def main(args):
R_train = load_numpy(path=args.data_dir, name=args.train_set)
R_train_keyphrase = load_numpy(path=args.data_dir, name=args.train_keyphrase_set).toarray()
R_train_keyphrase[R_train_keyphrase != 0] = 1
R_train_item_keyphrase = load_numpy(path=args.data_dir, name=args.train_item_keyphrase_set).T.toarray()
num_items, num_keyphrases = R_train_item_keyphrase.shape
for item in range(num_items):
item_keyphrase = R_train_item_keyphrase[item]
nonzero_keyphrases_index = item_keyphrase.nonzero()[0]
nonzero_keyphrases_frequency = item_keyphrase[nonzero_keyphrases_index]
candidate_index = nonzero_keyphrases_index[np.argsort(-nonzero_keyphrases_frequency)[:10]]
binarized_keyphrase = np.zeros(num_keyphrases)
binarized_keyphrase[candidate_index] = 1
R_train_item_keyphrase[item] = binarized_keyphrase
R_train_item_keyphrase = sparse.csr_matrix(R_train_item_keyphrase).T
params = dict()
# params['model_saved_path'] = args.model_saved_path
critiquing(R_train,
R_train_keyphrase,
R_train_item_keyphrase,
params,
args.num_users_sampled,
load_path=args.load_path,
save_path=args.save_path,
critiquing_function=args.critiquing_function)
def main(args):
num_users = pd.read_csv(args.data_dir + args.user_col +
'.csv')[args.user_col].nunique()
num_items = pd.read_csv(args.data_dir + args.item_col +
'.csv')[args.item_col].nunique()
df_train = pd.read_csv(args.data_dir + args.train_set)
df_train = df_train[df_train[args.rating_col] == 1]
df_train[args.keyphrase_vector_col] = df_train[
args.keyphrase_vector_col].apply(ast.literal_eval)
keyphrase_names = pd.read_csv(args.data_dir + args.keyphrase_set)[
args.keyphrase_col].values
params = dict()
params['model_saved_path'] = args.model_saved_path
critiquing(num_users,
num_items,
args.user_col,
args.item_col,
args.rating_col,
args.keyphrase_vector_col,
df_train,
keyphrase_names,
params,
args.num_users_sampled,
load_path=args.load_path,
save_path=args.save_path)
def main(args):
# Progress bar
progress = WorkSplitter()
# Show hyperparameter settings
progress.section("Parameter Setting")
print("Data Directory: {}".format(args.data_dir))
print("Number of Users Sampled: {}".format(args.num_users_sampled))
print("Number of Items Sampled: {}".format(args.num_items_sampled))
print("Number of Max Allowed Iterations: {}".format(
args.max_iteration_threshold))
print("Critiquing Model: {}".format(args.critiquing_model_name))
R_train = load_numpy(path=args.data_dir, name=args.train_set)
print("Train U-I Dimensions: {}".format(R_train.shape))
R_test = load_numpy(path=args.data_dir, name=args.test_set)
print("Test U-I Dimensions: {}".format(R_test.shape))
R_train_keyphrase = load_numpy(path=args.data_dir,
name=args.train_keyphrase_set).toarray()
print("Train Item Keyphrase U-I Dimensions: {}".format(
R_train_keyphrase.shape))
R_train_item_keyphrase = load_numpy(
path=args.data_dir, name=args.train_item_keyphrase_set).toarray()
table_path = load_yaml('config/global.yml', key='path')['tables']
parameters = find_best_hyperparameters(table_path + args.dataset_name,
'NDCG')
parameters_row = parameters.loc[parameters['model'] == args.model]
if args.dataset_name == "yelp/":
R_train_item_keyphrase = R_train_item_keyphrase.T
start_time = time.time()
results = critiquing(
matrix_Train=R_train,
matrix_Test=R_test,
keyphrase_freq=R_train_keyphrase,
item_keyphrase_freq=R_train_item_keyphrase,
