ajoubrel-ensae/BDC-team-1
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Correction export

Browse Source
This commit is contained in:
Antoine JOUBREL 2024-02-14 11:44:18 +00:00
parent 15125ef6db
commit c67337b10e
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
0_Cleaning_and_merge.py
View File

@ -82,7 +82,7 @@ with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:
## 2 - Construction of KPIs on a given period ## 2 - Construction of KPIs on a given period
def explanatory_variables(min_date = "2021-09-01", max_date = "2023-09-01", df_campaigns_information = df1_campaigns_information, df_products_purchased_reduced = df1_products_purchased_reduced, df_customerplus_clean = df1_customerplus_clean): def explanatory_variables(min_date, max_date, df_campaigns_information = df1_campaigns_information, df_products_purchased_reduced = df1_products_purchased_reduced, df_customerplus_clean = df1_customerplus_clean):
# Filtre de cohérence pour la mise en pratique de notre méthode # Filtre de cohérence pour la mise en pratique de notre méthode
max_date = pd.to_datetime(max_date, utc = True, format = 'ISO8601') max_date = pd.to_datetime(max_date, utc = True, format = 'ISO8601')
@ -138,7 +138,7 @@ def explanatory_variables(min_date = "2021-09-01", max_date = "2023-09-01", df_c
return df_customer_product return df_customer_product
# Fonction pour créer les variables expliquée # Fonction pour créer les variables expliquée
def explained_variable(min_date = "2023-08-01", max_date = "2023-11-01", df_products_purchased_reduced = df1_products_purchased_reduced): def explained_variable(min_date, max_date, df_products_purchased_reduced = df1_products_purchased_reduced):
# Filtrer la base d'achat # Filtrer la base d'achat
df_products_purchased_reduced = df_products_purchased_reduced[(df_products_purchased_reduced['purchase_date'] <= max_date) & (df_products_purchased_reduced['purchase_date'] > min_date)] df_products_purchased_reduced = df_products_purchased_reduced[(df_products_purchased_reduced['purchase_date'] <= max_date) & (df_products_purchased_reduced['purchase_date'] > min_date)]
@ -185,7 +185,7 @@ FILE_KEY_OUT_S3 = "dataset_train.csv"
FILE_PATH_OUT_S3 = BUCKET_OUT + "/" + FILE_KEY_OUT_S3 FILE_PATH_OUT_S3 = BUCKET_OUT + "/" + FILE_KEY_OUT_S3
with fs.open(FILE_PATH_OUT_S3, 'w') as file_out: with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:
dataset_test.to_csv(file_out, index = False) dataset_train.to_csv(file_out, index = False)
print("Exportation dataset train : SUCCESS") print("Exportation dataset train : SUCCESS")