junshan-kit 2.2.1__py2.py3-none-any.whl → 2.2.2__py2.py3-none-any.whl

junshan_kit/DataProcessor.py

@@ -1,10 +1,17 @@
+"""
+----------------------------------------------------------------------
+>>> Author       : Junshan Yin  
+>>> Last Updated : 2025-10-12
+----------------------------------------------------------------------
+"""
 
 import pandas as pd
 import os
 from sklearn.preprocessing import StandardScaler
 import junshan_kit.datahub
+import kit
 
-class CSVToPandas:
+class CSVToPandasMeta:
     def __init__(self):
         self.data_downloader = junshan_kit.datahub.kaggle_data()
         
@@ -79,7 +86,7 @@ class CSVToPandas:
         scaler = StandardScaler()
         df[num_cols] = scaler.fit_transform(df[num_cols])
 
-        # 导出后的大小
+        # The size after export
         m_export, n_export = df.shape
 
         if show_info:
@@ -103,3 +110,57 @@ class CSVToPandas:
 
 
 
+class CSV_TO_Pandas:
+    def __init__(self):
+        pass
+
+    def clean_data(self, csv_path, drop_cols: list, label_col: str, label_map: dict,  print_info = False):
+        # Step 0: Load the dataset
+        df = pd.read_csv(csv_path)
+
+        # Save original size
+        m_original, n_original = df.shape
+
+        # Step 1: Drop non-informative columns
+        df = df.drop(columns=drop_cols)
+
+        # Step 2: Remove rows with missing values
+        df = df.dropna(axis=0, how='any')
+        m_encoded, n_encoded = df.shape
+        
+        # Step 3: Map target label to -1 and +1
+        df[label_col] = df[label_col].map(label_map)
+
+        # Step 4: Encode categorical features (exclude label column)
+        text_feature_cols = df.select_dtypes(include=['object', 'string', 'category']).columns
+        text_feature_cols = [col for col in text_feature_cols if col != label_col]  # ✅ exclude label
+
+        df = pd.get_dummies(df, columns=text_feature_cols, dtype=int)
+        m_cleaned, n_cleaned = df.shape
+
+        # print info
+        if print_info:
+            pos_count = (df[label_col] == 1).sum()
+            neg_count = (df[label_col] == -1).sum()
+
+            # Step 6: Print dataset information
+            print('\n' + '='*80)
+            print(f"{'Dataset Info':^70}")
+            print('='*80)
+            print(f"{'Original size:':<40} {m_original} rows x {n_original} cols")
+            print(f"{'Size after dropping NaN & non-feature cols:':<40} {m_cleaned} rows x {n_cleaned} cols")
+            print(f"{'Positive samples (+1):':<40} {pos_count}")
+            print(f"{'Negative samples (-1):':<40} {neg_count}")
+            print(f"{'Size after one-hot encoding:':<40} {m_encoded} rows x {n_encoded} cols")
+            print('-'*80)
+            print(f"Note:")
+            print(f"{'Label column:':<40} {label_col}")
+            print(f"{'Dropped non-feature columns:':<40} {', '.join(drop_cols) if drop_cols else 'None'}")
+            print(f"{'text fetaure columns:':<40} {', '.join(list(text_feature_cols)) if list(text_feature_cols) else 'None'}")
+            print('='*80 + '\n')
+
+        return df
+
+        
+
+        

junshan_kit/datahub.py

@@ -1,3 +1,10 @@
+"""
+----------------------------------------------------------------------
+>>> Author       : Junshan Yin  
+>>> Last Updated : 2025-10-12
+----------------------------------------------------------------------
+"""
+
 import kagglehub
 import os, time
 import warnings

junshan_kit/kit.py

@@ -1,22 +1,35 @@
+"""
+----------------------------------------------------------------------
+>>> Author       : Junshan Yin  
+>>> Last Updated : 2025-10-13
+----------------------------------------------------------------------
+"""
+
 import zipfile
 import os
 
-def unzip_file(zip_path, dest_folder=None):
+def unzip_file(zip_path: str, unzip_folder: str):
     """
-    Extract a ZIP file to a folder.
-
-    Parameters:
+    Args:
         zip_path (str): Path to the ZIP file to extract.
-        dest_folder (str, optional): Folder to extract files into.
-                                    If None, the function uses a folder
-                                    with the same name as the ZIP file.
+        dest_folder (str, optional): Folder to extract files into. 
+            If None, the function will create a folder with the same 
+            name as the ZIP file (without extension).
+
+    Examples:
+        >>> zip_path = "./downloads/data.zip"
+        >>> unzip_folder = "./exp_data/data"
+        >>> unzip_file(zip_path, unzip_folder)
     """
-    if dest_folder is None:
-        dest_folder = os.path.splitext(os.path.basename(zip_path))[0]
 
-    os.makedirs(dest_folder, exist_ok=True)
+    if unzip_folder is None:
+        unzip_folder = os.path.splitext(os.path.basename(zip_path))[0]
+
+    os.makedirs(unzip_folder, exist_ok=True)
 
     with zipfile.ZipFile(zip_path, 'r') as zip_ref:
-        zip_ref.extractall(dest_folder)
+        zip_ref.extractall(unzip_folder)
+
+    print(f"✅ Extracted '{zip_path}' to '{os.path.abspath(unzip_folder)}'")
+
 
