Rename files and library to gitmetrics

.github/workflows/daily_collection.yaml

@@ -25,9 +25,9 @@ jobs:
       run: |
         uv pip install -U pip
         uv pip install .
-    - name: Collect Github Data
+    - name: Collect GitHub Data
       run: |
-        uv run github-analytics collect -v -q -t ${{ secrets.GITHUB_TOKEN }} -m -c daily.yaml
+        uv run gitmetrics collect -v -q -t ${{ secrets.GITHUB_TOKEN }} -m -c daily.yaml
       env:
         PYDRIVE_CREDENTIALS: ${{ secrets.PYDRIVE_CREDENTIALS }}
 
@@ -47,6 +47,6 @@ jobs:
         uv pip install -U pip
         uv pip install .[dev]
     - name: Slack alert if failure
-      run: python -m github_analytics.slack_utils -r ${{ github.run_id }} -c ${{ github.event.inputs.slack_channel || 'sdv-alerts' }}
+      run: python -m gitmetrics.slack_utils -r ${{ github.run_id }} -c ${{ github.event.inputs.slack_channel || 'sdv-alerts' }}
       env:
         SLACK_TOKEN: ${{ secrets.SLACK_TOKEN }}

.github/workflows/daily_summarize.yaml

@@ -28,7 +28,7 @@ jobs:
         uv pip install .
     - name: Run Summarize
       run: |
-        uv run github-analytics summarize \
+        uv run gitmetrics summarize \
           --input-folder gdrive://1ZvsuVbFAUk3BN-n6Pv_lUBLwviHZSxM2
       env:
         PYDRIVE_CREDENTIALS: ${{ secrets.PYDRIVE_CREDENTIALS }}
@@ -66,9 +66,9 @@ jobs:
         uv pip install .[dev]
     - name: Slack alert if failure
       run: |
-        uv run python -m github_analytics.slack_utils \
+        uv run python -m gitmetrics.slack_utils \
         -r ${{ github.run_id }} \
         -c ${{ github.event.inputs.slack_channel || 'sdv-alerts' }} \
-        -m 'Summarize GitHub Analytics build failed :fire: :dumpster-fire: :fire:'
+        -m 'Summarize GitMetrics build failed :fire: :dumpster-fire: :fire:'
       env:
         SLACK_TOKEN: ${{ secrets.SLACK_TOKEN }}

.github/workflows/manual.yaml

@@ -33,9 +33,9 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         python -m pip install .
-    - name: Collect Github Data
+    - name: Collect GitHub Data
       run: |
-        github-analytics collect -v -q \
+        gitmetrics collect -v -q \
           -t ${{ secrets.GITHUB_TOKEN }} \
           -p ${{ github.event.inputs.project }} \
           -r ${{ github.event.inputs.repositories }} \

.github/workflows/traffic_collection.yaml

@@ -12,7 +12,7 @@ on:
     - cron: "0 0 */14 * *"  # Runs every 14 days at midnight UTC
 
 jobs:
-  collect_traffic:
+  daily_traffic_collection:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v4
@@ -25,13 +25,13 @@ jobs:
       run: |
         uv pip install -U pip
         uv pip install .
-    - name: Collect Github Traffic Data
+    - name: Collect GitHub Traffic Data
       run: |
-        uv run github-analytics traffic -v -t ${{ secrets.GH_TRAFFIC_TOKEN }} -c traffic_config.yaml
+        uv run gitmetrics traffic -v -t ${{ secrets.GH_TRAFFIC_TOKEN }} -c traffic_config.yaml
       env:
         PYDRIVE_CREDENTIALS: ${{ secrets.PYDRIVE_CREDENTIALS }}
   alert:
-    needs: [daily_github_collection]
+    needs: [daily_traffic_collection]
     runs-on: ubuntu-latest
     if: failure()
     steps:
@@ -46,6 +46,6 @@ jobs:
         uv pip install -U pip
         uv pip install .[dev]
     - name: Slack alert if failure
-      run: python -m github_analytics.slack_utils -r ${{ github.run_id }} -c ${{ github.event.inputs.slack_channel || 'sdv-alerts' }}
+      run: python -m gitmetrics.slack_utils -r ${{ github.run_id }} -c ${{ github.event.inputs.slack_channel || 'sdv-alerts' }}
       env:
         SLACK_TOKEN: ${{ secrets.SLACK_TOKEN }}

