github workflows

.github/workflows/github-actions-basic.yml

@@ -0,0 +1,37 @@
+name: Python package
+
+on: [push]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    env:
+      working-directory: Chapter02
+    defaults:
+      run:
+        working-directory: ${{ env.working-directory }}
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10"]
+
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flake8 pytest
+          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+      - name: Lint with flake8
+        run: |
+          # stop the build if there are Python syntax errors or undefined names
+          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+          flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+      - name: Test with pytest
+        run: |
+          pytest

Chapter02/plot_outlier_detection_wine.py

@@ -0,0 +1,34 @@
+"""
+Outlier detection example for github actions.
+"""
+
+import numpy as np
+from sklearn.covariance import EllipticEnvelope
+from sklearn.svm import OneClassSVM
+import matplotlib.pyplot as plt
+import matplotlib.font_manager
+from sklearn.datasets import load_wine
+
+# Define "classifiers" to be used
+classifiers = {
+    "Empirical Covariance": EllipticEnvelope(support_fraction=1.0, contamination=0.25),
+    "Robust Covariance (Minimum Covariance Determinant)": EllipticEnvelope(
+        contamination=0.25
+    ),
+    "OCSVM": OneClassSVM(nu=0.25, gamma=0.35),
+}
+colors = ["m", "g", "b"]
+legend1 = {}
+legend2 = {}
+
+# Get data
+X1 = load_wine()["data"][:, [1, 2]]  # two clusters
+
+# Learn a frontier for outlier detection with several classifiers
+xx1, yy1 = np.meshgrid(np.linspace(0, 6, 500), np.linspace(1, 4.5, 500))
+for i, (clf_name, clf) in enumerate(classifiers.items()):
+    clf.fit(X1)
+    Z1 = clf.decision_function(np.c_[xx1.ravel(), yy1.ravel()])
+    Z1 = Z1.reshape(xx1.shape)
+
+

Chapter02/simple_classifier.py

@@ -0,0 +1,23 @@
+"""
+Random Forest Classifier on the wine dataset.
+"""
+
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.datasets import load_wine
+from sklearn.model_selection import train_test_split
+#import joblib
+
+# Load the dataset
+X, y = load_wine(return_X_y=True)
+y = y == 2
+
+# Train and test split
+X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
+
+# Train the classifier
+rfc = RandomForestClassifier(n_estimators=10, random_state=42)
+rfc.fit(X_train, y_train)
+
+# Dump file to joblib
+# joblib.dump(rfc, 'rfc.joblib')
+

Chapter02/test_basic.py

@@ -0,0 +1,2 @@
+def test_example():
+    pass

Chapter05/going_with_the_kubeflow/going_with_the_kubeflow/pipeline_basic_v1.py

@@ -107,8 +107,9 @@ def my_pipeline():
 # got this from running kubectl cluster-info --context kind-mlewp (this is cluster name)
 #endpoint = 'https://127.0.0.1:50663' 
 kfp_client = Client(host=endpoint)
-run = kfp_client.create_run_from_pipeline_func(ß
+run = kfp_client.create_run_from_pipeline_func(
     my_pipeline,
     mode=kfp.dsl.PipelineExecutionMode.V2_COMPATIBLE,
-)ßßß
+)
+url = f'{endpoint}/#/runs/details/{run.run_id}'
 print(url)

Chapter05/reaching_zen/reaching_zen/steps/data_loaders.py

@@ -117,8 +117,8 @@ def data_loader(
         dataset = load_iris(as_frame=True).frame
     elif params.dataset == SklearnDataset.breast_cancer:
         dataset = load_breast_cancer(as_frame=True).frame
-    elif params.dataset == SklearnDataset.diabetes:
-        dataset = load_diabetes(as_frame=True).frame
+    # elif params.dataset == SklearnDataset.diabetes:
+    #     dataset = load_diabetes(as_frame=True).frame
     logger.info(f"Loaded dataset {params.dataset.value}: %s", dataset.info())
     logger.info(dataset.head())
     ### YOUR CODE ENDS HERE ###