junshan-kit 2.2.4__py2.py3-none-any.whl → 2.2.6__py2.py3-none-any.whl

junshan_kit/DataProcessor.py

@@ -1,36 +1,44 @@
 """
 ----------------------------------------------------------------------
->>> Author       : Junshan Yin  
+>>> Author       : Junshan Yin
 >>> Last Updated : 2025-10-12
 ----------------------------------------------------------------------
 """
+
 import pandas as pd
 
+
 class CSV_TO_Pandas:
     def __init__(self):
         pass
 
-
-    def preprocess_dataset(self, csv_path, drop_cols: list, label_col: str, label_map: dict,  print_info = False):
+    def preprocess_dataset(
+        self,
+        csv_path,
+        drop_cols: list,
+        label_col: str,
+        label_map: dict,
+        print_info=False,
+    ):
         """
         Preprocess a CSV dataset by performing data cleaning, label mapping, and feature encoding.
 
         This function loads a dataset from a CSV file, removes specified non-feature columns,
-        drops rows with missing values, maps the target label to numerical values, and 
-        one-hot encodes categorical features. Optionally, it can print dataset statistics 
+        drops rows with missing values, maps the target label to numerical values, and
+        one-hot encodes categorical features. Optionally, it can print dataset statistics
         before and after preprocessing.
 
         Args:
-            csv_path (str): 
+            csv_path (str):
                 Path to the input CSV dataset.
-            drop_cols (list): 
+            drop_cols (list):
                 List of column names to drop from the dataset.
-            label_col (str): 
+            label_col (str):
                 Name of the target label column.
-            label_map (dict): 
+            label_map (dict):
                 Mapping dictionary for label conversion (e.g., {"yes": 1, "no": -1}).
-            print_info (bool, optional): 
-                Whether to print preprocessing information and dataset statistics. 
+            print_info (bool, optional):
+                Whether to print preprocessing information and dataset statistics.
                 Defaults to False.
 
         Returns:
@@ -65,15 +73,19 @@ class CSV_TO_Pandas:
         df = df.drop(columns=drop_cols)
 
         # Step 2: Remove rows with missing values
-        df = df.dropna(axis=0, how='any')
+        df = df.dropna(axis=0, how="any")
         m_encoded, n_encoded = df.shape
-        
-        # Step 3: Map target label to -1 and +1
+
+        # 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
+        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
@@ -84,19 +96,27 @@ class CSV_TO_Pandas:
             neg_count = (df[label_col] == -1).sum()
 
             # Step 6: Print dataset information
-            print('\n' + '='*80)
+            print("\n" + "=" * 80)
             print(f"{'Dataset Info':^70}")
-            print('='*80)
+            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"{'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"{'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
+            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/DataSets.py

@@ -0,0 +1,77 @@
+"""
+----------------------------------------------------------------------
+>>> Author       : Junshan Yin  
+>>> Last Updated : 2025-xx-xx
+----------------------------------------------------------------------
+"""
+
+import os, time
+import pandas as pd
+import junshan_kit.DataProcessor
+import junshan_kit.kit
+from sklearn.preprocessing import StandardScaler
+
+
+def download_data():
+    from junshan_kit.kit import JianguoyunDownloaderFirefox, JianguoyunDownloaderChrome
+
+    # User selects download method
+    while True:
+        # User inputs download URL
+        url = input("Enter the Jianguoyun download URL: ").strip()
+
+        print("Select download method:")
+        print("1. Firefox")
+        print("2. Chrome")
+        choice = input("Enter the number of your choice (1 or 2): ").strip()
+
+        if choice == "1":
+            JianguoyunDownloaderFirefox(url=url).run()
+            print("✅ Download completed using Firefox")
+            break
+        elif choice == "2":
+            JianguoyunDownloaderChrome(url=url).run()
+            print("✅ Download completed using Chrome")
+            break
+        else:
+            print("❌ Invalid choice. Please enter 1 or 2.\n")
+
+
+def credit_card_fraud_detection(data_name = "Credit Card Fraud Detection"):
+
+    csv_path = f'./exp_data/{data_name}' + 'creditcard.csv'
+    drop_cols = []
+    label_col = 'Class'
+    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()
+        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()
+    cleaner.preprocess_dataset(csv_path, drop_cols, label_col, label_map)
+
+
+    assert False
+    
+    dataloader = junshan_kit.DataProcessor.CSV_TO_Pandas()
+    dataloader.preprocess_dataset()
+    # Step 0: Load the dataset
+    csv_path = "creditcard.csv"
+    df = pd.read_csv(csv_path)
+
+
+
+def wine_and_food_pairing_dataset():
+    pass 
+

