rgwfuncs 0.0.24__py3-none-any.whl → 0.0.26__py3-none-any.whl

rgwfuncs/__init__.py

@@ -2,6 +2,6 @@
 # Dynamically importing functions from modules
 
 from .algebra_lib import compute_algebraic_expression, get_prime_factors_latex, simplify_algebraic_expression, solve_algebraic_expression
-from .df_lib import append_columns, append_percentile_classification_column, append_ranged_classification_column, append_ranged_date_classification_column, append_rows, append_xgb_labels, append_xgb_logistic_regression_predictions, append_xgb_regression_predictions, bag_union_join, bottom_n_unique_values, cascade_sort, delete_rows, df_docs, drop_duplicates, drop_duplicates_retain_first, drop_duplicates_retain_last, filter_dataframe, filter_indian_mobiles, first_n_rows, from_raw_data, insert_dataframe_in_sqlite_database, last_n_rows, left_join, limit_dataframe, load_data_from_path, load_data_from_query, load_data_from_sqlite_path, mask_against_dataframe, mask_against_dataframe_converse, numeric_clean, order_columns, print_correlation, print_dataframe, print_memory_usage, print_n_frequency_cascading, print_n_frequency_linear, rename_columns, retain_columns, right_join, send_data_to_email, send_data_to_slack, send_dataframe_via_telegram, sync_dataframe_to_sqlite_database, top_n_unique_values, union_join, update_rows
+from .df_lib import append_columns, append_percentile_classification_column, append_ranged_classification_column, append_ranged_date_classification_column, append_rows, append_xgb_labels, append_xgb_logistic_regression_predictions, append_xgb_regression_predictions, bag_union_join, bottom_n_unique_values, cascade_sort, delete_rows, drop_duplicates, drop_duplicates_retain_first, drop_duplicates_retain_last, filter_dataframe, filter_indian_mobiles, first_n_rows, from_raw_data, insert_dataframe_in_sqlite_database, last_n_rows, left_join, limit_dataframe, load_data_from_path, load_data_from_query, load_data_from_sqlite_path, mask_against_dataframe, mask_against_dataframe_converse, numeric_clean, order_columns, print_correlation, print_dataframe, print_memory_usage, print_n_frequency_cascading, print_n_frequency_linear, rename_columns, retain_columns, right_join, send_data_to_email, send_data_to_slack, send_dataframe_via_telegram, sync_dataframe_to_sqlite_database, top_n_unique_values, union_join, update_rows
 from .docs_lib import docs
-from .str_lib import send_telegram_message, str_docs
+from .str_lib import send_telegram_message

rgwfuncs/algebra_lib.py

@@ -1,10 +1,29 @@
 import re
 import math
+import ast
 from sympy import symbols, latex, simplify, solve, diff, Expr
 from sympy.parsing.sympy_parser import parse_expr
 from typing import Tuple, List, Dict, Optional
 
+
 def compute_algebraic_expression(expression: str) -> float:
+    """
+    Computes the numerical result of a given algebraic expression.
+
+    Evaluates an algebraic expression provided as a string and returns the computed result.
+    Supports various arithmetic operations, including addition, subtraction, multiplication,
+    division, and modulo, as well as mathematical functions from the math module.
+
+    Parameters:
+    expression (str): The algebraic expression to compute. This should be a string consisting
+                      of arithmetic operations and supported math module functions.
+
+    Returns:
+    float: The evaluated numerical result of the expression.
+
+    Raises:
+    ValueError: If the expression cannot be evaluated due to syntax errors or other issues.
+    """
     try:
         # Direct numerical evaluation
         # Safely evaluate the expression using the math module
@@ -15,10 +34,23 @@ def compute_algebraic_expression(expression: str) -> float:
     except Exception as e:
         raise ValueError(f"Error computing expression: {e}")
 
+
 def simplify_algebraic_expression(expression: str) -> str:
+    """
+    Simplifies an algebraic expression and returns it in LaTeX format.
+
+    Takes an algebraic expression written in Python syntax and simplifies it. The result is
+    returned as a LaTeX formatted string, suitable for academic or professional documentation.
 
+    Parameters:
+    expression (str): The algebraic expression to simplify.
+
+    Returns:
+    str: The simplified expression represented as a LaTeX string.
+    """
 
-    def recursive_parse_function_call(func_call: str, prefix: str, sym_vars: Dict[str, Expr]) -> Tuple[str, List[Expr]]:
+    def recursive_parse_function_call(
+            func_call: str, prefix: str, sym_vars: Dict[str, Expr]) -> Tuple[str, List[Expr]]:
         # print(f"Parsing function call: {func_call}")
 
         # Match the function name and arguments
@@ -30,7 +62,8 @@ def simplify_algebraic_expression(expression: str) -> str:
         args_str = match.group(2)
 
         # Check if it's a list for np
-        if prefix == 'np' and args_str.startswith("[") and args_str.endswith("]"):
+        if prefix == 'np' and args_str.startswith(
+                "[") and args_str.endswith("]"):
             parsed_args = [ast.literal_eval(args_str.strip())]
         else:
             parsed_args = []
@@ -38,77 +71,98 @@ def simplify_algebraic_expression(expression: str) -> str:
             for arg in raw_args:
                 arg = arg.strip()
                 if re.match(r'\w+\.\w+\(', arg):
-                    # Recursively evaluate the argument if it's another function call
-                    arg_val = recursive_eval_func(re.match(r'\w+\.\w+\(.*\)', arg), sym_vars)
-                    parsed_args.append(parse_expr(arg_val, local_dict=sym_vars))
+                    # Recursively evaluate the argument if it's another
+                    # function call
+                    arg_val = recursive_eval_func(
+                        re.match(r'\w+\.\w+\(.*\)', arg), sym_vars)
+                    parsed_args.append(
+                        parse_expr(
+                            arg_val,
+                            local_dict=sym_vars))
                 else:
                     parsed_args.append(parse_expr(arg, local_dict=sym_vars))
 
