ajout : remplac les notes manquantes par la moyenne de l'appellation

cleaning.py

@@ -1,9 +1,12 @@
 #!/usr/bin/env python3
 from pandas import DataFrame, to_numeric
+import pandas as pd
+
+SCORE_COLS = ["Robert", "Robinson", "Suckling"]
 
 
 def display_info(df: DataFrame) -> None:
-    print(df.all())
+    df.describe()
     print(df.info())
     print("\nNombre de valeurs manquantes par colonne :")
     print(df.isna().sum())
@@ -46,3 +49,28 @@ def mean_robinson(df: DataFrame) -> DataFrame:
 
 def mean_suckling(df: DataFrame) -> DataFrame:
     return mean_score(df, "Suckling")
+
+
+def fill_missing_scores(df: DataFrame) -> DataFrame:
+    """
+    Remplacer les notes manquantes par la moyenne
+    des vins de la même appellation.
+    """
+    df_copy = df.copy()
+    df_copy["Appellation"] = df_copy["Appellation"].astype(str).str.strip()
+
+    for score in SCORE_COLS:
+        df_copy[score] = to_numeric(df_copy[score], errors="coerce")
+
+    temp_cols: list[str] = []
+
+    for score in SCORE_COLS:
+        mean_df = mean_score(df_copy, score)
+        mean_name = f"mean_{score}"
+        temp_cols.append(mean_name)
+
+        df_copy = df_copy.merge(mean_df, on="Appellation", how="left")
+        df_copy[score] = df_copy[score].fillna(df_copy[mean_name])
+
+    df_copy = df_copy.drop(columns=temp_cols)
+    return df_copy

main.py

@@ -9,7 +9,9 @@ from cleaning import (display_info,
                       drop_empty_appellation,
                       mean_robert,
                       mean_robinson,
-                      mean_suckling)
+                      mean_suckling,
+                      fill_missing_scores,
+                      encode_appellation)
 
 
 def load_csv(filename: str) -> DataFrame:
@@ -44,14 +46,18 @@ def main() -> None:
 
     robinson_means = mean_robinson(df)
     save_csv(robinson_means, "mean_robinson_by_appellation.csv")
-    print("\n===: moyennes Robinson par appellation ===")
+    print("\n=== moyennes Robinson par appellation ===")
     print(robinson_means.head(10))
     
     suckling_means = mean_suckling(df)
     save_csv(suckling_means, "mean_suckling_by_appellation.csv")
-    print("\n===: moyennes Suckling par appellation ===")
+    print("\n=== moyennes Suckling par appellation ===")
     print(suckling_means.head(10))
     
+    df_missing_scores = fill_missing_scores(df)
+    save_csv(df_missing_scores, "donnee_filled.csv")
+    print("\n=== Après remplissage des notes manquantes ===")
+    display_info(df_missing_scores)  
 
 if __name__ == "__main__":
     try: