Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import numpy as np
- import pandas as pd
- from sklearn.datasets import load_breast_cancer
- data = load_breast_cancer()
- data_df = pd.DataFrame(data=data.data,columns=data.feature_names)
- from sklearn.preprocessing import StandardScaler
- standardized = StandardScaler()
- standardized.fit(data_df)
- scaled_data = standardized.transform(data_df)
- print(scaled_data)
- from sklearn.decomposition import PCA
- pca = PCA(n_components=2)
- pca.fit(scaled_data)
- x_pca = pca.transform(scaled_data)
- import matplotlib.pyplot as plt
- import seaborn as sns
- %matplotlib inline
- fig = plt.figure(figsize=(8,6))
- ax = fig.add_subplot(1,1,1)
- ax.set_xlabel("Principal component 1", fontsize=15)
- ax.set_ylabel("Principal component 2", fontsize=15)
- ax.set_title("2 Component PCA", fontsize=20)
- ax.scatter(x_pca[:,0], x_pca[:,1])
- plt.show()
- from sklearn.model_selection import cross_val_score
- from sklearn.decomposition import PCA
- from sklearn.neighbors import KNeighborsClassifier
- from sklearn.linear_model import LogisticRegression
- from sklearn.datasets import load_digits, load_breast_cancer
- from sklearn.preprocessing import StandardScaler
- data = load_breast_cancer()
- X, y = data.data, data.target
- scaler = StandardScaler()
- X_scaled = scaler.fit_transform(X)
- pca = PCA(n_components=10)
- X_pca = pca.fit_transform(X_scaled)
- models = {
- "Logistic Regression (Original)": LogisticRegression(),
- "Logistic Regression (Reduced)": LogisticRegression(),
- "KNN (Original)": KNeighborsClassifier(n_neighbors=5),
- "KNN (Reduced)": KNeighborsClassifier(n_neighbors=5)
- }
- for name, model in models.items():
- X_data = X_scaled if "Original" in name else X_pca
- scores = cross_val_score(model, X_data, y, cv=5, scoring='accuracy')
- print(f"{name}: Mean Accuracy = {scores.mean():.4f}")
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
