吴恩达机器学习作业_python实现
Posted 挂科难
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了吴恩达机器学习作业_python实现相关的知识,希望对你有一定的参考价值。
必做部分:(主要参考了黄海广老师的文档)
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
df = pd.read_csv('ex1data1.txt', names=['population', 'profit'])
data = df
#def normalize_feature(df):
#return df.apply(lambda column: (column - column.mean()) / column.std())#特征缩放
def get_X(df):#读取特征
ones = pd.DataFrame({'ones': np.ones(len(df))})#ones是m行1列的dataframe
data = pd.concat([ones, df], axis=1) # 合并数据,根据列合并 axis: 需要合并链接的轴,0是行,1是列
return data.iloc[:, :-1]
def linear_cost(theta , X , y):
m = X.shape[0] #样本数
inner = X @ theta - y #与目标的差值即h(theta),inner算出来为一行
square_sum = inner.T @ inner #h(theta)的平方
cost = square_sum/(2*m)
return cost
def gradient(theta, X, y):
m = X.shape[0]
inner = X.T @ (X@theta - y) #X仅有仅有一个特征,恒为1的不算,即该语句算的是更新theta1时,损失函数对theta1的求导
return inner/m
def batch_gradient_decent(theta, X, y, epoch, alpha=0.02):
cost_data = [linear_cost(theta, X, y)]
for _ in range(epoch): #_仅是一个循环标志,在循环中不会用到
theta = theta - alpha * gradient(theta, X, y)
cost_data.append(linear_cost(theta, X, y))
return theta, cost_data
X = get_X(df)
y = df.values[:, 1]
theta = np.zeros(df.shape[1])
epoch = 6000
final_theta, cost_data = batch_gradient_decent(theta, X, y, epoch)
b = final_theta[0]
k = final_theta[1]
plt.scatter(data.population, data.profit, label="Training data")
plt.plot(data.population, data.population*k + b, label="Prediction")
plt.xlabel('population')
plt.ylabel('profit')
plt.legend(loc=2)
forecast = float(input('population'))
predict_profit = forecast*k+b
print(predict_profit)
plt.scatter(forecast, predict_profit, marker='+', c='red')
plt.show()
我预测值(forecast)输入的23,用红色标记了
选作部分
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
ax = plt.axes(projection='3d')
df = pd.read_csv('ex1data2.txt', names=['square', 'bedrooms', 'price'])
def normalize_feature(df):
return df.apply(lambda column: (column - column.mean()) / column.std())
def get_X(df):#读取特征
ones = pd.DataFrame({'ones': np.ones(len(df))})#ones是m行1列的dataframe
data = pd.concat([ones, df], axis=1) # 合并数据,根据列合并 axis: 需要合并链接的轴,0是行,1是列
return data.iloc[:, :-1]
def lr_cost(theta, X, y):
m = X.shape[0]#m为样本数
inner = X @ theta - y # R(m*1),X @ theta等价于X.dot(theta)
square_sum = inner.T @ inner
cost = square_sum / (2 * m)
return cost
def gradient(theta, X, y):
m = X.shape[0] #样本个数
inner = X.T @ (X @ theta - y) # (m,n).T @ (m, 1) -> (n, 1),X @ theta等价于X.dot(theta)
return inner / m
def batch_gradient_decent(theta, X, y, epoch, alpha=0.01):
cost_data = [lr_cost(theta, X, y)]
for _ in range(epoch):
theta = theta - alpha * gradient(theta, X, y)
cost_data.append(lr_cost(theta, X, y))
return theta, cost_data
def normalEqn(X, y): #正规方程
theta = np.linalg.inv(X.T@X)@X.T@y#X.T@X等价于X.T.dot(X)
return theta
data = normalize_feature(df) #特征缩放
y = data.values[:, 2]
X = get_X(data)
ax.scatter(X['square'], X['bedrooms'], y, alpha=0.3)
plt.xlabel('square')
plt.ylabel('bedrooms')
ax.set_zlabel(r'$prices$')
epoch = 500
alpha = 0.01
theta = np.zeros(X.shape[1]) #在该问题中X有三个特征(1,square,bedrooms),所以theta初始为三个零
final_theta, cost_data = batch_gradient_decent(theta, X, y, epoch, alpha=alpha)
D = final_theta[0]
A = final_theta[1]
B = final_theta[2]
Z = A*X['square'] + B*X['bedrooms'] + D
ax.plot_trisurf(X['square'], X['bedrooms'], Z,
linewidth=0, antialiased=False)
predict_square = float(input('square:'))
predict_square = ((predict_square - df.square.mean())/df.square.std())
predict_bedrooms = float(input('bedrooms'))
predict_bedrooms = ((predict_bedrooms - df.bedrooms.mean())/df.bedrooms.std())
p = A * predict_square + B*predict_bedrooms + D
ax.scatter(predict_square, predict_bedrooms, marker='+', c='red')
p = p * df.price.std() + df.price.mean()
print('I predict the prices is :')
print(p)
plt.show()
输入为
square=1635
bedrooms=3
I predict the prices is :
292611.913236568
理论上说预测的点应该在所画的平面上,但实际却不在,可能是因为我平面画的不对。预测结果可以使用。
以上是关于吴恩达机器学习作业_python实现的主要内容,如果未能解决你的问题,请参考以下文章