         # print(f"Function name: {func_name}, Parsed arguments: {parsed_args}")
         return func_name, parsed_args
 
-
     def recursive_eval_func(match: re.Match, sym_vars: Dict[str, Expr]) -> str:
         # print("152", match)
         func_call = match.group(0)
         # print(f"153 Evaluating function call: {func_call}")
 
         if func_call.startswith("np."):
-            func_name, args = recursive_parse_function_call(func_call, 'np', sym_vars)
+            func_name, args = recursive_parse_function_call(
+                func_call, 'np', sym_vars)
             if func_name == 'diff':
                 expr = args[0]
                 if isinstance(expr, list):
                     # Calculate discrete difference
-                    diff_result = [expr[i] - expr[i - 1] for i in range(1, len(expr))]
+                    diff_result = [expr[i] - expr[i - 1]
+                                   for i in range(1, len(expr))]
                     return str(diff_result)
                 # Perform symbolic differentiation
                 diff_result = diff(expr)
                 return str(diff_result)
 
         if func_call.startswith("math."):
-            func_name, args = recursive_parse_function_call(func_call, 'math', sym_vars)
+            func_name, args = recursive_parse_function_call(
+                func_call, 'math', sym_vars)
             if hasattr(math, func_name):
                 result = getattr(math, func_name)(*args)
                 return str(result)
 
         if func_call.startswith("sym."):
-            initial_method_match = re.match(r'(sym\.\w+\([^()]*\))(\.(\w+)\((.*?)\))*', func_call, re.DOTALL)
+            initial_method_match = re.match(
+                r'(sym\.\w+\([^()]*\))(\.(\w+)\((.*?)\))*', func_call, re.DOTALL)
             if initial_method_match:
                 base_expr_str = initial_method_match.group(1)
-                base_func_name, base_args = recursive_parse_function_call(base_expr_str, 'sym', sym_vars)
+                base_func_name, base_args = recursive_parse_function_call(
+                    base_expr_str, 'sym', sym_vars)
                 if base_func_name == 'solve':
                     solutions = solve(base_args[0], base_args[1])
                     # print(f"Solutions found: {solutions}")
 
-                method_chain = re.findall(r'\.(\w+)\((.*?)\)', func_call, re.DOTALL)
-                final_solutions = [execute_chained_methods(sol, [(m, [method_args.strip()]) for m, method_args in method_chain], sym_vars) for sol in solutions]
+                method_chain = re.findall(
+                    r'\.(\w+)\((.*?)\)', func_call, re.DOTALL)
+                final_solutions = [execute_chained_methods(sol, [(m, [method_args.strip(
+                )]) for m, method_args in method_chain], sym_vars) for sol in solutions]
 
-                return "[" + ",".join(latex(simplify(sol)) for sol in final_solutions) + "]"
+                return "[" + ",".join(latex(simplify(sol))
+                                      for sol in final_solutions) + "]"
 
         raise ValueError(f"Unknown function call: {func_call}")
 
-    def execute_chained_methods(sym_expr: Expr, method_chain: List[Tuple[str, List[str]]], sym_vars: Dict[str, Expr]) -> Expr:
+    def execute_chained_methods(sym_expr: Expr,
+                                method_chain: List[Tuple[str,
+                                                         List[str]]],
+                                sym_vars: Dict[str,
+                                               Expr]) -> Expr:
         for method_name, method_args in method_chain:
             # print(f"Executing method: {method_name} with arguments: {method_args}")
             method = getattr(sym_expr, method_name, None)
             if method:
                 if method_name == 'subs' and isinstance(method_args[0], dict):
                     kwargs = method_args[0]
-                    kwargs = {parse_expr(k, local_dict=sym_vars): parse_expr(v, local_dict=sym_vars) for k, v in kwargs.items()}
+                    kwargs = {
+                        parse_expr(
+                            k,
+                            local_dict=sym_vars): parse_expr(
+                            v,
+                            local_dict=sym_vars) for k,
+                        v in kwargs.items()}
                     sym_expr = method(kwargs)
                 else:
-                    args = [parse_expr(arg.strip(), local_dict=sym_vars) for arg in method_args]
+                    args = [parse_expr(arg.strip(), local_dict=sym_vars)
+                            for arg in method_args]
                     sym_expr = method(*args)
             # print(f"Result after {method_name}: {sym_expr}")
         return sym_expr
 
-
-
     variable_names = set(re.findall(r'\b[a-zA-Z]\w*\b', expression))
     sym_vars = {var: symbols(var) for var in variable_names}
 
     patterns = {
-        #"numpy_diff_brackets": r"np\.diff\(\[.*?\]\)",
+        # "numpy_diff_brackets": r"np\.diff\(\[.*?\]\)",
         "numpy_diff_no_brackets": r"np\.diff\([^()]*\)",
         "math_functions": r"math\.\w+\((?:[^()]*(?:\([^()]*\)[^()]*)*)\)",
         # "sympy_functions": r"sym\.\w+\([^()]*\)(?:\.\w+\([^()]*\))?",
@@ -117,11 +171,14 @@ def simplify_algebraic_expression(expression: str) -> str:
     function_pattern = '|'.join(patterns.values())
 
     # Use a lambda function to pass additional arguments
-    processed_expression = re.sub(function_pattern, lambda match: recursive_eval_func(match, sym_vars), expression)
+    processed_expression = re.sub(
+        function_pattern, lambda match: recursive_eval_func(
+            match, sym_vars), expression)
     # print("Level 2 processed_expression:", processed_expression)
 
     try:
-        if processed_expression.startswith('[') and processed_expression.endswith(']'):
+        if processed_expression.startswith(
+                '[') and processed_expression.endswith(']'):
             return processed_expression
 
         expr = parse_expr(processed_expression, local_dict=sym_vars)
@@ -136,7 +193,28 @@ def simplify_algebraic_expression(expression: str) -> str:
     except Exception as e:
         raise ValueError(f"Error simplifying expression: {e}")
 
