opsci-toolbox 0.0.5__py3-none-any.whl → 0.0.7__py3-none-any.whl

opsci_toolbox/helpers/common.py

@@ -15,12 +15,27 @@ import pyarrow.parquet as pq
 from datetime import datetime
 import hashlib
 import ast
+import subprocess
 
 ####################################################################################################
 # FILE LOADERS
 ####################################################################################################
 
-def load_file(path, delimiter = ";", decimal ="."):
+def load_file(path: str, delimiter: str = ";", decimal: str = ".")  -> pd.DataFrame:
+    """
+    Load a file into a Pandas DataFrame based on the file extension.
+
+    Parameters:
+    path (str): The file path to load.
+    delimiter (str, optional): The delimiter used in CSV/TSV files. Default is ";".
+    decimal (str, optional): The character used for decimal points in CSV/TSV files. Default is ".".
+
+    Returns:
+    pd.DataFrame: The loaded data as a Pandas DataFrame.
+
+    Raises:
+    ValueError: If the file extension is not supported.
+    """
     extension = os.path.splitext(os.path.basename(path))[1]
     if extension == ".parquet":
         df = load_parquet(path)
@@ -38,9 +53,18 @@ def load_file(path, delimiter = ";", decimal ="."):
         print("Check your input file. Extension isn't supported : .parquet, .pickle, .json, .jsonl, .csv, .tsv")
     return df
 
-def load_parquet(path): 
+def load_parquet(path: str) -> pd.DataFrame:
     """
-    Load a parquet file into a DataFrame
+    Load a parquet file into a DataFrame.
+    
+    Parameters:
+    path (str): The file path to the parquet file.
+    
+    Returns:
+    pd.DataFrame: The loaded data as a Pandas DataFrame.
+    
+    Raises:
+    Exception: If there is an error reading the parquet file.
     """
     try:
         table = pq.read_table(path)
@@ -50,78 +74,108 @@ def load_parquet(path):
         print(e)
     return df
 
-# def load_pickle(path: str):
-#     """
-#     Load a pickle file into a dataframe
-#     """
-    
-#     with open(path, 'rb') as f:
-#         df=pickle.load(f)
-#     return df
-def load_pickle(path):
-    return pd.read_pickle(path)
-
-def write_pickle(data, path, filename):
+def load_pickle(path: str) -> pd.DataFrame:
     """
-    Write a dataframe into a pickle file
+    Load a pickle file into a DataFrame.
+    
+    Parameters:
+    path (str): The file path to the pickle file.
+    
+    Returns:
+    pd.DataFrame: The loaded data as a Pandas DataFrame.
     """
-    file_path=os.path.join(path, filename+'.pickle')
-    with open(file_path, 'wb') as f:
-        pickle.dump(data, f)
-    return file_path
+    return pd.read_pickle(path)
 
 
-def load_json(path: str):
+def load_json(path: str) -> pd.DataFrame:
     """
-    Load a json file into a DataFrame
+    Load a JSON file into a DataFrame.
+    
+    Parameters:
+    path (str): The file path to the JSON file.
+    
+    Returns:
+    pd.DataFrame: The loaded data as a Pandas DataFrame.
+    
+    Raises:
+    Exception: If there is an error reading the JSON file.
     """
-    df=pd.DataFrame()
+    df = pd.DataFrame()
     try:
         with open(path, 'r') as json_file:
             data = json.load(json_file)
-        df=pd.json_normalize(data)
-        
+        df = pd.json_normalize(data)
     except Exception as e:
-        pass
-        print(e)
+        print(f"Error reading the JSON file: {e}")
+        raise
     return df
 
-def load_jsonl(path: str):
+def load_jsonl(path: str) -> pd.DataFrame:
     """
-    Load a jsonl file into a dataframe
+    Load a JSON Lines (jsonl) file into a DataFrame.
+    
+    Parameters:
+    path (str): The file path to the jsonl file.
+    
+    Returns:
+    pd.DataFrame: The loaded data as a Pandas DataFrame.
+    
+    Raises:
+    Exception: If there is an error reading the jsonl file.
     """
     df = pd.DataFrame()
     try:
         data = []
         with open(path, 'r') as json_file:
-            for line in tqdm(json_file):
+            for line in tqdm(json_file, desc="Loading JSON Lines"):
                 try:
                     data.append(json.loads(line))
-                except:
-                    pass
+                except json.JSONDecodeError as line_error:
+                    print(f"Error decoding line: {line_error}")
             
         df = pd.json_normalize(data)
     except Exception as e:
-        pass
-        print(e)
+        print(f"Error reading the jsonl file: {e}")
+        raise
     return df
 
 
-def load_csv(path: str, delimiter: str =";", decimal:str ="."):
+def load_csv(path: str, delimiter: str = ";", decimal: str = ".") -> pd.DataFrame:
     """
-    Load a csv file into a dataframe 
+    Load a CSV file into a DataFrame.
+    
+    Parameters:
+    path (str): The file path to the CSV file.
+    delimiter (str, optional): The delimiter used in the CSV file. Default is ";".
+    decimal (str, optional): The character used for decimal points in the CSV file. Default is ".".
+    
+    Returns:
+    pd.DataFrame: The loaded data as a Pandas DataFrame.
+    
+    Raises:
+    Exception: If there is an error reading the CSV file.
     """
-    df= pd.DataFrame()
+    df = pd.DataFrame()
     try:
         df = pd.read_csv(path, delimiter=delimiter, encoding="utf-8", decimal=decimal)
     except Exception as e:
-        pass
-        print(e)
+        print(f"Error reading the CSV file: {e}")
+        raise
     return df
 
