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

Fix conflicts

Browse Source
This commit is contained in:
Alexis REVELLE 2024-03-07 13:05:49 +00:00
parent a49d14853e
commit af84a57c54
1 changed files with 9 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
0_2_Dataset_construction.py
View File

@ -146,22 +146,19 @@ BUCKET_OUT = f'projet-bdc2324-team1/Generalization/{type_of_comp}'
# Create test dataset and train dataset for sport companies
<<<<<<< HEAD
#start_date, end_of_features, final_date = df_coverage_modelization(list_of_comp, coverage_features = 0.7)
=======
# start_date, end_of_features, final_date = df_coverage_modelization(list_of_comp, coverage_train = 0.7)
>>>>>>> main
start_date = "2021-05-01"
end_of_features = "2022-11-01"
final_date = "2023-11-01"
<<<<<<< HEAD
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}
=======
anonymous_customer = {'1' : 1, '2' : 12184, '3' : 1, '4' : 2, '101' : 1,
'5' : 191835, '6' : 591412, '7' : 49632, '8' : 1942, '9' : 19683}
>>>>>>> main
'5' : 5_191835, '6' : 6_591412, '7' : 7_49632, '8' : 8_1942, '9' : 9_19683,
'10' : 10_19521, '11' : 11_36 , '12' : 12_1706757, '13' : 13_8422, '14' : 14_6354 }
for company in list_of_comp:
dataset = dataset_construction(min_date = start_date, end_features_date = end_of_features,
@ -170,21 +167,17 @@ for company in list_of_comp:
# On retire le client anonyme
dataset = dataset[dataset['customer_id'] != anonymous_customer[company]]
<<<<<<< HEAD
#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:]
=======
# On retire le client anonyme
dataset_test = dataset_test[dataset_test['customer_id'] != anonymous_customer[company]]
>>>>>>> main
# Dataset Test
# Exportation
FILE_KEY_OUT_S3 = "dataset_test" + company + ".csv"
FILE_PATH_OUT_S3 = BUCKET_OUT + "/Test_set/" + FILE_KEY_OUT_S3