rgwfuncs 0.0.66__tar.gz → 0.0.68__tar.gz

{rgwfuncs-0.0.66/src/rgwfuncs.egg-info → rgwfuncs-0.0.68}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.66
+Version: 0.0.68
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson

{rgwfuncs-0.0.66 → rgwfuncs-0.0.68}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "rgwfuncs"
-version = "0.0.66"
+version = "0.0.68"
 authors = [
   { name = "Ryan Gerard Wilson", email = "ryangerardwilson@gmail.com" },
 ]

{rgwfuncs-0.0.66 → rgwfuncs-0.0.68}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = rgwfuncs
-version = 0.0.66
+version = 0.0.68
 author = Ryan Gerard Wilson
 author_email = ryangerardwilson@gmail.com
 description = A functional programming paradigm for mathematical modelling and data science

{rgwfuncs-0.0.66 → rgwfuncs-0.0.68}/src/rgwfuncs/__init__.py

@@ -2,7 +2,7 @@
 # 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, 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, load_fresh_data_or_pull_from_cache, 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 .interactive_shell_lib import interactive_shell
+from .interactive_shell_lib import interactive_shell, setup_readline
 from .algebra_lib import cancel_polynomial_expression, compute_constant_expression, compute_constant_expression_involving_matrices, compute_constant_expression_involving_ordered_series, compute_prime_factors, expand_polynomial_expression, factor_polynomial_expression, plot_polynomial_functions, plot_x_points_of_polynomial_functions, python_polynomial_expression_to_latex, simplify_polynomial_expression, solve_homogeneous_polynomial_expression
 from .docs_lib import docs
 from .str_lib import send_telegram_message

{rgwfuncs-0.0.66 → rgwfuncs-0.0.68}/src/rgwfuncs/df_lib.py

@@ -509,6 +509,10 @@ def load_data_from_path(file_path: str) -> pd.DataFrame:
     # Ensure the file path is absolute
     file_path = os.path.abspath(file_path)
 
+    # Check if the file exists
+    if not os.path.isfile(file_path):
+        raise ValueError(f"File not found: {file_path}")
+
     # Determine file type by extension
     file_extension = file_path.split('.')[-1].lower()
 
@@ -518,6 +522,8 @@ def load_data_from_path(file_path: str) -> pd.DataFrame:
         df.replace('', None, inplace=True)
     elif file_extension in ['xls', 'xlsx']:
         df = pd.read_excel(file_path)
+    elif file_extension == 'ods':
+        df = pd.read_excel(file_path, engine='odf')
     elif file_extension == 'json':
         df = pd.read_json(file_path)
     elif file_extension == 'parquet':
@@ -2013,24 +2019,24 @@ def sync_dataframe_to_sqlite_database(
 def load_fresh_data_or_pull_from_cache(fetch_func: Callable[[], pd.DataFrame], cache_dir: str, file_prefix: str, cache_cutoff_hours: int) -> pd.DataFrame:
     """
     Retrieve data from a cache if a recent cache file exists, or fetch fresh data, save it to the cache, and return it.
-    
+
     This function checks a specified directory for the most recent cache file matching a specified prefix.
     If a recent cache file (within the cutoff time in hours) is found, the data is read from there.
     Otherwise, it calls the data-fetching function, saves the newly fetched data to a new cache file, and returns it.
 
     Parameters:
-    - fetch_func (typing.Callable[[], pd.DataFrame]): 
+    - fetch_func (typing.Callable[[], pd.DataFrame]):
         A callable function that, when executed, returns a pandas DataFrame with fresh data.
-    - cache_dir (str): 
+    - cache_dir (str):
         The directory where cache files are stored.
-    - file_prefix (str): 
+    - file_prefix (str):
         The prefix used for cache filenames to identify relevant cache files.
-    - cache_cutoff_hours (int): 
+    - cache_cutoff_hours (int):
         The maximum age of a cache file (in hours) to be considered valid.
         If no file is fresh enough, fresh data will be fetched.
 