-    print(f"✅ Extracted '{zip_path}' to '{os.path.abspath(dest_folder)}'")

junshan_kit/meta.py

@@ -1,3 +1,10 @@
+"""
+----------------------------------------------------------------------
+>>> Author       : Junshan Yin  
+>>> Last Updated : 2025-10-12
+----------------------------------------------------------------------
+"""
+
 import os
 import time
 import shutil
@@ -10,13 +17,16 @@ from selenium.webdriver.common.by import By
 from selenium.webdriver.support.ui import WebDriverWait
 from selenium.webdriver.support import expected_conditions as EC
 
+
 # =============================================================
 #                   KAGGLE DATA MANAGEMENT
 # =============================================================
 
 class KaggleData:
     def list_datasets(self):
-        """List available datasets from a specific user."""
+        """
+        List available datasets from a specific user.
+        """
         api = KaggleApi()
         api.authenticate()
         datasets = api.dataset_list(user='junshan888')
@@ -51,6 +61,11 @@ class KaggleData:
 from selenium.webdriver.chrome.options import Options as ChromeOptions
 
 class JianguoyunDownloaderChrome:
+    """ Example:
+    >>> url = "https://www.jianguoyun.com/p/DdyHJxUQqdHDDRjvtI0GIAA"
+    >>> downloader = JianguoyunDownloaderChrome(url)
+    >>> downloader.run()
+    """
     def __init__(self, url, download_path="./downloads"):
         self.url = url
         self.download_path = os.path.abspath(download_path)
@@ -148,6 +163,11 @@ from selenium.webdriver.firefox.options import Options as FirefoxOptions
 from selenium.webdriver.firefox.service import Service
 
 class JianguoyunDownloaderFirefox:
+    """ Example:
+    >>> url = "https://www.jianguoyun.com/p/DdyHJxUQqdHDDRjvtI0GIAA"
+    >>> downloader = JianguoyunDownloaderFirefox(url)
+    >>> downloader.run()
+    """
     def __init__(self, url, download_path="./downloads"):
         self.url = url
         self.download_path = os.path.abspath(download_path)
@@ -234,19 +254,3 @@ class JianguoyunDownloaderFirefox:
             self.close()
         print('*' * 60)
 
-
-# =============================================================
-#                           MAIN
-# =============================================================
-
-if __name__ == "__main__":
-    url = "https://www.jianguoyun.com/p/DdyHJxUQqdHDDRjvtI0GIAA"
-
-    use_chrome = True  # Set True to use Chrome, False for Firefox
-
-    if use_chrome:
-        downloader = JianguoyunDownloaderChrome(url)
-    else:
-        downloader = JianguoyunDownloaderFirefox(url)
-
-    downloader.run()

junshan_kit/test.py

@@ -1,3 +1,8 @@
-from datahub import JianguoDownloader
+from DataProcessor import CSV_TO_Pandas
 
-data2 = JianguoDownloader('www.lka.com', './expspe')
+
+data_ = CSV_TO_Pandas()
+
+
+
+data_.clean_data('data_csv/Electric Vehicle Population Data/Electric_Vehicle_Population_Data.csv', [], [], {})

{junshan_kit-2.2.1.dist-info → junshan_kit-2.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: junshan_kit
-Version: 2.2.1
+Version: 2.2.2
 Summary: This is an optimization tool.
 Author-email: Junshan Yin <junshanyin@163.com>
 Requires-Dist: kaggle==1.7.4.5

junshan_kit-2.2.2.dist-info/RECORD

@@ -0,0 +1,9 @@
+junshan_kit/DataProcessor.py,sha256=S-_QG2ZkHCGyhS8cxYEnO9z1vyKMrNHYd2j1DuAeNG0,6266
+junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+junshan_kit/datahub.py,sha256=_Q_3AlZ8vk1Ma6h9I44SxWBA8w9m1CQNvYztMcsxzUo,5377
+junshan_kit/kit.py,sha256=h4Q_87hEJbXH4A9ryaGMu_nle5RlM8OR_PaW_hWCVBY,1040
+junshan_kit/meta.py,sha256=SiY9P93aABrksNE6G3ft5gzcuP2cUgc4Vx6LH7ZFmzg,10113
+junshan_kit/test.py,sha256=FgzG4oG7kkq6rWasxdBSY1qx_B0navRI5Ei-wJ1Dvo0,180
+junshan_kit-2.2.2.dist-info/METADATA,sha256=Qe9kokd4FFGlKhg5NDaMhpQrhRSulPvCAr4wcp9rsEo,329
+junshan_kit-2.2.2.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
+junshan_kit-2.2.2.dist-info/RECORD,,

junshan_kit-2.2.1.dist-info/RECORD

@@ -1,9 +0,0 @@
-junshan_kit/DataProcessor.py,sha256=AW_1jROexC3s41-RgzqzYVwPI0sOf3tzjiph4qa_Vcw,3882
-junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-junshan_kit/datahub.py,sha256=I34e26psFS8WK4X6SNucKPLtdBm0Ujzqa0VDIRACah4,5163
-junshan_kit/kit.py,sha256=Y-GD6rPxi0BG4V_pALcYGUBt4GBCl2jbUE3MKLvGIq0,721
-junshan_kit/meta.py,sha256=5aHyUPVr3P3yoAdC4DzOZv4AtaO9iX8zGjluwpOly6Q,10017
-junshan_kit/test.py,sha256=uSckjcr_Wgj__YPTwD6x0GY8Hfn5GBEXIpRf9vIYBbU,91
-junshan_kit-2.2.1.dist-info/METADATA,sha256=0dNpnGogyiuxiC9JJXuD0aSzMjigCzps2ylaWgl08YM,329
-junshan_kit-2.2.1.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
-junshan_kit-2.2.1.dist-info/RECORD,,