imsciences 0.9.4__py3-none-any.whl → 0.9.5.1__py3-none-any.whl

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 +197,79 @@ 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_input_path, spend_input_path, 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.
+            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.
+            response_column (str): Column name to be used as the response metric.
+
+        Returns:
+            pd.DataFrame: Processed DataFrame.
+        """
+        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()
+            if ext == '.csv':
+                return pd.read_csv(file_path)
+            elif ext in ['.xlsx', '.xls']:
+                return pd.read_excel(file_path)
+            else:
+                raise ValueError("Unsupported file type. Please use a CSV or XLSX file.")
+
+        def write_file(df, file_path):
+            """Helper function to write DataFrame to CSV or XLSX files."""
+            ext = os.path.splitext(file_path)[1].lower()
+            if ext == '.csv':
+                df.to_csv(file_path, index=False)
+            elif ext in ['.xlsx', '.xls']:
+                df.to_excel(file_path, index=False, engine='openpyxl')
+            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)
+
+        # 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
+        write_file(merged_df, output_path)
+
+        return merged_df

{imsciences-0.9.4.dist-info → imsciences-0.9.5.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.4
+Version: 0.9.5.1
 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.dist-info → imsciences-0.9.5.1.dist-info}/RECORD

@@ -5,7 +5,7 @@ imsciences/__init__.py,sha256=_HuYeLbDMTdt7GpKI4r6-d7yRPZgcAQ7yOW0-ydR2Yo,117
 imsciences/datafunctions-IMS-24Ltp-3.py,sha256=3Snv-0iE_03StmyjtT-riOU9f4v8TaJWLoyZLJp6l8Y,141406
 imsciences/datafunctions.py,sha256=WZrXNLO-SYrCuFt0pAbha74psMOZPY7meWJ7yWEbRpk,169953
 imsciences/datapull.py,sha256=TPY0LDgOkcKTBk8OekbD0Grg5x0SomAK2dZ7MuT6X1E,19000
-imsciences/geo.py,sha256=bhtA8s4enWgT8oxyVP6inUgo_rvAEyZY-K6XnOizhkE,9530
+imsciences/geo.py,sha256=kBFc4_DEyQDQlnGnCc09qcydoaW5Lium6kTSdz3li3c,13526
 imsciences/mmm.py,sha256=M91Qs_ijtY4EytTo1rruWCOVGnV7DMVaYUhNpP1NVNc,73920
 imsciences/pull.py,sha256=bGz8B7bBQ5b9hrx3ipCFTWl_eebEb7rPL4dANKiVWTY,74015
 imsciences/unittesting.py,sha256=DYGqVCsZHrs_tZ-EXDW8q8CdlcsTnG8HsnmWjEE521c,45691
@@ -14,9 +14,9 @@ imsciencesdataprocessing/__init__.py,sha256=quSwsLs6IuLoA5Rzi0ZD40xZaQudwDteF7_a
 imsciencesdataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
 imsdataprocessing/__init__.py,sha256=quSwsLs6IuLoA5Rzi0ZD40xZaQudwDteF7_ai9JfTPk,32
 imsdataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
-imsciences-0.9.4.dist-info/LICENSE.txt,sha256=lVq2QwcExPX4Kl2DHeEkRrikuItcDB1Pr7yF7FQ8_z8,1108
-imsciences-0.9.4.dist-info/METADATA,sha256=KrKgJEhrswsrqBbCGkVu6l_k4B4SWW9DrOqS8mbF5IA,16612
-imsciences-0.9.4.dist-info/PKG-INFO-IMS-24Ltp-3,sha256=yqZbigwHjnYoqyI81PGz_AeofRFfOrwH_Vyawyef-mg,854
-imsciences-0.9.4.dist-info/WHEEL,sha256=ixB2d4u7mugx_bCBycvM9OzZ5yD7NmPXFRtKlORZS2Y,91
-imsciences-0.9.4.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
-imsciences-0.9.4.dist-info/RECORD,,
+imsciences-0.9.5.1.dist-info/LICENSE.txt,sha256=lVq2QwcExPX4Kl2DHeEkRrikuItcDB1Pr7yF7FQ8_z8,1108
+imsciences-0.9.5.1.dist-info/METADATA,sha256=aTHbZ8Hr_JNbE_UQwbP5CSJtPM-BHNmHnRUn9wlbQXE,16994
+imsciences-0.9.5.1.dist-info/PKG-INFO-IMS-24Ltp-3,sha256=yqZbigwHjnYoqyI81PGz_AeofRFfOrwH_Vyawyef-mg,854
+imsciences-0.9.5.1.dist-info/WHEEL,sha256=ixB2d4u7mugx_bCBycvM9OzZ5yD7NmPXFRtKlORZS2Y,91
+imsciences-0.9.5.1.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
+imsciences-0.9.5.1.dist-info/RECORD,,