junshan-kit 2.1.3__py2.py3-none-any.whl → 2.1.6__py2.py3-none-any.whl

junshan_kit/DataProcessor.py

@@ -0,0 +1,45 @@
+
+import pandas as pd
+import os
+
+import junshan_kit.datahub
+
+class CSVToPandas:
+    def __init__(self):
+        self.data_downloader = junshan_kit.datahub.kaggle_data()
+        
+
+    def read_csv(self, data_name):
+        self.csv_path = f'exp_data/{data_name}/{data_name}.csv'
+        if not os.path.exists(self.csv_path):
+            self.data_downloader.download_data(f'{data_name}', f'exp_data/{data_name}')  
+
+    # ----------------- ccfd_kaggle ----------------------------------
+    def ccfd_kaggle(self, data_name = 'ccfd-kaggle', show_info = True):
+        self.read_csv(data_name)
+        
+        df = pd.read_csv(self.csv_path)
+        m_before, n_before = df.shape
+        df = df.dropna(axis=0, how='any')
+        m_after, n_after = df.shape
+        df['Class'] = df['Class'].replace(0, -1)
+
+        if show_info:
+            pos_count = (df['Class'] == 1).sum()
+            neg_count = (df['Class'] == -1).sum()
+            
+            print('\n' + '='*60)
+            print(f"{'CCFD-Kaggle Dataset Info':^60}")
+            print('='*60)
+            print(f"{'Original size:':<25} {m_before} rows x {n_before} cols")
+            print(f"{'Size after dropping NaNs:':<25} {m_after} rows x {n_after} cols")
+            print(f"{'Export size:':<25} {m_after} rows x {n_after} cols")
+            print(f"{'Positive samples (+1):':<25} {pos_count}")
+            print(f"{'Negative samples (-1):':<25} {neg_count}")
+            print('-'*60)
+            print(f"More details: https://www.jianguoyun.com/p/Dd1clVgQ4ZThCxiwzZQGIAA")
+            print('='*60 + '\n')
+
+        return df
+
+

junshan_kit/datahub.py

@@ -1,24 +1,30 @@
 import kagglehub
 import os
+import warnings
 import shutil
 from kaggle.api.kaggle_api_extended import KaggleApi
 
 class kaggle_data:
-    def list_user_datasets(self):
+    def list_datasets(self):
         api = KaggleApi()
         api.authenticate()
-
-        # Get the list of datasets for a specific user
         datasets = api.dataset_list(user='junshan888')
-
+        print('Available datasets:')
         print('*' * 60)
         if datasets is not None:
             for ds in datasets:
                 if ds is not None:
-                    # Print the dataset title
                     print(ds.title)
         print('*' * 60)
     
+    def list_user_datasets(self):
+        warnings.warn(
+            "list_user_datasets() is deprecated. Use list_datasets() instead.",
+            DeprecationWarning,
+            stacklevel=2
+        )
+        return self.list_datasets()
+    
         # example:  list_user_datasets()
 
     #---------------------------------------------------------------
@@ -36,11 +42,13 @@ class kaggle_data:
     # example: read_data(copy_path='./exp_data')
 
 
+
+
+
 if __name__ == "__main__":
     # Your code here
     data = kaggle_data()
     # Example usage
-    print('Available datasets:')
     data.list_user_datasets()
     data.download_data(data_name='letter-libsvm', copy_path='./exp_data/Letter')
 

junshan_kit/test.py

@@ -0,0 +1,5 @@
+import DataProcessor
+
+
+data_loader = DataProcessor.CSVToPandas()
+data_loader.ccfd_kaggle()

{junshan_kit-2.1.3.dist-info → junshan_kit-2.1.6.dist-info}/METADATA

@@ -1,11 +1,12 @@
 Metadata-Version: 2.4
 Name: junshan_kit
-Version: 2.1.3
+Version: 2.1.6
 Summary: This is an optimization tool.
 Author-email: Junshan Yin <junshanyin@163.com>
 Requires-Dist: kaggle==1.7.4.5
 Requires-Dist: kagglehub==0.3.13
 Requires-Dist: numpy==2.2.6
+Requires-Dist: pandas==2.3.3
 Requires-Dist: scikit-learn==1.7.1
 Description-Content-Type: text/markdown
 

junshan_kit-2.1.6.dist-info/RECORD

@@ -0,0 +1,7 @@
+junshan_kit/DataProcessor.py,sha256=9mlLYxdDiMX7baZmfJk5QuxT4vx_V728XIFbkXmCP0s,1594
+junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+junshan_kit/datahub.py,sha256=BWcG_TPW1xf_y_GzxRXanuOAB01WugBiO5r53EDbr8s,1815
+junshan_kit/test.py,sha256=aEaobINtr4Ri0jX6D8u49xgftyA6SE12wx0P6m5x-2w,90
+junshan_kit-2.1.6.dist-info/METADATA,sha256=KZTS690qvlgOduiYwo6oqshsk4dqY8m9HcVtWu-aXTI,599
+junshan_kit-2.1.6.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
+junshan_kit-2.1.6.dist-info/RECORD,,

junshan_kit-2.1.3.dist-info/RECORD

@@ -1,5 +0,0 @@
-junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-junshan_kit/datahub.py,sha256=G1WmHEQvUnlpyZrC1vDCLBI-ZVeCA-lHoQ8qiL4I7p0,1655
-junshan_kit-2.1.3.dist-info/METADATA,sha256=HZwmPFyfHIJSdOfNWhBj0Ddg684BrpoV6_DCKkGxshk,570
-junshan_kit-2.1.3.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
-junshan_kit-2.1.3.dist-info/RECORD,,