rgwfuncs 0.0.23__py3-none-any.whl → 0.0.25__py3-none-any.whl

rgwfuncs/__init__.py

@@ -1,5 +1,7 @@
 # This file is automatically generated
 # Dynamically importing functions from modules
 
-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 .str_lib import send_telegram_message, str_docs
+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, 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

rgwfuncs/algebra_lib.py

@@ -0,0 +1,186 @@
+import re
+import math
+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:
+    try:
+        # Direct numerical evaluation
+        # Safely evaluate the expression using the math module
+        numeric_result = eval(expression, {"__builtins__": None, "math": math})
+
+        # Convert to float if possible
+        return float(numeric_result)
+    except Exception as e:
+        raise ValueError(f"Error computing expression: {e}")
+
+def simplify_algebraic_expression(expression: str) -> str:
+
+
+    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
+        match = re.match(fr'{prefix}\.(\w+)\((.*)\)', func_call, re.DOTALL)
+        if not match:
+            raise ValueError(f"Invalid function call: {func_call}")
+
+        func_name = match.group(1)
+        args_str = match.group(2)
+
+        # Check if it's a list for np
+        if prefix == 'np' and args_str.startswith("[") and args_str.endswith("]"):
+            parsed_args = [ast.literal_eval(args_str.strip())]
+        else:
+            parsed_args = []
+            raw_args = re.split(r',(?![^{]*\})', args_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))
+                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)
+            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))]
+                    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)
+            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)
+            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)
+                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]
+
+                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:
+        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()}
+                    sym_expr = method(kwargs)
+                else:
+                    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_no_brackets": r"np\.diff\([^()]*\)",
+        "math_functions": r"math\.\w+\((?:[^()]*(?:\([^()]*\)[^()]*)*)\)",
+        # "sympy_functions": r"sym\.\w+\([^()]*\)(?:\.\w+\([^()]*\))?",
+    }
+
+    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)
+    # print("Level 2 processed_expression:", processed_expression)
+
+    try:
+        if processed_expression.startswith('[') and processed_expression.endswith(']'):
+            return processed_expression
+
+        expr = parse_expr(processed_expression, local_dict=sym_vars)
+        final_result = simplify(expr)
+
+        if final_result.free_symbols:
+            latex_result = latex(final_result)
+            return latex_result
+        else:
+            return str(final_result)
+
+    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:
+    try:
+        # Create symbols for the variables in the expression
+        variable_symbols = set(re.findall(r'\b[a-zA-Z]\w*\b', expression))
+        sym_vars = {var: symbols(var) for var in variable_symbols}
+
+        # Parse the expression and solve it
+        expr = parse_expr(expression, local_dict=sym_vars)
+        var_symbol = symbols(variable)
+        solutions = solve(expr, var_symbol)
+
+        # Apply substitutions if provided
+        if subs:
+            subs_symbols = {symbols(k): v for k, v in subs.items()}
+            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]
+        result = r"\left[" + ", ".join(latex_solutions) + r"\right]"
+        print("158", result)
+        return result
+
+    except Exception as e:
+        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.
+    """
+    factors = []
+    while n % 2 == 0:
+        factors.append(2)
+        n //= 2
+    for i in range(3, int(math.sqrt(n)) + 1, 2):
+        while n % i == 0:
+            factors.append(i)
+            n //= i
+    if n > 2:
+        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()]
+    return " \\cdot ".join(latex_factors)
+
+
+

rgwfuncs/df_lib.py

@@ -29,43 +29,6 @@ import warnings
 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,

rgwfuncs/docs_lib.py

@@ -0,0 +1,49 @@
+import os
+import inspect
+from typing import Tuple, Optional, Dict, Callable
+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 based on a substring. Using '*' as a filter will print 
+    the docstrings for all functions.
+
+    Parameters:
+        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':
+            module_name, _ = os.path.splitext(filename)
+            print(f"\n# {module_name}.py")
+
+            # Import the module
+            module_path = f"rgwfuncs.{module_name}"
+            module = __import__(module_path, fromlist=[module_name])
+
+            # Get all functions from the module
+            functions = {
+                name: obj for name, obj
+                in inspect.getmembers(module, inspect.isfunction)
+                if obj.__module__ == module_path
+            }
+
+            # List function names
+            function_names = sorted(functions.keys())
+            for name in function_names:
+                # 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

@@ -9,45 +9,9 @@ import warnings
 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.

{rgwfuncs-0.0.23.dist-info → rgwfuncs-0.0.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.23
+Version: 0.0.25
 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')
 
 --------------------------------------------------------------------------------
 
-### 2. send_telegram_message
+## 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.
+
+--------------------------------------------------------------------------------
+
+### 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:
@@ -1001,27 +1092,36 @@ Print the cascading frequency of top n values for specified columns.
 
