Python进阶教程：机器学习入门（Scikit-learn）

1
from sklearn.datasets import load_iris
2
from sklearn.model_selection import train_test_split
3
from sklearn.tree import DecisionTreeClassifier
4
from sklearn.metrics import accuracy_score
5

6
# 1. 加载鸢尾花数据集
7
iris = load_iris()
8
X, y = iris.data, iris.target
9

10
# 2. 划分训练集/测试集
11
X_train, X_test, y_train, y_test = train_test_split(
12
    X, y, test_size=0.3, random_state=42
13
)
14

15
# 3. 训练模型
16
model = DecisionTreeClassifier(max_depth=3)
17
model.fit(X_train, y_train)
18

19
# 4. 评估
20
y_pred = model.predict(X_test)
21
print(f"准确率：{accuracy_score(y_test, y_pred):.2f}")
22

23
# 5. 预测新样本
24
new_sample = [[5.1, 3.5, 1.4, 0.2]]
25
print(f"预测类别：{iris.target_names[model.predict(new_sample)[0]]}")

1
from sklearn.linear_model import LinearRegression
2
from sklearn.model_selection import train_test_split
3
from sklearn.metrics import mean_squared_error
4
import numpy as np
5

6
# 模拟数据：房价与面积
7
np.random.seed(42)
8
X = np.random.rand(200, 1) * 100  # 面积 0-100
9
y = 3 * X[:, 0] + 10 + np.random.randn(200) * 5  # 房价
10

11
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
12

13
model = LinearRegression()
14
model.fit(X_train, y_train)
15

16
print(f"斜率：{model.coef_[0]:.2f}，截距：{model.intercept_:.2f}")
17
y_pred = model.predict(X_test)
18
print(f"均方误差：{mean_squared_error(y_test, y_pred):.2f}")

1
from sklearn.datasets import load_iris
2
from sklearn.model_selection import cross_val_score
3
from sklearn.svm import SVC
4

5
iris = load_iris()
6
model = SVC(kernel='linear', C=1.0)
7

8
# 5 折交叉验证
9
scores = cross_val_score(model, iris.data, iris.target, cv=5)
10
print(f"每折准确率：{scores}")
11
print(f"平均准确率：{scores.mean():.3f}")

1
from sklearn.cluster import KMeans
2
from sklearn.datasets import make_blobs
3
import matplotlib.pyplot as plt
4

5
# 生成聚类数据
6
X, _ = make_blobs(n_samples=300, centers=4, random_state=42)
7

8
# K-Means 聚类
9
kmeans = KMeans(n_clusters=4, random_state=42)
10
kmeans.fit(X)
11

12
# 查看聚类中心
13
print(f"聚类中心：
14
{kmeans.cluster_centers_}")
15
print(f"样本所属簇：{kmeans.labels_[:10]}")
16

17
# 可视化（可选）
18
# plt.scatter(X[:, 0], X[:, 1], c=kmeans.labels_)
19
# plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], marker="*", s=200, c="red")
20
# plt.show()

1
from sklearn.preprocessing import StandardScaler, OneHotEncoder
2
import numpy as np
3

4
# 特征缩放（对距离敏感的算法很重要）
5
X = np.array([[1, 1000], [2, 2000], [3, 3000]])
6
scaler = StandardScaler()
7
X_scaled = scaler.fit_transform(X)
8
print(X_scaled)
9

10
# 类别特征独热编码
11
from sklearn.preprocessing import LabelEncoder
12
colors = ["红", "绿", "蓝", "绿", "红"]
13
encoder = LabelEncoder()
14
print(encoder.fit_transform(colors))  # [0 1 2 1 0]

1
from sklearn.datasets import load_iris
2
from sklearn.model_selection import train_test_split
3
from sklearn.ensemble import RandomForestClassifier
4
from sklearn.metrics import classification_report
5

6
# 数据准备
7
iris = load_iris()
8
X_train, X_test, y_train, y_test = train_test_split(
9
    iris.data, iris.target, test_size=0.3, random_state=42
10
)
11

12
# 随机森林（比单棵树更稳）
13
model = RandomForestClassifier(n_estimators=100, random_state=42)
14
model.fit(X_train, y_train)
15

16
# 评估
17
y_pred = model.predict(X_test)
18
print(classification_report(y_test, y_pred, target_names=iris.target_names))
19

20
# 特征重要性
21
for name, imp in zip(iris.feature_names, model.feature_importances_):
22
    print(f"{name}: {imp:.3f}")