From 42b56f2345ed4566ea48306d3a727f1aa5c88218 Mon Sep 17 00:00:00 2001 From: Modassir Afzal <60973906+Moddy2024@users.noreply.github.com> Date: Fri, 21 Oct 2022 03:29:11 +0530 Subject: [PATCH] XGBoost Classifier (#7106) * Fixes: #{6551} * Update xgboostclassifier.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update xgboostclassifier.py * Update xgboostclassifier.py * Update xgboostclassifier.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fixes: #{6551} * Update xgboostclassifier.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update xgboostclassifier.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update xgboostclassifier.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update xgboostclassifier.py * Fixes : #6551 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fixes : #6551 * Fixes : #6551 * Fixes: #6551 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update xgboostclassifier.py * Update xgboostclassifier.py * Update xgboostclassifier.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fixes: #6551 * Fixes #6551 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fixes: {#6551} * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fixes: {#6551} * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fixes: #6551 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * FIXES: {#6551} * Fixes : { #6551} * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fixes : { #6551} * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fixes: { #6551] * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update xgboostclassifier.py * Update xgboostclassifier.py * Apply suggestions from code review * Update xgboostclassifier.py * Update xgboostclassifier.py * Update xgboostclassifier.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fixes: { #6551} * Update xgboostclassifier.py * Fixes: { #6551} * Update xgboostclassifier.py * Fixes: ( #6551) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fixes: { #6551} Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Christian Clauss --- machine_learning/xgboostclassifier.py | 82 +++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) create mode 100644 machine_learning/xgboostclassifier.py diff --git a/machine_learning/xgboostclassifier.py b/machine_learning/xgboostclassifier.py new file mode 100644 index 000000000000..bb5b48b7ab23 --- /dev/null +++ b/machine_learning/xgboostclassifier.py @@ -0,0 +1,82 @@ +# XGBoost Classifier Example +import numpy as np +from matplotlib import pyplot as plt +from sklearn.datasets import load_iris +from sklearn.metrics import plot_confusion_matrix +from sklearn.model_selection import train_test_split +from xgboost import XGBClassifier + + +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]) + """ + return (data["data"], data["target"]) + + +def xgboost(features: np.ndarray, target: np.ndarray) -> XGBClassifier: + """ + >>> 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, ...) + """ + classifier = XGBClassifier() + classifier.fit(features, target) + return classifier + + +def main() -> None: + + """ + >>> main() + + Url for the algorithm: + 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 + ) + + 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 + plot_confusion_matrix( + xgboost_classifier, + 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()