Create manual merge of ALN files after download.yml

.github/workflows/manual merge of ALN files after download.yml

@@ -0,0 +1,61 @@
+---
+name: Merge and Standardize CSV Files
+
+on:
+  workflow_dispatch:
+
+jobs:
+  merge_csvs:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v3
+
+      - name: Set Up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.x'
+
+      - name: Install Dependencies
+        run: pip install pandas
+
+      - name: Merge and Standardize CSV Files
+        run: |
+          python -c "
+          import os
+          import pandas as pd
+          from datetime import datetime
+          import glob
+
+          folder = './backend/schemas/source/data/ALN raw downloads for CFDA lookup files'
+          date_suffix = datetime.now().strftime('%Y%m%d')
+          output_file = f'{os.path.dirname(folder)}/cfda-lookup-{date_suffix}.csv'
+
+          csv_files = glob.glob(f'{folder}/*.csv')
+          if not csv_files:
+              print('No data found in the input files.')
+              exit(1)
+
+          all_data = [pd.read_csv(f) for f in csv_files]
+          all_columns = pd.concat(all_data, ignore_index=True).columns.unique()
+          standardized_data = [df.reindex(columns=all_columns, fill_value=None) for df in all_data]
+
+          column_mapping = {
+              'Title': 'Program Title',
+              'Assistance Listings Number': 'Program Number',
+              'Date Published': 'Date Published',
+              'Department/Ind. Agency': 'Department/Ind. Agency',
+              'Funded': 'Funded',
+              'Last Date Modified': 'Last Date Modified',
+              'POC Information': 'POC Information',
+              'Related Federal Assistance': 'Related Federal Assistance',
+              'Sub-Tier': 'Sub-Tier',
+              'Types of Assistance': 'Types of Assistance'
+          }
+
+          reordered_data = pd.concat(standardized_data, ignore_index=True)
+          reordered_data = reordered_data.rename(columns=column_mapping)
+
+          reordered_data.to_csv(output_file, index=False, encoding='utf-8')
+          print(f'Data from all CSV files in {folder} has been merged, standardized, and saved to {output_file} with UTF-8 encoding.')
+          "