Fix broken doctests in xgboost_classifier.py

Author: harsh-1o

machine_learning/xgboost_classifier.py

@@ -8,32 +8,33 @@
 
 
 def data_handling(data: dict) -> tuple:
-    # Split dataset into features and target
-    # data is features
     """
-    >>> 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])
+    Split dataset into features and target.
+    
+    >>> from sklearn.datasets import load_iris
+    >>> iris = load_iris()
+    >>> features, targets = data_handling(iris)
+    >>> features.shape
+    (150, 4)
+    >>> targets.shape
+    (150,)
     """
     return (data["data"], data["target"])
 
 
 def xgboost(features: np.ndarray, target: np.ndarray) -> XGBClassifier:
     """
-    # THIS TEST IS BROKEN!! >>> xgboost(np.array([[5.1, 3.6, 1.4, 0.2]]), np.array([0]))
-    XGBClassifier(base_score=0.5, booster='gbtree', callbacks=None,
-                  colsample_bylevel=1, colsample_bynode=1, colsample_bytree=1,
-                  early_stopping_rounds=None, enable_categorical=False,
-                  eval_metric=None, gamma=0, gpu_id=-1, grow_policy='depthwise',
-                  importance_type=None, interaction_constraints='',
-                  learning_rate=0.300000012, max_bin=256, max_cat_to_onehot=4,
-                  max_delta_step=0, max_depth=6, max_leaves=0, min_child_weight=1,
-                  missing=nan, monotone_constraints='()', n_estimators=100,
-                  n_jobs=0, num_parallel_tree=1, predictor='auto', random_state=0,
-                  reg_alpha=0, reg_lambda=1, ...)
+    Train an XGBoost classifier.
+    
+    >>> from sklearn.datasets import load_iris
+    >>> iris = load_iris()
+    >>> X_train, y_train = iris.data[:100], iris.target[:100]
+    >>> classifier = xgboost(X_train, y_train)
+    >>> predictions = classifier.predict(iris.data[:5])
+    >>> len(predictions)
+    5
+    >>> all(pred in [0, 1, 2] for pred in predictions)
+    True
     """
     classifier = XGBClassifier()
     classifier.fit(features, target)
@@ -46,20 +47,18 @@ def main() -> None:
     https://xgboost.readthedocs.io/en/stable/
     Iris type dataset is used to demonstrate algorithm.
     """
-
     # Load Iris dataset
     iris = load_iris()
     features, targets = data_handling(iris)
     x_train, x_test, y_train, y_test = train_test_split(
-        features, targets, test_size=0.25
+        features, targets, test_size=0.25, random_state=42
     )
-
     names = iris["target_names"]
-
+    
     # Create an XGBoost Classifier from the training data
     xgboost_classifier = xgboost(x_train, y_train)
-
-    # Display the confusion matrix of the classifier with both training and test sets
+    
+    # Display the confusion matrix of the classifier with test set
     ConfusionMatrixDisplay.from_estimator(
         xgboost_classifier,
         x_test,
@@ -74,6 +73,5 @@ def main() -> None:
 
 if __name__ == "__main__":
     import doctest
-
     doctest.testmod(verbose=True)
-    main()
+    main()