 --------------------------------------------------------------------------------
 
-### 37. `print_n_frequency_linear`
-Print the linear frequency of top n values for specified columns.
+### 36. `print_n_frequency_linear`
 
-• Parameters:
-  - df (pd.DataFrame)
-  - n (int)
-  - columns (str): Comma-separated columns.
-  - `order_by` (str)
+Prints the linear frequency of the top `n` values for specified columns.
+
+#### Parameters:
+- **df** (`pd.DataFrame`): The DataFrame to analyze.
+- **n** (`int`): The number of top values to print for each column.
+- **columns** (`list`): A list of column names to be analyzed.
+- **order_by** (`str`): The order of frequency. The available options are:
+  - `"ASC"`: Sort keys in ascending lexicographical order.
+  - `"DESC"`: Sort keys in descending lexicographical order.
+  - `"FREQ_ASC"`: Sort the frequencies in ascending order (least frequent first).
+  - `"FREQ_DESC"`: Sort the frequencies in descending order (most frequent first).
+  - `"BY_KEYS_ASC"`: Sort keys in ascending order, numerically if possible, handling special strings like 'NaN' as typical entries.
+  - `"BY_KEYS_DESC"`: Sort keys in descending order, numerically if possible, handling special strings like 'NaN' as typical entries.
+
+#### Example:
 
-• Example:
-    
     from rgwfuncs import print_n_frequency_linear
     import pandas as pd
 
-    df = pd.DataFrame({'City': ['NY','LA','NY','SF','LA','LA']})
-    print_n_frequency_linear(df, 2, 'City', 'FREQ_DESC')
-    
+    df = pd.DataFrame({'City': ['NY', 'LA', 'NY', 'SF', 'LA', 'LA']})
+    print_n_frequency_linear(df, 2, ['City'], 'FREQ_DESC')
+
+This example analyzes the `City` column, printing the top 2 most frequent values in descending order of frequency.
+
 
 --------------------------------------------------------------------------------
 
-### 38. `retain_columns`
+### 37. `retain_columns`
 Retain specified columns in the DataFrame and drop the others.
 
 • Parameters:
@@ -1043,7 +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:
@@ -1068,7 +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:
@@ -1093,7 +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:
@@ -1116,7 +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:
@@ -1139,7 +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:
@@ -1164,7 +1264,7 @@ Perform a left join on two DataFrames.
 
 --------------------------------------------------------------------------------
 
-### 44. `right_join`
+### 43. `right_join`
 Perform a right join on two DataFrames.
 
 • Parameters:
@@ -1189,7 +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.
 
@@ -1227,7 +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:
@@ -1251,6 +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-0.0.25.dist-info/RECORD

@@ -0,0 +1,11 @@
+rgwfuncs/__init__.py,sha256=SZg1HPP5D_3QimoYFH8zongQ9D9XPZWp-Qi-MZglvXw,1315
+rgwfuncs/algebra_lib.py,sha256=aayZogB2Rp9JAo5kVHpauqX_R346eI_rIuE5QNEMlKM,7789
+rgwfuncs/df_lib.py,sha256=OfbnAii_RND_euTJVou9nJaDqRLNbIMTCbaBelAUDvk,66247
+rgwfuncs/docs_lib.py,sha256=vlO8Rr6PYzyd2ZAenV_6t_iZJ3CoHja3PSLJverlAT4,1941
+rgwfuncs/str_lib.py,sha256=PHvxAg7_mZ_xe7DWJiAQ-PQ2fkYddKe8G0iQ1L78aZ0,2252
+rgwfuncs-0.0.25.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
+rgwfuncs-0.0.25.dist-info/METADATA,sha256=RQIG8bS4SFwHTycxQXpaYnyw2C8UIkQZEe7EfivMwao,38637
+rgwfuncs-0.0.25.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+rgwfuncs-0.0.25.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
+rgwfuncs-0.0.25.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
+rgwfuncs-0.0.25.dist-info/RECORD,,

rgwfuncs-0.0.23.dist-info/RECORD

@@ -1,9 +0,0 @@
-rgwfuncs/__init__.py,sha256=2nrp3c5VmVrKh0Ih6zELL8niH9nAHN0XnObqe-EpxlE,1169
-rgwfuncs/df_lib.py,sha256=8KMn4FucI19EFBHUoGOS7R4mo0degg6A6802sjy7BH4,67677
-rgwfuncs/str_lib.py,sha256=I5B0WOGaLUGaedMG7hqiKnIqV7Jc9h1RYlgOiC_-iGY,3678
-rgwfuncs-0.0.23.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
-rgwfuncs-0.0.23.dist-info/METADATA,sha256=_mVsZMv4umMXMW_Q2hBxABMm75pKuvJgMIMBldXxCtk,34680
-rgwfuncs-0.0.23.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-rgwfuncs-0.0.23.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
-rgwfuncs-0.0.23.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
-rgwfuncs-0.0.23.dist-info/RECORD,,