junshan-kit 2.4.3__py2.py3-none-any.whl → 2.4.5__py2.py3-none-any.whl

junshan_kit/DataProcessor.py

@@ -146,6 +146,7 @@ class CSV_TO_Pandas:
         """
         # Step 0: Load the dataset
         df = pd.read_csv(csv_path)
+        columns = df.columns
 
         # Save original size
         m_original, n_original = df.shape
@@ -214,13 +215,17 @@ class CSV_TO_Pandas:
             print(f"{'Label column:':<40} {label_col}")
             print(f"{'label_map:':<40} {label_map}")
             print(f"{'time column:':<40} {time_info}")
-            if time_info:
+            if time_info is not None:
                 print(f"{'trans_type : int, optional, default=1'}")
-                print(f"{' - 0 : Extract [\'year\', \'month\', \'day\', \'hour\']':<10}")
-                print(f"{' - 1 : Extract [\'hour\', \'dayofweek\', \'is_weekend\']':<10}")
+                print(f"{- 0 : Extract ['year', 'month', 'day', 'hour']:<50}")
+                print(f"{ - 1 : Extract ['hour', 'dayofweek', 'is_weekend']:<50}")
             print(
                 f"{'text fetaure columns:':<40} {', '.join(list(text_feature_cols)) if list(text_feature_cols) else 'None'}"
             )
+            print("-" * 80)
+            print(
+                f"{'all columns:':<40} {', '.join(columns)}"
+            )
             print("=" * 80 + "\n")
 
         return df

junshan_kit/DataSets.py

@@ -42,8 +42,8 @@ def _download_data(data_name, data_type):
     # unzip file
     junshan_kit.kit.unzip_file(f'./exp_data/{data_type}/{data_name}/{data_name}.zip', f'./exp_data/{data_type}/{data_name}') 
 
-def _export_csv(df, data_name):
-    path = f'./exp_data/{data_name}/'
+def _export_csv(df, data_name, data_type):
+    path = f'./exp_data/{data_type}/{data_name}/'
     os.makedirs(path, exist_ok=True)
     df.to_csv(path + f'{data_name}_num.csv')
     print(path + f'{data_name}.csv')
@@ -61,7 +61,7 @@ def _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_
     df = cleaner.preprocess_dataset(csv_path, drop_cols, label_col, label_map, data_name, user_one_hot_cols, print_info=print_info, time_info = time_info)
 
     if export_csv:
-        _export_csv(df, data_name)
+        _export_csv(df, data_name, data_type)
 
     return df
 
@@ -73,11 +73,10 @@ def _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_
 ----------------------------------------------------------------------
 """
 
-def credit_card_fraud_detection(data_name = "Credit Card Fraud Detection", print_info = False, export_csv=False):
+def credit_card_fraud_detection(data_name = "Credit Card Fraud Detection", print_info = False, export_csv=False, drop_cols = []):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/creditcard.csv'
-    drop_cols = []
     label_col = 'Class' 
     label_map = {0: -1, 1: 1}
     
@@ -88,24 +87,22 @@ def credit_card_fraud_detection(data_name = "Credit Card Fraud Detection", print
     return df
 
 
-def diabetes_health_indicators(data_name = "Diabetes Health Indicators", print_info = False, export_csv = False):
+def diabetes_health_indicators(data_name = "Diabetes Health Indicators", print_info = False, export_csv = False, drop_cols = []):
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/diabetes_dataset.csv'
-    drop_cols = []
     label_col = 'diagnosed_diabetes'
     label_map = {0: -1, 1: 1}
     
-
     df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv)
 
     return df
 
 
-def electric_vehicle_population(data_name = "Electric Vehicle Population", print_info = False, export_csv = False):
+def electric_vehicle_population(data_name = "Electric Vehicle Population", print_info = False, export_csv = False, drop_cols = ['VIN (1-10)', 'DOL Vehicle ID', 'Vehicle Location']):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/Electric_Vehicle_Population_Data.csv'
-    drop_cols = ['VIN (1-10)', 'DOL Vehicle ID', 'Vehicle Location']
+    # drop_cols = ['VIN (1-10)', 'DOL Vehicle ID', 'Vehicle Location']
     label_col = 'Electric Vehicle Type'
     label_map = {
     'Battery Electric Vehicle (BEV)': 1,
@@ -117,11 +114,10 @@ def electric_vehicle_population(data_name = "Electric Vehicle Population", print
 
     return df
 
-def global_house_purchase(data_name = "Global House Purchase", print_info = False, export_csv = False):
+def global_house_purchase(data_name = "Global House Purchase", print_info = False, export_csv = False, drop_cols = ['property_id']):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/global_house_purchase_dataset.csv'
-    drop_cols = ['property_id']
     label_col = 'decision'
     label_map = {0: -1, 1: 1}
     
@@ -131,11 +127,11 @@ def global_house_purchase(data_name = "Global House Purchase", print_info = Fals
     return df
 
 
-def health_lifestyle(data_name = "Health Lifestyle", print_info = False, export_csv = False):
+def health_lifestyle(data_name = "Health Lifestyle", print_info = False, export_csv = False, drop_cols = ['id']):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/health_lifestyle_dataset.csv'
-    drop_cols = ['id']
+    
     label_col = 'disease_risk'
     label_map = {0: -1, 1: 1}
     
@@ -145,7 +141,7 @@ def health_lifestyle(data_name = "Health Lifestyle", print_info = False, export_
     return df
 
 
-def medical_insurance_cost_prediction(data_name = "Medical Insurance Cost Prediction", print_info = False, export_csv = False):
+def medical_insurance_cost_prediction(data_name = "Medical Insurance Cost Prediction", print_info = False, export_csv = False, drop_cols = ['alcohol_freq']):
     """
     1. The missing values in this dataset are handled by directly removing the corresponding column. Since the `alcohol_freq` column contains a large number of missing values, deleting the rows would result in significant data loss, so the entire column is dropped instead.
 