.github/workflows/weekly_collection.yaml

@@ -27,12 +27,12 @@ jobs:
         uv pip install .
     - name: Collect GitHub Data
       run: |
-        uv run github-analytics collect -v -q -t ${{ secrets.GITHUB_TOKEN }} -m -c weekly.yaml
+        uv run gitmetrics collect -v -q -t ${{ secrets.GITHUB_TOKEN }} -m -c weekly.yaml
       env:
         PYDRIVE_CREDENTIALS: ${{ secrets.PYDRIVE_CREDENTIALS }}
     - name: Consolidate GitHub Data
       run: |
-        uv run github-analytics consolidate -v -c weekly.yaml
+        uv run gitmetrics consolidate -v -c weekly.yaml
       env:
         PYDRIVE_CREDENTIALS: ${{ secrets.PYDRIVE_CREDENTIALS }}
   alert:
@@ -51,6 +51,6 @@ jobs:
         uv pip install -U pip
         uv pip install .[dev]
     - name: Slack alert if failure
-      run: python -m github_analytics.slack_utils -r ${{ github.run_id }} -c ${{ github.event.inputs.slack_channel || 'sdv-alerts' }}
+      run: python -m gitmetrics.slack_utils -r ${{ github.run_id }} -c ${{ github.event.inputs.slack_channel || 'sdv-alerts' }}
       env:
         SLACK_TOKEN: ${{ secrets.SLACK_TOKEN }}

.gitignore

@@ -3,6 +3,7 @@ bigquery_creds.json
 client_secrets.json
 credentials.json
 sdv-dev.github.io/*
+uv.lock
 
 notebooks
 *.xlsx

CONFIGURATION.md

@@ -1,14 +1,14 @@
-# Github Analytics Configuration
+# GitMetrics Configuration
 
-The Github Analytics script can be configured using a YAML file that indicates which repositories
+The GitMetrics script can be configured using a YAML file that indicates which repositories
 to collect and where to store the collected data.
 
-Additionally, [Github Actions Workflows](.github/workflows) are being used to trigger the
+Additionally, [GitMetrics Workflows](.github/workflows) are being used to trigger the
 collection of such projects either manually or on a scheduled basis.
 
 ## Configuration file format
 
-The configuration file for `github-analytics` must have the following contents:
+The configuration file for `gitmetrics` must have the following contents:
 
 * `output_folder`: Folder where results will be written. Can be a Google Drive in the format
   gdrive://<folder-name>
@@ -48,7 +48,7 @@ projects:
 ### Adding an entire organization
 
 Optionally, an organization or user name can be added to the confiuration instead of the
-individual repositories, and then `github-analytics` will translate that into the list of
+individual repositories, and then `gitmetrics` will translate that into the list of
 repositories owned by that user or organization *which are not forks of other repositories*.
 
 For example, this configuration file would include all the repositories listed above,
@@ -78,12 +78,12 @@ projects:
 
 ## Default Configuration File
 
-By default, Github Analytics collects the projects configured in the [config.yaml](config.yaml)
+By default, GitMetrics collects the projects configured in the [config.yaml](config.yaml)
 file included in the project. However, passing a different configuration file when running the
 command line script is possible via the `-c` flag, as shown in the example above:
 
 ```bash
-$ github-analytics collect -c my_config_file.yaml ...
+$ gitmetrics collect -c my_config_file.yaml ...
 ```
 
 ### Importing other configuration files
@@ -142,11 +142,11 @@ projects:
 
 ## Daily and Weekly Collection
 
-Github Analytics is configured to collect data daily and weekly via the
+GitMetrics is configured to collect data daily and weekly via the
 [.github/workflow/daily.yaml](.github/workflow/daily.yaml) and [.github/workflow/weekly.yaml](
-.github/workflow/weekly.yaml) Github Action Workflows.
+.github/workflow/weekly.yaml) GitHub Action Workflows.
 
