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

Merge pull request 'fix premium' (#12) from generalization into main

Browse Source 
Reviewed-on: #12
This commit is contained in:
Alexis REVELLE 2024-03-28 12:19:21 +01:00
commit b268cd980d
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
utils_ml.py
View File

@ -27,7 +27,7 @@ import pickle
import warnings
def load_train_test(type_of_activity):
def load_train_test(type_of_activity, type_of_model):
BUCKET = f"projet-bdc2324-team1/Generalization_v2/{type_of_activity}"
File_path_train = BUCKET + "/Train_set.csv"
File_path_test = BUCKET + "/Test_set.csv"
@ -40,6 +40,11 @@ def load_train_test(type_of_activity):
dataset_test = pd.read_csv(file_in, sep=",")
# dataset_test['y_has_purchased'] = dataset_test['y_has_purchased'].fillna(0)
if type_of_model=='premium':
dataset_train['company'] = dataset_train['customer_id'].apply(lambda x: x.split('_')[0])
dataset_test['company'] = dataset_test['customer_id'].apply(lambda x: x.split('_')[0])
dataset_train = dataset_train[dataset_train['company'].isin(['1', '3', '4', '5', '6', '7', '8', '10', '11', '13'])]
dataset_test = dataset_test[dataset_test['company'].isin(['1', '3', '4', '5', '6', '7', '8', '10', '11', '13'])]
return dataset_train, dataset_test