线性回归和Ridge回归

网址：https://www.cnblogs.com/pinard/p/6023000.html

线性回归和交叉验证

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn import datasets,linear_model

读取csv里面的数据

data = pd.read_excel("F:dataCCPPFolds5x2_pp.xlsx");
x = data[['AT', 'V', 'AP', 'RH']]
y = data[['PE']]

划分训练集和测试集

from sklearn.cross_validation import train_test_split

x为待划分的样本特征集合，y为待划分的样本标签，x,y经train_test_split划分后，x_train为训练集特征集合，x_test为训练的标签；y_train为测试集合的样本特征集合，y_test为测试集合的样本标签

x_train,x_test,y_train,y_test = train_test_split(x, y, random_state=1)#可以通过test_size来设置划分比列

导入线性模型

from sklearn.linear_model import LinearRegression
linreg = LinearRegression()#线性回归函数

拟合

linreg.fit(x_train,y_train)
print("linreg.intercept_",linreg.intercept_,"linreg.coef_",linreg.coef_)

模型拟合测试级

y_pred = linreg.predict(x_test)
from sklearn import metrics

用scikit-learn计算MSE

print("MSE:",metrics.mean_squared_error(y_test, y_pred))

用scikit-learn计算RMSE

print("RMSE:",np.sqrt(metrics.mean_squared_error(y_test, y_pred)))

利用交叉验证来优化模型

from sklearn.model_selection import cross_val_predict

cv为s折交验证

predicted = cross_val_predict(linreg, x, y, cv=100)
print("predicted:",predicted.shape)

用scikit-learn计算MSE

print("MSE:",metrics.mean_squared_error(y, predicted))

用scikit-learn计算RMSE

print ("RMSE:",np.sqrt(metrics.mean_squared_error(y, predicted)))

画出图像

fig, ax = plt.subplots()
ax.scatter(y, predicted)
ax.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4)
ax.set_xlabel('Measured')
ax.set_ylabel('Predicted')
plt.show()

Ridge回归用scikit-learn选择Ridge回归超参数α

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn import datasets,linear_model
from sklearn import metrics

读取csv里面的数据

data = pd.read_excel("F:dataCCPPFolds5x2_pp.xlsx");
x = data[['AT', 'V', 'AP', 'RH']]
y = data[['PE']]

划分训练集和测试集

from sklearn.model_selection import train_test_split

x为待划分的样本特征集合，y为待划分的样本标签，x,y经train_test_split划分后，x_train为训练集特征集合，x_test为训练的标签；y_train为测试集合的样本特征集合，y_test为测试集合的样本标签

x_train,x_test,y_train,y_test = train_test_split(x, y, random_state=1)#可以通过test_size来设置划分比列
n_alphas = 200
alphas = np.logspace(-10,-2,n_alphas)
print("alphas:",alphas)
clf = linear_model.Ridge(fit_intercept=False)
coefs = []
for a in alphas:
#设置本次循环的超参数
clf.set_params(alpha=a)
#针对每个alpha做ridge回归
clf.fit(x_train, y_train)
y_predict = clf.predict(x_test)
error = metrics.mean_squared_error(y_predict,y_test)#计算方差
print("error:",error)
# 把每一个超参数alpha对应的theta存下来
coefs.append(clf.coef_)
print("coefs:",coefs)
from sklearn import metrics

ax = plt.gca()

ax.plot(alphas, coefs)

#将alpha的值取对数便于画图

ax.set_xscale('log')

#翻转x轴的大小方向，让alpha从大到小显示

ax.set_xlim(ax.get_xlim()[::-1])

plt.xlabel('alpha')

plt.ylabel('weights')

plt.title('Ridge coefficients as a function of the regularization')

plt.axis('tight')

plt.show()

自己编写的逻辑编写代码

定义LR回归模型

class LogisticReression:
def init(self, max_iter=200, learning_rate=0.01):
self.max_iter = max_iter
self.learning_rate = learning_rate
def sigmoid(self, x):
return 1 / (1 + exp(-x))
def data_matrix(self, X):
data_mat = []
for d in X:
data_mat.append([1.0, d])
return data_mat
#训练
def train(self, X, y):
# label = np.mat(y)
data_mat = self.data_matrix(X) # mn
self.weights = np.zeros((len(data_mat[0]), 1), dtype=np.float32)
for iter_ in range(self.max_iter):
for i in range(len(X)):
result = self.sigmoid(np.dot(data_mat[i], self.weights))
error = y[i] - result
self.weights += self.learning_rate * error * np.transpose( [data_mat[i]])
print('LR模型学习率={},最大迭代次数={}'.format( self.learning_rate, self.max_iter))
# 准确率
def accuracy(self, X_test, y_test):
right = 0
X_test = self.data_matrix(X_test)
for x, y in zip(X_test, y_test):
result = np.dot(x, self.weights)
if (result > 0 and y == 1) or (result < 0 and y == 0):
right += 1
return right / len(X_test)

构建数据

def create_data():
iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df['label'] = iris.target
df.columns = ['sepal length', 'sepal width', 'petal length', 'petal width', 'label']
data = np.array(df.iloc[:100, [0,1,-1]])
return data[:,:2], data[:,-1]
X, y = create_data()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

训练数据

LR = LogisticReression()
LR.train(X_train, y_train)

计算测试精度

score = LR.accuracy(X_test, y_test)
print("score:",score)
x_ponits = np.arange(3, 9)
y_ = -(LR.weights[1]*x_ponits + LR.weights[0])/LR.weights[2]
plt.plot(x_ponits, y_)