-These workflows are configured to execute the `github-analytics collect` command using the
+These workflows are configured to execute the `gitmetrics collect` command using the
 [daily.yaml](daily.yaml) and [weekly.yaml](weekly.yaml) configuration files respectively,
 which:
 - Import the [config.yaml](config.yaml) file, where all the project repositories are listed

README.md

@@ -1,30 +1,30 @@
-# Github Analytics
+# GitMetrics
 
-Scripts to extract multiple metrics from Github Projects.
+Scripts to extract multiple metrics from GitHub Projects.
 
 ## Install
 
 ```bash
-pip install git+ssh://[email protected]/datacebo/github-analytics
+pip install git+ssh://[email protected]/datacebo/gitmetrics
 ```
 
 ### Development
 
 For development, clone the repository and install `dev-requirements.txt`:
 
 ```bash
-git clone [email protected]:datacebo/github-analytics
-cd github-analytics
-pip install -r dev-requirements.txt
+git clone [email protected]:datacebo/gitmetrics
+cd gitmetrics
+pip install -e .[test,dev]
 ```
 
 # Local Usage
 
-To collect metrics from github by running `github-analytics` on your computer you need to provide:
+To collect metrics from GitHub by running `gitmetrics` on your computer you need to provide:
 
-1. A Github Token. Documentation about how to create a Personal Access Token can be found
+1. A GitHub Token. Documentation about how to create a Personal Access Token can be found
    [here](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/creating-a-personal-access-token)
-2. A list of Github Repositories for which to collect the metrics. The repositories need
+2. A list of GitHub Repositories for which to collect the metrics. The repositories need
    to be given as `{org-name}/{repo-name}`, like `sdv-dev/SDV`.
 3. (Optional) A filename where the output will be stored. If a name containing the `.xlsx`
    extension is given (like `path/to/my-filename.xlsx`), it will be used as provided.
@@ -36,44 +36,44 @@ To collect metrics from github by running `github-analytics` on your computer yo
 ## Python Interface
 
 In order to run the collection script from python, the `collect_project_metrics` function
-needs to be imported from the `github_analytics` package and executed passing the values
+needs to be imported from the `gitmetrics` package and executed passing the values
 indicated above.
 
 **NOTE**: For detailed output, logging must be enabled as shown in the example below.
 
 ```python3
 >>> import logging
 >>> logging.basicConfig(level=logging.INFO)
->>> from github_analytics import collect_project_metrics
+>>> from gitmetrics import collect_project_metrics
 >>> repositories = ['sdv-dev/RDT', 'sdv-dev/SDV', 'sdv-dev/Copulas', 'sdv-dev/CTGAN']
 >>> output_name = 'sdv-dev'
 >>> token = '<my-github-token>'
 >>> collect_project_metrics(token, repositories, output_name)
-INFO:github_analytics.main:Getting information for repository sdv-dev/RDT
+INFO:gitmetrics.main:Getting information for repository sdv-dev/RDT
 100%|███████████████████████████████████████████████████████████████| 143/143 [00:00<00:00, 195.00it/s]
 100%|███████████████████████████████████████████████████████████████| 182/182 [00:00<00:00, 364.64it/s]
 100%|███████████████████████████████████████████████████████████████| 37/37 [00:00<00:00, 91020.09it/s]
-INFO:github_analytics.main:Getting information for repository sdv-dev/SDV
+INFO:gitmetrics.main:Getting information for repository sdv-dev/SDV
 100%|███████████████████████████████████████████████████████████████| 389/389 [00:02<00:00, 193.20it/s]
 100%|███████████████████████████████████████████████████████████████| 219/219 [00:00<00:00, 231.17it/s]
 100%|███████████████████████████████████████████████████████████████| 561/561 [00:03<00:00, 158.39it/s]
-INFO:github_analytics.main:Getting information for repository sdv-dev/Copulas
+INFO:gitmetrics.main:Getting information for repository sdv-dev/Copulas
 100%|███████████████████████████████████████████████████████████████| 138/138 [00:00<00:00, 333.27it/s]
 100%|███████████████████████████████████████████████████████████████| 143/143 [00:00<00:00, 287.29it/s]
 100%|███████████████████████████████████████████████████████████████| 245/245 [00:01<00:00, 204.88it/s]
-INFO:github_analytics.main:Getting information for repository sdv-dev/CTGAN
+INFO:gitmetrics.main:Getting information for repository sdv-dev/CTGAN
 100%|███████████████████████████████████████████████████████████████| 113/113 [00:00<00:00, 287.26it/s]
 100%|██████████████████████████████████████████████████████████████| 64/64 [00:00<00:00, 134824.44it/s]
 100%|███████████████████████████████████████████████████████████████| 498/498 [00:02<00:00, 171.11it/s]
-INFO:github_analytics.main:Getting 164 missing users
+INFO:gitmetrics.main:Getting 164 missing users
  99%|██████████████████████████████████████████████████████████████▌| 163/164 [00:01<00:00, 121.99it/s]
-INFO:github_analytics.output:Creating file github-metrics-sdv-dev-2021-11-12.xlsx
+INFO:gitmetrics.output:Creating file github-metrics-sdv-dev-2021-11-12.xlsx
 ```
 
