imsciences 0.9.5.1__tar.gz → 0.9.5.3__tar.gz

{imsciences-0.9.5.1 → imsciences-0.9.5.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.5.1
+Version: 0.9.5.3
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.9.5.1 → imsciences-0.9.5.3}/imsciences/geo.py

@@ -199,13 +199,13 @@ class geoprocessing:
 
         return analysis_df
     
-    def process_city_analysis(self, raw_input_path, spend_input_path, output_path, group1, group2, response_column):
+    def process_city_analysis(self, raw_data, spend_data, output_path, group1, group2, response_column):
         """
         Process city analysis by grouping data, analyzing user metrics, and merging with spend data.
 
         Parameters:
-            raw_input_path (str): Path to the raw input data file (CSV or XLSX) containing at least 'date', 'city', and the specified response column.
-            spend_input_path (str): Path to the media spend data file (CSV or XLSX) with 'date', 'geo', and 'cost' columns. Costs should be numeric.
+            raw_data (str or pd.DataFrame): Raw input data as a file path (CSV/XLSX) or DataFrame.
+            spend_data (str or pd.DataFrame): Spend data as a file path (CSV/XLSX) or DataFrame.
             output_path (str): Path to save the final output file (CSV or XLSX).
             group1 (list): List of city regions for group 1.
             group2 (list): List of city regions for group 2.
@@ -217,13 +217,15 @@ class geoprocessing:
         import pandas as pd
         import os
 
-        def read_file(file_path):
-            """Helper function to read CSV or XLSX files."""
-            ext = os.path.splitext(file_path)[1].lower()
+        def read_file(data):
+            """Helper function to handle file paths or return DataFrame directly."""
+            if isinstance(data, pd.DataFrame):
+                return data
+            ext = os.path.splitext(data)[1].lower()
             if ext == '.csv':
-                return pd.read_csv(file_path)
+                return pd.read_csv(data)
             elif ext in ['.xlsx', '.xls']:
-                return pd.read_excel(file_path)
+                return pd.read_excel(data)
             else:
                 raise ValueError("Unsupported file type. Please use a CSV or XLSX file.")
 
@@ -237,9 +239,9 @@ class geoprocessing:
             else:
                 raise ValueError("Unsupported file type. Please use a CSV or XLSX file.")
 
-        # Read input files
-        raw_df = read_file(raw_input_path)
-        spend_df = read_file(spend_input_path)
+        # Read data
+        raw_df = read_file(raw_data)
+        spend_df = read_file(spend_data)
 
         # Ensure necessary columns are present
         required_columns = {'date', 'city', response_column}

{imsciences-0.9.5.1 → imsciences-0.9.5.3}/imsciences/mmm.py

@@ -492,15 +492,15 @@ class dataprocessing:
 
         return combined_df
     
-    def pivot_table(self, df, index_col, columns, values_col, filters_dict=None, fill_value=0, aggfunc="sum", margins=False, margins_name="Total", datetime_trans_needed=True, date_format="%Y-%m-%d", reverse_header_order=False, fill_missing_weekly_dates=False, week_commencing="W-MON"):       
+    def pivot_table(self, df, index_col, columns, values_col, filters_dict=None, fill_value=0, aggfunc="sum", margins=False, margins_name="Total", datetime_trans_needed=True, date_format="%Y-%m-%d", reverse_header_order=False, fill_missing_weekly_dates=True, week_commencing="W-MON"):       
         """
         Provides the ability to create pivot tables, filtering the data to get to data you want and then pivoting on certain columns
 
         Args:
             df (pandas.DataFrame): The DataFrame containing the data.
             index_col (str): Name of Column for your pivot table to index on
-            columns (str): Name of Columns for your pivot table.
-            values_col (str): Name of Values Columns for your pivot table.
+            columns (str or list): Name of Column(s) for your pivot table. Can be a single column or a list of columns.
+            values_col (str or list): Name of Values Column(s) for your pivot table. Can be a single column or a list of columns.
             filters_dict (dict, optional): Dictionary of conditions for the boolean mask i.e. what to filter your df on to get to your chosen cell. Defaults to None
             fill_value (int, optional): The value to replace nan with. Defaults to 0.
             aggfunc (str, optional): The method on which to aggregate the values column. Defaults to sum.
@@ -514,14 +514,19 @@ class dataprocessing:
         Returns:
             pandas.DataFrame: The pivot table specified
         """
-        
         # Validate inputs
         if index_col not in df.columns:
             raise ValueError(f"index_col '{index_col}' not found in DataFrame.")
-        if columns not in df.columns:
-            raise ValueError(f"columns '{columns}' not found in DataFrame.")
-        if values_col not in df.columns:
-            raise ValueError(f"values_col '{values_col}' not found in DataFrame.")
+
+        columns = [columns] if isinstance(columns, str) else columns
+        for col in columns:
+            if col not in df.columns:
+                raise ValueError(f"columns '{col}' not found in DataFrame.")
+
+        values_col = [values_col] if isinstance(values_col, str) else values_col
+        for col in values_col:
+            if col not in df.columns:
+                raise ValueError(f"values_col '{col}' not found in DataFrame.")
 
         # Apply filters if provided
         if filters_dict:

{imsciences-0.9.5.1 → imsciences-0.9.5.3}/imsciences.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.5.1
+Version: 0.9.5.3
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.9.5.1 → imsciences-0.9.5.3}/setup.py

@@ -8,7 +8,7 @@ def read_md(file_name):
             return f.read()
     return ''
 
-VERSION = '0.9.5.1'
+VERSION = '0.9.5.3'
 DESCRIPTION = 'IMS Data Processing Package'
 LONG_DESCRIPTION = read_md('README.md')