Merge pull request #25 from JuBiotech/finish-raw-data

Add and re-arrange raw data

.gitignore

@@ -605,3 +605,4 @@ idata_summary_*.xlsx
 idata_*
 *Sandbox*.ipynb
 !/docs/source/notebooks/*.png
+!/docs/source/notebooks/paper raw data/**/*.npy

docs/source/markdown/Installation.md

@@ -11,20 +11,8 @@ If you have already installed Miniconda, you can install Mamba on top of it but
 The newest conda version should also work, just replace `mamba` with `conda` in step 2.)
 ```
 
-2. Create a new Python environment (replace "name_of_environment" with your desired name) in the command line via
+2. Create a new Python environment in the command line using the provided [`environment.yml`](https://github.com/JuBiotech/peak-performance/blob/main/environment.yml) file from the repo.
+   Download `environment.yml` first, then navigate to its location on the command line interface and run the following command:
 ```
-mamba create -c conda-forge -n name_of_environment pymc nutpie arviz jupyter matplotlib openpyxl "python=3.10"
-```
-3. Install PeakPerformance:
-- __Recommended__: Clone the PeakPerformance repository, then open the command line, navigate to your local clone, activate the Python environment created in the previous step, and install PeakPerformance via
-```
-pip install -e .
-```
-- __Alternative a__: Activate the Python environment created in the previous step and install PeakPerformance via PyPI using
-```
-pip install peak-performance
-```
-- __Alternative b__: Download the latest Python wheel, then open the command line, navigate to the directory containing the wheel, activate the Python environment created above, and install PeakPerformance via
-```
-pip install name_of_wheel.whl
+mamba env create -f environment.yml
 ```

docs/source/notebooks/Create_validation_plot_from_raw_data.ipynb

@@ -11,18 +11,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
-    "%load_ext autoreload\n",
-    "%autoreload 2\n",
-    "\n",
-    "import arviz as az\n",
     "import json\n",
     "import numpy as np\n",
     "import pandas\n",
-    "import pymc as pm\n",
     "from matplotlib import pyplot as plt\n",
     "from pathlib import Path"
    ]
@@ -31,33 +26,33 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### 1) Preparation of evaluation of synthetic data (test 1)"
+    "# Preparation of evaluation of synthetic data (test 1)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
-    "with open('test1_all_data.txt', 'r') as file:\n",
+    "with open(Path(\"./paper raw data/test1_all_data.txt\"), \"r\") as file:\n",
     "    all_data = json.loads(file.read())"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### 2) Prepartion of border-line cases normal vs. skew normal (test 2)"
+    "# Prepartion of border-line cases normal vs. skew normal (test 2)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
-    "df = pandas.read_excel(\"test2_summary.xlsx\")\n",
+    "df = pandas.read_excel(Path(\"./paper raw data/test2_summary.xlsx\"))\n",
     "df_normal = df[(df.loc[:, \"model\"] == \"normal\") & (df.loc[:, \"Unnamed: 0\"].isin([\"area\", \"height\"]))]\n",
     "df_normal.reset_index(inplace=True)\n",
     "df_skew = df[(df.loc[:, \"model\"] == \"skew_normal\") & (df.loc[:, \"Unnamed: 0\"].isin([\"area\", \"height\"]))]\n",
@@ -78,16 +73,16 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### 3) Prepartion of comparison to MultiQuant (test 3)"
+    "# Prepartion of comparison to MultiQuant (test 3)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
-    "df_comparison_total = pandas.read_excel(\"test3_df_comparison.xlsx\")\n",
+    "df_comparison_total = pandas.read_excel(Path(\"./paper raw data/test3_df_comparison.xlsx\"))\n",
     "df_comparison_single = df_comparison_total[~df_comparison_total[\"PP experiment\"].isin([23, 24])]\n",
     "df_comparison_double = df_comparison_total[df_comparison_total[\"PP experiment\"].isin([23, 24])]"
    ]
@@ -96,12 +91,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### 4) Plotting in one graph (for PeakPerformance paper)"
+    "# Plotting in one graph (for PeakPerformance paper)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -224,14 +219,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Last updated: 2024-10-11T17:56:34.996952+02:00\n",
+      "Last updated: 2024-10-13T15:10:41.315414+02:00\n",
       "\n"
      ]
     }

docs/source/notebooks/Processing_test_1_raw_data.ipynb

@@ -1,51 +1,45 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Process raw data from synthetic tests"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
-    "%load_ext autoreload\n",
-    "%autoreload 2\n",