-def read_txt_to_list(file_path: str):
+def read_txt_to_list(file_path: str) -> list[str]:
     """
-    Read a text file line by line and append to a Python list 
+    Read a text file line by line and append to a Python list.
+    
+    Parameters:
+    file_path (str): The file path to the text file.
+    
+    Returns:
+    list[str]: A list of lines read from the text file.
+    
+    Raises:
+    FileNotFoundError: If the file does not exist.
+    Exception: If any other error occurs during file reading.
     """
     
     # Initialize an empty list to store the lines
@@ -136,12 +190,22 @@ def read_txt_to_list(file_path: str):
         print(f"File not found: {file_path}")
     except Exception as e:
         print(f"An error occurred: {e}")
+        raise
     return lines
 
-
-def read_json(path: str):
+def read_json(path: str) -> dict:
     """
-    Read a json file and return a dict
+    Read a JSON file and return a dictionary.
+    
+    Parameters:
+    path (str): The file path to the JSON file.
+    
+    Returns:
+    dict: The data read from the JSON file as a dictionary.
+    
+    Raises:
+    FileNotFoundError: If the file does not exist.
+    Exception: If there is an error reading the JSON file.
     """
     with open(path, 'r') as json_file:
         data = json.load(json_file)
@@ -149,25 +213,55 @@ def read_json(path: str):
 
 def read_txt_file(file_path: str) -> str:
     """
-    Read a text file
+    Read the content of a text file and return it as a string.
+    
+    Parameters:
+    file_path (str): The file path to the text file.
+    
+    Returns:
+    str: The content of the text file as a string.
+    
+    Raises:
+    FileNotFoundError: If the file does not exist.
+    Exception: If there is an error reading the text file.
     """
-    with open(file_path, 'r') as file:
-        content = file.read()
+    try:
+        with open(file_path, 'r') as file:
+            content = file.read()
+    except FileNotFoundError:
+        print(f"File not found: {file_path}")
+        raise
+    except Exception as e:
+        print(f"An error occurred while reading the file: {e}")
+        raise
     return content
 
-def read_jsonl(path: str):
+def read_jsonl(path: str) -> list[dict]:
     """
-    Load a jsonl file into a dataframe
+    Load a JSON Lines (jsonl) file into a list of dictionaries.
+    
+    Parameters:
+    path (str): The file path to the jsonl file.
+    
+    Returns:
+    list[dict]: A list of dictionaries containing the data read from the JSON Lines file.
+    
+    Raises:
+    FileNotFoundError: If the file does not exist.
+    Exception: If there is an error reading the jsonl file.
     """
     json_data = []
-    with open(path, 'r') as json_file:
-        for line in tqdm(json_file):
-            try:
-                json_data.append(json.loads(line))
-            except Exception as e:
-                pass
-                print(e)
-        
+    try:
+        with open(path, 'r') as json_file:
+            for line in tqdm(json_file, desc="Reading JSON Lines"):
+                try:
+                    json_data.append(json.loads(line))
+                except Exception as e:
+                    print(f"Error decoding line: {e}")
+                    raise
+    except FileNotFoundError:
+        print(f"File not found: {path}")
+        raise
     return json_data
 
 
@@ -176,37 +270,55 @@ def read_jsonl(path: str):
 #########################################################################################
 
 
-# def write_pickle(df: pd.DataFrame, path: str, name: str):
-#     """
-#     Write a dataframe into a pickle file
-#     """
-#     file_path=os.path.join(path, name+'.pickle')
+def write_pickle(data: pd.DataFrame, path: str, filename: str) -> str:
+    """
+    Write a DataFrame into a pickle file.
+    
+    Parameters:
+    data (pd.DataFrame): The DataFrame to be written to the pickle file.
+    path (str): The directory where the pickle file will be saved.
+    filename (str): The name of the pickle file (without the extension).
     
-#     with open(file_path, 'wb') as f:
-#         pickle.dump(df, f)
-#     return file_path
+    Returns:
+    str: The full path to the saved pickle file.
+    """
+    file_path = os.path.join(path, filename + '.pickle')
+    with open(file_path, 'wb') as f:
+        pickle.dump(data, f)
+    return file_path
 
 
-def write_list_to_txt(input_list: list, path: str, name: str):
+def write_list_to_txt(input_list: list, path: str, name: str) -> str:
     """
     Write a list to a text file, with each item on a new line.
 
     Parameters:
-    - file_path (str): The path to the text file.
     - input_list (list): The list to be written to the text file.
+    - path (str): The directory path where the text file will be saved.
+    - name (str): The name of the text file (without the extension).
+
+    Returns:
+    str: The full path to the saved text file.
     """
-    file_path=os.path.join(path, name+'.txt')
+    file_path = os.path.join(path, name + '.txt')
     with open(file_path, 'w') as file:
         for item in input_list:
             file.write(str(item) + '\n')
-            
     return file_path
 
