Bump python version and fix workflows

.github/workflows/daily.yaml

@@ -1,18 +1,19 @@
 name: Daily Collection
 
 on:
+  workflow_dispatch:
   schedule:
     - cron:  '0 0 * * *'
 
 jobs:
   collect:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v1
+      uses: actions/setup-python@v5
       with:
-        python-version: 3.8
+        python-version: '3.13'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

.github/workflows/dryrun.yaml

@@ -9,11 +9,11 @@ jobs:
   collect:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v1
+      uses: actions/setup-python@v5
       with:
-        python-version: 3.8
+        python-version: '3.13'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

.github/workflows/lint.yaml

@@ -0,0 +1,23 @@
+name: Style Checks
+
+on:
+  push:
+  pull_request:
+    types: [opened, reopened]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python 3.13
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.13'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install invoke .[dev]
+    - name: Run lint checks
+      run: invoke lint
+

.github/workflows/manual.yaml

@@ -24,11 +24,11 @@ jobs:
   collect:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v1
+      uses: actions/setup-python@v5
       with:
-        python-version: 3.8
+        python-version: '3.13'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

Makefile

@@ -59,11 +59,15 @@ install: clean-build clean-pyc ## install the package to the active Python's sit
 
 .PHONY: install-develop
 install-develop: clean-build clean-pyc ## install the package in editable mode and dependencies for development
-	pip install -r dev-requirements.txt -e .
+	pip install -e .[dev]
 
 
 # LINT TARGETS
 
 .PHONY: lint
 lint: ## check style with flake8 and isort
 	invoke lint
+
+.PHONY: fix-lint
+fix-lint:
+	invoke fix-lint

download_analytics/__main__.py

@@ -71,15 +71,21 @@ def _valid_date(arg):
 def _get_parser():
     # Logging
     logging_args = argparse.ArgumentParser(add_help=False)
-    logging_args.add_argument('-v', '--verbose', action='count', default=0,
-                              help='Be verbose. Use `-vv` for increased verbosity.')
-    logging_args.add_argument('-l', '--logfile',
-                              help='If given, file where the logs will be written.')
+    logging_args.add_argument(
+        '-v',
+        '--verbose',
+        action='count',
+        default=0,
+        help='Be verbose. Use `-vv` for increased verbosity.',
+    )
+    logging_args.add_argument(
+        '-l', '--logfile', help='If given, file where the logs will be written.'
+    )
 
     parser = argparse.ArgumentParser(
         prog='download-analytics',
         description='Download Analytics Command Line Interface',
-        parents=[logging_args]
+        parents=[logging_args],
     )
     parser.set_defaults(action=None)
     action = parser.add_subparsers(title='action')
@@ -90,36 +96,67 @@ def _get_parser():
     collect.set_defaults(action=_collect)
 
     collect.add_argument(
-        '-o', '--output-folder', type=str, required=False,
+        '-o',
+        '--output-folder',
+        type=str,
+        required=False,
         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>'
-        )
+        ),
     )
     collect.add_argument(
-        '-a', '--authentication-credentials', type=str, required=False,
-        help='Path to the GCP (BigQuery) credentials file to use.')
+        '-a',
+        '--authentication-credentials',
+        type=str,
+        required=False,
+        help='Path to the GCP (BigQuery) credentials file to use.',
+    )
     collect.add_argument(
-        '-c', '--config-file', type=str, default='config.yaml',
-        help='Path to the configuration file.')
+        '-c',
+        '--config-file',
+        type=str,
+        default='config.yaml',
+        help='Path to the configuration file.',
+    )
     collect.add_argument(
-        '-p', '--projects', nargs='*',
-        help='List of projects to collect. If not given use the configured ones.')
+        '-p',
+        '--projects',
+        nargs='*',
+        help='List of projects to collect. If not given use the configured ones.',
+    )
     collect.add_argument(
-        '-s', '--start-date', type=_valid_date, required=False,
-        help='Date from which to start pulling data.')
+        '-s',
+        '--start-date',
+        type=_valid_date,
+        required=False,
+        help='Date from which to start pulling data.',
+    )
     collect.add_argument(
-        '-m', '--max-days', type=int, required=False,
-        help='Max days of data to pull if start-date is not given.')
+        '-m',
+        '--max-days',
+        type=int,
+        required=False,
+        help='Max days of data to pull if start-date is not given.',
+    )
     collect.add_argument(
-        '-d', '--dry-run', action='store_true',
-        help='Do not run the actual query, only simulate it.')
+        '-d',
+        '--dry-run',
+        action='store_true',
+        help='Do not run the actual query, only simulate it.',
+    )
     collect.add_argument(
-        '-f', '--force', action='store_true',
-        help='Force the download even if the data already exists or there is a gap')
+        '-f',
+        '--force',
+        action='store_true',
+        help='Force the download even if the data already exists or there is a gap',
+    )
     collect.add_argument(
-        '-M', '--add-metrics', action='store_true',
-        help='Compute the aggregation metrics and create the corresponding spreadsheets.')
+        '-M',
+        '--add-metrics',
+        action='store_true',
+        help='Compute the aggregation metrics and create the corresponding spreadsheets.',
+    )
 
     return parser
 

download_analytics/bq.py

@@ -30,7 +30,10 @@ def _get_bq_client(credentials_file):
         scopes=['https://www.googleapis.com/auth/cloud-platform'],
     )
 
