机器学习之sklearn基础教程

pip install scikit-learn

from sklearn.preprocessing import StandardScaler
import numpy as np

# 创建一个数据集
X = np.array([[1, 2], [3, 4], [5, 6]])

# 初始化StandardScaler
scaler = StandardScaler()

# 使用fit_transform方法对数据进行缩放
X_scaled = scaler.fit_transform(X)

print(X_scaled)

from sklearn.preprocessing import MinMaxScaler

data = [[-1, 2], [-0.5, 6], [0, 10], [1, 18]]
scaler = MinMaxScaler()

# 使用fit_transform方法对数据进行缩放
scaled_data = scaler.fit_transform(data)

print(scaled_data)

from sklearn.preprocessing import MaxAbsScaler

X = np.array([[1, -1, 2], [2, 0, 0], [0, 1, -1]])
scaler = MaxAbsScaler()

# 使用fit_transform方法对数据进行缩放
X_scaled = scaler.fit_transform(X)

print(X_scaled)

from sklearn.preprocessing import RobustScaler

X = np.array([[1, -2, 2], [2, -1, 0], [0, 1, -1]])
scaler = RobustScaler()

# 使用fit_transform方法对数据进行缩放
X_scaled = scaler.fit_transform(X)

print(X_scaled)

from sklearn.preprocessing import Normalizer

X = np.array([[1, 2], [3, 4], [5, 6]])
normalizer = Normalizer(norm='l2')  # 可以选择'l1'或'l2'范数

# 使用fit_transform方法对数据进行缩放
X_normalized = normalizer.fit_transform(X)

print(X_normalized)

from sklearn.impute import SimpleImputer
imputer = SimpleImputer(strategy='mean')  # 可以选择'mean'、'median'、'most_frequent'等策略
X_train_imputed = imputer.fit_transform(X_train)

from sklearn.preprocessing import OneHotEncoder
encoder = OneHotEncoder()
X_train_encoded = encoder.fit_transform(X_train)

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
y_train_encoded = le.fit_transform(y_train)

from sklearn.feature_selection import VarianceThreshold
selector = VarianceThreshold(threshold=0.1)
X_train_selected = selector.fit_transform(X_train)

from sklearn.feature_selection import SelectKBest, f_regression
selector = SelectKBest(score_func=f_regression, k=5)
X_train_selected = selector.fit_transform(X_train, y_train)

from sklearn.decomposition import PCA
pca = PCA(n_components=2)  # 指定要保留的主成分数量
X_train_reduced = pca.fit_transform(X_train)

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(degree=2)  # 指定多项式的度数
X_train_poly = poly.fit_transform(X_train)

from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# 加载iris数据集
iris = load_iris()
X = iris.data
y = iris.target

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 初始化逻辑回归模型
logreg = LogisticRegression()

# 训练模型
logreg.fit(X_train, y_train)

# 预测测试集
y_pred = logreg.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy}")

from sklearn.datasets import make_regression
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# 生成一个简单的回归数据集
X, y = make_regression(n_samples=100, n_features=1, noise=0.1)

# 划分训练集和测试集（略）
# ...

# 初始化线性回归模型
linreg = LinearRegression()

# 训练模型
linreg.fit(X_train, y_train)

# 预测测试集
y_pred = linreg.predict(X_test)

# 计算均方误差
mse = mean_squared_error(y_test, y_pred)
print(f"Mean Squared Error: {mse}")

from sklearn.model_selection import cross_val_score, GridSearchCV
from sklearn.svm import SVC
from sklearn.datasets import load_iris

# 加载iris数据集（略）
# ...

# 初始化SVC模型
svc = SVC()

# 使用5折交叉验证评估模型性能
scores = cross_val_score(svc, X, y, cv=5)
print(f"Cross-validation scores: {scores}")
print(f"Mean cross-validation score: {scores.mean()}")

# 使用网格搜索找到最佳参数
parameters = {'kernel':('linear', 'rbf'), 'C':[1, 10]}
clf = GridSearchCV(svc, parameters, cv=5)
clf.fit(X_train, y_train)
print(f"Best parameters: {clf.best_params_}")
print(f"Best score: {clf.best_score_}")