吴恩达机器学习ex1 Python实现

机器学习小白入门，在看吴恩达机器学习课程的同时找到了课后的练习。开贴用于记录学习（copy）过程。
学习参考：吴恩达机器学习ex1

单变量线性回归

题目描述：在本部分的练习中，您将使用一个变量实现线性回归，以预测食品卡车的利润。假设你是一家餐馆的首席执行官，正在考虑不同的城市开设一个新的分店。该连锁店已经在各个城市拥有卡车，而且你有来自城市的利润和人口数据。
您希望使用这些数据来帮助您选择将哪个城市扩展到下一个城市。
数据集ex1data.txt见最后

1、导入工具包

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

2、读取数据

**
由于我是使用vitu.ai社区进行代码的编写，所以要先将数据集导入

path = 'ex1data.txt'
data = pd.read_csv(path,header=None,names=['Population','Profit'])
data.head()

3、数据可视化

data.plot(kind='scatter', x='Population', y='Profit', figsize=(12,8))
plt.show()

4、梯度下降

**
这个部分需要在现有数据集上，训练线性回归的参数θ。

加入一列x，用于更新θ0，然后我们将θ初始化为0，学习率初始化为0.01，迭代次数为1500次.

data.insert(0, 'Ones', 1)

4.1进行变量初始化

# 初始化X和y
cols = data.shape[1]
X = data.iloc[:,:-1]#X是data里的除最后列
y = data.iloc[:,cols-1:cols]#y是data最后一列

观察X（训练集）和y(目标变量）是否正确

X.head()#head()是观察前5行

y.head()

代价函数应该是numpy矩阵，所以我们需要转换X和Y，然后才能使用它们。我们还需要初始化theta。

X = np.matrix(X.values)
y = np.matrix(y.values)
theta = np.matrix(np.array([0,0]))

4.2计算代价函数（θ初始值为0）

def computeCost(X, y, theta):inner = np.power(((X * theta.T) - y), 2)return np.sum(inner) / (2 * len(X))
#这个部分计算J(Ѳ)，X是矩阵
computeCost(X, y, theta)

答案

4.3梯度下降

变化θ的值来使J(θ)变化，θ的最终结果将用来预测小吃店在35000及70000人城市规模的利润。

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) - yfor j in range(parameters):term = np.multiply(error, X[:,j])temp[0,j] = theta[0,j] - ((alpha / len(X)) * np.sum(term))theta = tempcost[i] = computeCost(X, y, theta)return theta, cost
#这个部分实现了Ѳ的更新

初始化学习速率以及要执行的迭代次数

alpha = 0.01
iters = 1500

运行梯度下降算法来使参数θ适合于训练集

g, cost = gradientDescent(X, y, theta, alpha, iters)
g

predict1 = [1,3.5]*g.T
print("predict1:",predict1)
predict2 = [1,7]*g.T
print("predict2:",predict2)
#预测35000和70000城市规模的小吃摊利润

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()
#原始数据以及拟合的直线

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
path = 'ex1data.txt'
data = pd.read_csv(path,header=None,names=['Population','Profit'])
data.head()
data.plot(kind='scatter', x='Population', y='Profit', figsize=(12,8))
plt.show()
data.insert(0, 'Ones', 1)
cols = data.shape[1]
X = data.iloc[:,:-1]#X是data里的除最后列
y = data.iloc[:,cols-1:cols]#y是data最后一列
X.head()#head()是观察前5行
y.head()
X = np.matrix(X.values)
y = np.matrix(y.values)
theta = np.matrix(np.array([0,0]))
def computeCost(X, y, theta):inner = np.power(((X * theta.T) - y), 2)return np.sum(inner) / (2 * len(X))
#这个部分计算J(Ѳ)，X是矩阵
computeCost(X, y, theta)
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) - yfor j in range(parameters):term = np.multiply(error, X[:,j])temp[0,j] = theta[0,j] - ((alpha / len(X)) * np.sum(term))theta = tempcost[i] = computeCost(X, y, theta)return theta, cost
#这个部分实现了Ѳ的更新
alpha = 0.01
iters = 1500
g, cost = gradientDescent(X, y, theta, alpha, iters)
g
predict1 = [1,3.5]*g.T
print("predict1:",predict1)
predict2 = [1,7]*g.T
print("predict2:",predict2)
#预测35000和70000城市规模的小吃摊利润
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()
#原始数据以及拟合的直线

数据ex1data.txt

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