import os
import tensorflow.compat.v1 as tf
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
os.environ["KMP_WARNINGS"] = "FALSE"
tf.logging.set_verbosity(tf.logging.ERROR)
if __name__ == "__main__":
col_names = ["user", "item", "label", "time", "sex",
"age", "occupation", "genre1", "genre2", "genre3"]
all_data = pd.read_csv("sample_data/sample_movielens_merged.csv",
sep=",", header=0)
# use first half data as first training part
first_half_data = all_data[:(len(all_data) // 2)]
train, test = split_by_ratio_chrono(first_half_data, test_size=0.2)
sparse_col = ["sex", "occupation", "genre1", "genre2", "genre3"]
dense_col = ["age"]
user_col = ["sex", "age", "occupation"]
item_col = ["genre1", "genre2", "genre3"]
train_data, data_info = DatasetFeat.build_trainset(train, user_col, item_col,
sparse_col, dense_col,
shuffle=False)
test_data = DatasetFeat.build_testset(test, shuffle=False)
print(data_info)
train_data.build_negative_samples(data_info, num_neg=1,
item_gen_mode="random", seed=2020)
test_data.build_negative_samples(data_info, num_neg=1,
item_gen_mode="random", seed=2222)
# remove unnecessary tensorflow logging
import os
import tensorflow as tf
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
os.environ["KMP_WARNINGS"] = "FALSE"
tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)
if __name__ == "__main__":
data = pd.read_csv("sample_data/sample_movielens_merged.csv",
sep=",",
header=0)
# convert to implicit data and do negative sampling afterwards
data["label"] = 1
# split into train and test data based on time
train_data, test_data = split_by_ratio_chrono(data, test_size=0.2)
# specify complete columns information
sparse_col = ["sex", "occupation", "genre1", "genre2", "genre3"]
dense_col = ["age"]
user_col = ["sex", "age", "occupation"]
item_col = ["genre1", "genre2", "genre3"]
train_data, data_info = DatasetFeat.build_trainset(train_data, user_col,
item_col, sparse_col,
dense_col)
test_data = DatasetFeat.build_testset(test_data, sparse_col, dense_col)
# sample negative items for each record
train_data.build_negative_samples(data_info)
test_data.build_negative_samples(data_info)
import os
import tensorflow as tf
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
os.environ["KMP_WARNINGS"] = "FALSE"
tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)
if __name__ == "__main__":
col_names = [
"user", "item", "label", "time", "sex", "age", "occupation", "genre1",
"genre2", "genre3"
]
data = pd.read_csv("sample_data/sample_movielens_merged.csv",
sep=",",
header=0)
train, test = split_by_ratio_chrono(data, test_size=0.2)
sparse_col = ["sex", "occupation", "genre1", "genre2", "genre3"]
dense_col = ["age"]
user_col = ["sex", "age", "occupation"]
item_col = ["genre1", "genre2", "genre3"]
train_data, data_info = DatasetFeat.build_trainset(train,
user_col,
item_col,
sparse_col,
dense_col,
shuffle=False)
test_data = DatasetFeat.build_testset(test, shuffle=False)
print(data_info)
train_data.build_negative_samples(data_info,
num_neg=1,