import matplotlib.pyplot as plt import pandas as pd from sklearn import datasets, neighbors from mlxtend.plotting import plot_decision_regions

def knn_comparison(data, k): x = data[['X','Y']].values y = data['class'].astype(int).values clf = neighbors.KNeighborsClassifier(n_neighbors=k) #sklearn knn classifier clf.fit(x, y) # Plotting decision region plot_decision_regions(x, y, clf=clf, legend=2) # Adding axes annotations plt.xlabel('X') plt.ylabel('Y') plt.title('Knn with K='+ str(k)) plt.show()

data1 = pd.read_csv('ushape.csv') for i in [1,5,20,30,40,80]: knn_comparison(data1, i)

from sklearn.neighbors import NearestNeighbors, KNeighborsClassifier, KNeighborsRegressor from sklearn.model_selection import cross_val_predict from sklearn.metrics import mean_squared_error, r2_score import matplotlib.pyplot as plt

data1 = pd.read_csv('ushape.csv') X = data1[['X','Y']].values y = data1['class'].astype(int).values knn = KNeighborsRegressor(n_neighbors=10) y_pred = cross_val_predict(knn, X, y, cv=5)

#we can plot the error to compare different k values as well error = [] for k in range(1,51): knn = KNeighborsRegressor(n_neighbors=k) y_pred = cross_val_predict(knn, X, y, cv=5) error.append(mean_squared_error(y,y_pred))

plt.plot(range(1,51),error)