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

fix path + test and train customer allocation'

Browse Source
This commit is contained in:
Alexis REVELLE 2024-03-06 11:49:37 +00:00
parent 4503114435
commit d8e2da70cb
1 changed files with 29 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
0_2_Dataset_construction.py
View File

@ -67,6 +67,10 @@ def dataset_construction(min_date, end_features_date, max_date, directory_path):
df_campaigns_information = display_databases(directory_path, file_name = "campaigns_information", datetime_col = ['opened_at', 'sent_at', 'campaign_sent_at'])
df_products_purchased_reduced = display_databases(directory_path, file_name = "products_purchased_reduced", datetime_col = ['purchase_date'])
# if directory_path == "101":
# df_products_purchased_reduced_1 = display_databases(directory_path, file_name = "products_purchased_reduced_1", datetime_col = ['purchase_date'])
# df_products_purchased_reduced = pd.concat([df_products_purchased_reduced, df_products_purchased_reduced_1])
# Filtre de cohérence pour la mise en pratique de notre méthode
max_date = pd.to_datetime(max_date, utc = True, format = 'ISO8601')
end_features_date = pd.to_datetime(end_features_date, utc = True, format = 'ISO8601')
@ -131,7 +135,7 @@ def dataset_construction(min_date, end_features_date, max_date, directory_path):
## Exportation
companies = {'musee' : ['1', '2', '3', '4', '101'],
companies = {'musee' : ['1', '2', '3', '4'], # , '101'
'sport': ['5', '6', '7', '8', '9'],
'musique' : ['10', '11', '12', '13', '14']}
@ -142,12 +146,31 @@ BUCKET_OUT = f'projet-bdc2324-team1/Generalization/{type_of_comp}'
# Create test dataset and train dataset for sport companies
start_date, end_of_features, final_date = df_coverage_modelization(list_of_comp, coverage_train = 0.7)
# start_date, end_of_features, final_date = df_coverage_modelization(list_of_comp, coverage_train = 0.7)
start_date = "2021-05-01"
end_of_features = "2022-11-01"
final_date = "2023-11-01"
anonymous_customer = {'1' : 1_1, '2' : 2_12184, '3' : 3_1, '4' : 4_2, '101' : 101_1,
'5' : 5_191835, '6' : 6_591412, '7' : 7_49632, '8' : 8_1942, '9' : 9_19683}
for company in list_of_comp:
dataset_test = dataset_construction(min_date = start_date, end_features_date = end_of_features,
dataset = dataset_construction(min_date = start_date, end_features_date = end_of_features,
max_date = final_date, directory_path = company)
# On retire le client anonyme
dataset = dataset[dataset['customer_id'] != anonymous_customer[company]]
#train test set
np.random.seed(42)
# Dataset Test
split_ratio = 0.7
split_index = int(len(dataset) * split_ratio)
dataset = dataset.sample(frac=1).reset_index(drop=True)
dataset_train = dataset.iloc[:split_index]
dataset_test = dataset.iloc[split_index:]
# Exportation
FILE_KEY_OUT_S3 = "dataset_test" + company + ".csv"
FILE_PATH_OUT_S3 = BUCKET_OUT + "/Test_set/" + FILE_KEY_OUT_S3
@ -158,11 +181,10 @@ for company in list_of_comp:
print("Exportation dataset test : SUCCESS")
# Dataset train
dataset_train = dataset_construction(min_date = start_date, end_features_date = end_of_features,
max_date = final_date, directory_path = company)
# Export
FILE_KEY_OUT_S3 = "dataset_train" + company + ".csv"
FILE_PATH_OUT_S3 = BUCKET_OUT + "/Train_test/" + FILE_KEY_OUT_S3
FILE_PATH_OUT_S3 = BUCKET_OUT + "/Train_set/" + FILE_KEY_OUT_S3
with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:
dataset_train.to_csv(file_out, index = False)