Nov 19, 2020 · Nov 19, 2020
diff --git a/classification/adaboost_classifier.py b/classification/adaboost_classifier.py
 from sklearn.ensemble import AdaBoostClassifier
 from sklearn.datasets import load_breast_cancer
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import plot_confusion_matrix
 from matplotlib import pyplot as plt


 """Adaboost classifier example"""


 def adaboost():
    cancer_df = load_breast_cancer()
    print(cancer_df.keys())
    X, y = cancer_df.data, cancer_df.target
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

    abc = AdaBoostClassifier(base_estimator=None,
                             n_estimators=300, learning_rate=1, random_state=0)
    abc.fit(X_train, y_train)
    y_pred = abc.predict(X_test)
    print(y_pred[:20])
    # Display Confusion Matrix of Classifier
    plot_confusion_matrix(
        abc,
        X_test,
        y_test,
        display_labels=cancer_df["target_names"],
        cmap="Blues",
        normalize="true",
    )
    plt.title("Normalized Confusion Matrix - Cancer Dataset")
    plt.show()

    # to see the accuracy of the model
    print("Accuracy of adaboost is:", abc.score(X_test, y_test))


 if __name__ == "__main__":
    adaboost()
diff --git a/classification/gaussian_n_bayes.py b/classification/gaussian_n_bayes.py
 # importing libraries
 from sklearn.naive_bayes import GaussianNB
 from sklearn.model_selection import train_test_split
 from sklearn.datasets import load_iris
 from sklearn.metrics import accuracy_score, classification_report
 import pandas as pd


 """To implement Gaussian naves bayes for flowers clssification"""


 def main():

    iris = load_iris()
    print(iris.keys())
    iris_df = pd.DataFrame(iris.data, columns=iris.feature_names)
    iris_df['target'] = iris.target
    print(iris_df.head())
    X, y = iris_df.drop('target', 1), iris_df.target
    print(X.shape, y.shape)
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
    model = GaussianNB()
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)
    print(y_pred[:10])
    accuracy = accuracy_score(y_test, y_pred)
    print("The accuracy of Gaussian naves is {}".format(accuracy))
    # classification report
    print(classification_report(y_test, y_pred))


 main()
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,39 @@
		from sklearn.ensemble import AdaBoostClassifier
		from sklearn.datasets import load_breast_cancer
		from sklearn.model_selection import train_test_split
		from sklearn.metrics import plot_confusion_matrix
		from matplotlib import pyplot as plt


		"""Adaboost classifier example"""


		def adaboost():
		cancer_df = load_breast_cancer()
		print(cancer_df.keys())
		X, y = cancer_df.data, cancer_df.target
		X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

		abc = AdaBoostClassifier(base_estimator=None,
		n_estimators=300, learning_rate=1, random_state=0)
		abc.fit(X_train, y_train)
		y_pred = abc.predict(X_test)
		print(y_pred[:20])
		# Display Confusion Matrix of Classifier
		plot_confusion_matrix(
		abc,
		X_test,
		y_test,
		display_labels=cancer_df["target_names"],
		cmap="Blues",
		normalize="true",
		)
		plt.title("Normalized Confusion Matrix - Cancer Dataset")
		plt.show()

		# to see the accuracy of the model
		print("Accuracy of adaboost is:", abc.score(X_test, y_test))


		if __name__ == "__main__":
		adaboost()
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,32 @@
		# importing libraries
		from sklearn.naive_bayes import GaussianNB
		from sklearn.model_selection import train_test_split
		from sklearn.datasets import load_iris
		from sklearn.metrics import accuracy_score, classification_report
		import pandas as pd


		"""To implement Gaussian naves bayes for flowers clssification"""


		def main():

		iris = load_iris()
		print(iris.keys())
		iris_df = pd.DataFrame(iris.data, columns=iris.feature_names)
		iris_df['target'] = iris.target
		print(iris_df.head())
		X, y = iris_df.drop('target', 1), iris_df.target
		print(X.shape, y.shape)
		X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
		model = GaussianNB()
		model.fit(X_train, y_train)
		y_pred = model.predict(X_test)
		print(y_pred[:10])
		accuracy = accuracy_score(y_test, y_pred)
		print("The accuracy of Gaussian naves is {}".format(accuracy))
		# classification report
		print(classification_report(y_test, y_pred))


		main()