
- },
- "outputs": [],
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/home/yuda/code/neuromatch/course-content-dl/venv/lib/python3.9/site-packages/torchtext/data/__init__.py:4: UserWarning: \n",
+ "/!\\ IMPORTANT WARNING ABOUT TORCHTEXT STATUS /!\\ \n",
+ "Torchtext is deprecated and the last released version will be 0.18 (this one). You can silence this warning by calling the following at the beginnign of your scripts: `import torchtext; torchtext.disable_torchtext_deprecation_warning()`\n",
+ " warnings.warn(torchtext._TORCHTEXT_DEPRECATION_MSG)\n"
+ ]
+ }
+ ],
"source": [
"# We import some libraries to load the dataset\n",
"import os\n",
@@ -135,11 +155,80 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {
- "execution": {}
- },
- "outputs": [],
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "cd6b527daf25440a8acc7a7645af679d",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Downloading builder script: 0%| | 0.00/4.03k [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "5b7c93b4ee524a01adec2669170ee097",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Downloading readme: 0%| | 0.00/6.84k [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "19e6cbe3cb7648b4b5e0b2ce60c12d6b",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Downloading data: 0%| | 0.00/81.4M [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "e5bfc518fd6a48deb991309cec03facd",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Generating train split: 0%| | 0/1600000 [00:00, ? examples/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "983915e475a747bd920d53cd924eb7ca",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Generating test split: 0%| | 0/498 [00:00, ? examples/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
"source": [
"from datasets import load_dataset\n",
"\n",
@@ -148,10 +237,8 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {
- "execution": {}
- },
+ "execution_count": 4,
+ "metadata": {},
"outputs": [
{
"data": {
@@ -175,7 +262,7 @@
"
\n",
" | \n",
" polarity | \n",
- " id | \n",
+ " user | \n",
" date | \n",
" query | \n",
" user | \n",
@@ -186,7 +273,7 @@
"
\n",
" 0 | \n",
" 0 | \n",
- " 1467810369 | \n",
+ " _TheSpecialOne_ | \n",
" Mon Apr 06 22:19:45 PDT 2009 | \n",
" NO_QUERY | \n",
" _TheSpecialOne_ | \n",
@@ -195,7 +282,7 @@
"
\n",
" 1 | \n",
" 0 | \n",
- " 1467810672 | \n",
+ " scotthamilton | \n",
" Mon Apr 06 22:19:49 PDT 2009 | \n",
" NO_QUERY | \n",
" scotthamilton | \n",
@@ -204,7 +291,7 @@
"
\n",
" 2 | \n",
" 0 | \n",
- " 1467810917 | \n",
+ " mattycus | \n",
" Mon Apr 06 22:19:53 PDT 2009 | \n",
" NO_QUERY | \n",
" mattycus | \n",
@@ -213,7 +300,7 @@
"
\n",
" 3 | \n",
" 0 | \n",
- " 1467811184 | \n",
+ " ElleCTF | \n",
" Mon Apr 06 22:19:57 PDT 2009 | \n",
" NO_QUERY | \n",
" ElleCTF | \n",
@@ -222,7 +309,7 @@
"
\n",
" 4 | \n",
" 0 | \n",
- " 1467811193 | \n",
+ " Karoli | \n",
" Mon Apr 06 22:19:57 PDT 2009 | \n",
" NO_QUERY | \n",
" Karoli | \n",
@@ -233,20 +320,23 @@
""
],
"text/plain": [
- " polarity ... text\n",
- "0 0 ... @switchfoot http://twitpic.com/2y1zl - Awww, t...\n",
- "1 0 ... is upset that he can't update his Facebook by ...\n",
- "2 0 ... @Kenichan I dived many times for the ball. Man...\n",
- "3 0 ... my whole body feels itchy and like its on fire \n",
- "4 0 ... @nationwideclass no, it's not behaving at all....\n",
- "\n",
- "[5 rows x 6 columns]"
+ " polarity user date query \\\n",
+ "0 0 _TheSpecialOne_ Mon Apr 06 22:19:45 PDT 2009 NO_QUERY \n",
+ "1 0 scotthamilton Mon Apr 06 22:19:49 PDT 2009 NO_QUERY \n",
+ "2 0 mattycus Mon Apr 06 22:19:53 PDT 2009 NO_QUERY \n",
+ "3 0 ElleCTF Mon Apr 06 22:19:57 PDT 2009 NO_QUERY \n",
+ "4 0 Karoli Mon Apr 06 22:19:57 PDT 2009 NO_QUERY \n",
+ "\n",
+ " user text \n",
+ "0 _TheSpecialOne_ @switchfoot http://twitpic.com/2y1zl - Awww, t... \n",
+ "1 scotthamilton is upset that he can't update his Facebook by ... \n",
+ "2 mattycus @Kenichan I dived many times for the ball. Man... \n",
+ "3 ElleCTF my whole body feels itchy and like its on fire \n",
+ "4 Karoli @nationwideclass no, it's not behaving at all.... "
]
},
"execution_count": 4,
- "metadata": {
- "tags": []
- },
+ "metadata": {},
"output_type": "execute_result"
}
],
@@ -270,10 +360,8 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {
- "execution": {}
- },
+ "execution_count": 5,
+ "metadata": {},
"outputs": [],
"source": [
"X = df.text.values\n",
@@ -297,10 +385,8 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {
- "execution": {}
- },
+ "execution_count": 6,
+ "metadata": {},
"outputs": [
{
"name": "stdout",
@@ -330,10 +416,8 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {
- "execution": {}
- },
+ "execution_count": 7,
+ "metadata": {},
"outputs": [
{
"name": "stdout",
@@ -353,56 +437,36 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {
- "execution": {}
- },
+ "execution_count": 8,
+ "metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
- "model_id": "499e7fb54aa048afb3cba78dd8d6bb0e",
+ "model_id": "cd7802db570b408eb5f29af92ca95be1",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
- "HBox(children=(FloatProgress(value=0.0, max=1280000.0), HTML(value='')))"
+ " 0%| | 0/1280000 [00:00, ?it/s]"
]
},
- "metadata": {
- "tags": []
- },
+ "metadata": {},
"output_type": "display_data"
},
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n"
- ]
- },
{
"data": {
"application/vnd.jupyter.widget-view+json": {
- "model_id": "fff9bd0ae74e46b0ad97ad980a834a58",
+ "model_id": "dcc80b45cf1c40769f49d27d96bbeaed",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
- "HBox(children=(FloatProgress(value=0.0, max=320000.0), HTML(value='')))"
+ " 0%| | 0/320000 [00:00, ?it/s]"
]
},
- "metadata": {
- "tags": []
- },
+ "metadata": {},
"output_type": "display_data"
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n"
- ]
}
],
"source": [
@@ -421,10 +485,8 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {
- "execution": {}
- },
+ "execution_count": 9,
+ "metadata": {},
"outputs": [
{
"name": "stdout",
@@ -458,10 +520,8 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {
- "execution": {}
- },
+ "execution_count": 10,
+ "metadata": {},
"outputs": [
{
"name": "stdout",
@@ -487,22 +547,17 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {
- "execution": {}
- },
+ "execution_count": 11,
+ "metadata": {},
"outputs": [
{
"data": {
- "image/png": "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",
+ "image/png": "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",
"text/plain": [
- "