imsciences 0.9.5__py3-none-any.whl → 0.9.5.2__py3-none-any.whl

imsciences/geo.py

@@ -199,14 +199,14 @@ class geoprocessing:
 
         return analysis_df
     
-    def process_city_analysis(self, raw_df, spend_df, 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_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.
+            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.
             response_column (str): Column name to be used as the response metric.
@@ -215,6 +215,33 @@ class geoprocessing:
             pd.DataFrame: Processed DataFrame.
         """
         import pandas as pd
+        import os
+
+        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(data)
+            elif ext in ['.xlsx', '.xls']:
+                return pd.read_excel(data)
+            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 data
+        raw_df = read_file(raw_data)
+        spend_df = read_file(spend_data)
 
         # Ensure necessary columns are present
         required_columns = {'date', 'city', response_column}
@@ -245,6 +272,6 @@ class geoprocessing:
         merged_df['cost'] = merged_df['cost'].fillna(0)
 
         # Save the final output
-        merged_df.to_csv(output_path, index=False)
+        write_file(merged_df, output_path)
 
-        return merged_df
+        return merged_df

{imsciences-0.9.5.dist-info → imsciences-0.9.5.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.5
+Version: 0.9.5.2
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.9.5.dist-info → imsciences-0.9.5.2.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=7HATwnpJcxl5xZLK_MJw8slPt5P-JaQ91u3LaTc57g4,12422
+imsciences/geo.py,sha256=J8AkLk1Nyty3VBkPFqcseXjtlSvXVNkHW_nymERz3nA,13472
 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-0.9.5.dist-info/LICENSE.txt,sha256=lVq2QwcExPX4Kl2DHeEkRrikuItcDB1Pr7yF7FQ8_z8,1108
-imsciences-0.9.5.dist-info/METADATA,sha256=ir4uP9YbIpWix7UP9dmWcCCJOi3O7URKY-DmuR4cNW4,16992
-imsciences-0.9.5.dist-info/PKG-INFO-IMS-24Ltp-3,sha256=yqZbigwHjnYoqyI81PGz_AeofRFfOrwH_Vyawyef-mg,854
-imsciences-0.9.5.dist-info/WHEEL,sha256=ixB2d4u7mugx_bCBycvM9OzZ5yD7NmPXFRtKlORZS2Y,91
-imsciences-0.9.5.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
-imsciences-0.9.5.dist-info/RECORD,,
+imsciences-0.9.5.2.dist-info/LICENSE.txt,sha256=lVq2QwcExPX4Kl2DHeEkRrikuItcDB1Pr7yF7FQ8_z8,1108
+imsciences-0.9.5.2.dist-info/METADATA,sha256=Zvfy7-y18I-ZFj4aTL18nJOPp57k4uwj5p5ajze5GwI,16994
+imsciences-0.9.5.2.dist-info/PKG-INFO-IMS-24Ltp-3,sha256=yqZbigwHjnYoqyI81PGz_AeofRFfOrwH_Vyawyef-mg,854
+imsciences-0.9.5.2.dist-info/WHEEL,sha256=ixB2d4u7mugx_bCBycvM9OzZ5yD7NmPXFRtKlORZS2Y,91
+imsciences-0.9.5.2.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
+imsciences-0.9.5.2.dist-info/RECORD,,