@@ -154,7 +150,7 @@ def medical_insurance_cost_prediction(data_name = "Medical Insurance Cost Predic
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/medical_insurance.csv'
-    drop_cols = ['alcohol_freq']
+    
     label_col = 'is_high_risk'
     label_map = {0: -1, 1: 1}
     
@@ -164,11 +160,11 @@ def medical_insurance_cost_prediction(data_name = "Medical Insurance Cost Predic
     return df
 
 
-def particle_physics_event_classification(data_name = "Particle Physics Event Classification", print_info = False, export_csv = False):
+def particle_physics_event_classification(data_name = "Particle Physics Event Classification", print_info = False, export_csv = False, drop_cols = []):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/Particle Physics Event Classification.csv'
-    drop_cols = []
+    
     label_col = 'Label'
     label_map = {'s': -1, 'b': 1}
     
@@ -179,11 +175,11 @@ def particle_physics_event_classification(data_name = "Particle Physics Event Cl
 
 
 
-def adult_income_prediction(data_name = "Adult Income Prediction", print_info = False, export_csv=False):
+def adult_income_prediction(data_name = "Adult Income Prediction", print_info = False, export_csv=False, drop_cols = []):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/adult.csv'
-    drop_cols = []
+    
     label_col = 'income'
     label_map = {'<=50K': -1, '>50K': 1}
     
@@ -193,11 +189,11 @@ def adult_income_prediction(data_name = "Adult Income Prediction", print_info =
     return df
 
 
-def TamilNadu_weather_2020_2025(data_name = "TN Weather 2020-2025", print_info = False, export_csv = False):
+def TamilNadu_weather_2020_2025(data_name = "TN Weather 2020-2025", print_info = False, export_csv = False, drop_cols = ['Unnamed: 0']):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/TNweather_1.8M.csv'
-    drop_cols = ['Unnamed: 0']
+    
     label_col = 'rain_tomorrow'
     label_map = {0: -1, 1: 1}
 
@@ -214,11 +210,11 @@ def TamilNadu_weather_2020_2025(data_name = "TN Weather 2020-2025", print_info =
 
     return df
 
-def YouTube_Recommendation(data_name = "YouTube Recommendation", print_info = False, export_csv = False):
+def YouTube_Recommendation(data_name = "YouTube Recommendation", print_info = False, export_csv = False, drop_cols = ['user_id']):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/youtube recommendation dataset.csv'
-    drop_cols = ['user_id']
+    
     label_col = 'subscribed_after'
     label_map = {0: -1, 1: 1}
 

{junshan_kit-2.4.3.dist-info → junshan_kit-2.4.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: junshan_kit
-Version: 2.4.3
+Version: 2.4.5
 Summary: This is an optimization tool.
 Author-email: Junshan Yin <junshanyin@163.com>
 Requires-Dist: kaggle==1.7.4.5

{junshan_kit-2.4.3.dist-info → junshan_kit-2.4.5.dist-info}/RECORD

@@ -1,6 +1,6 @@
 junshan_kit/ComOptimizers.py,sha256=MUgFnm1DbbvNKv5-7nHJCLOfq4VjoNk1KLRR-ji5rOA,4637
-junshan_kit/DataProcessor.py,sha256=rp1zOTOoF98idwGM_QRzr8yC9M5fj1uyfVhdmV02kyQ,8962
-junshan_kit/DataSets.py,sha256=FJu0B90eiKdKKHQJr_aLNkOvwk4Vhk8mN73jYHZVEjc,8366
+junshan_kit/DataProcessor.py,sha256=oAbf9QsCaLjnN2yrcn8qGof56dSkEv9jHkWiB1CxfTw,9106
+junshan_kit/DataSets.py,sha256=PspH23YbB9cSuh5KQp7Dam3fWsfyH0pwL12nt7KN_tQ,8470
 junshan_kit/ExperimentHub.py,sha256=MKduxa7U16zMoavgS-lVOCL2ypcMLpAaD8k7JitNqRU,11493
 junshan_kit/Models.py,sha256=GRTunJON1vLQz2IxgsoOKvjP-3zSJJLuB3CkJTAiImo,6884
 junshan_kit/Print_Info.py,sha256=vogYcXvoGcRGZV-7svi_mtiCZH6c8d-RhbZLFrLbKr8,3012
@@ -11,6 +11,6 @@ junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 junshan_kit/check_args.py,sha256=7m4xSPAwqqQ0SPeKc-MCewDIDB7kFgsNYS2AuTTzGtk,3599
 junshan_kit/datahub.py,sha256=4c3P2TORMZ4va6NrSiojDCpnY_CGDlJV-5PG3u1_Isk,9081
 junshan_kit/kit.py,sha256=hpA4Zpn1VAuhdJSBBXswVum0CSk6QnB05GGLYoaRatQ,9792
-junshan_kit-2.4.3.dist-info/METADATA,sha256=YZLdpsItctrrUyByIXIS8pTtz_ZPuBgEaAbUyaE1-K8,266
-junshan_kit-2.4.3.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
-junshan_kit-2.4.3.dist-info/RECORD,,
+junshan_kit-2.4.5.dist-info/METADATA,sha256=w5OjSbU0MXzViQmIv8J2YR1Jx87gMWVyKeqEIuR3AUU,266
+junshan_kit-2.4.5.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
+junshan_kit-2.4.5.dist-info/RECORD,,