-def write_jsonl(data: list,  path: str, name: str):
+def write_jsonl(data: list[dict], path: str, name: str) -> str:
     """
-    Write a jsonl file. Function takes as input a list of dict.
+    Write data to a JSON Lines (jsonl) file. Each dictionary in the list represents a single JSON object.
+
+    Parameters:
+    - data (list[dict]): The list of dictionaries to be written to the JSON Lines file.
+    - path (str): The directory path where the JSON Lines file will be saved.
+    - name (str): The name of the JSON Lines file (without the extension).
+
+    Returns:
+    str: The full path to the saved JSON Lines file.
     """
-    file_path=os.path.join(path, name+'.jsonl')
+    file_path = os.path.join(path, name + '.jsonl')
     with open(file_path, 'w') as file:
         for entry in data:
             json.dump(entry, file)
@@ -214,41 +326,67 @@ def write_jsonl(data: list,  path: str, name: str):
     return file_path
 
 
-def write_json(json_dict: dict, path: str, name: str):
+def write_json(json_dict: dict, path: str, name: str) -> str:
     """
-    Write a dict into a json file
+    Write a dictionary to a JSON file.
+
+    Parameters:
+    - json_dict (dict): The dictionary to be written to the JSON file.
+    - path (str): The directory path where the JSON file will be saved.
+    - name (str): The name of the JSON file (without the extension).
+
+    Returns:
+    str: The full path to the saved JSON file.
     """
-    file_path=os.path.join(path, name+'.json')
+    file_path = os.path.join(path, name + '.json')
     with open(file_path, 'w') as outfile:
         json.dump(json_dict, outfile)
     return file_path
 
 
-def write_dataframe_to_json(df: pd.DataFrame, path: str, name: str, orient='records'):
+def write_dataframe_to_json(df: pd.DataFrame, path: str, name: str, orient: str = 'records') -> str:
     """
-    Write a dataframe into a json file
+    Write a DataFrame to a JSON file.
+
+    Parameters:
+    - df (pd.DataFrame): The DataFrame to be written to the JSON file.
+    - path (str): The directory path where the JSON file will be saved.
+    - name (str): The name of the JSON file (without the extension).
+    - orient (str, optional): The format of the JSON file. Default is 'records'.
+
+    Returns:
+    str: The full path to the saved JSON file.
     """
-    file_path=os.path.join(path, name+".json")
+    file_path = os.path.join(path, name + ".json")
     df.to_json(file_path, orient=orient, lines=True)
+    return file_path
     
     
-def save_dataframe_excel(df: pd.DataFrame, path: str, name :str, sheet_name:str):
+def save_dataframe_excel(df: pd.DataFrame, path: str, name: str, sheet_name: str) -> str:
     """
-    Write a dataframe into a XLSX file
+    Write a DataFrame to an Excel file.
+
+    Parameters:
+    - df (pd.DataFrame): The DataFrame to be written to the Excel file.
+    - path (str): The directory path where the Excel file will be saved.
+    - name (str): The name of the Excel file (without the extension).
+    - sheet_name (str): The name of the Excel sheet.
+
+    Returns:
+    str: The full path to the saved Excel file.
     """
-    
-    file_path=os.path.join(path,  f"{name}.xlsx")
+    file_path = os.path.join(path, f"{name}.xlsx")
     df.to_excel(file_path, sheet_name=sheet_name, index=False)
     print(file_path, "- File created")
     return file_path
 
-def add_dataframe_to_excel(df: pd.DataFrame, existing_file_path: str, new_sheet_name: str):
+def add_dataframe_to_excel(df: pd.DataFrame, existing_file_path: str, new_sheet_name: str) -> None:
     """
     Adds a DataFrame to an existing Excel file as a new sheet.
 
     Parameters:
+    - df (pd.DataFrame): The DataFrame to be added.
     - existing_file_path (str): Path to the existing Excel file.
-    - dataframe (pd.DataFrame): The DataFrame to be added.
     - new_sheet_name (str): Name of the new sheet in the Excel file.
 
     Returns:
@@ -257,7 +395,7 @@ def add_dataframe_to_excel(df: pd.DataFrame, existing_file_path: str, new_sheet_
     # Read existing Excel file into a dictionary of DataFrames
     excel_file = pd.read_excel(existing_file_path, sheet_name=None)
 
-    # Add the new DataFrame to the dictionary with the specified sheet aname
+    # Add the new DataFrame to the dictionary with the specified sheet name
     excel_file[new_sheet_name] = df
 
     # Write the updated dictionary of DataFrames back to the Excel file
@@ -265,46 +403,62 @@ def add_dataframe_to_excel(df: pd.DataFrame, existing_file_path: str, new_sheet_
         for sheet_name, df in excel_file.items():
             df.to_excel(writer, sheet_name=sheet_name, index=False)
 
-def save_dataframe_csv(df: pd.DataFrame, path: str, name: str):
+def save_dataframe_csv(df: pd.DataFrame, path: str, name: str) -> str:
     """
-    This function saves a DataFrame to a CSV file within a project directory.
-    
-    :param df: The DataFrame to be saved.
-    :type df: pandas.DataFrame
-    
-    :param dir_csv: The directory where the CSV file will be saved.
-    :type dir_csv: str
-    
-    :param name: The desired name for the CSV file (without extension).
-    :type name: str
+    Save a DataFrame to a CSV file within a specified directory.
+
+    Parameters:
+    - df (pd.DataFrame): The DataFrame to be saved.
+    - path (str): The directory where the CSV file will be saved.
+    - name (str): The desired name for the CSV file (without extension).
+
+    Returns:
+    str: The full path to the saved CSV file.
     """
-    names = df.columns
+    file_path = os.path.join(path, f"{name}.csv")
     df.to_csv(
-        os.path.join(path, f"{name}.csv"),
-        header=names,
+        file_path,
         sep=";",
         encoding="utf-8",
         index=False,
         decimal=",",
     )
-    print("FILE SAVED: ", os.path.join(path, f"{name}.csv"))
+    print("File saved:", file_path)
+    return file_path
 
