def test_recommend_movies(pretrained, inputs, linear_feature_columns,
dnn_feature_columns, DEVICE):
# model = xDeepFM(linear_feature_columns, dnn_feature_columns, task='regression', device=DEVICE)
model = FiBiNET(linear_feature_columns,
dnn_feature_columns,
task='regression',
device=DEVICE)
model.load_state_dict(torch.load(pretrained))
pred_ans = model.predict(inputs, batch_size=256)
print(f'Predict rating: {pred_ans}')
pred_movie_list = []
idx = np.argsort(pred_ans, axis=0)[::-1]
for i, ans_idx in enumerate(idx[:, 0]):
if i < 5:
print(
f"Predict rating: {pred_ans[ans_idx][0] :.3f}, movie_id: {data.iloc[ans_idx]['movie_id']}, gender: {data.iloc[ans_idx]['gender']}, age: {data.iloc[ans_idx]['age']}, user_id: {data.iloc[ans_idx]['user_id']}"
)
pred_movie_list.append(data.iloc[ans_idx]['movie_id'])
# print(inputs['movie_id'].iloc[i])
# print('movie_max',data.loc[:, ['movie_id']].max(axis=0)) # 1682
return pred_movie_list
def recommend_movies(pretrained, inputs, linear_feature_columns,
dnn_feature_columns, DEVICE, df):
data = df
# print(data)
# model = xDeepFM(linear_feature_columns, dnn_feature_columns, task='regression', device=DEVICE)
model = FiBiNET(linear_feature_columns,
dnn_feature_columns,
task='regression',
device=DEVICE)
model.load_state_dict(torch.load(pretrained))
pred_ans = model.predict(inputs, batch_size=256)
# print(f'Predict rating: {pred_ans}')
pred_movie_list = []
pred_movie_genres = []
pred_rating = []
idx = np.argsort(pred_ans, axis=0)[::-1]
movie_genres = [
col for col in data.columns
if col not in ['movie_id', 'movie_title', 'unknown']
]
for i, ans_idx in enumerate(idx[:, 0]):
# TODO: Add arguments (rank)
if i < 2:
genres = [
movie_genre for movie_genre in movie_genres
if data.iloc[ans_idx][movie_genre] == 1
]
print(
f"Predict rating: {pred_ans[ans_idx][0] :.3f}, movie_id: {data.iloc[ans_idx]['movie_id']}, movie_title: {data.iloc[ans_idx]['movie_title']}, gender: {data.iloc[ans_idx]['gender']}, age: {data.iloc[ans_idx]['age']}, genres: {genres}"
)
pred_movie_list.append(data.iloc[ans_idx]['movie_title'])
pred_movie_genres.append(genres)
pred_rating.append(pred_ans[ans_idx][0])
# print(inputs['movie_id'].iloc[i])
# print('movie_max',data.loc[:, ['movie_id']].max(axis=0)) # 1682
return pred_movie_list, pred_movie_genres, pred_rating
def test_FiBiNET(bilinear_type):
model_name = "FiBiNET"
sample_size = SAMPLE_SIZE
x, y, feature_columns = get_test_data(sample_size, 3, 3)
model = FiBiNET(
feature_columns,
feature_columns,
bilinear_type=bilinear_type,
dnn_hidden_units=[8, 8],
dnn_dropout=0.5,
)
check_model(model, model_name, x, y)
def train_recommend_movies(csv_file, DEVICE):
"""
Description:
Train recommend system on:
Model: "xDeepFM",
Target: "rating",
Input features: ["movie_id", "gender", "age"],
Save model to: "save_model/xDeepFM_MSE{}.h5"
Parameters:
csv_file: "path to *.csv"
DEVICE: "cuda:0"
"""
data = pd.read_csv(csv_file)
# sparse_features = ["movie_id", "user_id",
# "gender", "age", "occupation", "zip"]
sparse_features = ["movie_id", "gender", "age"]
movie_genres = [
'Action', 'Adventure', 'Animation', 'Childrens', 'Comedy', 'Crime',
'Documentary', 'Drama', 'Fantasy', 'Film_Noir', 'Horror', 'Musical',
'Mystery', 'Romance', 'Sci_Fi', 'Thriller', 'War', 'Western'
]
target = ['rating']
# 1.Label Encoding for sparse features,and do simple Transformation for dense features
for feat in sparse_features:
lbe = LabelEncoder()
data[feat] = lbe.fit_transform(data[feat])
sparse_features.extend(movie_genres)
# 2.count #unique features for each sparse field
fixlen_feature_columns = [
SparseFeat(feat, data[feat].nunique()) for feat in sparse_features
]
# 他自己的資料型態
# SparseFeat(name='movie_id', vocabulary_size=187, embedding_dim=4, use_hash=False, dtype='int32', embedding_name='movie_id', group_name='default_group')
linear_feature_columns = fixlen_feature_columns
dnn_feature_columns = fixlen_feature_columns
feature_names = get_feature_names(
linear_feature_columns + dnn_feature_columns
) # movie_id, user_id, gender, age, occupation, zip.
