Refactor code for improved readability and consistency across multiple Jupyter notebooks

- Added missing commas in various print statements and function calls for better syntax.
- Reformatted code to enhance clarity, including breaking long lines and aligning parameters.
- Updated function signatures to use float type for sigma parameters instead of int for better precision.
- Cleaned up comments and documentation strings for clarity and consistency.
- Ensured consistent formatting in plotting functions and data handling.

M2/Machine Learning/TP_4/2025_M2_ISF_TP_4.ipynb

@@ -58,14 +58,15 @@
     "import seaborn as sns\n",
     "\n",
     "sns.set()\n",
-    "import plotly.express as px\n",
-    "\n",
-    "# Machine Learning\n",
-    "import sklearn.preprocessing as preproc\n",
     "from imblearn.over_sampling import RandomOverSampler\n",
     "\n",
+    "import plotly.express as px\n",
+    "\n",
     "# Statistiques\n",
     "from scipy.stats import chi2_contingency\n",
+    "\n",
+    "# Machine Learning\n",
+    "import sklearn.preprocessing as preproc\n",
     "from sklearn import metrics\n",
     "from sklearn.ensemble import GradientBoostingClassifier\n",
     "from sklearn.model_selection import (\n",
@@ -93,7 +94,7 @@
    "source": [
     "def cramers_V(var1, var2):\n",
     "    crosstab = np.array(\n",
-    "        pd.crosstab(var1, var2, rownames=None, colnames=None)\n",
+    "        pd.crosstab(var1, var2, rownames=None, colnames=None),\n",
     "    )  # Cross table building\n",
     "    stat = chi2_contingency(crosstab)[\n",
     "        0\n",
@@ -16171,7 +16172,9 @@
    "source": [
     "# Observation de la distribution\n",
     "fig = px.histogram(\n",
-    "    data_model, x=\"SINISTRE\", title=\"Distribution de la variable 'sinistré'\"\n",
+    "    data_model,\n",
+    "    x=\"SINISTRE\",\n",
+    "    title=\"Distribution de la variable 'sinistré'\",\n",
     ")\n",
     "fig.show()"
    ]
@@ -16221,17 +16224,15 @@
     "for col in data_set.columns:\n",
     "    if True in data_model[col].isna().unique():\n",
     "        variables_na.append(data_model[col])\n",
-    "    else:\n",
-    "        if str(data_model[col].dtypes) in [\"int32\", \"int64\", \"float64\"]:\n",
-    "            if len(data_model[col].unique()) == 2:\n",
-    "                variables_categorielles.append(data_model[col])\n",
-    "            else:\n",
-    "                variables_numeriques.append(data_model[col])\n",
+    "    elif str(data_model[col].dtypes) in [\"int32\", \"int64\", \"float64\"]:\n",
+    "        if len(data_model[col].unique()) == 2:\n",
+    "            variables_categorielles.append(data_model[col])\n",
     "        else:\n",
-    "            if len(data_model[col].unique()) == 2:\n",
-    "                variables_categorielles.append(data_model[col])\n",
-    "            else:\n",
-    "                variables_categorielles.append(data_model[col])"
+    "            variables_numeriques.append(data_model[col])\n",
+    "    elif len(data_model[col].unique()) == 2:\n",
+    "        variables_categorielles.append(data_model[col])\n",
+    "    else:\n",
+    "        variables_categorielles.append(data_model[col])"
    ]
   },
   {
@@ -16631,7 +16632,8 @@
     "    col = []\n",
     "    for var2 in vars_categorielles:\n",
     "        cramers = cramers_V(\n",
-    "            vars_categorielles[var1], vars_categorielles[var2]\n",
+    "            vars_categorielles[var1],\n",
+    "            vars_categorielles[var2],\n",
