# -*- coding: utf-8 -*-
"""
Created on Sat Jul 4 16:49:40 2020
@author: cheetah023
"""
import numpy as np
import scipy.io as sci
import matplotlib.pyplot as plt
import scipy.optimize as opt
#函数定义
def cofiCostFunc(params, Y, R, num_users,
num_movies, num_features, lamda):
J = 0
X = np.reshape(params[0:num_movies*num_features],[num_movies,num_features])
Theta = np.reshape(params[num_movies*num_features:],[num_users,num_features])
J = np.sum(((np.dot(X,Theta.T) - Y) ** 2) * R) / 2
reg = (lamda / 2) * (np.sum(Theta ** 2) + np.sum(X ** 2))
J = J + reg
return J
def cofiGradient(params, Y, R, num_users,
num_movies, num_features, lamda):
X = np.reshape(params[0:num_movies*num_features],[num_movies,num_features])
Theta = np.reshape(params[num_movies*num_features:],[num_users,num_features])
X_grad = ((X @ Theta.T - Y) * R) @ Theta + lamda * X
Theta_grad = ((X @ Theta.T - Y) * R).T @ X + lamda * Theta
grad = np.r_[X_grad.flatten(),Theta_grad.flatten()]
return grad
def loadMovieList():
fid = open('movie_ids.txt','r',encoding='Latin-1')
n =1682
movieList = []
for line in fid:
idx = line.find(' ') + 1
movieList.append(line[idx:])
fid.close()
return movieList
def normalizeRatings(Y, R):
m,n = Y.shape
y_mean = np.sum(Y,axis=1) / np.sum(R,axis=1)
y_mean = y_mean.reshape([m,1])
y_mean_t = np.tile(y_mean,(1,n))
y_norm = (Y - y_mean_t) * R
return y_norm, y_mean
#Part 1: Loading movie ratings dataset
data = sci.loadmat('ex8_movies.mat')
#print('data.keys',data.keys())
Y = data['Y']
R = data['R']
print('Y:',Y.shape)
print('R:',R.shape)
score1 = np.sum(Y[0,:]) / np.sum(R[0,:])
print('Average rating for movie 1 (Toy Story):',score1);
plt.figure(0)
plt.imshow(Y)
plt.xlabel('Users')
plt.ylabel('Movies')
#Part 2: Collaborative Filtering Cost Function
data = sci.loadmat('ex8_movieParams.mat')
#print('data',data.keys())
X = data['X']
Theta = data['Theta']
num_users = data['num_users']
num_movies = data['num_movies']
num_features = data['num_features']
#减少数量，跑得快
num_users = 4; num_movies = 5; num_features = 3
X = X[0:num_movies, 0:num_features]
Theta = Theta[0:num_users, 0:num_features]
Y = Y[0:num_movies, 0:num_users]
R = R[0:num_movies, 0:num_users]
params = np.r_[X.flatten(),Theta.flatten()]
J = cofiCostFunc(params, Y, R, num_users,
num_movies,num_features, 0)
print('Cost at loaded parameters:',J)
print('(this value should be about 22.22)')
#Part 3: Collaborative Filtering Gradient
#检查梯度的函数没写
#Part 4: Collaborative Filtering Cost Regularization
J = cofiCostFunc(params, Y, R, num_users,
num_movies,num_features, 1.5)
print('Cost at loaded parameters (lambda = 1.5):',J)
print('(this value should be about 31.34)')
#Part 5: Collaborative Filtering Gradient Regularization
#检查梯度的函数没写
#Part 6: Entering ratings for a new user
movieList = loadMovieList()
my_ratings = np.zeros([1682, 1])
my_ratings[0] = 4
my_ratings[97] = 2
my_ratings[6] = 3
my_ratings[11]= 5
my_ratings[53] = 4
my_ratings[63]= 5
my_ratings[65]= 3
my_ratings[68] = 5
my_ratings[182] = 4
my_ratings[225] = 5
my_ratings[354]= 5
for i in range(0, len(my_ratings)):
if my_ratings[i] > 0:
print('Rated %d for %s'%(my_ratings[i],movieList[i]))
#Part 7: Learning Movie Ratings
data = sci.loadmat('ex8_movies.mat')
Y = data['Y']
R = data['R']
Y = np.column_stack([my_ratings,Y])
R_myrating = my_ratings != 0
R = np.column_stack([R_myrating,R])
[Ynorm, Ymean] = normalizeRatings(Y, R)
num_users = Y.shape[1]
num_movies = Y.shape[0]
num_features = 10;
X = np.random.random([num_movies,num_features])
theta = np.random.random([num_users,num_features])
initial_params = np.r_[X.flatten(),theta.flatten()]
lamda = 10
params = opt.fmin_cg(f=cofiCostFunc,x0=initial_params,
args=(Ynorm, R, num_users,num_movies, num_features, lamda),
fprime=cofiGradient,
maxiter=100,disp=True)
X = np.reshape(params[0:num_movies*num_features],[num_movies,num_features])
theta = np.reshape(params[num_movies*num_features:],[num_users,num_features])
P = X @ theta.T
my_predictions = P[:,0] + Ymean.flatten()
print('P',P.shape)
print('Ymean',Ymean.shape)
print('my_predictions',my_predictions.shape)
idx = np.argsort(my_predictions)[::-1]
print('idx',idx.shape)
for i in range(0,10):
j = idx[i]
print('Predicting rating ',my_predictions[j])
print('for ',movieList[j])
运行结果：
Y: (1682, 943) R: (1682, 943) Average rating for movie 1 (Toy Story): 3.8783185840707963 Cost at loaded parameters: 22.224603725685675 (this value should be about 22.22) Cost at loaded parameters (lambda = 1.5): 31.34405624427422 (this value should be about 31.34) Rated 4 for Toy Story (1995)
Rated 3 for Twelve Monkeys (1995)
Rated 5 for Usual Suspects, The (1995)
Rated 4 for Outbreak (1995)
Rated 5 for Shawshank Redemption, The (1994)
Rated 3 for While You Were Sleeping (1995)
Rated 5 for Forrest Gump (1994)
Rated 2 for Silence of the Lambs, The (1991)
Rated 4 for Alien (1979)
Rated 5 for Die Hard 2 (1990)
Rated 5 for Sphere (1998)
Warning: Maximum number of iterations has been exceeded. Current function value: 38956.345281 Iterations: 100 Function evaluations: 153 Gradient evaluations: 153 P (1682, 944) Ymean (1682, 1) my_predictions (1682,) idx (1682,) Predicting rating 5.00000042235092 for Marlene Dietrich: Shadow and Light (1996)
Predicting rating 5.000000293775594 for Santa with Muscles (1996)
Predicting rating 5.000000254944607 for They Made Me a Criminal (1939)
Predicting rating 5.000000222955008 for Entertaining Angels: The Dorothy Day Story (1996)
Predicting rating 5.000000130674626 for Saint of Fort Washington, The (1993)
Predicting rating 5.000000102308117 for Great Day in Harlem, A (1994)
Predicting rating 4.999999978328779 for Someone Else's America (1995)
Predicting rating 4.999995528723899 for Star Kid (1997)
Predicting rating 4.9999934984042165 for Aiqing wansui (1994)
Predicting rating 4.99999223680014 for Prefontaine (1997)
总结：
1、检查梯度的函数checkCostFunction没有实现
2、矩阵内积@用起来比dot简洁