-def solve_algebraic_expression(expression: str, variable: str, subs: Optional[Dict[str, float]] = None) -> str:
+
+def solve_algebraic_expression(
+        expression: str, variable: str, subs: Optional[Dict[str, float]] = None) -> str:
+    """
+    Solves an algebraic equation for a specified variable and returns solutions in LaTeX format.
+
+    Solves the given equation for a designated variable. May optionally include substitutions
+    for other variables in the equation. The solutions are provided as a LaTeX formatted string.
+
+    Parameters:
+    expression (str): The algebraic equation to solve.
+    variable (str): The variable to solve the equation for.
+    subs (Optional[Dict[str, float]]): An optional dictionary of substitutions for variables
+                                       in the equation.
+
+    Returns:
+    str: The solutions of the equation, formatted as a LaTeX string.
+
+    Raises:
+    ValueError: If the equation cannot be solved due to errors in expression or parameters.
+    """
+
     try:
         # Create symbols for the variables in the expression
         variable_symbols = set(re.findall(r'\b[a-zA-Z]\w*\b', expression))
@@ -153,7 +231,9 @@ def solve_algebraic_expression(expression: str, variable: str, subs: Optional[Di
             solutions = [simplify(sol.subs(subs_symbols)) for sol in solutions]
 
         # Convert solutions to LaTeX strings if possible
-        latex_solutions = [latex(simplify(sol)) if sol.free_symbols else str(sol) for sol in solutions]
+        latex_solutions = [
+            latex(
+                simplify(sol)) if sol.free_symbols else str(sol) for sol in solutions]
         result = r"\left[" + ", ".join(latex_solutions) + r"\right]"
         print("158", result)
         return result
@@ -162,11 +242,20 @@ def solve_algebraic_expression(expression: str, variable: str, subs: Optional[Di
         raise ValueError(f"Error solving the expression: {e}")
 
 
-
 def get_prime_factors_latex(n: int) -> str:
     """
-    Return the prime factors of a number as a LaTeX expression.
+    Computes the prime factors of a number and returns the factorization as a LaTeX string.
+
+    Determines the prime factorization of the given integer. The result is formatted as a LaTeX
+    string, enabling easy integration into documents or presentations that require mathematical notation.
+
+    Parameters:
+    n (int): The number for which to compute prime factors.
+
+    Returns:
+    str: The LaTeX representation of the prime factorization.
     """
+
     factors = []
     while n % 2 == 0:
         factors.append(2)
@@ -179,8 +268,6 @@ def get_prime_factors_latex(n: int) -> str:
         factors.append(n)
 
     factor_counts = {factor: factors.count(factor) for factor in set(factors)}
-    latex_factors = [f"{factor}^{{{count}}}" if count > 1 else str(factor) for factor, count in factor_counts.items()]
+    latex_factors = [f"{factor}^{{{count}}}" if count > 1 else str(
+        factor) for factor, count in factor_counts.items()]
     return " \\cdot ".join(latex_factors)
-
-
-

rgwfuncs/df_lib.py

@@ -21,51 +21,14 @@ from email.mime.base import MIMEBase
 from email import encoders
 from googleapiclient.discovery import build
 import base64
-import inspect
-from typing import Optional, Callable, Dict, List, Tuple, Any
+# import inspect
+from typing import Optional, Dict, List, Tuple, Any
 import warnings
 
 # Suppress all FutureWarnings
 warnings.filterwarnings("ignore", category=FutureWarning)
 
 
-def df_docs(method_type_filter: Optional[str] = None) -> None:
-    """
-    Print a list of function names in alphabetical order. If method_type_filter
-    is specified, print the docstrings of the functions that match the filter.
-    Using '*' as a filter will print the docstrings for all functions.
-
-    Parameters:
-        method_type_filter: Optional filter string representing a function name,
-        or '*' to display docstrings for all functions.
-    """
-    # Get the current module's namespace
-    current_module = __name__
-
-    local_functions: Dict[str, Callable] = {
-        name: obj for name, obj in globals().items()
-        if inspect.isfunction(obj) and obj.__module__ == current_module
-    }
-
-    # List of function names sorted alphabetically
-    function_names = sorted(local_functions.keys())
-
-    # Print function names
-    print("Functions in alphabetical order:")
-    for name in function_names:
-        print(name)
-
-    # If a filter is provided or '*', print the docstrings of functions
-    if method_type_filter:
-        # print("\nFiltered function documentation:")
-        for name, func in local_functions.items():
-            docstring: Optional[str] = func.__doc__
-            if docstring:
-                if method_type_filter == '*' or method_type_filter == name:
-                    # Print the entire docstring for the matching function
-                    print(f"\n{name}:\n{docstring}")
-
-
 def numeric_clean(
         df: pd.DataFrame,
         column_names: str,
@@ -835,7 +798,12 @@ def print_dataframe(df: pd.DataFrame, source: Optional[str] = None) -> None:
     gc.collect()
 
 
-def send_dataframe_via_telegram(df: pd.DataFrame, bot_name: str, message: Optional[str] = None, as_file: bool = True, remove_after_send: bool = True) -> None:
+def send_dataframe_via_telegram(
+        df: pd.DataFrame,
+        bot_name: str,
+        message: Optional[str] = None,
+        as_file: bool = True,
+        remove_after_send: bool = True) -> None:
     """
     Send a DataFrame via Telegram using a specified bot configuration.
 
@@ -1672,7 +1640,12 @@ def print_n_frequency_cascading(
     report = generate_cascade_report(df, columns, n, order_by)
     print(json.dumps(report, indent=2))
 
-def print_n_frequency_linear(df: pd.DataFrame, n: int, columns: list, order_by: str = "FREQ_DESC") -> None:
+
+def print_n_frequency_linear(
+        df: pd.DataFrame,
+        n: int,
+        columns: list,
+        order_by: str = "FREQ_DESC") -> None:
     """
     Print the linear frequency of top n values for specified columns.
 