     "        )  # V de Cramer\n",
     "        col.append(round(cramers, 2))  # arrondi du résultat\n",
     "    rows.append(col)\n",
@@ -16658,7 +16660,7 @@
     "    for j in range(i + 1, v_cramer_resultats.shape[0]):\n",
     "        if v_cramer_resultats.iloc[i, j] > 0.7:\n",
     "            print(\n",
-    "                f\"{v_cramer_resultats.index.to_numpy()[i]} et {v_cramer_resultats.colmns[j]} sont trop dépendantes, V-CRAMER = {v_cramer_resultats.iloc[i, j]}\"\n",
+    "                f\"{v_cramer_resultats.index.to_numpy()[i]} et {v_cramer_resultats.colmns[j]} sont trop dépendantes, V-CRAMER = {v_cramer_resultats.iloc[i, j]}\",\n",
     "            )"
    ]
   },
@@ -16856,7 +16858,7 @@
     "    for j in range(i + 1, nb_variables):\n",
     "        if abs(correlations_num.iloc[i, j]) > 0.7:\n",
     "            print(\n",
-    "                f\"{correlations_num.index.to_numpy()[i]} et {correlations_num.columns[j]} sont trop dépendantes, corr = {correlations_num.iloc[i, j]}\"\n",
+    "                f\"{correlations_num.index.to_numpy()[i]} et {correlations_num.columns[j]} sont trop dépendantes, corr = {correlations_num.iloc[i, j]}\",\n",
     "            )"
    ]
   },
@@ -17520,7 +17522,7 @@
     "# One hot encoding des variables catégorielles\n",
     "preproc_ohe = preproc.OneHotEncoder(handle_unknown=\"ignore\")\n",
     "preproc_ohe = preproc.OneHotEncoder(drop=\"first\", sparse_output=False).fit(\n",
-    "    vars_categorielles\n",
+    "    vars_categorielles,\n",
     ")\n",
     "\n",
     "variables_categorielles_ohe = preproc_ohe.transform(vars_categorielles)\n",
@@ -17704,7 +17706,8 @@
     "\n",
     "vars_numeriques_scaled = preproc_scale.transform(vars_numeriques)\n",
     "vars_numeriques_scaled = pd.DataFrame(\n",
-    "    vars_numeriques_scaled, columns=vars_numeriques.columns\n",
+    "    vars_numeriques_scaled,\n",
+    "    columns=vars_numeriques.columns,\n",
     ")\n",
     "vars_numeriques_scaled.head()"
    ]
@@ -17756,7 +17759,9 @@
    "outputs": [],
    "source": [
     "X_global = vars_numeriques_scaled.merge(\n",
-    "    variables_categorielles_ohe, left_index=True, right_index=True\n",
+    "    variables_categorielles_ohe,\n",
+    "    left_index=True,\n",
+    "    right_index=True,\n",
     ")\n",
     "# Réorganisation des données\n",
     "X = X_global.to_numpy()\n",
@@ -17772,7 +17777,11 @@
    "source": [
     "# Sampling en 80% train et 20% test\n",
     "X_train, X_test, y_train, y_test = train_test_split(\n",
-    "    X, Y, test_size=0.2, random_state=42, stratify=Y\n",
+    "    X,\n",
+    "    Y,\n",
+    "    test_size=0.2,\n",
+    "    random_state=42,\n",
+    "    stratify=Y,\n",
     ")"
    ]
   },
@@ -17824,7 +17833,9 @@
     "    estimator=gbc,\n",
     "    param_grid=param_grid,\n",
     "    cv=StratifiedKFold(\n",
-    "        n_splits=num_folds, shuffle=True, random_state=42\n",
+    "        n_splits=num_folds,\n",
+    "        shuffle=True,\n",
+    "        random_state=42,\n",
     "    ),  # Validation croisée avec 5 folds\n",
     "    scoring=\"recall\",  # Métrique d'évaluation (moins c'est mieux)\n",
     "    n_jobs=-1,  # Utiliser tous les cœurs du processeur\n",
@@ -17884,7 +17895,11 @@
    "source": [
     "# Recall de chaque fold\n",
     "recall_scores = cross_val_score(\n",
-    "    best_gbc, X_train, y_train, cv=num_folds, scoring=\"recall\"\n",
+    "    best_gbc,\n",
+    "    X_train,\n",
+    "    y_train,\n",
+    "    cv=num_folds,\n",