绘制图

plt.scatter(X[:50,0],X[:50,1], label='0')
plt.scatter(X[50:,0],X[50:,1], label='1')
plt.legend()
plt.show()

scikit-learn

# from sklearn import datasets

# from sklearn.linear_model import LogisticRegression

# from sklearn.model_selection import train_test_split

# from sklearn.preprocessing import StandardScaler

# from sklearn.metrics import accuracy_score

# import matplotlib.pyplot as plt

# from matplotlib.colors import ListedColormap

# from mlxtend.plotting import plot_decision_regions

# from sklearn.metrics import accuracy_score

# import numpy as np

# iris = datasets.load_iris()

# x = iris.data[:,[2,3]]

# y = iris.target

# print("y:",y)

# X_train,X_test,y_train,y_test = train_test_split(x , y, test_size=0.3, random_state = 1)

# print("x_train:",X_test.shape)

# print("y_train;",y_test.shape)

# #sigmoid 函数

# def sigmoid(z):

# return 1.0/(1.0+np.exp(-z))

# sc = StandardScaler()

# sc.fit(X_train)

# X_train_std = sc.transform(X_train)

# X_test_std = sc.transform(X_test)

# print("X_test:",X_test)

# Ir = LogisticRegression(C=1000.0,random_state=1)

# Ir.fit(X_train_std,y_train)

# y_pred = Ir.predict(X_test)

# print("y_test:",y_test)

# print("y_pred:",y_pred)

# print("score:",accuracy_score(y_test, y_pred))

# print("Ir.coef:",Ir.coef_)

# X_combined_std = np.vstack((X_train_std,X_test_std))

# y_combined = np.hstack((y_train,y_test))

# plot_decision_regions(X=X_combined_std,y=y_combined,clf=Ir,legend = 2)

# plt.xlabel('petal length [standardized]')

# plt.ylabel('petal width [standardized]')

# plt.legend(loc='upper right')

# plt.savefig('Iris.png')

# plt.show()

from math import exp

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

#定义LR回归模型

class LogisticReression:

def init(self, max_iter=200, learning_rate=0.01):

self.max_iter = max_iter

self.learning_rate = learning_rate

def sigmoid(self, x):

return 1 / (1 + exp(-x))

def data_matrix(self, X):

data_mat = []

for d in X:

data_mat.append([1.0, *d])

return data_mat

#训练

def train(self, X, y):

# label = np.mat(y)

data_mat = self.data_matrix(X) # m*n

self.weights = np.zeros((len(data_mat[0]), 1), dtype=np.float32)

for iter_ in range(self.max_iter):

for i in range(len(X)):

result = self.sigmoid(np.dot(data_mat[i], self.weights))

error = y[i] - result

self.weights += self.learning_rate * error * np.transpose( [data_mat[i]])

print('LR模型学习率={},最大迭代次数={}'.format( self.learning_rate, self.max_iter))

# 准确率

def accuracy(self, X_test, y_test):

right = 0

X_test = self.data_matrix(X_test)

for x, y in zip(X_test, y_test):

result = np.dot(x, self.weights)

if (result > 0 and y == 1) or (result < 0 and y == 0):

right += 1

return right / len(X_test)

#构建数据

def create_data():

iris = load_iris()

df = pd.DataFrame(iris.data, columns=iris.feature_names)

df['label'] = iris.target

df.columns = ['sepal length', 'sepal width', 'petal length', 'petal width', 'label']

data = np.array(df.iloc[:100, [0,1,-1]])

return data[:,:2], data[:,-1]

X, y = create_data()

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

#训练数据

LR = LogisticReression()

LR.train(X_train, y_train)

#计算测试精度

score = LR.accuracy(X_test, y_test)

print("score:",score)

x_ponits = np.arange(3, 9)

y_ = -(LR.weights[1]*x_ponits + LR.weights[0])/LR.weights[2]

plt.plot(x_ponits, y_)

# 绘制图

plt.scatter(X[:50,0],X[:50,1], label='0')

plt.scatter(X[50:,0],X[50:,1], label='1')

plt.legend()

plt.show()

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn import metrics
import seaborn as sn
import matplotlib.pyplot as plt

第一步构建数据

candidates = {'gmat': [780,750,690,710,680,730,690,720,740,690,610,690,710,680,770,610,580,650,540,590,620,600,550,550,570,670,660,580,650,660,640,620,660,660,680,650,670,580,590,690],
'gpa': [4,3.9,3.3,3.7,3.9,3.7,2.3,3.3,3.3,1.7,2.7,3.7,3.7,3.3,3.3,3,2.7,3.7,2.7,2.3,3.3,2,2.3,2.7,3,3.3,3.7,2.3,3.7,3.3,3,2.7,4,3.3,3.3,2.3,2.7,3.3,1.7,3.7],
'work_experience': [3,4,3,5,4,6,1,4,5,1,3,5,6,4,3,1,4,6,2,3,2,1,4,1,2,6,4,2,6,5,1,2,4,6,5,1,2,1,4,5],
'admitted': [1,1,1,1,1,1,0,1,1,0,0,1,1,1,1,0,0,1,0,0,0,0,0,0,0,1,1,0,1,1,0,0,1,1,1,0,0,0,0,1] }
df = pd.DataFrame(candidates,columns= ['gmat', 'gpa','work_experience','admitted'])
X = df[['gmat', 'gpa','work_experience']]
y = df['admitted']

75%的数据用来做训练集，25%的数据用作测试集

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.25,random_state=0)
logistic_regression= LogisticRegression()

训练

logistic_regression.fit(X_train,y_train)

预测

y_pred=logistic_regression.predict(X_test)

绘制热力图

confusion_matrix = pd.crosstab(y_test, y_pred, rownames=['Actual'], colnames=['Predicted'])
sn.heatmap(confusion_matrix, annot=True)
plt.show()
print('精度: ',metrics.accuracy_score(y_test, y_pred))