@@ -1719,23 +1692,36 @@ def print_n_frequency_linear(df: pd.DataFrame, n: int, columns: list, order_by:
                 return val
 
     def sort_frequency(frequency, order_by):
-        keys = frequency.keys()
+        # keys = frequency.keys()
 
-        # Convert keys to numerical values where possible, leaving `NaN` as a special string
-        parsed_keys = [(try_parse_numeric(key), key) for key in keys]
+        # Convert keys to numerical values where possible, leaving `NaN` as a
+        # special string
+        # parsed_keys = [(try_parse_numeric(key), key) for key in keys]
 
         if order_by in {"BY_KEYS_ASC", "BY_KEYS_DESC"}:
             reverse = order_by == "BY_KEYS_DESC"
-            sorted_items = sorted(frequency.items(), key=lambda item: try_parse_numeric(item[0]), reverse=reverse)
+            sorted_items = sorted(
+                frequency.items(),
+                key=lambda item: try_parse_numeric(
+                    item[0]),
+                reverse=reverse)
         else:
             if order_by == "ASC":
-                sorted_items = sorted(frequency.items(), key=lambda item: item[0])
+                sorted_items = sorted(
+                    frequency.items(), key=lambda item: item[0])
             elif order_by == "DESC":
-                sorted_items = sorted(frequency.items(), key=lambda item: item[0], reverse=True)
+                sorted_items = sorted(
+                    frequency.items(),
+                    key=lambda item: item[0],
+                    reverse=True)
             elif order_by == "FREQ_ASC":
-                sorted_items = sorted(frequency.items(), key=lambda item: item[1])
+                sorted_items = sorted(
+                    frequency.items(), key=lambda item: item[1])
             else:  # Default to "FREQ_DESC"
-                sorted_items = sorted(frequency.items(), key=lambda item: item[1], reverse=True)
+                sorted_items = sorted(
+                    frequency.items(),
+                    key=lambda item: item[1],
+                    reverse=True)
 
         return dict(sorted_items)
 
@@ -1887,7 +1873,10 @@ def right_join(
     return df1.merge(df2, how='right', left_on=left_on, right_on=right_on)
 
 
-def insert_dataframe_in_sqlite_database(db_path: str, tablename: str, df: pd.DataFrame) -> None:
+def insert_dataframe_in_sqlite_database(
+        db_path: str,
+        tablename: str,
+        df: pd.DataFrame) -> None:
     """
     Inserts a Pandas DataFrame into a SQLite database table.
 
@@ -1949,7 +1938,10 @@ def insert_dataframe_in_sqlite_database(db_path: str, tablename: str, df: pd.Dat
         df.to_sql(tablename, conn, if_exists='append', index=False)
 
 
-def sync_dataframe_to_sqlite_database(db_path: str, tablename: str, df: pd.DataFrame) -> None:
+def sync_dataframe_to_sqlite_database(
+        db_path: str,
+        tablename: str,
+        df: pd.DataFrame) -> None:
     """
     Processes and saves a DataFrame to an SQLite database, adding a timestamp column
     and replacing the existing table if needed. Creates the table if it does not exist.

rgwfuncs/docs_lib.py

@@ -1,26 +1,27 @@
 import os
 import inspect
-from typing import Tuple, Optional, Dict, Callable
+from typing import Optional
 import warnings
 
 # Suppress all FutureWarnings
 warnings.filterwarnings("ignore", category=FutureWarning)
 
+
 def docs(method_type_filter: Optional[str] = None) -> None:
     """
     Print a list of function names in alphabetical order from all modules.
     If method_type_filter is specified, print the docstrings of the functions
-    that match the filter. Using '*' as a filter will print the docstrings 
-    for all functions.
+    that match the filter based on a substring. Using '*' as a filter will print
+    the docstrings for all functions.
 
     Parameters:
-        method_type_filter: Optional filter string representing a function name,
-        or '*' to display docstrings for all functions.
+        method_type_filter: Optional filter string representing a filter for
+        function names, or '*' to display docstrings for all functions.
     """
 
     # Directory containing your modules
     module_dir = os.path.dirname(__file__)
-    
+
     # Iterate over each file in the module directory
     for filename in sorted(os.listdir(module_dir)):
         if filename.endswith('.py') and filename != '__init__.py':
@@ -41,10 +42,10 @@ def docs(method_type_filter: Optional[str] = None) -> None:
             # List function names
             function_names = sorted(functions.keys())
             for name in function_names:
-                print(f"{name}")
-
-                # If a filter is provided or '*', print the docstring
-                if method_type_filter and (method_type_filter == '*' or method_type_filter == name):
+                # If a filter is provided or '*', check if the function name
+                # contains the filter
+                if method_type_filter and (
+                        method_type_filter == '*' or method_type_filter in name):
                     docstring: Optional[str] = functions[name].__doc__
                     if docstring:
                         print(f"\n{name}:\n{docstring}")

rgwfuncs/str_lib.py

@@ -1,53 +1,16 @@
 import os
 import json
 import requests
-import inspect
-from typing import Tuple, Optional, Dict, Callable
+from typing import Tuple
 import warnings
 
 # Suppress all FutureWarnings
 warnings.filterwarnings("ignore", category=FutureWarning)
 
 
-def str_docs(method_type_filter: Optional[str] = None) -> None:
-    """
-    Print a list of function names in alphabetical order. If method_type_filter
-    is specified, print the docstrings of the functions that match the filter.
-    Using '*' as a filter will print the docstrings for all functions.
-
-    Parameters:
-        method_type_filter: Optional filter string representing a function name,
-        or '*' to display docstrings for all functions.
-    """
-    # Get the current module's namespace
-    current_module = __name__
-
-    local_functions: Dict[str, Callable] = {
-        name: obj for name, obj in globals().items()
-        if inspect.isfunction(obj) and obj.__module__ == current_module
-    }
-
-    # List of function names sorted alphabetically
-    function_names = sorted(local_functions.keys())
-
-    # Print function names
-    print("Functions in alphabetical order:")
-    for name in function_names:
-        print(name)
-
-    # If a filter is provided or '*', print the docstrings of functions
-    if method_type_filter:
-        # print("\nFiltered function documentation:")
-        for name, func in local_functions.items():
-            docstring: Optional[str] = func.__doc__
-            if docstring:
-                if method_type_filter == '*' or method_type_filter == name:
-                    # Print the entire docstring for the matching function
-                    print(f"\n{name}:\n{docstring}")
-
-
 def send_telegram_message(preset_name: str, message: str) -> None:
-    """Send a Telegram message using the specified preset.
+    """
+    Send a Telegram message using the specified preset.
 
