imsciences 0.9.4__tar.gz → 0.9.5__tar.gz

{imsciences-0.9.4 → imsciences-0.9.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.4
+Version: 0.9.5
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com
@@ -236,6 +236,11 @@ Table of Contents
 - **Usage**: `process_itv_analysis(self, raw_df, itv_path, cities_path, media_spend_path, output_path, group1, group2)`
 - **Example**: `process_itv_analysis(df, 'itv regional mapping.csv', 'Geo_Mappings_with_Coordinates.xlsx', 'IMS.xlsx', 'itv_for_test_analysis_itvx.csv', ['West', 'Westcountry', 'Tyne Tees'], ['Central Scotland', 'North Scotland'])`
 
+## 3. `process_city_analysis`
+- **Description**: Processes city-level data for geo experiments by grouping user metrics, merging with media spend data, and saving the result.
+- **Usage**: `process_city_analysis(raw_df, spend_df, output_path, group1, group2, response_column)`
+- **Example**: `process_city_analysis(df, spend, output, ['Barnsley'], ['Aberdeen'], 'newUsers')`
+
 ---
 
 ## Data Visualisations

{imsciences-0.9.4 → imsciences-0.9.5}/README.md

@@ -211,6 +211,11 @@ Table of Contents
 - **Usage**: `process_itv_analysis(self, raw_df, itv_path, cities_path, media_spend_path, output_path, group1, group2)`
 - **Example**: `process_itv_analysis(df, 'itv regional mapping.csv', 'Geo_Mappings_with_Coordinates.xlsx', 'IMS.xlsx', 'itv_for_test_analysis_itvx.csv', ['West', 'Westcountry', 'Tyne Tees'], ['Central Scotland', 'North Scotland'])`
 
+## 3. `process_city_analysis`
+- **Description**: Processes city-level data for geo experiments by grouping user metrics, merging with media spend data, and saving the result.
+- **Usage**: `process_city_analysis(raw_df, spend_df, output_path, group1, group2, response_column)`
+- **Example**: `process_city_analysis(df, spend, output, ['Barnsley'], ['Aberdeen'], 'newUsers')`
+
 ---
 
 ## Data Visualisations

{imsciences-0.9.4 → imsciences-0.9.5}/imsciences/geo.py

@@ -30,6 +30,11 @@ class geoprocessing:
         print("   - Usage: process_itv_analysis(self, raw_df, itv_path, cities_path, media_spend_path, output_path, group1, group2)")
         print("   - Example:process_itv_analysis(df,'itv regional mapping.csv', 'Geo_Mappings_with_Coordinates.xlsx', 'IMS.xlsx', 'itv_for_test_analysis_itvx.csv', ['West', 'Westcountry', 'Tyne Tees'], ['Central Scotland', 'North Scotland'])")
         
+        print("\n3. process_city_analysis")
+        print("   - Description: Processes city-level data for geo experiments by grouping user metrics, merging with media spend data, and saving the result.")
+        print("   - Usage: process_city_analysis(raw_df, spend_df, output_path, group1, group2, response_column)")
+        print("   - Example:process_city_analysis(df, spend, output, ['Barnsley'], ['Aberdeen'], 'newUsers')")
+                
     def pull_ga(self, credentials_file, property_id, start_date, country, metrics):
         """
         Pulls Google Analytics data using the BetaAnalyticsDataClient.
@@ -192,4 +197,54 @@ class geoprocessing:
         # Save the final output
         analysis_df.to_csv(output_path, index=False)
 
-        return analysis_df
+        return analysis_df
+    
+    def process_city_analysis(self, raw_df, spend_df, output_path, group1, group2, response_column):
+        """
+        Process city analysis by grouping data, analyzing user metrics, and merging with spend data.
+
+        Parameters:
+            raw_df (pd.DataFrame): Raw input data containing at least 'date' and 'city' columns, along with the specified response column.
+            spend_df (pd.DataFrame): DataFrame containing media spend data with 'date', 'geo', and 'cost' columns. Costs should be numeric.
+            output_path (str): Path to save the final output CSV file.
+            group1 (list): List of city regions for group 1.
+            group2 (list): List of city regions for group 2.
+            response_column (str): Column name to be used as the response metric.
+
+        Returns:
+            pd.DataFrame: Processed DataFrame.
+        """
+        import pandas as pd
+
+        # Ensure necessary columns are present
+        required_columns = {'date', 'city', response_column}
+        if not required_columns.issubset(raw_df.columns):
+            raise ValueError(f"Input DataFrame must contain the following columns: {required_columns}")
+
+        spend_required_columns = {'date', 'geo', 'cost'}
+        if not spend_required_columns.issubset(spend_df.columns):
+            raise ValueError(f"Spend DataFrame must contain the following columns: {spend_required_columns}")
+
+        # Convert cost column to numeric after stripping currency symbols and commas
+        spend_df['cost'] = spend_df['cost'].replace('[^\d.]', '', regex=True).astype(float)
+
+        # Rename and process input DataFrame
+        raw_df = raw_df.rename(columns={'city': 'geo', response_column: 'response'})
+
+        # Filter and group data
+        filtered_df = raw_df[raw_df['geo'].isin(group1 + group2)].copy()
+
+        grouped_df = filtered_df.groupby(['date', 'geo'], as_index=False).agg({'response': 'sum'})
+
+        assignment_map = {city: 1 for city in group1}
+        assignment_map.update({city: 2 for city in group2})
+        grouped_df['assignment'] = grouped_df['geo'].map(assignment_map)
+
+        # Merge with spend data
+        merged_df = pd.merge(grouped_df, spend_df, on=['date', 'geo'], how='left')
+        merged_df['cost'] = merged_df['cost'].fillna(0)
+
+        # Save the final output
+        merged_df.to_csv(output_path, index=False)
+
+        return merged_df

{imsciences-0.9.4 → imsciences-0.9.5}/imsciences.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.4
+Version: 0.9.5
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com
@@ -236,6 +236,11 @@ Table of Contents
 - **Usage**: `process_itv_analysis(self, raw_df, itv_path, cities_path, media_spend_path, output_path, group1, group2)`
 - **Example**: `process_itv_analysis(df, 'itv regional mapping.csv', 'Geo_Mappings_with_Coordinates.xlsx', 'IMS.xlsx', 'itv_for_test_analysis_itvx.csv', ['West', 'Westcountry', 'Tyne Tees'], ['Central Scotland', 'North Scotland'])`
 
+## 3. `process_city_analysis`
+- **Description**: Processes city-level data for geo experiments by grouping user metrics, merging with media spend data, and saving the result.
+- **Usage**: `process_city_analysis(raw_df, spend_df, output_path, group1, group2, response_column)`
+- **Example**: `process_city_analysis(df, spend, output, ['Barnsley'], ['Aberdeen'], 'newUsers')`
+
 ---
 
 ## Data Visualisations

{imsciences-0.9.4 → imsciences-0.9.5}/setup.py

@@ -8,7 +8,7 @@ def read_md(file_name):
             return f.read()
     return ''
 
-VERSION = '0.9.4'
+VERSION = '0.9.5'
 DESCRIPTION = 'IMS Data Processing Package'
 LONG_DESCRIPTION = read_md('README.md')