junshan_kit/kit.py

@@ -0,0 +1,242 @@
+"""
+----------------------------------------------------------------------
+>>> Author       : Junshan Yin  
+>>> Last Updated : 2025-10-13
+----------------------------------------------------------------------
+"""
+
+import zipfile
+import os, time
+
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+
+def unzip_file(zip_path: str, unzip_folder: str):
+    """
+    Args:
+        zip_path (str): Path to the ZIP file to extract.
+        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 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(unzip_folder)
+
+    print(f"✅ Extracted '{zip_path}' to '{os.path.abspath(unzip_folder)}'")
+
+
+# =============================================================
+#                   JIANGUOYUN (NUTSTORE) CHROME VERSION
+# =============================================================
+
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+class JianguoyunDownloaderChrome:
+    """ Example:
+    >>> url = "https://www.jianguoyun.com/p/DSQqUq8QqdHDDRiy6I0GIAA"
+    >>> downloader = JianguoyunDownloaderChrome(url)
+    >>> downloader.run()
+    """
+    def __init__(self, url, download_path="./exp_data"):
+        self.url = url
+        self.download_path = os.path.abspath(download_path)
+        os.makedirs(self.download_path, exist_ok=True)
+
+        self.chrome_options = ChromeOptions()
+        prefs = {
+            "download.default_directory": self.download_path,
+            "download.prompt_for_download": False,
+            "download.directory_upgrade": True,
+            "safebrowsing.enabled": True,
+            "profile.default_content_setting_values.automatic_downloads": 1,
+        }
+        self.chrome_options.add_experimental_option("prefs", prefs)
+        self.chrome_options.add_argument("--disable-gpu")
+        self.chrome_options.add_argument("--no-sandbox")
+        self.chrome_options.add_argument("--disable-dev-shm-usage")
+        self.chrome_options.add_argument("--enable-features=NetworkService,NetworkServiceInProcess")
+        # Uncomment for headless mode:
+        # self.chrome_options.add_argument("--headless")
+
+        self.driver = webdriver.Chrome(options=self.chrome_options)
+
+    def open_page(self):
+        print(f"🌐 Opening page: {self.url}")
+        self.driver.get(self.url)
+        print(f"✅ Page loaded: {self.driver.title}")
+
+    def click_download_button(self):
+        """Find and click the 'Download' button (supports English and Chinese)."""
+        print("🔍 Searching for the download button...")
+        wait = WebDriverWait(self.driver, 30)
+
+        try:
+            # Match both English 'Download' (case-insensitive) and Chinese '下载'
+            xpath = (
+                "//span[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //button[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //a[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //span[contains(text(),'下载')]"
+                " | //button[contains(text(),'下载')]"
+                " | //a[contains(text(),'下载')]"
+            )
+
+            button = wait.until(EC.element_to_be_clickable((By.XPATH, xpath)))
+
+            # Click using JavaScript to avoid overlay or interaction issues
+            self.driver.execute_script("arguments[0].click();", button)
+            print(f"✅ Download button clicked. Files will be saved to: {self.download_path}")
+
+            # If the cloud service opens a new tab, switch to it
+            time.sleep(3)
+            if len(self.driver.window_handles) > 1:
+                self.driver.switch_to.window(self.driver.window_handles[-1])
+                print("📂 Switched to the new download tab.")
+
+        except Exception as e:
+            print("❌ Failed to find or click the download button:", e)
+            raise
+
+
+    def wait_for_downloads(self, timeout=3600):
+        print("⏳ Waiting for downloads to finish...")
+        start_time = time.time()
+        while time.time() - start_time < timeout:
+            downloading = [f for f in os.listdir(self.download_path) if f.endswith(".crdownload")]
+            if not downloading:
+                print("✅ Download completed!")
+                return
+            time.sleep(2)
+        print("⚠️ Timeout: download not completed within 1 hour")
+
+    def close(self):
+        self.driver.quit()
+        print("🚪 Browser closed.")
+
+    def run(self):
+        print('*' * 60)
+        try:
+            self.open_page()
+            self.click_download_button()
+            self.wait_for_downloads()
+        except Exception as e:
+            print("❌ Error:", e)
+        finally:
+            self.close()
+        print('*' * 60)
+
+
+# =============================================================
+#                   JIANGUOYUN (NUTSTORE) FIREFOX VERSION
+# =============================================================
+
+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/DSQqUq8QqdHDDRiy6I0GIAA"
+    >>> downloader = JianguoyunDownloaderFirefox(url)
+    >>> downloader.run()
+    """
+    def __init__(self, url, download_path="./exp_data"):
+        self.url = url
+        self.download_path = os.path.abspath(download_path)
+        os.makedirs(self.download_path, exist_ok=True)
+
+        options = FirefoxOptions()
+        options.add_argument("--headless")
+        options.set_preference("browser.download.folderList", 2)
+        options.set_preference("browser.download.manager.showWhenStarting", False)
+        options.set_preference("browser.download.dir", self.download_path)
+        options.set_preference("browser.helperApps.neverAsk.saveToDisk",
+                            "application/zip,application/octet-stream,application/x-zip-compressed,multipart/x-zip")
+        options.set_preference("pdfjs.disabled", True)
+
+        service = Service("/snap/bin/geckodriver")
+        self.driver = webdriver.Firefox(service=service, options=options)
+
+    def open_page(self):
+        print(f"🌐 Opening page: {self.url}")
+        self.driver.get(self.url)
+        print(f"✅ Page loaded: {self.driver.title}")
+
+    def click_download_button(self):
+        """Find and click the 'Download' button (supports English and Chinese)."""
+        print("🔍 Searching for the download button...")
+        wait = WebDriverWait(self.driver, 30)
+
+        try:
+            # Match both English 'Download' (case-insensitive) and Chinese '下载'
+            xpath = (
+                "//span[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //button[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //a[contains(translate(text(),'DOWNLOAD下载','download下载'),'download')]"
+                " | //span[contains(text(),'下载')]"
+                " | //button[contains(text(),'下载')]"
+                " | //a[contains(text(),'下载')]"
+            )
+
+            button = wait.until(EC.element_to_be_clickable((By.XPATH, xpath)))
+
+            # Click using JavaScript to avoid overlay or interaction issues
+            self.driver.execute_script("arguments[0].click();", button)
+            print(f"✅ Download button clicked. Files will be saved to: {self.download_path}")
+
+            # If the cloud service opens a new tab, switch to it
+            time.sleep(3)
+            if len(self.driver.window_handles) > 1:
+                self.driver.switch_to.window(self.driver.window_handles[-1])
+                print("📂 Switched to the new download tab.")
+
+        except Exception as e:
+            print("❌ Failed to find or click the download button:", e)
+            raise
+
+    def wait_for_download(self, timeout=3600):
+        """Wait until all downloads are finished (auto-detects browser type)."""
+        print("⏳ Waiting for downloads to finish...")
+        start_time = time.time()
+
+        # Determine the temporary file extension based on the browser type
+        temp_ext = ".crdownload" if "chrome" in self.driver.capabilities["browserName"].lower() else ".part"
+
+        while time.time() - start_time < timeout:
+            downloading = [f for f in os.listdir(self.download_path) if f.endswith(temp_ext)]
+            if not downloading:
+                print("✅ Download completed!")
+                return True
+            time.sleep(2)
+
+
+    def close(self):
+        print("🛑 Closing browser...")
+        self.driver.quit()
+
+    def run(self):
+        print('*' * 60)
+        try:
+            self.open_page()
+            self.click_download_button()
+            self.wait_for_download(timeout=3600)
+        except Exception as e:
+            print("❌ Error:", e)
+        finally:
+            self.close()
+        print('*' * 60)
+
+
+
+

