add plotting diagnostics, cdf comparisons, update data to be stored i…

…n .parquet format and gitignore accordingly, allow for manual runs of deploy.yml once merged into main with workflow_dispatch

.github/workflows/deploy.yml

@@ -4,6 +4,7 @@ on:
   push:
     tags:
       - "v[0-9]+.[0-9]+.[0-9]+"
+  workflow_dispatch:
 
 permissions:
   contents: write
@@ -20,14 +21,14 @@ jobs:
         python-version: "3.12"
     - name: Install dependencies
       run: python -m pip install build . --upgrade pip
-    - name: Build package distribution
-      run: python -m build --sdist --wheel --outdir dist/ .
-    - name: Publish package distribution to PyPI
-      uses: pypa/gh-action-pypi-publish@release/v1
-      with:
-        skip_existing: true
-        user: __token__
-        password: ${{ secrets.PYPI_API_TOKEN }}
+    # - name: Build package distribution
+    #   run: python -m build --sdist --wheel --outdir dist/ .
+    # - name: Publish package distribution to PyPI
+    #   uses: pypa/gh-action-pypi-publish@release/v1
+    #   with:
+    #     skip_existing: true
+    #     user: __token__
+    #     password: ${{ secrets.PYPI_API_TOKEN }}
 
   docs:
     runs-on: ubuntu-latest

.gitignore

@@ -130,5 +130,5 @@ dmypy.json
 
 # Misc.
 .DS_Store
-cleaned_individual_microdata_gbd2023_2024_03_18.csv
-microdata_2024_05_03.csv
+*.csv
+*.parquet

src/ensemble/model.py

@@ -338,7 +338,6 @@ def fit(self, data: npt.ArrayLike) -> EnsembleResult:
         sample_variance = np.var(data, ddof=1)
         ecdf = stats.ecdf(data).cdf.probabilities
         equantiles = stats.ecdf(data).cdf.quantiles
-        print(len(equantiles), ", num of empirical quantiles")
 
         # fill matrix with cdf values over support of data
         num_distributions = len(self.distributions)