+    "    scoring=\"recall\",\n",
     ")\n",
     "\n",
     "# Afficher les scores pour chaque fold\n",
@@ -17893,7 +17908,11 @@
     "\n",
     "# Accuracy de chaque fold\n",
     "accuracy_scores = cross_val_score(\n",
-    "    best_gbc, X_train, y_train, cv=num_folds, scoring=\"accuracy\"\n",
+    "    best_gbc,\n",
+    "    X_train,\n",
+    "    y_train,\n",
+    "    cv=num_folds,\n",
+    "    scoring=\"accuracy\",\n",
     ")\n",
     "\n",
     "# Afficher les scores pour chaque fold\n",
@@ -17903,7 +17922,11 @@
     "\n",
     "# Precision de chaque fold\n",
     "precision_scores = cross_val_score(\n",
-    "    best_gbc, X_train, y_train, cv=num_folds, scoring=\"precision\"\n",
+    "    best_gbc,\n",
+    "    X_train,\n",
+    "    y_train,\n",
+    "    cv=num_folds,\n",
+    "    scoring=\"precision\",\n",
     ")\n",
     "\n",
     "# Afficher les scores pour chaque fold\n",
@@ -52512,7 +52535,9 @@
     "# Observation de la distribution sur Y_train\n",
     "df = pd.DataFrame(y_train_resampled, columns=[\"SINISTRE\"])\n",
     "fig = px.histogram(\n",
-    "    df, x=\"SINISTRE\", title=\"Distribution de la variable Y_train_resampled\"\n",
+    "    df,\n",
+    "    x=\"SINISTRE\",\n",
+    "    title=\"Distribution de la variable Y_train_resampled\",\n",
     ")\n",
     "fig.show()"
    ]
@@ -52565,7 +52590,9 @@
     "    estimator=gb,\n",
     "    param_grid=param_grid,\n",
     "    cv=StratifiedKFold(\n",
-    "        n_splits=num_folds, shuffle=True, random_state=42\n",
+    "        n_splits=num_folds,\n",
+    "        shuffle=True,\n",
+    "        random_state=42,\n",
     "    ),  # Validation croisée stratifiée avec 5 plis\n",
     "    scoring=\"recall\",  # Métrique d'évaluation\n",
     "    n_jobs=-1,  # Utiliser tous les cœurs du processeur\n",
@@ -52618,7 +52645,11 @@
     "# Zoom sur la CV\n",
     "# Recall de chaque fold\n",
     "recall_scores = cross_val_score(\n",
-    "    best_gbc, X_train_resampled, y_train_resampled, cv=num_folds, scoring=\"recall\"\n",
+    "    best_gbc,\n",
+    "    X_train_resampled,\n",
+    "    y_train_resampled,\n",
+    "    cv=num_folds,\n",
+    "    scoring=\"recall\",\n",
     ")\n",
     "\n",
     "# Afficher les scores pour chaque fold\n",
@@ -52627,7 +52658,11 @@
     "\n",
     "# Accuracy de chaque fold\n",
     "accuracy_scores = cross_val_score(\n",
-    "    best_gbc, X_train_resampled, y_train_resampled, cv=num_folds, scoring=\"accuracy\"\n",
+    "    best_gbc,\n",
+    "    X_train_resampled,\n",
+    "    y_train_resampled,\n",
+    "    cv=num_folds,\n",
+    "    scoring=\"accuracy\",\n",
     ")\n",
     "\n",
     "# Afficher les scores pour chaque fold\n",
@@ -52637,7 +52672,11 @@
     "\n",
     "# Precision de chaque fold\n",
     "precision_scores = cross_val_score(\n",
-    "    best_gbc, X_train_resampled, y_train_resampled, cv=num_folds, scoring=\"precision\"\n",
+    "    best_gbc,\n",
+    "    X_train_resampled,\n",
+    "    y_train_resampled,\n",
+    "    cv=num_folds,\n",
+    "    scoring=\"precision\",\n",
     ")\n",
     "\n",
     "# Afficher les scores pour chaque fold\n",
@@ -53146,7 +53185,8 @@
     "# Matrice de confusion\n",
     "confusion_matrix = metrics.confusion_matrix(y_test, y_pred)\n",
     "cm_display = metrics.ConfusionMatrixDisplay(\n",
-    "    confusion_matrix=confusion_matrix, display_labels=[False, True]\n",
+    "    confusion_matrix=confusion_matrix,\n",
+    "    display_labels=[False, True],\n",
     ")\n",
     "\n",
     "cm_display.plot()"