num_users_sampled=args.num_users_sampled,
num_items_sampled=args.num_items_sampled,
max_iteration_threshold=args.max_iteration_threshold,
dataset_name=args.dataset_name,
model=models[args.model],
parameters_row=parameters_row,
critiquing_model_name=args.critiquing_model_name,
keyphrase_selection_method=args.keyphrase_selection_method,
topk=args.topk,
lamb=args.lamb)
print("Final Time Elapsed: {}".format(inhour(time.time() - start_time)))
table_path = load_yaml('config/global.yml', key='path')['tables']
save_dataframe_csv(results, table_path, args.save_path)
def main(args):
# Progress bar
progress = WorkSplitter()
# Show hyperparameter settings
progress.section("Parameter Setting")
print("Data Directory: {}".format(args.data_dir))
print("Number of Users Sampled: {}".format(args.num_users_sampled))
print("Number of Items Sampled: {}".format(args.num_items_sampled))
print("Number of Max Allowed Iterations: {}".format(args.max_iteration_threshold))
print("Critiquing Model: {}".format(args.critiquing_model_name))
R_train = load_numpy(path=args.data_dir, name=args.train_set)
print("Train U-I Dimensions: {}".format(R_train.shape))
R_test = load_numpy(path=args.data_dir, name=args.test_set)
print("Test U-I Dimensions: {}".format(R_test.shape))
R_train_keyphrase = load_numpy(path=args.data_dir, name=args.train_keyphrase_set).toarray()
print("Train Item Keyphrase U-I Dimensions: {}".format(R_train_keyphrase.shape))
R_train_item_keyphrase = load_numpy(path=args.data_dir, name=args.train_item_keyphrase_set).toarray()
table_path = load_yaml('config/global.yml', key='path')['tables']
# parameters = find_best_hyperparameters(table_path+args.dataset_name, 'NDCG')
# parameters_row = parameters.loc[parameters['model'] == args.model]
parameters_row = {
'iter' : 10,
'lambda' : 200,
'rank' : 200
}
keyphrases_names = load_dataframe_csv(path = args.data_dir, name = "Keyphrases.csv")['Phrases'].tolist()
results = critiquing(matrix_Train=R_train,
matrix_Test=R_test,
keyphrase_freq=R_train_keyphrase,
item_keyphrase_freq=R_train_item_keyphrase.T,
num_users_sampled=args.num_users_sampled,
num_items_sampled=args.num_items_sampled,
max_iteration_threshold=args.max_iteration_threshold,
dataset_name=args.dataset_name,
model=models[args.model],
parameters_row=parameters_row,
critiquing_model_name=args.critiquing_model_name,
lamb = args.lambdas,
keyphrases_names = keyphrases_names,
keyphrase_selection_method = args.keyphrase_selection_method)
table_path = load_yaml('config/global.yml', key='path')['tables']
save_dataframe_csv(results, table_path, args.save_path)
def main(args):
# Progress bar
progress = WorkSplitter()
# Show hyperparameter settings
progress.section("Parameter Setting")
print("Data Directory: {}".format(args.data_dir))
print("Number of Users Sampled: {}".format(args.num_users_sampled))
print("Number of Items Sampled: {}".format(args.num_items_sampled))
print("Number of Max Allowed Iterations: {}".format(
args.max_iteration_threshold))
print("Critiquing Model: {}".format(args.critiquing_model_name))
R_train = load_numpy(path=args.data_dir, name=args.train_set)
print("Train U-I Dimensions: {}".format(R_train.shape))
R_test = load_numpy(path=args.data_dir, name=args.test_set)
print("Test U-I Dimensions: {}".format(R_test.shape))
R_train_keyphrase = load_numpy(path=args.data_dir,
name=args.train_keyphrase_set).toarray()