-def write_txt_file(data: str,  path: str, name: str):
+def write_txt_file(data: str, path: str, name: str) -> str:
     """
-    Write a text file
+    Write a string to a text file.
+
+    Parameters:
+    - data (str): The string to be written to the text file.
+    - path (str): The directory path where the text file will be saved.
+    - name (str): The name of the text file (without the extension).
+
+    Returns:
+    str: The full path to the saved text file.
     """
-    file_path=os.path.join(path, name+'.txt')
+    file_path = os.path.join(path, name + '.txt')
     with open(file_path, "w") as file:
         file.write(data)
     return file_path
 
-def split_df_into_chunks(df, path, name, chunk_size = 10000):
+def split_df_into_chunks(df: pd.DataFrame, path: str, name: str, chunk_size: int = 10000) -> list[str]:
     """
-    Split a dataframe into n pickle files
+    Split a DataFrame into multiple pickle files with a specified chunk size.
+
+    Parameters:
+    - df (pd.DataFrame): The DataFrame to be split.
+    - path (str): The directory path where the pickle files will be saved.
+    - name (str): The base name for the pickle files.
+    - chunk_size (int, optional): The size of each chunk. Default is 10000.
+
+    Returns:
+    list[str]: A list of file paths to the saved pickle files.
     """
     num_chunks = -(-len(df) // chunk_size)  # Calculate the number of chunks using ceil division
 
-    file_paths=[]
+    file_paths = []
 
     # create smaller datasets of chunk_size each
     for i in range(num_chunks):
@@ -317,16 +471,19 @@ def split_df_into_chunks(df, path, name, chunk_size = 10000):
 
     return file_paths
 
-
-
 ###################################################################################################
 # FOLDERS / FILES HELPERS
 ###################################################################################################
 
-def create_dir(path:str):
+def create_dir(path: str) -> str:
     """
-    Create a local directory
+    Create a local directory if it doesn't exist.
+
+    Parameters:
+    - path (str): The directory path to be created.
 
+    Returns:
+    str: The path of the created directory.
     """
     if not os.path.exists(path):
         os.makedirs(path)
@@ -334,18 +491,31 @@ def create_dir(path:str):
     return path
 
 
-def list_files_in_dir(path: str, filetype:str ='*.json'):
+def list_files_in_dir(path: str, filetype: str = '*.json') -> list[str]:
     """
-    List files of a specific format in a directory
+    List files of a specific format in a directory.
+
+    Parameters:
+    - path (str): The directory path to search for files.
+    - filetype (str, optional): The file type pattern to search for. Default is '*.json'.
+
+    Returns:
+    list[str]: A list of file paths matching the specified file type pattern.
     """
     pattern = os.path.join(path, filetype)
     files = glob.glob(pattern)
     return files
 
 
-def list_subdirectories(root_directory: str):
+def list_subdirectories(root_directory: str) -> list[str]:
     """
-    List subdirectories in a root directory
+    List subdirectories in a root directory.
+
+    Parameters:
+    - root_directory (str): The root directory path.
+
+    Returns:
+    list[str]: A list of subdirectory names.
     """
     subdirectories = []
     for entry in os.scandir(root_directory):
@@ -354,9 +524,15 @@ def list_subdirectories(root_directory: str):
     return subdirectories
 
 
-def list_recursive_subdirectories(root_directory: str):
+def list_recursive_subdirectories(root_directory: str) -> list[str]:
     """
-    List recursively all subdirectories from a root directory
+    List recursively all subdirectories from a root directory.
+
+    Parameters:
+    - root_directory (str): The root directory path.
+
+    Returns:
+    list[str]: A list of subdirectory paths.
     """
     subdirectories = []
     for root, dirs, files in os.walk(root_directory):
@@ -364,9 +540,16 @@ def list_recursive_subdirectories(root_directory: str):
     return subdirectories
 
 
-def list_files_in_subdirectories(path:str, filetype:str='*.json'):
+def list_files_in_subdirectories(path: str, filetype: str = '*.json') -> list[str]:
     """
-    Walk through subdirectories of a root directory to list files of a specific format 
+    Walk through subdirectories of a root directory to list files of a specific format.
+
+    Parameters:
+    - path (str): The root directory path.
+    - filetype (str, optional): The file type pattern to search for. Default is '*.json'.
+
+    Returns:
+    list[str]: A list of file paths matching the specified file type pattern in subdirectories.
     """
     files = []
 
@@ -381,21 +564,36 @@ def list_files_in_subdirectories(path:str, filetype:str='*.json'):
 
     return files
 
-def copy_file(source_path: str, destination_path: str, new_filename:str):
+def copy_file(source_path: str, destination_path: str, new_filename: str = '') -> str:
     """
-    Function to copy a file to another path
+    Copy a file from a source path to a destination path.
+
+    Parameters:
+    - source_path (str): The path of the source file.
+    - destination_path (str): The path of the destination directory.
+    - new_filename (str, optional): The new filename. If not provided, the original filename is used.
+
+    Returns:
+    str: The path of the copied file.
     """
     if new_filename:
-        file_path=os.path.join(destination_path, new_filename)
+        file_path = os.path.join(destination_path, new_filename)
     else:
-        filename=os.path.basename(source_path)
-        file_path=os.path.join(destination_path,filename)
+        filename = os.path.basename(source_path)
+        file_path = os.path.join(destination_path, filename)
+    
     shutil.copy(source_path, file_path)
     return file_path
 
