import numpy as np import pandas as pd from matplotlib import pyplot as plt from sklearn.datasets import load_breast_cancer from sklearn.metrics import confusion_matrix, classification_report from sklearn.neighbors import KNeighborsClassifier from sklearn.model_selection import train_test_split import seaborn as sns

breast_cancer = load_breast_cancer()

breast_cancer.feature_names

breast_cancer.target

X = pd.DataFrame(breast_cancer.data, columns=breast_cancer.feature_names) X = X[['mean area', 'mean perimeter', 'worst area', 'worst radius']] y = pd.Categorical.from_codes(breast_cancer.target, breast_cancer.target_names) y = pd.get_dummies(y) y.drop(['benign'], axis=1, inplace=True)

y.head()

# Proportion of records labeled as malignant y['malignant'].mean()

# Create a dataframe from X & y for exploratory analysis bc_data = pd.concat([X,y], axis=1)

bc_data.head()

bc_data.describe()

sns.pairplot(bc_data, hue='malignant')

# MinMax Scaler transforms features into [0,1] # Formula: X_rescaled = (Xi - Xmin) / (Xmax-Xmin) from sklearn.preprocessing import MinMaxScaler scaler = MinMaxScaler() X_ = scaler.fit_transform(X) X_rescaled = pd.DataFrame(X_, columns=X.columns)

X_rescaled.describe()

X_train, X_test, y_train, y_test = train_test_split(X_rescaled, y, test_size=0.3, random_state=1)

knn = KNeighborsClassifier(n_neighbors=5, metric='euclidean') knn.fit(X_train, y_train) y_pred = knn.predict(X_test) print(confusion_matrix(y_test,y_pred)) print(classification_report(y_test,y_pred))

from sklearn.metrics import roc_auc_score print('ROC AUC: ', roc_auc_score(y_test,y_pred))

from sklearn.model_selection import cross_val_score max_K = 100 cv_scores = [ ] for K in range(1,max_K): knn = KNeighborsClassifier(n_neighbors = K) scores = cross_val_score(knn,X_train,y_train.values.ravel(),cv = 5,scoring = "accuracy") cv_scores.append(scores.mean())

cv_scores[:4]

sns.lineplot(x=range(1,max_K), y=cv_scores)