机器学习Sklearn学习总结3——回归与聚类算法
目录
一、线性回归
线性回归与梯度下降对比的代码：
二、线性回归改进——岭回归
三、线性回归各指标的案例
四、模型的保存与加载
五、KMeans聚类算法
代码案例：
KMeans总结
六、总结
代码集
一、线性回归
线性回归与梯度下降对比的代码：
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression, SGDRegressor
from sklearn.metrics import mean_squared_error
def linear1():
"""
正规方程的优化方法对波士顿房价进行预测
:return:
"""
# 1）获取数据
boston = load_boston()
print("特征数量：\n", boston.data.shape)
# 2) 划分数据集
x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
# 3) 标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4）预估器
estimator = LinearRegression()
estimator.fit(x_train, y_train)
# 5)得出模型
print("正规方程——权重系数为：\n", estimator.coef_)
print("正规方程——偏置为：\n", estimator.intercept_)
# 6)模型评估
y_predict = estimator.predict(x_test)
print("预测房价：\n", y_predict)
error = mean_squared_error(y_test, y_predict)
print("正规方程——均方误差为：\n", error)
return None
def linear2():
"""
梯度下降的优化方法对波士顿房价进行预测
:return:
"""
# 1）获取数据
boston = load_boston()
# 2) 划分数据集
x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
# 3) 标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4）预估器
estimator = SGDRegressor(learning_rate="constant", eta0=0.01, max_iter=10000)
estimator.fit(x_train, y_train)
# 5)得出模型
print("梯度下降——权重系数为：\n", estimator.coef_)
print("梯度下降——偏置为：\n", estimator.intercept_)
# 6)模型评估
y_predict = estimator.predict(x_test)
print("预测房价：\n", y_predict)
error = mean_squared_error(y_test, y_predict)
print("梯度下降——均方误差为：\n", error)
return None
if __name__ == '__main__':
# 代码1：正规方程的优化方法对波士顿房价进行预测
linear1()
# 代码2：梯度下降的优化方法对波士顿房价进行预测
linear2()
二、线性回归改进——岭回归
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression, SGDRegressor, Ridge
from sklearn.metrics import mean_squared_error
def linear3():
"""
岭回归对波士顿房价进行预测
:return:
"""
# 1）获取数据
boston = load_boston()
# 2) 划分数据集
x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
# 3) 标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4）预估器
estimator = Ridge(alpha=0.5, max_iter=10000)
estimator.fit(x_train, y_train)
# 5)得出模型
print("岭回归——权重系数为：\n", estimator.coef_)
print("岭回归——偏置为：\n", estimator.intercept_)
# 6)模型评估
y_predict = estimator.predict(x_test)
print("预测房价：\n", y_predict)
error = mean_squared_error(y_test, y_predict)
print("岭回归——均方误差为：\n", error)
return None
if __name__ == '__main__':
# 代码3：岭回归对波士顿房价进行预测
linear3()
三、线性回归各指标的案例
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report
from sklearn.metrics import roc_auc_score
def handle_data():
# 1、读取数据
data = pd.read_csv("cancel.csv")
# 2、缺失值处理
# 1）替换-》np.nan
data = data.replace(to_replace="?", value=np.nan)
# 2)删除缺失样本
data.dropna(inplace=True)
# 3、划分数据集
# 筛选特征值和目标值
x = data.iloc[:, 1:-1]
y = data["Class"]
x_train, x_test, y_train, y_test = train_test_split(x, y)
# 标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 5、预估器流程
estimator = LogisticRegression()
estimator.fit(x_train, y_train)
# 逻辑回归的模型参数：回归系数和偏置
print("逻辑回归的模型参数：回归系数和偏置:\n", estimator.coef_, "\n", estimator.intercept_)
# 6、模型评估
# 方法1：直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值：\n", y_test == y_predict)
# 方法2： 计算准确率
score = estimator.score(x_test, y_test)
print("准确率：\n", score)
# 查看精确率、召回率、F1-score
report = classification_report(y_test, y_predict, labels=[2, 4], target_names=["良性", "恶性"])
# y_true: 每个样本的真实类别，必须为0（反例），1（正例）标记
# 将y_test 转换成 0 1
y_true = np.where(y_test > 3, 1, 0)
msg = roc_auc_score(y_true, y_predict)
if __name__ == '__main__':
handle_data()
四、模型的保存与加载
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression, SGDRegressor, Ridge
from sklearn.metrics import mean_squared_error
import joblib
def linear3():
"""
岭回归对波士顿房价进行预测
:return:
"""
# 1）获取数据
boston = load_boston()
# 2) 划分数据集
x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