-def remove_file(file_path):
+def remove_file(file_path: str) -> None:
     """
-    Remove a single file
+    Remove a single file.
+
+    Parameters:
+    - file_path (str): The path of the file to be removed.
+
+    Returns:
+    None
     """
     try:
         os.remove(file_path)
@@ -403,20 +601,33 @@ def remove_file(file_path):
     except OSError as e:
         print(f"Error removing file {file_path}: {e}")
         
-def remove_folder(folder_path):
+def remove_folder(folder_path: str) -> None:
     """
-    Remove a folder and all the files inside
+    Remove a folder and all its contents.
+
+    Parameters:
+    - folder_path (str): The path of the folder to be removed.
+
+    Returns:
+    None
     """
     try:
         shutil.rmtree(folder_path)
         print(f"Folder {folder_path} and its contents removed successfully.")
     except OSError as e:
-        print(f"Error removing folder {folder_path}: {e}")  
+        print(f"Error removing folder {folder_path}: {e}")
            
         
-def get_file_size(file_path):
+def get_file_size(file_path: str) -> tuple[int, str]:
     """
-    Get a single file size in a readable format (KB, MB, GB)
+    Get the size of a single file in a readable format (KB, MB, GB).
+
+    Parameters:
+    - file_path (str): The path of the file.
+
+    Returns:
+    tuple[int, str]: A tuple containing the size of the file in bytes and its formatted size.
+    If the file is not found, returns None.
     """
     try:
         size = os.path.getsize(file_path)
@@ -439,9 +650,16 @@ def get_file_size(file_path):
         print(f"File not found: {file_path}")
         return None
 
-def get_folder_size(folder_path):
+def get_folder_size(folder_path: str) -> tuple[int, str]:
     """
-    Get size of all files contained in a folder in a readable format (KB, MB, GB)
+    Get the size of all files contained in a folder in a readable format (KB, MB, GB).
+
+    Parameters:
+    - folder_path (str): The path of the folder.
+
+    Returns:
+    tuple[int, str]: A tuple containing the total size of all files in bytes and its formatted size.
+    If the folder is not found, returns None.
     """
     total_size = 0
 
@@ -469,9 +687,16 @@ def get_folder_size(folder_path):
         print(f"Folder not found: {folder_path}")
         return None
 
-def file_creation_date(file_path):
+def file_creation_date(file_path: str) -> datetime:
     """
-    Return the last update timestamp
+    Return the last update timestamp of a file.
+
+    Parameters:
+    - file_path (str): The path of the file.
+
+    Returns:
+    datetime: The last update timestamp as a datetime object.
+    If the file does not exist, returns None.
     """
     # Check if the file exists
     if os.path.exists(file_path):
@@ -488,27 +713,34 @@ def file_creation_date(file_path):
 ############################################################################
     
     
-def transform_to_n_items_list(input_list : list, n: int):
+def transform_to_n_items_list(lst: list, n: int) -> list[list]:
     """
     Transform a list into a list of n-items sublists.
 
     Parameters:
-    - input_list: The input list to be transformed.
-    - n: The number of items in each sublist.
+    - lst (list): The input list to be transformed.
+    - n (int): The number of items in each sublist.
 
     Returns:
-    A list of n-items sublists.
+    list[list]: A list of n-items sublists.
     """
-    return [input_list[i:i + n] for i in range(0, len(input_list), n)]
+    return [lst[i:i + n] for i in range(0, len(lst), n)]
 
-def unduplicate_list(lst):
+
+def unduplicate_list(lst: list) -> list:
     """ 
-    Unduplicate elements of a list
+    Remove duplicate elements from a list.
+
+    Parameters:
+    - lst (list): The input list with possible duplicate elements.
+
+    Returns:
+    list: A list with duplicate elements removed.
     """
     return list(set(lst))
 
 
-def sort_list(lst, reverse=False):
+def sort_list(lst: list, reverse: bool = False) -> list:
     """
     Sort the list in ascending or descending order.
 
@@ -518,12 +750,12 @@ def sort_list(lst, reverse=False):
                      If False (default), sort the list in ascending order.
 
     Returns:
-    - list: A new list sorted based on the specified order.
+    list: A new list sorted based on the specified order.
     """
     return sorted(lst, reverse=reverse)
 
 
-def map_list(lst, function):
+def map_list(lst: list, function: callable) -> list:
     """
     Apply a function to each element of the list.
 
@@ -532,12 +764,12 @@ def map_list(lst, function):
     - function (callable): The function to apply to each element.
 
     Returns:
-    - list: A new list with the function applied to each element.
+    list: A new list with the function applied to each element.
     """
     return [function(element) for element in lst]
 
 
-def flatten_list(lst):
+def flatten_list(lst: list) -> list:
     """
     Flatten a nested list into a single list.
 
@@ -545,7 +777,7 @@ def flatten_list(lst):
     - lst (list): The input nested list.
 
     Returns:
-    - list: A new list with all nested elements flattened.
+    list: A new list with all nested elements flattened.
     """
     flattened_list = []
 
@@ -560,7 +792,7 @@ def flatten_list(lst):
     return flattened_list
 
 
-def find_occurrences(lst, element):
+def find_occurrences(lst: list, element) -> int:
     """
     Find the occurrences of a specific element in the list.
 
@@ -569,12 +801,12 @@ def find_occurrences(lst, element):
     - element: The element to find occurrences of.
 
