Created LGBM classifier @ lgbm_classifier.py

machine_learning/lgbm_classifier.py

@@ -0,0 +1,73 @@
+# LGBM Classifier Example
+import numpy as np
+from matplotlib import pyplot as plt
+from sklearn.datasets import load_iris
+from sklearn.metrics import ConfusionMatrixDisplay
+from sklearn.model_selection import train_test_split
+from lightgbm import LGBMClassifier
+
+
+def data_handling(data: dict) -> tuple:
+    """
+    Splits dataset into features and target labels.
+
+    >>> data_handling({'data': '[5.1, 3.5, 1.4, 0.2]', 'target': [0]})
+    ('[5.1, 3.5, 1.4, 0.2]', [0])
+    >>> data_handling({'data': '[4.9, 3.0, 1.4, 0.2], [4.7, 3.2, 1.3, 0.2]', 'target': [0, 0]})
+    ('[4.9, 3.0, 1.4, 0.2], [4.7, 3.2, 1.3, 0.2]', [0, 0])
+    """
+    return data["data"], data["target"]
+
+
+def lgbm_classifier(features: np.ndarray, target: np.ndarray) -> LGBMClassifier:
+    """
+    Trains an LGBM Classifier on the given features and target labels.
+
+    >>> lgbm_classifier(np.array([[5.1, 3.6, 1.4, 0.2]]), np.array([0]))
+    LGBMClassifier()
+    """
+    classifier = LGBMClassifier()
+    classifier.fit(features, target)
+    return classifier
+
+
+def main() -> None:
+    """
+    Main function to demonstrate LGBM classification on the Iris dataset.
+
+    URL for LightGBM documentation:
+    https://lightgbm.readthedocs.io/en/latest/
+    """
+    # Load the Iris dataset
+    iris = load_iris()
+    features, targets = data_handling(iris)
+
+    # Split the dataset into training and testing sets
+    x_train, x_test, y_train, y_test = train_test_split(
+        features, targets, test_size=0.25, random_state=42
+    )
+
+    # Class names for display
+    names = iris["target_names"]
+
+    # Train the LGBM classifier
+    lgbm_clf = lgbm_classifier(x_train, y_train)
+
+    # Display the confusion matrix for the classifier
+    ConfusionMatrixDisplay.from_estimator(
+        lgbm_clf,
+        x_test,
+        y_test,
+        display_labels=names,
+        cmap="Blues",
+        normalize="true",
+    )
+    plt.title("Normalized Confusion Matrix - IRIS Dataset")
+    plt.show()
+
+
+if __name__ == "__main__":
+    import doctest
+
+    doctest.testmod(verbose=True)
+    main()

machine_learning/lgbm_regressor.py

@@ -0,0 +1,62 @@
+# LGBM Regressor Example using Bank Marketing Dataset
+import numpy as np
+from sklearn.datasets import fetch_openml
+from sklearn.metrics import mean_absolute_error, mean_squared_error
+from sklearn.model_selection import train_test_split
+from lightgbm import LGBMRegressor
+
+
+def data_handling(data: dict) -> tuple:
+    # Split dataset into features and target. Data is features.
+    """
+    >>> data_handling((
+    ...  {'data':'[0.12, 0.02, 0.01, 0.25, 0.09]',
+    ...  'target':([1])}))
+    ('[0.12, 0.02, 0.01, 0.25, 0.09]', [1])
+    """
+    return (data["data"], data["target"])
+
+
+def lgbm_regressor(
+    features: np.ndarray, target: np.ndarray, test_features: np.ndarray
+) -> np.ndarray:
+    """
+    >>> lgbm_regressor(np.array([[ 0.12,  0.02,  0.01,  0.25,  0.09]]), np.array([1]),
+    ... np.array([[0.11,  0.03,  0.02,  0.28,  0.08]]))
+    array([[0.98]], dtype=float32)
+    """
+    lgbm = LGBMRegressor(verbosity=0, random_state=42)
+    lgbm.fit(features, target)
+    # Predict target for test data
+    predictions = lgbm.predict(test_features)
+    predictions = predictions.reshape(len(predictions), 1)
+    return predictions
+
+
+def main() -> None:
+    """
+    The URL for this algorithm:
+    https://lightgbm.readthedocs.io/en/latest/
+    Bank Marketing Dataset is used to demonstrate the algorithm.
+
+    Expected error values:
+    Mean Absolute Error: 0.2 (approx.)
+    Mean Square Error: 0.15 (approx.)
+    """
+    # Load Bank Marketing dataset
+    bank_data = fetch_openml(name="bank-marketing", version=1, as_frame=False)
+    data, target = data_handling(bank_data)
+    x_train, x_test, y_train, y_test = train_test_split(
+        data, target, test_size=0.25, random_state=1
+    )
+    predictions = lgbm_regressor(x_train, y_train, x_test)
+    # Error printing
+    print(f"Mean Absolute Error: {mean_absolute_error(y_test, predictions)}")
+    print(f"Mean Square Error: {mean_squared_error(y_test, predictions)}")
+
+
+if __name__ == "__main__":
+    import doctest
+
+    doctest.testmod(verbose=True)
+    main()