force input/output folders

Author: gsheni

.github/workflows/dryrun.yaml

@@ -10,7 +10,7 @@ concurrency:
   cancel-in-progress: true
 jobs:
   dry_run:
-    environment: dry
+    environment: stage
     runs-on: ubuntu-latest-large
     timeout-minutes: 25
     steps:
@@ -31,17 +31,21 @@ jobs:
         uv run pymetrics collect-pypi \
           --max-days 30 \
           --add-metrics \
+          --output-folder $${{ secrets.PYPI_OUTPUT_FOLDER }} \
           --dry-run
       env:
         PYDRIVE_CREDENTIALS: ${{ secrets.PYDRIVE_CREDENTIALS }}
         BIGQUERY_CREDENTIALS: ${{ secrets.BIGQUERY_CREDENTIALS }}
+        PYPI_OUTPUT_FOLDER: ${{ secrets.PYPI_OUTPUT_FOLDER }}
     - name: Collect Anaconda Downloads - Dry Run
       run: |
         uv run pymetrics collect-anaconda \
           --max-days 90 \
+          --output-folder $${{ secrets.ANACONDA_OUTPUT_FOLDER }} \
           --dry-run
       env:
         PYDRIVE_CREDENTIALS: ${{ secrets.PYDRIVE_CREDENTIALS }}
+        ANACONDA_OUTPUT_FOLDER: ${{ secrets.ANACONDA_OUTPUT_FOLDER }}
     - name: Summarize - Dry Run
       run: |
         uv run pymetrics summarize \

pymetrics/__main__.py

@@ -85,7 +85,6 @@ def _summarize(args):
     summarize_downloads(
         projects=projects,
         vendors=vendors,
-        input_file=args.input_file,
         output_folder=output_folder,
         dry_run=args.dry_run,
         verbose=args.verbose,
@@ -127,7 +126,7 @@ def _get_parser():
     action = parser.add_subparsers(title='action')
     action.required = True
 
-    # collect
+    # collect PyPI
     collect_pypi = action.add_parser(
         'collect-pypi', help='Collect download data from PyPi.', parents=[logging_args]
     )
@@ -137,7 +136,7 @@ def _get_parser():
         '-o',
         '--output-folder',
         type=str,
-        required=False,
+        required=True,
         help=(
             'Path to the folder where data will be stored. It can be a local path or a'
             ' Google Drive folder path in the format gdrive://<folder-id>'
@@ -191,7 +190,7 @@ def _get_parser():
         help='Compute the aggregation metrics and create the corresponding spreadsheets.',
     )
 
-    # collect
+    # summarize
     summarize = action.add_parser(
         'summarize', help='Summarize the downloads data.', parents=[logging_args]
     )
@@ -203,25 +202,18 @@ def _get_parser():
         default='summarize_config.yaml',
         help='Path to the configuration file.',
     )
-    summarize.add_argument(
-        '-i',
-        '--input-file',
-        type=str,
-        default=None,
-        help='Path to the pypi.csv. Default None, which means to use output-folder for pypi.csv',
-    )
     summarize.add_argument(
         '-o',
         '--output-folder',
         type=str,
-        required=False,
+        required=True,
         help=(
-            'Path to the folder where data will be outputted. It can be a local path or a'
+            'Path to the folder where data will be pypi.csv exists. It can be a local path or a'
             ' Google Drive folder path in the format gdrive://<folder-id>'
         ),
     )
 
-    # collect
+    # collect Anaconda
     collect_anaconda = action.add_parser(
         'collect-anaconda', help='Collect download data from Anaconda.', parents=[logging_args]
     )
@@ -237,7 +229,7 @@ def _get_parser():
         '-o',
         '--output-folder',
         type=str,
-        required=False,
+        required=True,
         help=(
             'Path to the folder where data will be outputted. It can be a local path or a'
             ' Google Drive folder path in the format gdrive://<folder-id>'

pymetrics/summarize.py

@@ -142,6 +142,8 @@ def get_previous_pypi_downloads(input_file, output_folder):
     LOGGER.info('Parsing version column to Version class objects')
     if data and 'version' in data.columns:
         data['version'] = data['version'].apply(parse)
+    if not data:
+        data = pd.DataFrame()
     return data
 
 
@@ -223,7 +225,6 @@ def summarize_downloads(
     projects,
     vendors,
     output_folder,
-    input_file=None,
     dry_run=False,
     verbose=False,
 ):