示例 1:鸢尾花分类(分类任务)
from sklearn.datasets import load_iris
iris = load_iris()
X = iris.data
y = iris.target
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
from sklearn.linear_model import LogisticRegression
model = LogisticRegression()
model.fit(X_train, y_train)
from sklearn.metrics import accuracy_score, classification_report
y_pred = model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy}")
report = classification_report(y_test, y_pred)
print(report)
示例 2:波士顿房价预测(回归任务)
from sklearn.datasets import load_boston
boston = load_boston()
X = boston.data
y = boston.target
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
from sklearn.linear_model import LinearRegression
model = LinearRegression()
model.fit(X_train, y_train)
from sklearn.metrics import mean_squared_error, r2_score
y_pred = model.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print(f"Mean Squared Error: {mse}")
r2 = r2_score(y_test, y_pred)
print(f"R^2 Score: {r2}")
示例 3:客户分群(聚类任务)
import numpy as np
np.random.seed(42)
X = np.random.rand(100, 2) * [50, 100000]
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
from sklearn.cluster import KMeans
kmeans = KMeans(n_clusters=3, random_state=42)
kmeans.fit(X_scaled)
labels = kmeans.labels_
from sklearn.metrics import silhouette_score
silhouette_avg = silhouette_score(X_scaled, labels)
print(f"Silhouette Score: {silhouette_avg}")
print(f"Cluster Centers: {kmeans.cluster_centers_}")