     Returns:
-    - int: The number of occurrences of the specified element in the list.
+    int: The number of occurrences of the specified element in the list.
     """
     return lst.count(element)
 
 
-def is_subset(subset, superset):
+def is_subset(subset: list, superset: list) -> bool:
     """
     Check if one list is a subset of another.
 
@@ -583,11 +815,11 @@ def is_subset(subset, superset):
     - superset (list): The superset list.
 
     Returns:
-    - bool: True if the subset is a subset of the superset, False otherwise.
+    bool: True if the subset is a subset of the superset, False otherwise.
     """
     return all(element in superset for element in subset)
 
-def common_elements(list1, list2):
+def common_elements(list1: list, list2: list) -> list:
     """
     Find the common elements between two lists.
 
@@ -596,12 +828,12 @@ def common_elements(list1, list2):
     - list2 (list): The second list.
 
     Returns:
-    - list: A new list containing the common elements between list1 and list2.
+    list: A new list containing the common elements between list1 and list2.
     """
     return list(set(list1) & set(list2))
 
 
-def shuffle_list(lst):
+def shuffle_list(lst: list) -> list:
     """
     Shuffle the elements of the list randomly.
 
@@ -609,14 +841,14 @@ def shuffle_list(lst):
     - lst (list): The input list.
 
     Returns:
-    - list: A new list with the elements shuffled randomly.
+    list: A new list with the elements shuffled randomly.
     """
     shuffled_list = lst.copy()
     random.shuffle(shuffled_list)
     return shuffled_list
 
 
-def sample_list(lst, sample_size):
+def sample_list(lst: list, sample_size) -> list:
     """
     Sample a list based on an integer or a float representing the sample size.
 
@@ -626,7 +858,11 @@ def sample_list(lst, sample_size):
                                  If a float, the percentage of elements to keep.
 
     Returns:
-    - list: A new list containing the sampled elements.
+    list: A new list containing the sampled elements.
+
+    Raises:
+    - ValueError: If the sample size is invalid (negative integer or float outside [0, 1]).
+    - TypeError: If the sample size is neither an integer nor a float.
     """
     if isinstance(sample_size, int):
         if sample_size < 0:
@@ -640,7 +876,7 @@ def sample_list(lst, sample_size):
     else:
         raise TypeError("Sample size must be an integer or a float.")
 
-def count_elements(lst):
+def count_elements(lst: list) -> dict:
     """
     Count the occurrences of each element in the list.
 
@@ -648,46 +884,70 @@ def count_elements(lst):
     - lst (list): The input list.
 
     Returns:
-    - dict: A dictionary where keys are unique elements from the list, and values are their counts.
+    dict: A dictionary where keys are unique elements from the list, and values are their counts.
     """
     return dict(Counter(lst))
 
-def scale_list(lst, min_val=1, max_val=5):
+def scale_list(lst: list, min_val: float = 1, max_val: float = 5) -> list:
+    """
+    Scale the values of a list to a specified range.
+
+    Parameters:
+    - lst (list): The input list of values to be scaled.
+    - min_val (float): The minimum value of the output range (default is 1).
+    - max_val (float): The maximum value of the output range (default is 5).
+
+    Returns:
+    - list: A new list with values scaled to the specified range.
+    """
     min_w = min(lst)
     max_w = max(lst)
-    scaled_w = [ ]
+    scaled_w = []
     for x in lst:
         try:
             scaled_value = (x - min_w) / (max_w - min_w) * (max_val - min_val) + min_val
-        except : 
-            pass
+        except ZeroDivisionError:
             scaled_value = min_val
-        
         scaled_w.append(scaled_value)
     return scaled_w
 
-def df_scale_column(df, col_to_scale, col_out, min_val, max_val):
+
+def df_scale_column(df: pd.DataFrame, col_to_scale: str, col_out: str, min_val: float, max_val: float) -> pd.DataFrame:
+    """
+    Scale values in a DataFrame column to a specified range.
+
+    Parameters:
+    - df (pd.DataFrame): The input DataFrame.
+    - col_to_scale (str): The name of the column to be scaled.
+    - col_out (str): The name of the new column to store scaled values.
+    - min_val (float): The minimum value of the output range.
+    - max_val (float): The maximum value of the output range.
+
+    Returns:
+    - pd.DataFrame: The DataFrame with a new column containing scaled values.
+    """
     min_freq = df[col_to_scale].min()
     max_freq = df[col_to_scale].max()
-    df[col_out] = df[col_to_scale].apply(lambda x : ((x - min_freq) / (max_freq - min_freq)) * (max_val - min_val) + min_val)
+    df[col_out] = df[col_to_scale].apply(lambda x: ((x - min_freq) / (max_freq - min_freq)) * (max_val - min_val) + min_val)
     return df
 
 ############################################################################
 # ZIP HELPERS
 ############################################################################      
     
-def zip_file(source_file_path, zip_file_path, name):
+def zip_file(source_file_path: str, zip_file_path: str, name: str) -> str:
     """
     Zip a single file.
 
-    Args:
-        source_file_path (str): Path to the file to be zipped.
-        zip_file_path (str): Path for the resulting zip file.
+    Parameters:
+    - source_file_path (str): Path to the file to be zipped.
+    - zip_file_path (str): Path for the resulting zip file.
+    - name (str): Name for the resulting zip file (without extension).
 