{junshan_kit-2.2.4.dist-info → junshan_kit-2.2.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: junshan_kit
-Version: 2.2.4
+Version: 2.2.6
 Summary: This is an optimization tool.
 Author-email: Junshan Yin <junshanyin@163.com>
 Requires-Dist: kaggle==1.7.4.5

junshan_kit-2.2.6.dist-info/RECORD

@@ -0,0 +1,7 @@
+junshan_kit/DataProcessor.py,sha256=eryVmS5BFZj8wjDN2QWVHqkbFgFuWU0HXV9s6TGf9QM,4442
+junshan_kit/DataSets.py,sha256=jaKB5kh1pOR-o97hab2G2r_YfH69Bs4zR2CkiOfpyss,2085
+junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+junshan_kit/kit.py,sha256=tB1TpW9hW1EweK1RQwHOdUo7uG1QU4vSeyR0fdaSydo,9569
+junshan_kit-2.2.6.dist-info/METADATA,sha256=CqdL1Yui6UbnUt5teWg0EpYP8ofCdviwWK8EkM_MuKw,329
+junshan_kit-2.2.6.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
+junshan_kit-2.2.6.dist-info/RECORD,,

junshan_kit-2.2.4.dist-info/RECORD

@@ -1,5 +0,0 @@
-junshan_kit/DataProcessor.py,sha256=ZysCzYyMxi6uuGb6LyJmyl_QnmqrADHNGcxOdC7_COQ,4232
-junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-junshan_kit-2.2.4.dist-info/METADATA,sha256=MTVQXdnHWcZYhb4zAbx5rdwniT21Wy6BhO031XfOjMk,329
-junshan_kit-2.2.4.dist-info/WHEEL,sha256=tkmg4JIqwd9H8mL30xA7crRmoStyCtGp0VWshokd1Jc,105
-junshan_kit-2.2.4.dist-info/RECORD,,