junshan-kit 2.4.5__py2.py3-none-any.whl → 2.4.6__py2.py3-none-any.whl

junshan_kit/DataProcessor.py

@@ -217,15 +217,14 @@ class CSV_TO_Pandas:
             print(f"{'time column:':<40} {time_info}")
             if time_info is not None:
                 print(f"{'trans_type : int, optional, default=1'}")
-                print(f"{- 0 : Extract ['year', 'month', 'day', 'hour']:<50}")
-                print(f"{ - 1 : Extract ['hour', 'dayofweek', 'is_weekend']:<50}")
+                print("- 0 : Extract ['year', 'month', 'day', 'hour']")
+                print("- 1 : Extract ['hour', 'dayofweek', 'is_weekend']")
             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("all columns:")
+            print(list(columns))
             print("=" * 80 + "\n")
 
         return df

junshan_kit/DataSets.py

@@ -49,7 +49,7 @@ def _export_csv(df, data_name, data_type):
     print(path + f'{data_name}.csv')
 
 
-def _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, user_one_hot_cols = [], export_csv = False, time_info = None):
+def _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, user_one_hot_cols = [], export_csv = False, time_info = None, Standard = False):
     if not os.path.exists(csv_path):
         print('\n' + '*'*60)
         print(f"Please download the data.")
@@ -73,7 +73,7 @@ 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, drop_cols = []):
+def credit_card_fraud_detection(data_name = "Credit Card Fraud Detection", print_info = False, export_csv=False, drop_cols = [], Standard = False):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/creditcard.csv'
@@ -81,24 +81,24 @@ def credit_card_fraud_detection(data_name = "Credit Card Fraud Detection", print
     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)
+    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, Standard = Standard)
     
 
     return df
 
 
-def diabetes_health_indicators(data_name = "Diabetes Health Indicators", print_info = False, export_csv = False, drop_cols = []):
+def diabetes_health_indicators(data_name = "Diabetes Health Indicators", print_info = False, export_csv = False, drop_cols = [], Standard = False):
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/diabetes_dataset.csv'
     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)
+    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, Standard = Standard)
 
     return df
 
 
-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']):
+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'], Standard = False):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/Electric_Vehicle_Population_Data.csv'
@@ -110,11 +110,11 @@ def electric_vehicle_population(data_name = "Electric Vehicle Population", print
     }
     
 
-    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv)
+    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, Standard = Standard)
 
     return df
 
-def global_house_purchase(data_name = "Global House Purchase", print_info = False, export_csv = False, drop_cols = ['property_id']):
+def global_house_purchase(data_name = "Global House Purchase", print_info = False, export_csv = False, drop_cols = ['property_id'], Standard =False):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/global_house_purchase_dataset.csv'
@@ -122,12 +122,12 @@ def global_house_purchase(data_name = "Global House Purchase", print_info = Fals
     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)
+    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, Standard = Standard)
 
     return df
 
 
-def health_lifestyle(data_name = "Health Lifestyle", print_info = False, export_csv = False, drop_cols = ['id']):
+def health_lifestyle(data_name = "Health Lifestyle", print_info = False, export_csv = False, drop_cols = ['id'], Standard =False):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/health_lifestyle_dataset.csv'
@@ -136,12 +136,12 @@ def health_lifestyle(data_name = "Health Lifestyle", print_info = False, export_
     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)
+    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, Standard = Standard)
 
     return df
 
 
-def medical_insurance_cost_prediction(data_name = "Medical Insurance Cost Prediction", print_info = False, export_csv = False, drop_cols = ['alcohol_freq']):
+def medical_insurance_cost_prediction(data_name = "Medical Insurance Cost Prediction", print_info = False, export_csv = False, drop_cols = ['alcohol_freq'], Standard = False):
     """
     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.
 
