吴恩达《机器学习》ex1

本文是吴恩达《机器学习》课程中的习题一的python实现。

简介

习题一围绕线性回归进行，分别在人口(Population)-利润(Profit)数据集和房屋信息数据集(size, num,price)中训练模型，并进行预测。所使用的数据可在文末获取。

人口-利润数据集

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

# read data
original_data = pd.read_csv('data/ex1data1.txt', header=None, names=["population","profit"])
original_data.head()
# outputs
# 	population	profit
# 	0	6.1101	17.5920
# 	1	5.5277	9.1302
# 	2	8.5186	13.6620
# 	3	7.0032	11.8540
# 	4	5.8598	6.8233

# plot data
original_data.plot(kind='scatter',x='population',y='profit',figsize=(20,10))
plt.show

# define cost function. here we use Euclidean distance(欧几里得距离)
# X,y,theta are matrices
def cost_function(X,y,theta):
	error = X * theta.T - y
    return np.sum(np.power(error,2)) /(2 * len(X)) 

# insert 1 vertically, used to match constant b
original_data.insert(0,'ones',1)
X = original_data.iloc[:,:-1]
y = original_data.iloc[:,original_data.shape[1]-1:original_data.shape[1]]
X = np.matrix(X.values)
y = np.matrix(y.values)
# init theta as zero. although random value almost always get better performance, we use zero here
theta = np.matrix(np.array([0,0]))
X.shape,y.shape,theta.shape
# outputs
# ((97, 2), (97, 1), (1, 2))

# define gradient_descent function
# none vectorized implementation
# alpha here means learning rate
def gradient_descent(X,y,theta,alpha,iter):
    cost = np.zeros(iter)
    temp = np.matrix(np.zeros(theta.shape))
    for i in range(iter):
        y_prediction= X * theta.T
        error = y_prediction - y
        for j in range(theta.ravel().shape[1]):
        	step = alpha * np.sum(np.multiply(X[:,j],error)) /len(X)
            temp[0,j]= theta[0,j] - step
        theta = temp
        cost[i] = cost_function(X,y,theta) 
    return theta, cost

# vectorized implementation gets rid of inner loops to improve performance
def gradient_descent(X,y,theta,alpha,iter):
    cost = np.zeros(iter)
    temp = np.matrix(np.zeros(theta.shape))
    for i in range(iter):
        y_prediction= X * theta.T
        error = y_prediction - y
        temp = theta - (alpha / len(X)) * error.T * X
        theta = temp
        cost[i] = cost_function(X,y,theta) 
    return theta, cost

# fit linear model
alpha = 0.01
iter = 50000
theta, cost =gradient_descent(X,y,theta,alpha, iter)
theta, cost
# outputs
# (matrix([[-3.89578088,  1.19303364]]),array([6.73719046, 5.93159357, 5.90115471, ..., 4.47697138, 4.47697138,4.47697138]))

# plot our model
x = np.linspace(original_data.population.min(), original_data.population.max(), 100)
f = theta[0, 0] + (theta[0, 1] * x)

fig, ax = plt.subplots(figsize=(20,10))
ax.plot(x, f, 'r', label='Prediction')
ax.scatter(original_data.population, original_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()

房屋信息数据集

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

# read data
original_data2 = pd.read_csv('data/ex1data2.txt', header=None, names=["population","profit"])
original_data2.head()
# outputs
#	size	num		price
#0	2104	3	399900
#1	1600	3	329900
#2	2400	3	369000
#3	1416	2	232000
#4	3000	4	539900

# data ranges in the columns vary, so the data needs to be normalized.
# the normalization in the next line is incorrect, as only variable X should be normalized.
original_data2 = (original_data2 - original_data2.mean())/original_data2.std()
original_data2.insert(0,'ones',1)

# get params ready
original_data2 = pd.read_csv('data/ex1data2.txt', header=None, names=["population","profit"])
original_data2.insert(0,'ones',1)
X = original_data2.iloc[:,0:-1]
X = np.matrix(X.values)
X = (X-X.mean())/X.std()
y = original_data2.iloc[:,cols-1:cols]
y = np.matrix(y.values)
theta = np.matrix(np.zeros(3))

def cost_function(X,y,theta):
	error = X * theta.T - y
    return np.sum(np.power(error,2)) /(2 * len(X)) 

def gradient_descent(X,y,theta,alpha,iter):
    cost = np.zeros(iter)
    temp = np.matrix(np.zeros(theta.shape))
    for i in range(iter):
        y_prediction= X * theta.T
        error = y_prediction - y
        temp = theta - (alpha / len(X)) * error.T * X
        theta = temp
        cost[i] = cost_function(X,y,theta) 
    return theta, cost

alpha = 0.01
iter = 5000
theta,cost = gradient_descent(X,y,theta,alpha,iter)
theta,cost
# outputs
# (matrix([[-126521.82261505,  140760.46376147, -126330.73512184]]) array([6.20680077e+10, 5.87415374e+10, 5.56011097e+10, ..., 2.05772493e+09, 2.05772493e+09, 2.05772493e+09]))

在归一化数据的时候，训练集和测试集要保证使用同样的过程。否则预测的结果将会不准确。

数据集下载

链接: https://pan.baidu.com/s/1zteJBsMJ0GRwqRb5opOgwg 提取码: 78ah