-    "\n",
-    "import arviz as az\n",
-    "import json\n",
     "import numpy as np\n",
     "import pandas\n",
-    "import pymc as pm\n",
     "from matplotlib import pyplot as plt\n",
     "from pathlib import Path"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
     "raw_data_files = [\n",
-    "    \"Normal model_normal data_noise level 0.6.xlsx\",\n",
-    "    \"Normal model_normal data_noise level 1.2.xlsx\",\n",
-    "    \"Normal model_skew normal data_noise level 0.6.xlsx\",\n",
-    "    \"Skew normal model_skew normal data_noise level 0.6.xlsx\",\n",
-    "    \"Skew normal model_skew normal data_noise level 1.2.xlsx\",\n",
-    "    \"Skew normal model_normal data_noise level 0.6.xlsx\",\n",
+    "    Path(\"./paper raw data/synthetic data sets for validation/Normal model_normal data_noise level 0.6.xlsx\"),\n",
+    "    Path(\"./paper raw data/synthetic data sets for validation/Normal model_normal data_noise level 1.2.xlsx\"),\n",
+    "    Path(\"./paper raw data/synthetic data sets for validation/Normal model_skew normal data_noise level 0.6.xlsx\"),\n",
+    "    Path(\"./paper raw data/synthetic data sets for validation/Skew normal model_skew normal data_noise level 0.6.xlsx\"),\n",
+    "    Path(\"./paper raw data/synthetic data sets for validation/Skew normal model_skew normal data_noise level 1.2.xlsx\"),\n",
+    "    Path(\"./paper raw data/synthetic data sets for validation/Skew normal model_normal data_noise level 0.6.xlsx\"),\n",
     "]\n",
     "\n",
     "parameters = [\"mean\", \"std\", \"area\", \"height\", \"alpha\", \"baseline_intercept\", \"baseline_slope\"]"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Prepare data in df_results"
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -149,7 +143,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -159,9 +153,9 @@
       "model: normal, data: normal, noise level: 0.6\n",
       "model: normal, data: normal, noise level: 1.2\n",
       "model: normal, data: skew normal, noise level: 0.6\n",
-      "model: skew normal, data: normal, noise level: 0.6\n",
       "model: skew normal, data: skew normal, noise level: 0.6\n",
-      "model: skew normal, data: skew normal, noise level: 1.2\n"
+      "model: skew normal, data: skew normal, noise level: 1.2\n",
+      "model: skew normal, data: normal, noise level: 0.6\n"
      ]
     }
    ],
@@ -180,7 +174,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -191,7 +185,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -221,14 +215,6 @@
        "   0.1425229338854569,\n",
        "   0.029251994462966387,\n",
        "   0.02178598822049324]],\n",
-       " 'normal data, skew normal model': [[0.9993873333333333,\n",
-       "   1.145324094260921,\n",
-       "   1.0038603930164334,\n",
-       "   1.0021702322498285],\n",
-       "  [0.025492314214288193,\n",
-       "   0.06460165579288266,\n",
-       "   0.0295645094605588,\n",
-       "   0.022277250178015084]],\n",
        " 'skew normal data, skew normal model': [[1.0003276666666665,\n",
        "   1.0178059537564914,\n",
        "   0.9995769654521169,\n",
@@ -244,10 +230,18 @@
        "  [0.029588612507556917,\n",
        "   0.13828870506270582,\n",
        "   0.050852728197426554,\n",
-       "   0.03782158437972263]]}"
+       "   0.03782158437972263]],\n",
+       " 'normal data, skew normal model': [[0.9993873333333333,\n",
+       "   1.145324094260921,\n",
+       "   1.0038603930164334,\n",
+       "   1.0021702322498285],\n",
+       "  [0.025492314214288193,\n",
+       "   0.06460165579288266,\n",
+       "   0.0295645094605588,\n",
+       "   0.022277250178015084]]}"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -275,7 +269,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -284,7 +278,7 @@
        "dict_keys(['normal data, normal model', 'normal data (higher noise), normal model', 'skew normal data, normal model', 'skew normal data, skew normal model', 'skew normal data (higher noise), skew normal model', 'normal data, skew normal model'])"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -297,7 +291,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -309,14 +303,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Last updated: 2024-10-11T18:34:57.629742+02:00\n",
+      "Last updated: 2024-10-13T15:03:43.532805+02:00\n",
       "\n"
      ]
     }

environment.yml

@@ -0,0 +1,16 @@
+name: pp_env
+channels:
+  - conda-forge
+dependencies:
+  - arviz
+  - jupyter
+  - matplotlib
+  - numba
+  - numpy
+  - nutpie
+  - openpyxl
+  - pip
+  - pymc
+  - python=3.11
+  - pip:
+    - peak-performance