# 3) 标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4）预估器
estimator = Ridge(alpha=0.5, max_iter=10000)
estimator.fit(x_train, y_train)
# 保存模型
joblib.dump(estimator, "my.ridge.pkl")
# 加载模型
estimator = joblib.load("my.ridge.pkl")
# 5)得出模型
print("岭回归——权重系数为：\n", estimator.coef_)
print("岭回归——偏置为：\n", estimator.intercept_)
# 6)模型评估
y_predict = estimator.predict(x_test)
print("预测房价：\n", y_predict)
error = mean_squared_error(y_test, y_predict)
print("岭回归——均方误差为：\n", error)
return None
if __name__ == '__main__':
# 代码3：岭回归对波士顿房价进行预测
linear3()
五、KMeans聚类算法
代码案例：
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression, SGDRegressor, Ridge
from sklearn.metrics import mean_squared_error
import joblib
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score
def linear4():
"""
KMeans算法对波士顿房价进行预测
:return:
"""
# 1）获取数据
boston = load_boston()
# 2) 划分数据集
x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
# 3) 标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4）预估器
estimator = KMeans(n_clusters=3)
estimator.fit(boston)
y_predict = estimator.predict(boston)
# 模型评估-轮廓系数
silhouette_score(boston, y_predict)
return None
if __name__ == '__main__':
linear4()
KMeans总结
特点分析：采用迭代算法，直观易懂并且非常实用。
缺点：容易收敛到局部最优解（多次聚类）。
应用场景： 没有进行聚类之前（没有目标值）。
六、总结
代码集
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression, SGDRegressor, Ridge
from sklearn.metrics import mean_squared_error
import joblib
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score
def linear1():
"""
正规方程的优化方法对波士顿房价进行预测
:return:
"""
# 1）获取数据
boston = load_boston()
print("特征数量：\n", boston.data.shape)
# 2) 划分数据集
x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
# 3) 标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4）预估器
estimator = LinearRegression()
estimator.fit(x_train, y_train)
# 5)得出模型
print("正规方程——权重系数为：\n", estimator.coef_)
print("正规方程——偏置为：\n", estimator.intercept_)
# 6)模型评估
y_predict = estimator.predict(x_test)
print("预测房价：\n", y_predict)
error = mean_squared_error(y_test, y_predict)
print("正规方程——均方误差为：\n", error)
return None
def linear2():
"""
梯度下降的优化方法对波士顿房价进行预测
:return:
"""
# 1）获取数据
boston = load_boston()
# 2) 划分数据集
x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
# 3) 标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4）预估器
estimator = SGDRegressor(learning_rate="constant", eta0=0.01, max_iter=10000)
estimator.fit(x_train, y_train)
# 5)得出模型
print("梯度下降——权重系数为：\n", estimator.coef_)
print("梯度下降——偏置为：\n", estimator.intercept_)
# 6)模型评估
y_predict = estimator.predict(x_test)
print("预测房价：\n", y_predict)
error = mean_squared_error(y_test, y_predict)
print("梯度下降——均方误差为：\n", error)
return None
def linear3():
"""
岭回归对波士顿房价进行预测
:return:
"""
# 1）获取数据
boston = load_boston()
# 2) 划分数据集
x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
# 3) 标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4）预估器
estimator = Ridge(alpha=0.5, max_iter=10000)
estimator.fit(x_train, y_train)
# 保存模型
joblib.dump(estimator, "my.ridge.pkl")
# 加载模型
estimator = joblib.load("my.ridge.pkl")
# 5)得出模型
print("岭回归——权重系数为：\n", estimator.coef_)
print("岭回归——偏置为：\n", estimator.intercept_)
# 6)模型评估
y_predict = estimator.predict(x_test)
print("预测房价：\n", y_predict)
error = mean_squared_error(y_test, y_predict)
print("岭回归——均方误差为：\n", error)
return None
def linear4():
"""
KMeans算法对波士顿房价进行预测
:return:
"""
# 1）获取数据
boston = load_boston()
# 2) 划分数据集
x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
# 3) 标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4）预估器
estimator = KMeans(n_clusters=3)
estimator.fit(boston)
y_predict = estimator.predict(boston)
# 模型评估-轮廓系数
silhouette_score(boston, y_predict)
return None
if __name__ == '__main__':
# 代码1：正规方程的优化方法对波士顿房价进行预测
# linear1()
# 代码2：梯度下降的优化方法对波士顿房价进行预测
# linear2()
# 代码3：岭回归对波士顿房价进行预测
linear3()