fix(learning.ipynb): correction cross_val_score avec uniquement X_test et y_test

This commit is contained in:
2026-04-01 15:30:50 +02:00
parent d74d15d7b1
commit 8074c95720

View File

@@ -2,10 +2,19 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 12,
"id": "faafb9a0", "id": "faafb9a0",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The autoreload extension is already loaded. To reload it, use:\n",
" %reload_ext autoreload\n"
]
}
],
"source": [ "source": [
"%matplotlib inline\n", "%matplotlib inline\n",
"%load_ext autoreload\n", "%load_ext autoreload\n",
@@ -101,7 +110,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 13,
"id": "8342340f", "id": "8342340f",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@@ -126,7 +135,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 14,
"id": "9dfdc01f", "id": "9dfdc01f",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@@ -175,7 +184,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 15,
"id": "99de3ed7", "id": "99de3ed7",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -208,7 +217,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 16,
"id": "09eca16d", "id": "09eca16d",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -246,7 +255,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 17,
"id": "b94a89f2", "id": "b94a89f2",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -323,7 +332,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 18,
"id": "4f1c169f", "id": "4f1c169f",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -360,7 +369,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 19,
"id": "91cedffb", "id": "91cedffb",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -457,7 +466,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 20,
"id": "4c21cd56", "id": "4c21cd56",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -473,9 +482,9 @@
"text/markdown": [ "text/markdown": [
"| Méthode | R² |\n", "| Méthode | R² |\n",
"| :---: | :---: |\n", "| :---: | :---: |\n",
"|AD|0.393010|\n", "|AD|0.386319|\n",
"|Normalisation + AD|0.393010|\n", "|Normalisation + AD|0.386319|\n",
"|Standardisation + AD|0.393034|\n" "|Standardisation + AD|0.386319|\n"
], ],
"text/plain": [ "text/plain": [
"<IPython.core.display.Markdown object>" "<IPython.core.display.Markdown object>"
@@ -496,9 +505,9 @@
"text/markdown": [ "text/markdown": [
"| Méthode | R² |\n", "| Méthode | R² |\n",
"| :---: | :---: |\n", "| :---: | :---: |\n",
"|AD|0.403744|\n", "|AD|0.382689|\n",
"|Normalisation + AD|0.403744|\n", "|Normalisation + AD|0.382695|\n",
"|Standardisation + AD|0.403761|\n" "|Standardisation + AD|0.382691|\n"
], ],
"text/plain": [ "text/plain": [
"<IPython.core.display.Markdown object>" "<IPython.core.display.Markdown object>"
@@ -519,9 +528,9 @@
"text/markdown": [ "text/markdown": [
"| Méthode | R² |\n", "| Méthode | R² |\n",
"| :---: | :---: |\n", "| :---: | :---: |\n",
"|AD|0.400791|\n", "|AD|0.371764|\n",
"|Normalisation + AD|0.400791|\n", "|Normalisation + AD|0.374744|\n",
"|Standardisation + AD|0.400821|\n" "|Standardisation + AD|0.371729|\n"
], ],
"text/plain": [ "text/plain": [
"<IPython.core.display.Markdown object>" "<IPython.core.display.Markdown object>"
@@ -534,7 +543,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"best score= 0.40376125774243815 depth= 4 method= Standardisation + AD\n" "best score= 0.3863187373819251 depth= 3 method= AD\n"
] ]
} }
], ],
@@ -562,7 +571,7 @@
" else make_pipeline(scaler(), DecisionTreeRegressor(max_depth=depth))\n", " else make_pipeline(scaler(), DecisionTreeRegressor(max_depth=depth))\n",
" )\n", " )\n",
" model.fit(X_train, y_train)\n", " model.fit(X_train, y_train)\n",
" score: float = cross_val_score(model, X, y_log, cv=5).mean()\n", " score: float = cross_val_score(model, X_test, y_test, cv=5).mean()\n",
" ad_table.ajoutligne(f\"{name}\", score)\n", " ad_table.ajoutligne(f\"{name}\", score)\n",
"\n", "\n",
" if score > best_score_ad:\n", " if score > best_score_ad:\n",
@@ -616,7 +625,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 21,
"id": "f72f499f", "id": "f72f499f",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -632,9 +641,9 @@
"text/markdown": [ "text/markdown": [
"| Méthode | R² |\n", "| Méthode | R² |\n",
"| :---: | :---: |\n", "| :---: | :---: |\n",
"|KNN|0.371305|\n", "|KNN|0.370389|\n",
