junshan-kit 2.3.2__py2.py3-none-any.whl → 2.3.4__py2.py3-none-any.whl

junshan_kit/DataProcessor.py

@@ -18,7 +18,7 @@ class CSV_TO_Pandas:
         drop_cols: list,
         label_col: str,
         label_map: dict,
-        data_name: str,
+        title_name: str,
         user_one_hot_cols = [],
         print_info=False,
         Standard = False
@@ -106,7 +106,7 @@ class CSV_TO_Pandas:
 
             # Step 6: Print dataset information
             print("\n" + "=" * 80)
-            print(f"{f'{data_name} - Info':^70}")
+            print(f"{f'{title_name} - Info':^70}")
             print("=" * 80)
             print(f"{'Original size:':<40} {m_original} rows x {n_original} cols")
             print(

junshan_kit/DataSets.py

@@ -36,6 +36,9 @@ def _download_data(data_name):
         else:
             print("❌ Invalid choice. Please enter 1 or 2.\n")
 
+    # unzip file
+    junshan_kit.kit.unzip_file(f'./exp_data/{data_name}/{data_name}.zip', f'./exp_data/{data_name}') 
+
 def _export_csv(df, data_name):
     path = f'./data_trans_fea/{data_name}/'
     os.makedirs(path, exist_ok=True)
@@ -49,10 +52,10 @@ def _run(csv_path, data_name, drop_cols, label_col, label_map, print_info, user_
         print(f"Please download the data.")
         print(csv_path)
         _download_data(data_name)
-        junshan_kit.kit.unzip_file(f'./exp_data/{data_name}/{data_name}.zip', f'./exp_data/{data_name}')   
+        # junshan_kit.kit.unzip_file(f'./exp_data/{data_name}/{data_name}.zip', f'./exp_data/{data_name}')   
     
     cleaner = junshan_kit.DataProcessor.CSV_TO_Pandas()
-    df = cleaner.preprocess_dataset(csv_path, drop_cols, label_col, label_map, data_name,user_one_hot_cols, print_info=print_info)
+    df = cleaner.preprocess_dataset(csv_path, drop_cols, label_col, label_map, data_name, user_one_hot_cols, print_info=print_info)
 
     if export_csv:
         _export_csv(df, data_name)
@@ -169,6 +172,13 @@ def TamilNadu_weather_2020_2025(data_name = "TN Weather 2020-2025", print_info =
     csv_path = f'./exp_data/{data_name}/TNweather_1.8M.csv'
     label_col = 'rain_tomorrow'
     label_map = {0: -1, 1: 1}
+
+    if not os.path.exists(csv_path):
+        print('\n' + '*'*60)
+        print(f"Please download the data.")
+        print(csv_path)
+        _download_data(data_name)
+        # junshan_kit.kit.unzip_file(f'./exp_data/{data_name}/{data_name}.zip', f'./exp_data/{data_name}')   
     
     # Step 0: Load the dataset
     df = pd.read_csv(csv_path)

{junshan_kit-2.3.2.dist-info → junshan_kit-2.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: junshan_kit
-Version: 2.3.2
+Version: 2.3.4
 Summary: This is an optimization tool.
 Author-email: Junshan Yin <junshanyin@163.com>
 Requires-Dist: kaggle==1.7.4.5

junshan_kit-2.3.4.dist-info/RECORD

@@ -0,0 +1,7 @@
+junshan_kit/DataProcessor.py,sha256=E9EDF6XBNNOTuEhSON_jnId-iKgf4QG3szB-goeXECA,4968
+junshan_kit/DataSets.py,sha256=L3D0eBCKHWqpy3qXZvWQP_yKaNzWyj5W1_OLS736xjg,8972
+junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+junshan_kit/kit.py,sha256=tB1TpW9hW1EweK1RQwHOdUo7uG1QU4vSeyR0fdaSydo,9569
+junshan_kit-2.3.4.dist-info/METADATA,sha256=Mz0Rw0l0PUVvFwT8jqtudWcYFHhoScgU5qa2Kxfg5AQ,329
+junshan_kit-2.3.4.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
+junshan_kit-2.3.4.dist-info/RECORD,,

junshan_kit-2.3.2.dist-info/RECORD

@@ -1,7 +0,0 @@
-junshan_kit/DataProcessor.py,sha256=YIZMy2gnqnT8n9MMT-q7WtRB1bbA4ITwPxNBEasAnLQ,4966
-junshan_kit/DataSets.py,sha256=qN4lTVaUsKlu4b8tkZ3aMgHg9lyZTQJlYsgc0uLwUys,8570
-junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-junshan_kit/kit.py,sha256=tB1TpW9hW1EweK1RQwHOdUo7uG1QU4vSeyR0fdaSydo,9569
-junshan_kit-2.3.2.dist-info/METADATA,sha256=OcuB7peGzVOuC0KIcohSPiCBdAs9BZ1mpZjX4ySSKpk,329
-junshan_kit-2.3.2.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
-junshan_kit-2.3.2.dist-info/RECORD,,