 
 ## Command Line Interface
 
-In order to run the collection script from the command line, the `github-analytics collect` command
+In order to run the collection script from the command line, the `gitmetrics collect` command
 must be called passing the following optional arguments:
 
 - `-c / --config-file CONFIG_FILE`: Path to the config file to use. Defaults to `config.yaml`.
@@ -91,13 +91,13 @@ must be called passing the following optional arguments:
   spreadsheet.
 - `-n / --not-incremental`: If indicated, collect data from scratch instead of doing it
   incrementally over the existing data.
-- `-t / --token`: Github token to use. If not given, it will be requested in a prompt.
+- `-t / --token`: GitHub token to use. If not given, it will be requested in a prompt.
 - `-l / --logfile LOGFILE`: Write logs to the indicated logfile.
 - `-v / --verbose`: Be more verbose.
 
 ```bash
-$ github-analytics github -p sdv-dev -c config.yaml
-Please input your Github Token: <my-github-token>
+$ gitmetrics github -p sdv-dev -c config.yaml
+Please input your GitHub Token: <my-github-token>
 2021-11-12 15:42:43,100 - INFO - Getting information for repository sdv-dev/RDT
 100%|███████████████████████████████████████████████████████████████| 143/143 [00:00<00:00, 300.87it/s]
 100%|███████████████████████████████████████████████████████████████| 182/182 [00:00<00:00, 324.25it/s]
@@ -144,7 +144,7 @@ aggregation metrics for the entire project.
 
 ## Google Drive Integration
 
-Github Analytics is capable of reading and writing results in Google Spreadsheets.
+GitMetrics is capable of reading and writing results in Google Spreadsheets.
 
 For this to work, the following things are required:
 
@@ -156,11 +156,11 @@ For this to work, the following things are required:
    the corresponding `settings.yaml` file, or passed via the `PYDRIVE_CREDENTIALS` environment
    variable.
 
-# Github Analytics Configuration
+# GitMetrics Configuration
 
-The Github Analytics script can be configured using a YAML file that indicates which repositories
+The GitMetrics script can be configured using a YAML file that indicates which repositories
 to collect and where to store the collected data, as well as when to execute the collection
-of data using Github Actions.
+of data using GitHub Actions.
 
 For more details about how to configure this, check the [CONFIGURATION.md](CONFIGURATION.md)
 document.

gitmetrics/__init__.py

@@ -0,0 +1,5 @@
+"""Scripts to extract multiple metrics from GitHub projects."""
+
+from gitmetrics.main import collect_project_metrics, collect_projects
+
+__all__ = ['collect_project_metrics', 'collect_projects']