num_epochs = 10
# Read data
train, test = data.get_movielens_data()
num_users, num_items = train.shape
# Prepare the test triplets
test_uid, test_pid, test_nid = data.get_triplets(test)
model = build_model(num_users, num_items, latent_dim)
# Print the model structure
print(model.summary())
# Sanity check, should be around 0.5
print('AUC before training %s' % metrics.full_auc(model, test))
for epoch in range(num_epochs):
print('Epoch %s' % epoch)
# Sample triplets from the training data
uid, pid, nid = data.get_triplets(train)
X = {
'user_input': uid,
'positive_item_input': pid,
'negative_item_input': nid
}
model.fit(X,
# Compile the model by including optimization function and the loss function
# 'optimization function': adam (learning rate = default in keras model)
# 'loss function': binary crossentropy to keep the output of the predictions betweeen [0, 1]
model.compile(optimizer='adam',loss= 'binary_crossentropy')
# print the model summary, if needed
model.summary()
# list for storing the training loss
loss = []
best_hr, best_ndcg, best_iter = None, None, None
# Sanity check (if needed), AUC should be around 0.5
auc, ndcg_value, hr_value = metrics.full_auc(model, test)
print('Metric before training: ndcg %s, hr %s' % (ndcg_value, hr_value))
# iterate over the num_epochs (default = 10)
for epoch in range(num_epochs):
print('Epoch %s' % epoch)
# get Sample triplets from the training data (to be fed into the model)
uid, pid, nid = data.get_triplets(train)
X = {
'user_input': uid,
'positive_item_input': pid,
'negative_item_input': nid
}
test_uid, test_pid, test_nid = data.get_triplets(test)
test_user_features, test_positive_item_features, test_negative_item_features = data.get_dense_triplets(
test_uid, test_pid, test_nid, num_users, num_items)
# Sample triplets from the training data
uid, pid, nid = data.get_triplets(train)
user_features, positive_item_features, negative_item_features = data.get_dense_triplets(
uid, pid, nid, num_users, num_items)
model = get_graph(num_users, num_items, 256)
# Print the model structure
print(model.summary())
# Sanity check, should be around 0.5
print('AUC before training %s' % metrics.full_auc(model, test))
for epoch in range(num_epochs):
print('Epoch %s' % epoch)
model.fit(
{
'user_input': user_features,
'positive_item_input': positive_item_features,
'negative_item_input': negative_item_features,
'triplet_loss': np.ones(len(uid))
},
validation_data={
'user_input': test_user_features,
'positive_item_input': test_positive_item_features,
def main():
logging.info('reading data')
item_mat = data.get_mult()
trainM = sparse.csr_matrix(
data.read_user(f_in='data/dummy/cf-train-10-users.dat',
num_u=50,
num_v=1929))
testM = sparse.csr_matrix(
data.read_user(f_in='data/dummy/cf-test-10-users.dat',
num_u=50,
num_v=1929))
trainList = list()
testList = list()
for user in range(trainM.shape[0]):
negative = 0
for item in range(trainM.shape[1]):
if trainM[user, item] == 1:
trainList.append([user, item, 1])
else:
if negative < 20:
trainList.append([user, item, 0])
negative += 1
train = np.array(trainList).astype('float32')
testList = list()
for user in range(testM.shape[0]):
negative = 0
for item in range(testM.shape[1]):
if testM[user, item] == 1:
testList.append([user, item, 1])
# else:
# if negative < 10:
# testList.append( [user, item, 0] )
# negative+=1
test = np.array(testList).astype('float32')
num_item_feat = item_mat.shape[1]
model = CollaborativeDeepLearning(item_mat, [num_item_feat, 50, 10])
model.pretrain(lamda_w=0.001, encoder_noise=0.3, epochs=10)
model_history = model.fineture(train,
test,
lamda_u=0.01,
lamda_v=0.1,
lamda_n=0.1,
lr=0.01,
epochs=500)
testing_rmse = model.getRMSE(test)
print('Testing RMSE = {}'.format(testing_rmse))
import metrics
print('AUC %s' % metrics.full_auc(model.cdl_model, testM))
import matplotlib.pyplot as plt
M_low = 50
M_high = 300
recall_levels = M_high - M_low + 1
recallArray = np.zeros(6)
x = 0
for n in [50, 100, 150, 200, 250, 300]:
test_recall = metrics.recall_at_k(model.cdl_model, testM, k=n)
recallArray[x] = test_recall
print('Recall: %.2f.' % (test_recall))
x += 1
plt.plot([50, 100, 150, 200, 250, 300], recallArray)
plt.ylabel("Recall")
plt.xlabel("M")
plt.title("Proposed: Recall@M")
plt.show()