Files
ArtStudies/M2/Advanced Machine Learning/TP1.ipynb

209 lines
4.8 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "8226e658",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "7e95cb09",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.microsoft.datawrangler.viewer.v0+json": {
"columns": [
{
"name": "index",
"rawType": "int64",
"type": "integer"
},
{
"name": "X1",
"rawType": "float64",
"type": "float"
},
{
"name": "X2",
"rawType": "float64",
"type": "float"
},
{
"name": "Y",
"rawType": "float64",
"type": "float"
}
],
"ref": "018727a2-2342-424f-8395-021f40817c5a",
"rows": [
[
"0",
"-0.8363543",
"4.520502",
"-19.868094121443526"
],
[
"1",
"0.4020083",
"3.252834",
"-10.46598545005849"
],
[
"2",
"-0.2492138",
"3.610425",
"-12.91499193423918"
],
[
"3",
"-0.6257167",
"4.58877",
"-20.67839639765537"
],
[
"4",
"-0.9899948",
"4.893924",
"-22.99404413854238"
]
],
"shape": {
"columns": 3,
"rows": 5
}
},
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>X1</th>\n",
" <th>X2</th>\n",
" <th>Y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>-0.836354</td>\n",
" <td>4.520502</td>\n",
" <td>-19.868094</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.402008</td>\n",
" <td>3.252834</td>\n",
" <td>-10.465985</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>-0.249214</td>\n",
" <td>3.610425</td>\n",
" <td>-12.914992</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>-0.625717</td>\n",
" <td>4.588770</td>\n",
" <td>-20.678396</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>-0.989995</td>\n",
" <td>4.893924</td>\n",
" <td>-22.994044</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" X1 X2 Y\n",
"0 -0.836354 4.520502 -19.868094\n",
"1 0.402008 3.252834 -10.465985\n",
"2 -0.249214 3.610425 -12.914992\n",
"3 -0.625717 4.588770 -20.678396\n",
"4 -0.989995 4.893924 -22.994044"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data = pd.read_excel(\"./data/data_pdp.xlsx\")\n",
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "4e9a9a97",
"metadata": {},
"outputs": [],
"source": [
"def partial_dependant_function(data: pd.DataFrame, model: object, feature: str, grid_points: list) -> list:\n",
" \"\"\"Compute the Partial Dependence Plot (PDP) for a given feature.\"\"\"\n",
" pdp = []\n",
" for val in grid_points:\n",
" data_temp = data.copy()\n",
" data_temp[feature] = val\n",
" preds = model.predict(data_temp)\n",
" pdp.append(preds.mean())\n",
" return pdp"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9553a1d8",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "studies",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}