     Args:
         preset_name (str): The name of the preset to use for sending the message.
@@ -73,19 +36,20 @@ def send_telegram_message(preset_name: str, message: str) -> None:
                 return preset
         return None
 
-    def get_telegram_bot_details(config: dict, preset_name: str) -> Tuple[str, str]:
+    def get_telegram_bot_details(
+            config: dict, preset_name: str) -> Tuple[str, str]:
         """Retrieve the Telegram bot token and chat ID from the preset."""
         preset = get_telegram_preset(config, preset_name)
         if not preset:
-            raise RuntimeError(f"Telegram bot preset '{preset_name}' not found in the configuration file")
+            raise RuntimeError(
+                f"Telegram bot preset '{preset_name}' not found in the configuration file")
 
         bot_token = preset.get("bot_token")
         chat_id = preset.get("chat_id")
 
         if not bot_token or not chat_id:
             raise RuntimeError(
-                f"Telegram bot token or chat ID for '{preset_name}' not found in the configuration file"
-            )
+                f"Telegram bot token or chat ID for '{preset_name}' not found in the configuration file")
 
         return bot_token, chat_id
 

{rgwfuncs-0.0.24.dist-info → rgwfuncs-0.0.26.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.24
+Version: 0.0.26
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson
@@ -135,22 +135,126 @@ To display all docstrings, use:
 
 --------------------------------------------------------------------------------
 
-## String Based Functions
+## Documentation Access Functions
 
-### 1. str_docs
-Print a list of available function names in alphabetical order. If a filter is provided, print the matching docstrings.
+### 1. docs
+Print a list of available function names in alphabetical order. If a filter is provided, print the docstrings of functions containing the term.
 
 • Parameters:
   - `method_type_filter` (str): Optional, comma-separated to select docstring types, or '*' for all.
 
 • Example:
 
-    import rgwfuncs
-    rgwfuncs.str_docs(method_type_filter='numeric_clean,limit_dataframe')
+    from rgwfuncs import docs
+    docs(method_type_filter='numeric_clean,limit_dataframe')
+
+--------------------------------------------------------------------------------
+
+## Algebra Based Functions
+
+This section provides comprehensive functions for handling algebraic expressions, performing tasks such as computation, simplification, solving equations, and prime factorization, all outputted in LaTeX format.
+
+### 1. `compute_algebraic_expression`
+
+Evaluates complex algebraic expressions and provides numerical results.
+
+- **Parameters:**
+  - `expression` (str): A string representing an arithmetic operation.
+
+- **Returns:**
+  - `float`: The computed numerical result.
+
+- **Example:**
+
+    from rgwfuncs import compute_algebraic_expression
+    result1 = compute_algebraic_expression("2 + 2")
+    print(result1)  # Output: 4.0
+
+    result2 = compute_algebraic_expression("10 % 3")
+    print(result2)  # Output: 1.0
+
+    result3 = compute_algebraic_expression("math.gcd(36, 60) * math.sin(math.radians(45)) * 10000")
+    print(result3)  # Output: 84852.8137423857
+
+These examples illustrate the ability to handle basic arithmetic, the modulo operator, and functions utilizing the Python math module.
+
+--------------------------------------------------------------------------------
+
+### 2. `simplify_algebraic_expression`
+
+Simplifies expressions and returns them in LaTeX format.
+
+- **Parameters:**
+  - `expression` (str): A string of the expression to simplify.
+
+- **Returns:**
+  - `str`: Simplified expression in LaTeX.
+
+- **Example:**
+
+    from rgwfuncs import simplify_algebraic_expression
+    simplified_expr1 = simplify_algebraic_expression("2*x + 3*x")
+    print(simplified_expr1)  # Output: "5 x"
+
+    simplified_expr2 = simplify_algebraic_expression("(np.diff(3*x**8)) / (np.diff(8*x**30) * 11*y**3)")
+    print(simplified_expr2)  # Output: "\frac{1}{110 x^{22} y^{3}}"
+
+These examples demonstrate simplification of polynomial expressions and more complex ratios involving derivatives.
+
+--------------------------------------------------------------------------------
+
+### 3. `solve_algebraic_expression`
+
+Solves equations for specified variables, with optional substitutions, returning LaTeX-formatted solutions.
+
+- **Parameters:**
+  - `expression` (str): A string of the equation to solve.
+  - `variable` (str): The variable to solve for.
+  - `subs` (Optional[Dict[str, float]]): Substitutions for variables.
+
+- **Returns:**
+  - `str`: Solutions formatted in LaTeX.
+
+- **Example:**
+
+    from rgwfuncs import solve_algebraic_expression
+    solutions1 = solve_algebraic_expression("a*x**2 + b*x + c", "x", {"a": 3, "b": 7, "c": 5})
+    print(solutions1)  # Output: "\left[-7/6 - sqrt(11)*I/6, -7/6 + sqrt(11)*I/6\right]"
+
+    solutions2 = solve_algebraic_expression("x**2 - 4", "x")
+    print(solutions2)  # Output: "\left[-2, 2\right]"
+    
+Here, we solve both a quadratic equation with complex solutions and a simpler polynomial equation.
 
 --------------------------------------------------------------------------------
 
-### 2. send_telegram_message
+### 4. `get_prime_factors_latex`
+
+Computes prime factors of a number and presents them in LaTeX format.
+
+- **Parameters:**
+  - `n` (int): The integer to factorize.
+
+- **Returns:**
+  - `str`: Prime factorization in LaTeX.
+
+- **Example:**
+
+    from rgwfuncs import get_prime_factors_latex
+    factors1 = get_prime_factors_latex(100)
+    print(factors1)  # Output: "2^{2} \cdot 5^{2}"
+
+    factors2 = get_prime_factors_latex(60)
+    print(factors2)  # Output: "2^{2} \cdot 3 \cdot 5"
+
+    factors3 = get_prime_factors_latex(17)
+    print(factors3)  # Output: "17"    
+ 
+--------------------------------------------------------------------------------
+
+## String Based Functions
+
+### 1. send_telegram_message
 
 Send a message to a Telegram chat using a specified preset from your configuration file.
 