     Returns:
-    - pd.DataFrame: 
+    - pd.DataFrame:
         The pandas DataFrame containing either cached or freshly fetched data.
     """
 
@@ -2047,7 +2053,7 @@ def load_fresh_data_or_pull_from_cache(fetch_func: Callable[[], pd.DataFrame], c
     # Retrieve the latest cache file if it exists
     for filename in os.listdir(cache_dir):
         if filename.startswith(file_prefix) and filename.endswith(".csv"):
-            timestamp_str: str = filename[len(file_prefix)+1:].replace('.csv', '')
+            timestamp_str: str = filename[len(file_prefix) + 1:].replace('.csv', '')
             try:
                 file_time: datetime = datetime.strptime(timestamp_str, '%Y%m%d%H%M%S')
                 if latest_cache_time is None or file_time > latest_cache_time:
@@ -2069,4 +2075,3 @@ def load_fresh_data_or_pull_from_cache(fetch_func: Callable[[], pd.DataFrame], c
         df.to_csv(os.path.join(cache_dir, cache_filename), index=False)
 
     return df
-

rgwfuncs-0.0.68/src/rgwfuncs/interactive_shell_lib.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+import code
+import readline
+import rlcompleter  # noqa: F401
+import sys  # noqa: F401
+import os
+import atexit
+from typing import Dict, Any
+from .df_lib import *  # noqa: F401, F403, E402
+from .algebra_lib import *  # noqa: F401, F403, E402
+from .str_lib import *  # noqa: F401, F403, E402
+from .docs_lib import *  # noqa: F401, F403, E402
+
+# File for command history
+HISTORY_FILE = os.path.expanduser("~/.rgwfuncs_shell_history")
+
+def setup_readline():
+    """Set up readline for command history persistence"""
+    readline.set_history_length(1000)  # Limit history to 1000 lines
+    readline.parse_and_bind("tab: complete")  # Enable tab completion
+    if os.path.exists(HISTORY_FILE):
+        try:
+            readline.read_history_file(HISTORY_FILE)
+        except Exception as e:
+            print(f"Warning: Could not load history file: {e}")
+    atexit.register(readline.write_history_file, HISTORY_FILE)
+
+def interactive_shell(local_vars: Dict[str, Any]) -> None:
+    """
+    Launches an interactive prompt for inspecting and modifying local variables, making all methods
+    in the rgwfuncs library available by default. Persists command history across sessions.
+
+    Parameters:
+        local_vars (dict): Dictionary of local variables to be available in the interactive shell.
+    """
+    if not isinstance(local_vars, dict):
+        raise TypeError("local_vars must be a dictionary")
+
+    # Set up readline for history and completion
+    setup_readline()
+
+    # Make imported functions available in the REPL
+    local_vars.update(globals())
+
+    # Create interactive console with local context
+    console = code.InteractiveConsole(locals=local_vars)
+
+    # Start interactive session with a custom banner
+    banner = "Welcome to the rgwfuncs interactive shell.\nUse up/down arrows for command history.\nType 'exit()' or Ctrl+D to quit."
+    console.interact(banner=banner, exitmsg="Goodbye.")

{rgwfuncs-0.0.66 → rgwfuncs-0.0.68/src/rgwfuncs.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.66
+Version: 0.0.68
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson

rgwfuncs-0.0.66/src/rgwfuncs/interactive_shell_lib.py

@@ -1,32 +0,0 @@
-import code
-import readline
-import rlcompleter  # noqa: F401
-import sys  # noqa: F401
-from typing import Dict, Any
-from .df_lib import *  # noqa: F401, F403, E402
-from .algebra_lib import *  # noqa: F401, F403, E402
-from .str_lib import *  # noqa: F401, F403, E402
-from .docs_lib import *  # noqa: F401, F403, E402
-
-
-def interactive_shell(local_vars: Dict[str, Any]) -> None:
-    """
-    Launches an interactive prompt for inspecting and modifying local variables, making all methods
-    in the rgwfuncs library available by default.
-
-    Parameters:
-        local_vars (dict): Dictionary of local variables to be available in the interactive shell.
-    """
-    if not isinstance(local_vars, dict):
-        raise TypeError("local_vars must be a dictionary")
-
-    readline.parse_and_bind("tab: complete")
-
-    # Make imported functions available in the REPL
-    local_vars.update(globals())
-
-    # Create interactive console with local context
-    console = code.InteractiveConsole(locals=local_vars)
-
-    # Start interactive session
-    console.interact(banner="Welcome to the rgwfuncs interactive shell.")