def predictForUser(user, W, training, predictType="exp"):
### TO IMPLEMENT
# given a user ID, predicts all movie ratings for the user
return [
predictMovieForUser(movie, user, W, training, predictType=predictType)
for movie in lib.getUsefulStats(training)["u_movies"]
]
def predictForUser(user, W, training, predictType="exp"):
trStats = lib.getUsefulStats(training)
# print(trStats["u_movies"])
return [
predictMovieForUser(movie, user, W, training, predictType)
for movie in trStats["u_movies"]
]
def predictForUser(user, W, training, predictType="exp"):
### TO IMPLEMENT
# given a user ID, predicts all movie ratings for the user
# similar to the above predict function but just for 1 user.
return [
predictMovieForUser(movie, user, W, training, predictType=predictType)
for movie in lib.getUsefulStats(training)["u_movies"]
]
def predictForUser(user, W, training, predictType="exp"):
### TO IMPLEMENT
# given a user ID, predicts all movie ratings for the user
trainingStats = lib.getUsefulStats(training)
user_ratings = []
for movie in trainingStats:
user_ratings.append(
predictMovieForUser(movie, user, W, training, predictType))
return np.array(user_ratings)
def predictForUser(user, W, training, predictType="exp"):
### TO IMPLEMENT
# given a user ID, predicts all movie ratings for the user
###########################################################################
# START OF YOUR CODE #
###########################################################################
all_movies = lib.getUsefulStats(training)["u_movies"]
movies_pred = []
for movie in all_movies:
pred = predictMovieForUser(movie, user, W, training, predictType=predictType)
movies_pred.append(pred)
return movies_pred
import numpy as np
import rbm
import projectLib as lib
import pickle
training = lib.getTrainingData()
validation = lib.getValidationData()
# You could also try with the chapter 4 data
# training = lib.getChapter4Data()
trStats = lib.getUsefulStats(training)
vlStats = lib.getUsefulStats(validation)
K = 5
# SET PARAMETERS HERE!!!
# number of hidden units
# F = 10
epochs = 30
# gradientLearningRate = 0.1
# file for past trained data
fileName = 'best_W'
try:
# try to load existing trained weight, if any
best_W = pickle.load(open(fileName, 'rb'))
except:
# otherwise, train/tune
## Parameter to tune
import numpy as np
import rbm
import projectLib as lib
import pickle
training = lib.getTrainingData()
validation = lib.getValidationData()
# You could also try with the chapter 4 data
# training = lib.getChapter4Data()
trStats = lib.getUsefulStats(training)
vlStats = lib.getUsefulStats(validation)
K = 5
# mode = 'batch'
mode = 'single'
finalW = np.zeros([5,5,5])
finalRMSE = 100
def run_RBM(F, epochs, epsilon, B, weightcost, momentum, f, mode):
# Initialise all our arrays
W = rbm.getInitialWeights(trStats["n_movies"], F, K)
bestW = np.zeros(W.shape)
bestRMSE = 100
posprods = np.zeros(W.shape)
negprods = np.zeros(W.shape)
grad = np.zeros(W.shape)