@@ -176,20 +280,7 @@ Send a message to a Telegram chat using a specified preset from your configurati
 
 Below is a quick reference of available functions, their purpose, and basic usage examples.
 
-### 1. df_docs
-Print a list of available function names in alphabetical order. If a filter is provided, print the matching docstrings.
-
-• Parameters:
-  - `method_type_filter` (str): Optional, comma-separated to select docstring types, or '*' for all.
-
-• Example:
-
-    import rgwfuncs
-    rgwfuncs.df_docs(method_type_filter='numeric_clean,limit_dataframe')
-
---------------------------------------------------------------------------------
-
-### 2. `numeric_clean`
+### 1. `numeric_clean`
 Cleans the numeric columns in a DataFrame according to specified treatments.
 
 • Parameters:
@@ -218,7 +309,7 @@ Cleans the numeric columns in a DataFrame according to specified treatments.
 
 --------------------------------------------------------------------------------
 
-### 3. `limit_dataframe`
+### 2. `limit_dataframe`
 Limit the DataFrame to a specified number of rows.
 
 • Parameters:
@@ -239,7 +330,7 @@ Limit the DataFrame to a specified number of rows.
 
 --------------------------------------------------------------------------------
 
-### 4. `from_raw_data`
+### 3. `from_raw_data`
 Create a DataFrame from raw data.
 
 • Parameters:
@@ -265,7 +356,7 @@ Create a DataFrame from raw data.
 
 --------------------------------------------------------------------------------
 
-### 5. `append_rows`
+### 4. `append_rows`
 Append rows to the DataFrame.
 
 • Parameters:
@@ -290,7 +381,7 @@ Append rows to the DataFrame.
 
 --------------------------------------------------------------------------------
 
-### 6. `append_columns`
+### 5. `append_columns`
 Append new columns to the DataFrame with None values.
 
 • Parameters:
@@ -311,7 +402,7 @@ Append new columns to the DataFrame with None values.
     
 --------------------------------------------------------------------------------
 
-### 7. `update_rows`
+### 6. `update_rows`
 Update specific rows in the DataFrame based on a condition.
 
 • Parameters:
@@ -333,7 +424,7 @@ Update specific rows in the DataFrame based on a condition.
     
 --------------------------------------------------------------------------------
 
-### 8. `delete_rows`
+### 7. `delete_rows`
 Delete rows from the DataFrame based on a condition.
 
 • Parameters:
@@ -354,7 +445,7 @@ Delete rows from the DataFrame based on a condition.
     
 --------------------------------------------------------------------------------
 
-### 9. `drop_duplicates`
+### 8. `drop_duplicates`
 Drop duplicate rows in the DataFrame, retaining the first occurrence.
 
 • Parameters:
@@ -374,7 +465,7 @@ Drop duplicate rows in the DataFrame, retaining the first occurrence.
     
 --------------------------------------------------------------------------------
 
-### 10. `drop_duplicates_retain_first`
+### 9. `drop_duplicates_retain_first`
 Drop duplicate rows based on specified columns, retaining the first occurrence.
 
 • Parameters:
@@ -395,7 +486,7 @@ Drop duplicate rows based on specified columns, retaining the first occurrence.
     
 --------------------------------------------------------------------------------
 
-### 11. `drop_duplicates_retain_last`
+### 10. `drop_duplicates_retain_last`
 Drop duplicate rows based on specified columns, retaining the last occurrence.
 
 • Parameters:
@@ -417,7 +508,7 @@ Drop duplicate rows based on specified columns, retaining the last occurrence.
 
 --------------------------------------------------------------------------------
 
-### 12. `load_data_from_query`
+### 11. `load_data_from_query`
 
 Load data from a database query into a DataFrame based on a configuration preset.
 
@@ -444,7 +535,7 @@ Load data from a database query into a DataFrame based on a configuration preset
     
 --------------------------------------------------------------------------------
 
-### 13. `load_data_from_path`
+### 12. `load_data_from_path`
 Load data from a file into a DataFrame based on the file extension.
 
 • Parameters:
@@ -463,7 +554,7 @@ Load data from a file into a DataFrame based on the file extension.
 
 --------------------------------------------------------------------------------
 
-### 14. `load_data_from_sqlite_path`
+### 13. `load_data_from_sqlite_path`
 Execute a query on a SQLite database file and return the results as a DataFrame.
 
 • Parameters:
@@ -483,7 +574,7 @@ Execute a query on a SQLite database file and return the results as a DataFrame.
 
 --------------------------------------------------------------------------------
 
-### 15. `first_n_rows`
+### 14. `first_n_rows`
 Display the first n rows of the DataFrame (prints out in dictionary format).
 
 • Parameters:
@@ -501,7 +592,7 @@ Display the first n rows of the DataFrame (prints out in dictionary format).
 
 --------------------------------------------------------------------------------
 
-### 16. `last_n_rows`
+### 15. `last_n_rows`
 Display the last n rows of the DataFrame (prints out in dictionary format).
 
 • Parameters:
@@ -519,7 +610,7 @@ Display the last n rows of the DataFrame (prints out in dictionary format).
 
 --------------------------------------------------------------------------------
 
-### 17. `top_n_unique_values`
+### 16. `top_n_unique_values`
 Print the top n unique values for specified columns in the DataFrame.
 
 • Parameters:
@@ -538,7 +629,7 @@ Print the top n unique values for specified columns in the DataFrame.
 
 --------------------------------------------------------------------------------
 
-### 18. `bottom_n_unique_values`
+### 17. `bottom_n_unique_values`
 Print the bottom n unique values for specified columns in the DataFrame.
 
