mirror of
https://github.com/guezoloic/millesima_projetS6.git
synced 2026-03-28 19:13:42 +00:00
72 lines
2.2 KiB
Python
Executable File
72 lines
2.2 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
|
|
from os import getcwd
|
|
from os.path import normpath, join
|
|
from sys import argv
|
|
from pandas import read_csv, DataFrame
|
|
|
|
from cleaning import (display_info,
|
|
drop_empty_appellation,
|
|
mean_robert,
|
|
mean_robinson,
|
|
mean_suckling,
|
|
fill_missing_scores,
|
|
encode_appellation)
|
|
|
|
|
|
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:
|
|
if len(argv) != 2:
|
|
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))
|
|
|
|
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)
|
|
|
|
df_ready = encode_appellation(df_missing_scores)
|
|
save_csv(df_ready, "donnee_ready.csv")
|
|
print("\n=== Après remplacer la colonne 'Appellation' par des colonnes indicatrices ===")
|
|
display_info(df_ready)
|
|
print(df_ready.filter(like="App_").any().head())
|
|
|
|
if __name__ == "__main__":
|
|
try:
|
|
main()
|
|
except Exception as e:
|
|
print(f"ERREUR: {e}") |