print("Train User Keyphrase U-I Dimensions: {}".format(
R_train_keyphrase.shape))
R_train_item_keyphrase = load_numpy(
path=args.data_dir, name=args.train_item_keyphrase_set).toarray()
print("Train Item Keyphrase U-I Dimensions: {}".format(
R_train_item_keyphrase.shape))
# table_path = load_yaml('config/global.yml', key='path')['tables']
# parameters = find_best_hyperparameters(table_path+args.dataset_name, 'NDCG')
# parameters_row = parameters.loc[parameters['model'] == args.model]
parameters_row = pd.DataFrame({'iter': [4], 'lambda': [80], 'rank': [200]})
results = critiquing(matrix_Train=R_train,
matrix_Test=R_test,
keyphrase_freq=R_train_keyphrase,
item_keyphrase_freq=R_train_item_keyphrase,
num_users_sampled=args.num_users_sampled,
num_items_sampled=args.num_items_sampled,
max_iteration_threshold=args.max_iteration_threshold,
dataset_name=args.dataset_name,
model=models[args.model],
parameters_row=parameters_row,
critiquing_model_name=args.critiquing_model_name)
# table_path = load_yaml('config/global.yml', key='path')['tables']
table_path = '/home/shuyang/data4/LatentLinearCritiquingforConvRecSys/'
save_dataframe_csv(results, table_path, args.save_path)
def main(args):
# Progress bar
progress = WorkSplitter()
# Show hyperparameter settings
progress.section("Parameter Setting")
print("Data Directory: {}".format(args.data_dir))
print("Number of Users Sampled: {}".format(args.num_users_sampled))
print("Number of Items Sampled: {}".format(args.num_items_sampled))
print("Number of Max Allowed Iterations: {}".format(
args.max_iteration_threshold))
print("Critiquing Model: {}".format(args.critiquing_model_name))
R_train = load_numpy(path=args.data_dir, name=args.train_set)
print("Train U-I Dimensions: {}".format(R_train.shape))
R_test = load_numpy(path=args.data_dir, name=args.test_set)
print("Test U-I Dimensions: {}".format(R_test.shape))
R_train_keyphrase = load_numpy(path=args.data_dir,
name=args.train_keyphrase_set).toarray()
print("Train Item Keyphrase U-I Dimensions: {}".format(
R_train_keyphrase.shape))
R_train_item_keyphrase = load_numpy(
path=args.data_dir, name=args.train_item_keyphrase_set).toarray()
table_path = load_yaml('config/global.yml', key='path')['tables']
parameters = find_best_hyperparameters(table_path + args.dataset_name,
'NDCG')
parameters_row = parameters.loc[parameters['model'] == args.model]
lambs = [
0.001, 0.01, 0.05, 0.1, 0.5, 1, 5, 10, 30, 50, 70, 90, 100, 200, 500,
1000, 10000, 100000
]
topks = [10, 20, 50, 100]
if args.dataset_name == "yelp/":
R_train_item_keyphrase = R_train_item_keyphrase.T
for topk in topks:
for lamb in lambs:
results = critiquing(
matrix_Train=R_train,
matrix_Test=R_test,
keyphrase_freq=R_train_keyphrase,
item_keyphrase_freq=R_train_item_keyphrase,
num_users_sampled=args.num_users_sampled,
num_items_sampled=args.num_items_sampled,
max_iteration_threshold=args.max_iteration_threshold,
dataset_name=args.dataset_name,
model=models[args.model],
parameters_row=parameters_row,
critiquing_model_name=args.critiquing_model_name,
keyphrase_selection_method=args.keyphrase_selection_method,
topk=topk,
lamb=lamb)
table_path = load_yaml('config/global.yml', key='path')['tables']
topk_path = "topk_" + str(topk) + "/"
save_name = args.save_path + topk_path + "tuning_at_lamb_" + str(
lamb) + "_with_" + args.keyphrase_selection_method + ".csv"
save_dataframe_csv(results, table_path, save_name)