 • Parameters:
@@ -557,7 +648,7 @@ Print the bottom n unique values for specified columns in the DataFrame.
 
 --------------------------------------------------------------------------------
 
-### 19. `print_correlation`
+### 18. `print_correlation`
 Print correlation for multiple pairs of columns in the DataFrame.
 
 • Parameters:
@@ -582,7 +673,7 @@ Print correlation for multiple pairs of columns in the DataFrame.
 
 --------------------------------------------------------------------------------
 
-### 20. `print_memory_usage`
+### 19. `print_memory_usage`
 Print the memory usage of the DataFrame in megabytes.
 
 • Parameters:
@@ -599,7 +690,7 @@ Print the memory usage of the DataFrame in megabytes.
 
 --------------------------------------------------------------------------------
 
-### 21. `filter_dataframe`
+### 20. `filter_dataframe`
 Return a new DataFrame filtered by a given query expression.
 
 • Parameters:
@@ -625,7 +716,7 @@ Return a new DataFrame filtered by a given query expression.
 
 --------------------------------------------------------------------------------
 
-### 22. `filter_indian_mobiles`
+### 21. `filter_indian_mobiles`
 Filter and return rows containing valid Indian mobile numbers in the specified column.
 
 • Parameters:
@@ -647,7 +738,7 @@ Filter and return rows containing valid Indian mobile numbers in the specified c
 
 --------------------------------------------------------------------------------
 
-### 23. `print_dataframe`
+### 22. `print_dataframe`
 Print the entire DataFrame and its column types. Optionally print a source path.
 
 • Parameters:
@@ -665,7 +756,7 @@ Print the entire DataFrame and its column types. Optionally print a source path.
 
 --------------------------------------------------------------------------------
 
-### 24. `send_dataframe_via_telegram`
+### 23. `send_dataframe_via_telegram`
 Send a DataFrame via Telegram using a specified bot configuration.
 
 • Parameters:
@@ -692,7 +783,7 @@ Send a DataFrame via Telegram using a specified bot configuration.
 
 --------------------------------------------------------------------------------
 
-### 25. `send_data_to_email`
+### 24. `send_data_to_email`
 Send an email with an optional DataFrame attachment using the Gmail API via a specified preset.
 
 • Parameters:
@@ -722,7 +813,7 @@ Send an email with an optional DataFrame attachment using the Gmail API via a sp
 
 --------------------------------------------------------------------------------
 
-### 26. `send_data_to_slack`
+### 25. `send_data_to_slack`
 Send a DataFrame or message to Slack using a specified bot configuration.
 
 • Parameters:
@@ -748,7 +839,7 @@ Send a DataFrame or message to Slack using a specified bot configuration.
 
 --------------------------------------------------------------------------------
 
-### 27. `order_columns`
+### 26. `order_columns`
 Reorder the columns of a DataFrame based on a string input.
 
 • Parameters:
@@ -770,7 +861,7 @@ Reorder the columns of a DataFrame based on a string input.
 
 --------------------------------------------------------------------------------
 
-### 28. `append_ranged_classification_column`
+### 27. `append_ranged_classification_column`
 Append a ranged classification column to the DataFrame.
 
 • Parameters:
@@ -794,7 +885,7 @@ Append a ranged classification column to the DataFrame.
 
 --------------------------------------------------------------------------------
 
-### 29. `append_percentile_classification_column`
+### 28. `append_percentile_classification_column`
 Append a percentile classification column to the DataFrame.
 
 • Parameters:
@@ -818,7 +909,7 @@ Append a percentile classification column to the DataFrame.
 
 --------------------------------------------------------------------------------
 
-### 30. `append_ranged_date_classification_column`
+### 29. `append_ranged_date_classification_column`
 Append a ranged date classification column to the DataFrame.
 
 • Parameters:
@@ -847,7 +938,7 @@ Append a ranged date classification column to the DataFrame.
 
 --------------------------------------------------------------------------------
 
-### 31. `rename_columns`
+### 30. `rename_columns`
 Rename columns in the DataFrame.
 
 • Parameters:
@@ -869,7 +960,7 @@ Rename columns in the DataFrame.
 
 --------------------------------------------------------------------------------
 
-### 32. `cascade_sort`
+### 31. `cascade_sort`
 Cascade sort the DataFrame by specified columns and order.
 
 • Parameters:
@@ -895,7 +986,7 @@ Cascade sort the DataFrame by specified columns and order.
 
 --------------------------------------------------------------------------------
 
-### 33. `append_xgb_labels`
+### 32. `append_xgb_labels`
 Append XGB training labels (TRAIN, VALIDATE, TEST) based on a ratio string.
 
 • Parameters:
@@ -917,7 +1008,7 @@ Append XGB training labels (TRAIN, VALIDATE, TEST) based on a ratio string.
 
 --------------------------------------------------------------------------------
 
-### 34. `append_xgb_regression_predictions`
+### 33. `append_xgb_regression_predictions`
 Append XGB regression predictions to the DataFrame. Requires an `XGB_TYPE` column for TRAIN/TEST splits.
 
 • Parameters:
@@ -949,7 +1040,7 @@ Append XGB regression predictions to the DataFrame. Requires an `XGB_TYPE` colum
 
 --------------------------------------------------------------------------------
 
-### 35. `append_xgb_logistic_regression_predictions`
+### 34. `append_xgb_logistic_regression_predictions`
 Append XGB logistic regression predictions to the DataFrame. Requires an `XGB_TYPE` column for TRAIN/TEST splits.
 
 • Parameters:
@@ -981,7 +1072,7 @@ Append XGB logistic regression predictions to the DataFrame. Requires an `XGB_TY
 
 --------------------------------------------------------------------------------
 
-### 36. `print_n_frequency_cascading`
+### 35. `print_n_frequency_cascading`
 Print the cascading frequency of top n values for specified columns.
 
 • Parameters:
@@ -1001,7 +1092,7 @@ Print the cascading frequency of top n values for specified columns.
 
