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

generalization #7

Merged
arevelle-ensae merged 9 commits from generalization into main 2024-03-07 13:58:03 +01:00
Conversation 0 Commits 9 Files Changed 4 +4 -4
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit bed6a5c901 - Show all commits

8
0_2_Dataset_construction.py
View File

@ -42,7 +42,7 @@ def compute_time_intersection(datecover):
return sorted(formated_dates) return sorted(formated_dates)
def df_coverage_modelization(sport, coverage_train = 0.7): def df_coverage_modelization(sport, coverage_features = 0.7):
""" """
This function returns start_date, end_of_features and final dates This function returns start_date, end_of_features and final dates
that help to construct train and test datasets that help to construct train and test datasets
@ -81,7 +81,7 @@ def dataset_construction(min_date, end_features_date, max_date, directory_path):
df_campaigns_information['opened_at'][df_campaigns_information['opened_at'] >= end_features_date] = np.datetime64('NaT') df_campaigns_information['opened_at'][df_campaigns_information['opened_at'] >= end_features_date] = np.datetime64('NaT')
#Filtre de la base df_products_purchased_reduced #Filtre de la base df_products_purchased_reduced
df_products_purchased_reduced = df_products_purchased_reduced[(df_products_purchased_reduced['purchase_date'] <= end_features_date) & (df_products_purchased_reduced['purchase_date'] >= min_date)] df_products_purchased_features = df_products_purchased_reduced[(df_products_purchased_reduced['purchase_date'] <= end_features_date) & (df_products_purchased_reduced['purchase_date'] >= min_date)]
print("Data filtering : SUCCESS") print("Data filtering : SUCCESS")
@ -91,7 +91,7 @@ def dataset_construction(min_date, end_features_date, max_date, directory_path):
df_campaigns_kpi = campaigns_kpi_function(campaigns_information = df_campaigns_information) df_campaigns_kpi = campaigns_kpi_function(campaigns_information = df_campaigns_information)
# KPI sur le comportement d'achat # KPI sur le comportement d'achat
df_tickets_kpi = tickets_kpi_function(tickets_information = df_products_purchased_reduced) df_tickets_kpi = tickets_kpi_function(tickets_information = df_products_purchased_features)
# KPI sur les données socio-démographiques # KPI sur les données socio-démographiques
df_customerplus_clean = customerplus_kpi_function(customerplus_clean = df_customerplus_clean_0) df_customerplus_clean = customerplus_kpi_function(customerplus_clean = df_customerplus_clean_0)
@ -146,7 +146,7 @@ BUCKET_OUT = f'projet-bdc2324-team1/Generalization/{type_of_comp}'
# Create test dataset and train dataset for sport companies # 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_features = 0.7)
start_date = "2021-05-01" start_date = "2021-05-01"
end_of_features = "2022-11-01" end_of_features = "2022-11-01"
final_date = "2023-11-01" final_date = "2023-11-01"