rgwfuncs 0.0.65__tar.gz → 0.0.67__tar.gz

{rgwfuncs-0.0.65/src/rgwfuncs.egg-info → rgwfuncs-0.0.67}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.65
+Version: 0.0.67
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson

{rgwfuncs-0.0.65 → rgwfuncs-0.0.67}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "rgwfuncs"
-version = "0.0.65"
+version = "0.0.67"
 authors = [
   { name = "Ryan Gerard Wilson", email = "ryangerardwilson@gmail.com" },
 ]

{rgwfuncs-0.0.65 → rgwfuncs-0.0.67}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = rgwfuncs
-version = 0.0.65
+version = 0.0.67
 author = Ryan Gerard Wilson
 author_email = ryangerardwilson@gmail.com
 description = A functional programming paradigm for mathematical modelling and data science

{rgwfuncs-0.0.65 → rgwfuncs-0.0.67}/src/rgwfuncs/df_lib.py

@@ -2,7 +2,7 @@ import pandas as pd
 import pymssql
 import os
 import json
-from datetime import datetime
+from datetime import datetime, timedelta
 import time
 import gc
 import mysql.connector
@@ -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-0.0.65 → rgwfuncs-0.0.67/src/rgwfuncs.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.65
+Version: 0.0.67
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson