linear regression code with python

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

path = 'F:\coursera_homework\machine-learning-ex1\ex1\ex1data1.txt'  
data = pd.read_csv(path, header=None, names=['Population', 'Profit'])  
print data.head()
#print data.describe()
'''fig=plt.figure()
ax = fig.add_subplot(111)
ax.scatter(data.Population, data.Profit, label='Traning Data')
ax.set_xlabel('Population')  
ax.set_ylabel('Profit') 
plt.show()'''
data.plot(kind='scatter', x='Population', y='Profit', figsize=(12,8)) 
plt.show()

def computeCost(X, y, theta):  #代价函数
    inner = np.power(((X * theta.T) - y), 2)
    return np.sum(inner) / (2 * len(X))

data.insert(0, 'Ones', 1)
#print data.head()
cols = data.shape[1]  
X = data.iloc[:,0:cols-1]  
y = data.iloc[:,cols-1:cols] 
#print X
X = np.matrix(X.values)  
y = np.matrix(y.values)  
theta = np.matrix(np.array([0,0]))  
#print X
#print y
def gradientDescent(X, y, theta, alpha, iters):  
    temp = np.matrix(np.zeros(theta.shape))
    parameters = int(theta.ravel().shape[1])
    cost = np.zeros(iters)

    for i in range(iters):
        error = (X * theta.T) - y

        for j in range(parameters):
            term = np.multiply(error, X[:,j])
            temp[0,j] = theta[0,j] - ((alpha / len(X)) * np.sum(term))

        theta = temp
        cost[i] = computeCost(X, y, theta)

    return theta, cost

def errorate(g,X,y):  #求错误率,亲测为1,因为是回归问题
    error=0
    D=np.mat(np.zeros(y.shape))
    len=X.shape[0]
    print "len",len
    for i in range(len):
        D[i]=g[0,0]+g[0,1]*X[i,1:]
        if D[i]!=y[i]: error+=1
    print "e:",error
    print "D:",D[0:10]
    return error/X.shape[0]

alpha=0.01
iters=1000
g,cost=gradientDescent(X, y, theta, alpha, iters)  
print g  #theta的值
print cost[-1]
print "errorate:",errorate(g,X,y)


x = np.linspace(data.Population.min(), data.Population.max(), 100)  
f = g[0, 0] + (g[0, 1] * x)

fig, ax = plt.subplots(figsize=(12,8))  
ax.plot(x, f, 'r', label='Prediction')  
ax.scatter(data.Population, data.Profit, label='Traning Data')  
ax.legend(loc=2)  
ax.set_xlabel('Population')  
ax.set_ylabel('Profit')  
ax.set_title('Predicted Profit vs. Population Size')  
plt.show()

fig, ax = plt.subplots(figsize=(12,8))  
ax.plot(np.arange(iters), cost, 'r')  
ax.set_xlabel('Iterations')  
ax.set_ylabel('Cost')  
ax.set_title('Error vs. Training Epoch')  
plt.show()

处理的数据如下(左边是店的population,右边是对应的profit):

6.1101,17.592
5.5277,9.1302
8.5186,13.662
7.0032,11.854
5.8598,6.8233
8.3829,11.886
7.4764,4.3483
8.5781,12
6.4862,6.5987
5.0546,3.8166
5.7107,3.2522
14.164,15.505
5.734,3.1551
8.4084,7.2258
5.6407,0.71618
5.3794,3.5129
6.3654,5.3048
5.1301,0.56077
6.4296,3.6518
7.0708,5.3893
6.1891,3.1386
20.27,21.767
5.4901,4.263
6.3261,5.1875
5.5649,3.0825
18.945,22.638
12.828,13.501
10.957,7.0467
13.176,14.692
22.203,24.147
5.2524,-1.22
6.5894,5.9966
9.2482,12.134
5.8918,1.8495
8.2111,6.5426
7.9334,4.5623
8.0959,4.1164
5.6063,3.3928
12.836,10.117
6.3534,5.4974
5.4069,0.55657
6.8825,3.9115
11.708,5.3854
5.7737,2.4406
7.8247,6.7318
7.0931,1.0463
5.0702,5.1337
5.8014,1.844
11.7,8.0043
5.5416,1.0179
7.5402,6.7504
5.3077,1.8396
7.4239,4.2885
7.6031,4.9981
6.3328,1.4233
6.3589,-1.4211
6.2742,2.4756
5.6397,4.6042
9.3102,3.9624
9.4536,5.4141
8.8254,5.1694
5.1793,-0.74279
21.279,17.929
14.908,12.054
18.959,17.054
7.2182,4.8852
8.2951,5.7442
10.236,7.7754
5.4994,1.0173
20.341,20.992
10.136,6.6799
7.3345,4.0259
6.0062,1.2784
7.2259,3.3411
5.0269,-2.6807
6.5479,0.29678
7.5386,3.8845
5.0365,5.7014
10.274,6.7526
5.1077,2.0576
5.7292,0.47953
5.1884,0.20421
6.3557,0.67861
9.7687,7.5435
6.5159,5.3436
8.5172,4.2415
9.1802,6.7981
6.002,0.92695
5.5204,0.152
5.0594,2.8214
5.7077,1.8451
7.6366,4.2959
5.8707,7.2029
5.3054,1.9869
8.2934,0.14454
13.394,9.0551
5.4369,0.61705

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Sure, I can help you with that! Logistic regression is a popular algorithm for binary classification problems. In Python, you can use the scikit-learn library to implement logistic regression. Here's an example code snippet for logistic regression in Python: ```python from sklearn.linear_model import LogisticRegression from sklearn.model_selection import train_test_split from sklearn.metrics import accuracy_score # Assuming you have your data and labels ready X = ... # Input features y = ... # Binary labels # Split the data into training and testing sets X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # Create a logistic regression model model = LogisticRegression() # Train the model model.fit(X_train, y_train) # Make predictions on the test set y_pred = model.predict(X_test) # Calculate accuracy score accuracy = accuracy_score(y_test, y_pred) print("Accuracy:", accuracy) ``` This code imports the necessary modules, splits the data into training and testing sets using `train_test_split`, creates a logistic regression model using `LogisticRegression()`, trains the model using `fit`, makes predictions on the test set using `predict`, and calculates the accuracy score using `accuracy_score`. Make sure to replace `X` and `y` with your actual data and labels. Additionally, you may need to preprocess your data before applying logistic regression. I hope this helps you get started with logistic regression in Python! Let me know if you have any further questions.
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值