     Returns:
-        None
+    str: Path to the resulting zip file.
     """
-    file_path=os.path.join(zip_file_path, name+".zip")
+    file_path = os.path.join(zip_file_path, f"{name}.zip")
  
     with zipfile.ZipFile(file_path, 'w') as zip_file:
         # The second argument to `arcname` is used to set the name of the file inside the zip
@@ -695,18 +955,19 @@ def zip_file(source_file_path, zip_file_path, name):
 
     return file_path
     
-def zip_folder(source_folder_path, zip_file_path, name):
+def zip_folder(source_folder_path: str, zip_file_path: str, name: str) -> str:
     """
     Zip an entire folder.
 
-    Args:
-        source_folder_path (str): Path to the folder to be zipped.
-        zip_file_path (str): Path for the resulting zip file.
+    Parameters:
+    - source_folder_path (str): Path to the folder to be zipped.
+    - zip_file_path (str): Path for the resulting zip file.
+    - name (str): Name for the resulting zip file (without extension).
 
     Returns:
-        None
+    str: Path to the resulting zip file.
     """
-    file_path=os.path.join(zip_file_path, name+".zip")
+    file_path = os.path.join(zip_file_path, f"{name}.zip")
     
     with zipfile.ZipFile(file_path, 'w', zipfile.ZIP_DEFLATED) as zip_file:
         for foldername, subfolders, filenames in os.walk(source_folder_path):
@@ -717,13 +978,19 @@ def zip_folder(source_folder_path, zip_file_path, name):
                 
     return file_path
 
-def unzip_file(zip_file_path, destination_path):
+def unzip_file(zip_file_path: str, destination_path: str) -> None:
     """
-    unzip a zip file
+    Unzip a zip file.
+
+    Parameters:
+    - zip_file_path (str): Path to the zip file to be unzipped.
+    - destination_path (str): Path where the contents of the zip file will be extracted.
+
+    Returns:
+    None
     """
     with zipfile.ZipFile(zip_file_path, "r") as zip_ref:
         zip_ref.extractall(destination_path)
-        
     
 
 ############################################################################
@@ -731,19 +998,32 @@ def unzip_file(zip_file_path, destination_path):
 ############################################################################   
 
 
-def create_google_spreadsheet_client(credentials:str):
+def create_google_spreadsheet_client(credentials: str):
     """
-    Create a Gspread client to interact with Google Sheets
+    Create a Gspread client to interact with Google Sheets.
+
+    Parameters:
+    - credentials (str): Path to the JSON file containing Google Service Account credentials.
+
+    Returns:
+    gspread.Client: A client object for interacting with Google Sheets.
     """
     return gspread.service_account(filename=credentials)
 
-def read_google_spreadsheet(client, sheet_id: str, worksheet_name: str):
+def read_google_spreadsheet(client: gspread.Client, sheet_id: str, worksheet_name: str) -> pd.DataFrame:
     """
-    Function to read a Google spreadsheet in a DataFrame
+    Read data from a Google spreadsheet and return it as a DataFrame.
+
+    Parameters:
+    - client (gspread.Client): A Gspread client object authenticated with Google Sheets API.
+    - sheet_id (str): The ID of the Google spreadsheet.
+    - worksheet_name (str): The name of the worksheet within the spreadsheet.
+
+    Returns:
+    pd.DataFrame: A DataFrame containing the data from the specified worksheet.
     """
     try:
-    
-        # Open the Google Spreadsheet by name
+        # Open the Google Spreadsheet by ID
         sheet = client.open_by_key(sheet_id)
         
         # Select a specific worksheet by name
@@ -763,29 +1043,52 @@ def read_google_spreadsheet(client, sheet_id: str, worksheet_name: str):
         print(f"An error occurred: {e}")
 
 
-def list_google_worksheets(client, sheet_id:str):
+def list_google_worksheets(client: gspread.Client, sheet_id: str) -> list:
     """
-    Return a list of worksheet names for a spreadsheet ID
+    Return a list of worksheet names for a spreadsheet ID.
+
+    Parameters:
+    - client (gspread.Client): A Gspread client object authenticated with Google Sheets API.
+    - sheet_id (str): The ID of the Google spreadsheet.
+
+    Returns:
+    list: A list of worksheet names.
     """
     sheet = client.open_by_key(sheet_id)
     worksheet_obj = sheet.worksheets()
     worksheet_list = [sheet.title for sheet in worksheet_obj]
     return worksheet_list
     
-def get_spreadsheet_permissions(client, sheet_id:str):
+def get_spreadsheet_permissions(client: gspread.Client, sheet_id: str) -> pd.DataFrame:
     """
-    Return a DataFrame with the list of user email and type that can access the document
+    Return a DataFrame with the list of user email and type that can access the document.
+
+    Parameters:
+    - client (gspread.Client): A Gspread client object authenticated with Google Sheets API.
+    - sheet_id (str): The ID of the Google spreadsheet.
+
+    Returns:
+    pd.DataFrame: A DataFrame containing the list of user email addresses and their access types.
     """
     sheet = client.open_by_key(sheet_id)
-    permissions=sheet.list_permissions()
-    user_list=[(user.get("emailAddress"),user.get("type")) for user in permissions if user.get("emailAddress") is not None]
+    permissions = sheet.list_permissions()
+    user_list = [(user.get("emailAddress"), user.get("type")) for user in permissions if user.get("emailAddress") is not None]
     df = pd.DataFrame(user_list, columns=['email', 'type'])
     return df
 
