mirror of
https://github.com/guezoloic/millesima-ai-engine.git
synced 2026-03-28 18:03:47 +00:00
ajout : moyennes des notes par appellation
This commit is contained in:
48
cleaning.py
Normal file
48
cleaning.py
Normal file
@@ -0,0 +1,48 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
from pandas import DataFrame, to_numeric
|
||||||
|
|
||||||
|
|
||||||
|
def display_info(df: DataFrame) -> None:
|
||||||
|
print(df.all())
|
||||||
|
print(df.info())
|
||||||
|
print("\nNombre de valeurs manquantes par colonne :")
|
||||||
|
print(df.isna().sum())
|
||||||
|
|
||||||
|
|
||||||
|
def drop_empty_appellation(df: DataFrame) -> DataFrame:
|
||||||
|
|
||||||
|
return df.dropna(subset=["Appellation"])
|
||||||
|
|
||||||
|
|
||||||
|
def mean_score(df: DataFrame, col: str) -> DataFrame:
|
||||||
|
"""
|
||||||
|
Calcule la moyenne d'une colonne de score par appellation.
|
||||||
|
- Convertit les valeurs en numériques, en remplaçant les non-convertibles par NaN
|
||||||
|
- Calcule la moyenne par appellation
|
||||||
|
- Remplace les NaN résultants par 0
|
||||||
|
|
||||||
|
"""
|
||||||
|
tmp = df[["Appellation", col]].copy()
|
||||||
|
|
||||||
|
tmp[col] = to_numeric(tmp[col], errors="coerce")
|
||||||
|
|
||||||
|
# moyenne par appellation
|
||||||
|
means = tmp.groupby("Appellation", as_index=False)[col].mean()
|
||||||
|
|
||||||
|
means[col] = means[col].fillna(0)
|
||||||
|
|
||||||
|
means = means.rename(columns={col: f"mean_{col}"})
|
||||||
|
|
||||||
|
return means
|
||||||
|
|
||||||
|
|
||||||
|
def mean_robert(df: DataFrame) -> DataFrame:
|
||||||
|
return mean_score(df, "Robert")
|
||||||
|
|
||||||
|
|
||||||
|
def mean_robinson(df: DataFrame) -> DataFrame:
|
||||||
|
return mean_score(df, "Robinson")
|
||||||
|
|
||||||
|
|
||||||
|
def mean_suckling(df: DataFrame) -> DataFrame:
|
||||||
|
return mean_score(df, "Suckling")
|
||||||
54
main.py
54
main.py
@@ -5,19 +5,53 @@ from os.path import normpath, join
|
|||||||
from sys import argv
|
from sys import argv
|
||||||
from pandas import read_csv, DataFrame
|
from pandas import read_csv, DataFrame
|
||||||
|
|
||||||
|
from cleaning import (display_info,
|
||||||
|
drop_empty_appellation,
|
||||||
|
mean_robert,
|
||||||
|
mean_robinson,
|
||||||
|
mean_suckling)
|
||||||
|
|
||||||
|
|
||||||
|
def load_csv(filename: str) -> DataFrame:
|
||||||
|
path: str = normpath(join(getcwd(), filename))
|
||||||
|
return read_csv(path)
|
||||||
|
|
||||||
|
|
||||||
|
def save_csv(df: DataFrame, out_filename: str) -> None:
|
||||||
|
df.to_csv(out_filename, index=False)
|
||||||
|
|
||||||
|
|
||||||
def main() -> None:
|
def main() -> None:
|
||||||
if len(argv) != 2:
|
if len(argv) != 2:
|
||||||
raise ValueError(f"{argv[0]} <filename.csv>")
|
raise ValueError(f"Usage: {argv[0]} <filename.csv>")
|
||||||
|
|
||||||
|
df = load_csv(argv[1])
|
||||||
|
|
||||||
|
print("=== Avant nettoyage ===")
|
||||||
|
display_info(df)
|
||||||
|
|
||||||
|
df = drop_empty_appellation(df)
|
||||||
|
save_csv(df, "donnee_clean.csv")
|
||||||
|
|
||||||
|
print("\n=== Après nettoyage d'appellations manquantes ===")
|
||||||
|
display_info(df)
|
||||||
|
|
||||||
|
#la moyenne des notes des vins pour chaque appellation
|
||||||
|
robert_means = mean_robert(df)
|
||||||
|
save_csv(robert_means, "mean_robert_by_appellation.csv")
|
||||||
|
print("\n=== moyenne Robert par appellation ===")
|
||||||
|
print(robert_means.head(10))
|
||||||
|
|
||||||
|
robinson_means = mean_robinson(df)
|
||||||
|
save_csv(robinson_means, "mean_robinson_by_appellation.csv")
|
||||||
|
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(suckling_means.head(10))
|
||||||
|
|
||||||
path: str = normpath(join(getcwd(), argv[1]))
|
|
||||||
db: DataFrame = read_csv(path)
|
|
||||||
print(db.all())
|
|
||||||
print(db.info())
|
|
||||||
print("\nnombre de valeurs manquantes pour chaque colonne :")
|
|
||||||
print(db.isna().sum())
|
|
||||||
db = db.dropna(subset=["Appellation"])
|
|
||||||
db.to_csv("donnee_clean.csv", index=False)
|
|
||||||
print(db.isna().sum())
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
try:
|
try:
|
||||||
|
|||||||
Reference in New Issue
Block a user