@@ -155,12 +155,12 @@ def medical_insurance_cost_prediction(data_name = "Medical Insurance Cost Predic
     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)
+    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, Standard = Standard)
 
     return df
 
 
-def particle_physics_event_classification(data_name = "Particle Physics Event Classification", print_info = False, export_csv = False, drop_cols = []):
+def particle_physics_event_classification(data_name = "Particle Physics Event Classification", print_info = False, export_csv = False, drop_cols = [], Standard =False):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/Particle Physics Event Classification.csv'
@@ -169,13 +169,13 @@ def particle_physics_event_classification(data_name = "Particle Physics Event Cl
     label_map = {'s': -1, 'b': 1}
     
 
-    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv)
+    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, Standard = Standard)
 
     return df
 
 
 
-def adult_income_prediction(data_name = "Adult Income Prediction", print_info = False, export_csv=False, drop_cols = []):
+def adult_income_prediction(data_name = "Adult Income Prediction", print_info = False, export_csv=False, drop_cols = [], Standard = False):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/adult.csv'
@@ -184,12 +184,12 @@ def adult_income_prediction(data_name = "Adult Income Prediction", print_info =
     label_map = {'<=50K': -1, '>50K': 1}
     
 
-    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv)
+    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, Standard = Standard)
 
     return df
 
 
-def TamilNadu_weather_2020_2025(data_name = "TN Weather 2020-2025", print_info = False, export_csv = False, drop_cols = ['Unnamed: 0']):
+def TamilNadu_weather_2020_2025(data_name = "TN Weather 2020-2025", print_info = False, export_csv = False, drop_cols = ['Unnamed: 0'], Standard = False):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/TNweather_1.8M.csv'
@@ -197,20 +197,17 @@ def TamilNadu_weather_2020_2025(data_name = "TN Weather 2020-2025", print_info =
     label_col = 'rain_tomorrow'
     label_map = {0: -1, 1: 1}
 
-    # Extraction mode.
-    # - 0 : Extract ['year', 'month', 'day', 'hour']
-    # - 1 : Extract ['hour', 'dayofweek', 'is_weekend']
     time_info = {
         'time_col_name': 'time',
         'trans_type': 0
     }
 
-    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, time_info=time_info)
+    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, time_info=time_info, Standard = Standard)
 
 
     return df
 
-def YouTube_Recommendation(data_name = "YouTube Recommendation", print_info = False, export_csv = False, drop_cols = ['user_id']):
+def YouTube_Recommendation(data_name = "YouTube Recommendation", print_info = False, export_csv = False, drop_cols = ['user_id'], Standard = False):
 
     data_type = "binary"
     csv_path = f'./exp_data/{data_type}/{data_name}/youtube recommendation dataset.csv'
@@ -226,6 +223,6 @@ def YouTube_Recommendation(data_name = "YouTube Recommendation", print_info = Fa
         'trans_type': 1
     }
     
-    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, time_info=time_info)
+    df = _run(csv_path, data_name, data_type, drop_cols, label_col, label_map, print_info, export_csv=export_csv, time_info=time_info, Standard = Standard)
 
     return df

{junshan_kit-2.4.5.dist-info → junshan_kit-2.4.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: junshan_kit
-Version: 2.4.5
+Version: 2.4.6
 Summary: This is an optimization tool.
 Author-email: Junshan Yin <junshanyin@163.com>
 Requires-Dist: kaggle==1.7.4.5

{junshan_kit-2.4.5.dist-info → junshan_kit-2.4.6.dist-info}/RECORD

@@ -1,6 +1,6 @@
 junshan_kit/ComOptimizers.py,sha256=MUgFnm1DbbvNKv5-7nHJCLOfq4VjoNk1KLRR-ji5rOA,4637
-junshan_kit/DataProcessor.py,sha256=oAbf9QsCaLjnN2yrcn8qGof56dSkEv9jHkWiB1CxfTw,9106
-junshan_kit/DataSets.py,sha256=PspH23YbB9cSuh5KQp7Dam3fWsfyH0pwL12nt7KN_tQ,8470
+junshan_kit/DataProcessor.py,sha256=hX9W7wmte941jQkt834BcOUKnkkODX7oPW9HrlJCfkc,9064
+junshan_kit/DataSets.py,sha256=iQrCTubKCSB7xvKS9LvSdZzNTuOEj78vH3KYC1cQNDw,8743
 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-2.4.5.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,,
+junshan_kit-2.4.6.dist-info/METADATA,sha256=jAn8rIxCSoRZe1ZcjTBsqfD-5cAlhydSORSMb2sr_4I,266
+junshan_kit-2.4.6.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
+junshan_kit-2.4.6.dist-info/RECORD,,