arthur/ArtStudies
1
0
Fork 0
mirror of https://github.com/ArthurDanjou/ArtStudies.git synced 2026-01-14 15:54:13 +01:00
Code Issues Packages Projects Releases Wiki Activity

Ajout de l'exécution de cellules pour le One Hot Encoding, la normalisation des variables numériques et la séparation des données en ensembles d'apprentissage et de test.

Browse Source
This commit is contained in:
Arthur Danjou
2025-10-13 18:24:13 +02:00
parent a63b1bf94c
commit 1ccdcb3803
1 changed files with 19 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
M2/Machine Learning/TP_3/2025_TP_3_M2_ISF.ipynb
View File

@@ -2104,7 +2104,7 @@
"\n", "\n",
"# Visualiser avec Plotly\n", "# Visualiser avec Plotly\n",
"fig = px.imshow(correlation_cat,\n", "fig = px.imshow(correlation_cat,\n",
" text_auto='.2f',\n", " text_auto='.2f', # type: ignore\n",
" aspect=\"auto\",\n", " aspect=\"auto\",\n",
" color_continuous_scale='RdBu_r',\n", " color_continuous_scale='RdBu_r',\n",
" title='Matrice de corrélation des variables catégorielles (V de Cramér)')\n", " title='Matrice de corrélation des variables catégorielles (V de Cramér)')\n",
@@ -3066,11 +3066,16 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 38,
"id": "b8530717", "id": "b8530717",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": [
"encoder = preproc.OneHotEncoder(sparse_output=False, drop='first')\n",
"encoder.fit(vars_categorielles)\n",
"vars_categorielles_enc = encoder.transform(vars_categorielles)\n",
"vars_categorielles_enc = pd.DataFrame(vars_categorielles_enc, columns=encoder.get_feature_names_out()) # type: ignore"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@@ -3082,11 +3087,16 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 39,
"id": "4ff3847d", "id": "4ff3847d",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": [
"scaler = preproc.StandardScaler()\n",
"scaler.fit(vars_numeriques)\n",
"vars_numeriques_scaled = scaler.transform(vars_numeriques)\n",
"vars_numeriques_scaled = pd.DataFrame(vars_numeriques_scaled, columns=vars_numeriques.columns)"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
@@ -3106,11 +3116,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 40,
"id": "6a1c7907", "id": "6a1c7907",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": [
"train, test = train_test_split(data_model, test_size=0.2, random_state=42)"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",