 
-def create_google_spreadsheet(client, df, filename:str, worksheet_name:str = "Sheet1"):
+def create_google_spreadsheet(client: gspread.Client, df: pd.DataFrame, filename: str, worksheet_name: str = "Sheet1") -> gspread.Spreadsheet:
     """
-    Load a dataframe in a new spreadsheet 
+    Create a new Google spreadsheet and load a DataFrame into it.
+
+    Parameters:
+    - client (gspread.Client): A Gspread client object authenticated with Google Sheets API.
+    - df (pd.DataFrame): The DataFrame to be loaded into the spreadsheet.
+    - filename (str): The desired filename for the new spreadsheet.
+    - worksheet_name (str, optional): The name of the worksheet within the spreadsheet. Defaults to "Sheet1".
+
+    Returns:
+    gspread.Spreadsheet: The created spreadsheet object.
     """
     spreadsheet = client.create(filename)
     worksheet = spreadsheet.sheet1
@@ -795,17 +1098,34 @@ def create_google_spreadsheet(client, df, filename:str, worksheet_name:str = "Sh
 
     return spreadsheet
 
-def share_google_spreadsheet(spreadsheet, email, user_type="user", user_role="writer", notify=False, email_message=None, with_link=False):
+def share_google_spreadsheet(spreadsheet: gspread.Spreadsheet, email: str, user_type: str = "user", user_role: str = "writer", notify: bool = False, email_message: str = None, with_link: bool = False) -> gspread.Spreadsheet:
     """
-    Share a spreadsheet with a user
+    Share a spreadsheet with a user.
+
+    Parameters:
+    - spreadsheet (gspread.Spreadsheet): The Google spreadsheet object to be shared.
+    - email (str): The email address of the user with whom the spreadsheet will be shared.
+    - user_type (str, optional): The permission type for the user. Defaults to "user".
+    - user_role (str, optional): The role assigned to the user. Defaults to "writer".
+    - notify (bool, optional): Whether to notify the user about the sharing. Defaults to False.
+    - email_message (str, optional): The message to include in the notification email.
+    - with_link (bool, optional): Whether to include a link to the shared document in the notification email. Defaults to False.
+
+    Returns:
+    gspread.Spreadsheet: The updated spreadsheet object.
     """
-    spreadsheet.share(email, perm_type=user_type, role=user_role, notify = notify, email_message=email_message, with_link=with_link)
+    spreadsheet.share(email, perm_type=user_type, role=user_role, notify=notify, email_message=email_message, with_link=with_link)
     return spreadsheet
 
-
-def generate_short_id(variables : dict):
+def generate_short_id(variables: dict) -> tuple[str, str]:
     """
-    Generate a 8 characters ID using a dict as input
+    Generate an 8-character ID using a dictionary as input.
+
+    Parameters:
+    - variables (dict): A dictionary containing the variables to be serialized.
+
+    Returns:
+    tuple: A tuple containing the generated short ID and the serialized variables.
     """
     # Serialize variables into JSON string
     serialized_variables = json.dumps(variables, sort_keys=True)
@@ -815,7 +1135,7 @@ def generate_short_id(variables : dict):
     short_id = hash_value[:8]
     return short_id, serialized_variables
 
-def df_transform_column_as_list(column):
+def df_transform_column_as_list(column: pd.Series) -> pd.Series:
     def transform(cell):
         if isinstance(cell, str):
             # Check if it's a list formatted as string, and convert to list
@@ -824,9 +1144,7 @@ def df_transform_column_as_list(column):
             else:
                 try:
                     values = ast.literal_eval(cell)
-                    
                 except Exception as e:
-                    pass
                     # If it's a single URL as string, make it a list
                     values = [cell]
         elif isinstance(cell, (int, float, bool)):
@@ -844,7 +1162,11 @@ def df_transform_column_as_list(column):
     return column.apply(transform)
 
 
-def top_rows_per_category(df, col_to_sort, col_to_gb, cols_to_keep, top_rows) : 
+def top_rows_per_category(df: pd.DataFrame, 
+                          col_to_sort: str, 
+                          col_to_gb: str, 
+                          cols_to_keep: list[str], 
+                          top_rows: int) -> pd.DataFrame:
     """
     Select top rows for each category in a dataframe
     """
@@ -855,7 +1177,7 @@ def top_rows_per_category(df, col_to_sort, col_to_gb, cols_to_keep, top_rows) :
                 )[cols_to_keep]
     return df_gb
 
-def format_number(number):
+def format_number(number: int) -> str:
     """
     Function to format a number in K, M or B
     """
@@ -866,4 +1188,32 @@ def format_number(number):
     elif number < 1000000000:
         return f"{number / 1000000:.1f}M"
     else:
-        return f"{number / 1000000000:.1f}B"
+        return f"{number / 1000000000:.1f}B"
+
+
+
+def unrar_file(rar_file_path : str, output_dir : str) -> None:
+    """
+    Extracts a .rar file to the specified output directory using the unrar command.
+    
+    Parameters:
+    rar_file_path (str): The path to the .rar file.
+    output_dir (str): The directory where the contents should be extracted.
+    
+    Returns:
+    None
+    """
+    try:
+        # Ensure the output directory exists
+        subprocess.run(['mkdir', '-p', output_dir], check=True)
+        
+        # Run the unrar command
+        result = subprocess.run(['unrar', 'x', '-y', rar_file_path, output_dir], 
+                                stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+        
+        # Check if the extraction was successful
+        if result.returncode != 0:
+            print(f"Extraction failed. Error: {result.stderr}")
+            
+    except Exception as e:
+        print(f"An error occurred: {e}")