5

import numpy as np, matplotlib.pyplot as plt

from collections import Counter

data = np.random.rand(100)

train, test = data[:50], data[50:]

labels = ['Class1' if x <= 0.5 else 'Class2' for x in train]

def knn(x, k):

    d = sorted([(abs(x - xi), li) for xi, li in zip(train, labels)])

    return Counter([l for _, l in d[:k]]).most_common(1)[0][0]

k_vals = [1, 2, 3, 4, 5, 20, 30]

for k in k_vals:

    print(f"\nResults for k = {k}:")

    preds = [knn(x, k) for x in test]

    for i, p in enumerate(preds, 51):

        print(f"x{i} (value: {test[i-51]:.4f}) → {p}")

    plt.figure()

    plt.scatter(train, [0]*50, c=['blue' if l=='Class1' else 'red' for l in labels], label='Train')

    plt.scatter([test[i] for i in range(50) if preds[i]=='Class1'], [1]*preds.count('Class1'), c='blue', marker='x', label='Class1')

    plt.scatter([test[i] for i in range(50) if preds[i]=='Class2'], [1]*preds.count('Class2'), c='red', marker='x', label='Class2')

    plt.title(f"k = {k}"); plt.yticks([0,1], ['Train','Test'])

    plt.legend(); plt.grid(True); plt.show()

Comments

Post a Comment

Popular posts from this blog

9

import scipy.io, numpy as np, matplotlib.pyplot as plt from sklearn.model_selection import train_test_split from sklearn.naive_bayes import GaussianNB from sklearn.metrics import accuracy_score d = scipy.io.loadmat('olivettifaces.mat') X, y = d['faces'].T, np.repeat(np.arange(40), 10) Xt, Xs, yt, ys = train_test_split(X, y, test_size=0.3, stratify=y, random_state=42) m = GaussianNB().fit(Xt, yt) yp = m.predict(Xs) print("Acc: %.2f%%" % (accuracy_score(ys, yp) * 100)) i = np.random.choice(len(Xs), 20, replace=False) imgs = Xs[i].reshape(-1, 64, 64).transpose(0, 2, 1) plt.figure(figsize=(12,6)) for j in range(20):     plt.subplot(4, 5, j+1)     plt.imshow(imgs[j], cmap='gray')     plt.title(f"T:{ys[i[j]]}, P:{yp[i[j]]}", fontsize=8)     plt.axis('off') plt.tight_layout(); plt.show() #we need to upload olivettiface dataset
Read more

7

 import numpy as np, pandas as pd, seaborn as sns, matplotlib.pyplot as plt from sklearn.linear_model import LinearRegression from sklearn.model_selection import train_test_split from sklearn.preprocessing import PolynomialFeatures from sklearn.metrics import mean_squared_error, r2_score from sklearn.datasets import fetch_openml boston = fetch_openml(name='boston', version=1, as_frame=True) X, y = boston.data.values, boston.target.values Xt, Xs, yt, ys = train_test_split(X, y, test_size=0.2) m = LinearRegression().fit(Xt, yt) yp = m.predict(Xs) print("Linear R²=%.2f" % r2_score(ys, yp)) plt.scatter(Xs[:,5], ys, c='b'); plt.scatter(Xs[:,5], yp, c='r'); plt.title("Boston"); plt.show() df = sns.load_dataset('mpg').dropna() df['horsepower'] = pd.to_numeric(df['horsepower'], errors='coerce') df = df.dropna() X, y = df[['horsepower', 'weight']], df['mpg'] Xt, Xs, yt, ys = train_test_split(X, y...
Read more

10

from sklearn.datasets import load_breast_cancer from sklearn.cluster import KMeans from sklearn.preprocessing import StandardScaler from sklearn.decomposition import PCA from sklearn.metrics import confusion_matrix, classification_report import matplotlib.pyplot as plt X, y = load_breast_cancer(return_X_y=True) X = StandardScaler().fit_transform(X) y_pred = KMeans(n_clusters=2, random_state=42, n_init=10).fit_predict(X) print(confusion_matrix(y, y_pred)) print(classification_report(y, y_pred)) X_pca = PCA(2).fit_transform(X) plt.scatter(*X_pca.T, c=y_pred, cmap='coolwarm', alpha=0.7) plt.title("K-Means Clustering (PCA)") plt.show()
Read more