# 3.generate input data for model
train, test = train_test_split(data, test_size=0.2)
train_model_input = {name: train[name] for name in feature_names}
test_model_input = {
name: test[name]
for name in feature_names
} # dict of movie_id, user_id, gender, age, occupation, zip values
# 4.Define Model,train,predict and evaluate
# model = DeepFM(linear_feature_columns, dnn_feature_columns, task='regression', device=device)
model = FiBiNET(linear_feature_columns,
dnn_feature_columns,
task='regression',
device=DEVICE)
# model = xDeepFM(linear_feature_columns, dnn_feature_columns, task='regression', device=device)
model.compile(
"adam",
"mse",
metrics=['mse'],
)
history = model.fit(
train_model_input,
train[target].values,
batch_size=256,
epochs=10,
verbose=2,
validation_split=0.2,
)
pred_ans = model.predict(test_model_input, batch_size=256)
print("test MSE",
round(mean_squared_error(test[target].values, pred_ans), 4))
print("test MAE",
round(mean_absolute_error(test[target].values, pred_ans), 4))
# torch.save(model.state_dict(), './recommend_system/save_model/xDeepFM_MSE{}.h5' .format(round(mean_squared_error(test[target].values, pred_ans), 4)))
torch.save(
model.state_dict(),
'./recommend_system/save_model/FiBiNET_MSE{}.h5'.format(
round(mean_squared_error(test[target].values, pred_ans), 4)))
dnn_feature_columns)
# 3.generate input data for model
train, test = train_test_split(data, test_size=0.2)
train_model_input = {name: train[name] for name in feature_names}
test_model_input = {name: test[name] for name in feature_names}
# 4.Define Model,train,predict and evaluate
device = 'cpu'
use_cuda = True
if use_cuda and torch.cuda.is_available():
print('cuda ready...')
device = 'cuda:0'
model = FiBiNET(linear_feature_columns,
dnn_feature_columns,
task='binary',
device=device)
model.compile(
"adam",
"binary_crossentropy",
metrics=["binary_crossentropy", "auc"],
)
history = model.fit(train_model_input,
train[target].values,
batch_size=256,
epochs=10,
verbose=2,
validation_split=0.2)
pred_ans = model.predict(test_model_input, batch_size=256)
#print(pred_ans)
#print(" ")
dnn_feature_columns)
# 3.generate input data for model
train, test = train_test_split(data, test_size=0.2)
train_model_input = {name: train[name] for name in feature_names}
test_model_input = {name: test[name] for name in feature_names}
# 4.Define Model,train,predict and evaluate
device = 'cpu'
use_cuda = True
if use_cuda and torch.cuda.is_available():
print('cuda ready...')
device = 'cuda:0'
model = FiBiNET(linear_feature_columns,
dnn_feature_columns,
task='regression',
device=device)
model.compile(
"adam",
"mse",
metrics=['mse'],
)
history = model.fit(train_model_input,
train[target].values,
batch_size=256,
epochs=87,
verbose=2,
validation_split=0.2)
pred_ans = model.predict(test_model_input, batch_size=256)
print("test MSE",