-    return bigquery.Client(credentials=credentials, project=credentials.project_id,)
+    return bigquery.Client(
+        credentials=credentials,
+        project=credentials.project_id,
+    )
 
 
 def run_query(query, dry_run=False, credentials_file=None):
@@ -41,14 +44,14 @@ def run_query(query, dry_run=False, credentials_file=None):
 
     job_config = bigquery.QueryJobConfig(dry_run=True, use_query_cache=False)
     dry_run_job = client.query(query, job_config=job_config)
-    LOGGER.info('Estimated processed GBs: %.2f', dry_run_job.total_bytes_processed / 1024 ** 3)
+    LOGGER.info('Estimated processed GBs: %.2f', dry_run_job.total_bytes_processed / 1024**3)
 
     if dry_run:
         return None
 
     query_job = client.query(query)
     data = query_job.to_dataframe()
-    LOGGER.info('Total processed GBs: %.2f', query_job.total_bytes_processed / 1024 ** 3)
-    LOGGER.info('Total billed GBs: %.2f', query_job.total_bytes_billed / 1024 ** 3)
+    LOGGER.info('Total processed GBs: %.2f', query_job.total_bytes_processed / 1024**3)
+    LOGGER.info('Total billed GBs: %.2f', query_job.total_bytes_billed / 1024**3)
 
     return data

download_analytics/drive.py

@@ -91,11 +91,7 @@ def upload(content, filename, folder, convert=False):
     except FileNotFoundError:
         file_config = {
             'title': filename,
-            'parents': [
-                {
-                    'id': folder
-                }
-            ],
+            'parents': [{'id': folder}],
         }
         drive_file = drive.CreateFile(file_config)
 

download_analytics/main.py

@@ -9,8 +9,16 @@
 LOGGER = logging.getLogger(__name__)
 
 
-def collect_downloads(projects, output_folder, start_date=None, max_days=1, credentials_file=None,
-                      dry_run=False, force=False, add_metrics=True):
+def collect_downloads(
+    projects,
+    output_folder,
+    start_date=None,
+    max_days=1,
+    credentials_file=None,
+    dry_run=False,
+    force=False,
+    add_metrics=True,
+):
     """Pull data about the downloads of a list of projects.
 
     Args:
@@ -49,7 +57,7 @@ def collect_downloads(projects, output_folder, start_date=None, max_days=1, cred
         max_days=max_days,
         credentials_file=credentials_file,
         dry_run=dry_run,
-        force=force
+        force=force,
     )
 
     if pypi_downloads.empty:

download_analytics/metrics.py

@@ -3,6 +3,8 @@
 import logging
 import re
 
+import pandas as pd
+
 from download_analytics.output import create_spreadsheet
 
 LOGGER = logging.getLogger(__name__)
@@ -35,24 +37,21 @@ def _historical_groupby(downloads, groupbys=None):
 
     for groupby in groupbys:
         grouped = downloads.groupby([year_month, groupby])
-        grouped_sizes = grouped.size().unstack(-1)
+        grouped_sizes = grouped.size().unstack(-1)  # noqa: PD010
         if len(groupbys) > 1:
             grouped_sizes.columns = f"{groupby}='" + grouped_sizes.columns + "'"
 
         base[grouped_sizes.columns] = grouped_sizes.fillna(0)
 
     totals = base.sum()
     totals.name = 'total'
-    base = base.append(totals)
+    base = pd.concat([base, totals], ignore_index=True)
 
     return base.reset_index().iloc[::-1]
 
 
 def _get_sheet_name(column):
-    words = [
-        f'{word[0].upper()}{word[1:]}'
-        for word in column.split('_')
-    ]
+    words = [f'{word[0].upper()}{word[1:]}' for word in column.split('_')]
     return ' '.join(['By'] + words)
 
 
@@ -121,7 +120,7 @@ def _version_element_order_key(version):
                 # while it shouldn't enter the `if`.
                 pass
 
-    components.append(last_component[len(last_numeric):])
+    components.append(last_component[len(last_numeric) :])
 
     return components
 
@@ -133,7 +132,7 @@ def _version_order_key(version_column):
 def _mangle_columns(downloads):
     downloads = downloads.rename(columns=RENAME_COLUMNS)
     downloads['full_python_version'] = downloads['python_version']
-    downloads['python_version'] = downloads['python_version'].str.rsplit('.', 1).str[0]
+    downloads['python_version'] = downloads['python_version'].str.rsplit('.', n=1).str[0]
     downloads['project_version'] = downloads['project'] + '-' + downloads['version']
     downloads['distro_version'] = downloads['distro_name'] + ' ' + downloads['distro_version']
     downloads['distro_kernel'] = downloads['distro_version'] + ' - ' + downloads['distro_kernel']
@@ -150,9 +149,7 @@ def compute_metrics(downloads, output_path=None):
     downloads = _mangle_columns(downloads)
 
     LOGGER.debug('Aggregating by month')
-    sheets = {
-        'By Month': _by_month(downloads)
-    }
+    sheets = {'By Month': _by_month(downloads)}
 
     for column in GROUPBY_COLUMNS:
         name = _get_sheet_name(column)