 --------------------------------------------------------------------------------
 
-### 37. `print_n_frequency_linear`
+### 36. `print_n_frequency_linear`
 
 Prints the linear frequency of the top `n` values for specified columns.
 
@@ -1030,7 +1121,7 @@ This example analyzes the `City` column, printing the top 2 most frequent values
 
 --------------------------------------------------------------------------------
 
-### 38. `retain_columns`
+### 37. `retain_columns`
 Retain specified columns in the DataFrame and drop the others.
 
 • Parameters:
@@ -1052,7 +1143,7 @@ Retain specified columns in the DataFrame and drop the others.
 
 --------------------------------------------------------------------------------
 
-### 39. `mask_against_dataframe`
+### 38. `mask_against_dataframe`
 Retain only rows with common column values between two DataFrames.
 
 • Parameters:
@@ -1077,7 +1168,7 @@ Retain only rows with common column values between two DataFrames.
 
 --------------------------------------------------------------------------------
 
-### 40. `mask_against_dataframe_converse`
+### 39. `mask_against_dataframe_converse`
 Retain only rows with uncommon column values between two DataFrames.
 
 • Parameters:
@@ -1102,7 +1193,7 @@ Retain only rows with uncommon column values between two DataFrames.
 
 --------------------------------------------------------------------------------
 
-### 41. `union_join`
+### 40. `union_join`
 Perform a union join, concatenating two DataFrames and dropping duplicates.
 
 • Parameters:
@@ -1125,7 +1216,7 @@ Perform a union join, concatenating two DataFrames and dropping duplicates.
 
 --------------------------------------------------------------------------------
 
-### 42. `bag_union_join`
+### 41. `bag_union_join`
 Perform a bag union join, concatenating two DataFrames without dropping duplicates.
 
 • Parameters:
@@ -1148,7 +1239,7 @@ Perform a bag union join, concatenating two DataFrames without dropping duplicat
 
 --------------------------------------------------------------------------------
 
-### 43. `left_join`
+### 42. `left_join`
 Perform a left join on two DataFrames.
 
 • Parameters:
@@ -1173,7 +1264,7 @@ Perform a left join on two DataFrames.
 
 --------------------------------------------------------------------------------
 
-### 44. `right_join`
+### 43. `right_join`
 Perform a right join on two DataFrames.
 
 • Parameters:
@@ -1198,7 +1289,7 @@ Perform a right join on two DataFrames.
 
 --------------------------------------------------------------------------------
 
-### 45. `insert_dataframe_in_sqlite_database`
+### 44. `insert_dataframe_in_sqlite_database`
 
 Inserts a Pandas DataFrame into a SQLite database table. If the specified table does not exist, it will be created with column types automatically inferred from the DataFrame's data types.
 
@@ -1236,7 +1327,7 @@ Inserts a Pandas DataFrame into a SQLite database table. If the specified table
 
 --------------------------------------------------------------------------------
 
-### 46. `sync_dataframe_to_sqlite_database`
+### 45. `sync_dataframe_to_sqlite_database`
 Processes and saves a DataFrame to an SQLite database, adding a timestamp column and replacing the existing table if needed. Creates the table if it does not exist.
 
 • Parameters:
@@ -1260,6 +1351,8 @@ Processes and saves a DataFrame to an SQLite database, adding a timestamp column
 
 --------------------------------------------------------------------------------
 
+
+
 ## Additional Info
 
 For more information, refer to each function’s docstring by calling:

rgwfuncs-0.0.26.dist-info/RECORD

@@ -0,0 +1,11 @@
+rgwfuncs/__init__.py,sha256=SZg1HPP5D_3QimoYFH8zongQ9D9XPZWp-Qi-MZglvXw,1315
+rgwfuncs/algebra_lib.py,sha256=1_ZTDVdfZcnXTlOOZlI2sAyJm2gA1lyje8l3h68kjlI,10902
+rgwfuncs/df_lib.py,sha256=G_H3PXNVeseX2YLjkkrmO9eXA_7r29swUZlbPBDZjXA,66612
+rgwfuncs/docs_lib.py,sha256=y3wSAOPO3qsA4HZ7xAtW8HimM8w-c8hjcEzMRLJ96ao,1960
+rgwfuncs/str_lib.py,sha256=rtAdRlnSJIu3JhI-tA_A0wCiPK2m-zn5RoGpBxv_g-4,2228
+rgwfuncs-0.0.26.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
+rgwfuncs-0.0.26.dist-info/METADATA,sha256=VXXptuvGxZt1riPsQjIGkYTnyxvikcWht9sjcnLEpU4,38637
+rgwfuncs-0.0.26.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+rgwfuncs-0.0.26.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
+rgwfuncs-0.0.26.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
+rgwfuncs-0.0.26.dist-info/RECORD,,

rgwfuncs-0.0.24.dist-info/RECORD

@@ -1,11 +0,0 @@
-rgwfuncs/__init__.py,sha256=UrSka0KkoaZfLtODgbEbGvo67-L0LK1-e9waRn2a95g,1334
-rgwfuncs/algebra_lib.py,sha256=aayZogB2Rp9JAo5kVHpauqX_R346eI_rIuE5QNEMlKM,7789
-rgwfuncs/df_lib.py,sha256=8KMn4FucI19EFBHUoGOS7R4mo0degg6A6802sjy7BH4,67677
-rgwfuncs/docs_lib.py,sha256=iZlQMNS52FuiblCI0oXJVznSuCndeG6WqZfsm-Xnd7U,1918
-rgwfuncs/str_lib.py,sha256=I5B0WOGaLUGaedMG7hqiKnIqV7Jc9h1RYlgOiC_-iGY,3678
-rgwfuncs-0.0.24.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
-rgwfuncs-0.0.24.dist-info/METADATA,sha256=-Nv5cA1xWJNfDSp53_jkaTce5n93hAH7mS7bv2IFWes,35516
-rgwfuncs-0.0.24.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-rgwfuncs-0.0.24.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
-rgwfuncs-0.0.24.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
-rgwfuncs-0.0.24.dist-info/RECORD,,