"|Normalisation + KNN|0.392151|\n", "|Normalisation + KNN|0.341947|\n",
"|Standardisation + KNN|0.392397|\n" "|Standardisation + KNN|0.369662|\n"
], ],
"text/plain": [ "text/plain": [
"<IPython.core.display.Markdown object>" "<IPython.core.display.Markdown object>"
@@ -655,9 +664,9 @@
"text/markdown": [ "text/markdown": [
"| Méthode | R² |\n", "| Méthode | R² |\n",
"| :---: | :---: |\n", "| :---: | :---: |\n",
"|KNN|0.391092|\n", "|KNN|0.390801|\n",
"|Normalisation + KNN|0.412238|\n", "|Normalisation + KNN|0.349482|\n",
"|Standardisation + KNN|0.402197|\n" "|Standardisation + KNN|0.381631|\n"
], ],
"text/plain": [ "text/plain": [
"<IPython.core.display.Markdown object>" "<IPython.core.display.Markdown object>"
@@ -670,7 +679,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"best score= 0.4122380532367001 neighbor= 5 method= Normalisation + KNN\n" "best score= 0.39080066451618123 neighbor= 5 method= KNN\n"
] ]
} }
], ],
@@ -698,7 +707,7 @@
" else make_pipeline(scaler(), KNeighborsRegressor(n_neighbors=n))\n", " else make_pipeline(scaler(), KNeighborsRegressor(n_neighbors=n))\n",
" )\n", " )\n",
" model.fit(X_train, y_train)\n", " model.fit(X_train, y_train)\n",
" score: float = cross_val_score(model, X, y_log, cv=5).mean()\n", " score: float = cross_val_score(model, X_test, y_test, cv=5).mean()\n",
" knn_table.ajoutligne(f\"{name}\", score)\n", " knn_table.ajoutligne(f\"{name}\", score)\n",
"\n", "\n",
" if score > best_score_ad:\n", " if score > best_score_ad:\n",
@@ -740,7 +749,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 22,
"id": "9f764f3a", "id": "9f764f3a",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -750,8 +759,8 @@
"| Méthode | R² |\n", "| Méthode | R² |\n",
"| :---: | :---: |\n", "| :---: | :---: |\n",
"|LR|0.452908|\n", "|LR|0.452908|\n",
"|AD|0.403761|\n", "|AD|0.386319|\n",
"|KNN|0.412238|\n" "|KNN|0.390801|\n"
], ],
"text/plain": [ "text/plain": [
"<IPython.core.display.Markdown object>" "<IPython.core.display.Markdown object>"
@@ -804,7 +813,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 23,
"id": "9084e87e", "id": "9084e87e",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -841,7 +850,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 13, "execution_count": 24,
"id": "fdcdfb17", "id": "fdcdfb17",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -851,7 +860,7 @@
"0.24194691318111572" "0.24194691318111572"
] ]
}, },
"execution_count": 13, "execution_count": 24,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@@ -893,7 +902,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14, "execution_count": 25,
"id": "c4f6c27f", "id": "c4f6c27f",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -903,7 +912,7 @@
"<Axes: >" "<Axes: >"
] ]
}, },
"execution_count": 14, "execution_count": 25,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
}, },
@@ -938,7 +947,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 15, "execution_count": 26,
"id": "2e512052", "id": "2e512052",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -1125,7 +1134,7 @@
"App_Haut-Médoc -0.070383" "App_Haut-Médoc -0.070383"
] ]
}, },
"execution_count": 15, "execution_count": 26,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@@ -1146,7 +1155,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 16, "execution_count": 27,
"id": "4010aa12", "id": "4010aa12",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -1156,7 +1165,7 @@
"0.24551258031003886" "0.24551258031003886"
] ]
}, },
"execution_count": 16, "execution_count": 27,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@@ -1204,7 +1213,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 17, "execution_count": 28,
"id": "1510f763", "id": "1510f763",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@@ -1213,9 +1222,9 @@
"text/markdown": [ "text/markdown": [
"| Méthode | R² |\n", "| Méthode | R² |\n",
"| :---: | :---: |\n", "| :---: | :---: |\n",
"|Random Forest|0.493344|\n", "|Random Forest|0.492498|\n",
"|Normalisation + RF|0.493113|\n", "|Normalisation + RF|0.492721|\n",
"|Standardisation + RF|0.493782|\n" "|Standardisation + RF|0.500235|\n"
], ],
"text/plain": [ "text/plain": [
"<IPython.core.display.Markdown object>" "<IPython.core.display.Markdown object>"
@@ -1279,7 +1288,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.10.20" "version": "3.14.3"
} }
}, },
"nbformat": 4, "nbformat": 4,