Create cml.yaml

Breast_cancer_ML/.github/workflows/cml.yaml

@@ -0,0 +1,18 @@
+name: Breast-cancer-ML
+on: [push]
+jobs:
+  run:
+    runs-on: [ubuntu-latest]
+    container: docker://dvcorg/cml-py3:latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: cml_run
+        env:
+          repo_token: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Your ML workflow goes here
+          pip install -r requirements.txt
+          python BC_ML.py
+
+          echo "MODEL METRICS"
+

Breast_cancer_ML/BC_ML.py

@@ -117,6 +117,8 @@ def cross_val_pred(self):
         from sklearn.model_selection import cross_val_predict
         import scikitplot as skplt
         import matplotlib.pyplot as plt
+        from sklearn.ensemble import RandomForestClassifier
+
         randomforest_cs = RandomForestClassifier(n_estimators=5, max_depth=5,
                                                  criterion='entropy',random_state=0)
         pred_LogisticRegression = cross_val_predict(randomforest_cs, self.features, self.target)
@@ -132,11 +134,9 @@ def visualize_performance_eval(self):
 
 
 
-
-if __name__ == '__main__':
-    brst_cancer_ml_model  = BreastCancer()
-    brst_cancer_ml_model.preprocess_df()
-    brst_cancer_ml_model.train_ML_models()
-    brst_cancer_ml_model.compute_performance_evals()
-    brst_cancer_ml_model.visualize_performance_eval()
-    brst_cancer_ml_model.cross_val_pred()
+brst_cancer_ml_model  = BreastCancer()
+brst_cancer_ml_model.preprocess_df()
+brst_cancer_ml_model.train_ML_models()
+brst_cancer_ml_model.compute_performance_evals()
+brst_cancer_ml_model.visualize_performance_eval()
+brst_cancer_ml_model.cross_val_pred()

Breast_cancer_ML/requirements.txt

@@ -0,0 +1,5 @@
+numpy
+pandas
+matplotlib
+scikit-plot
+-U scikit-learn