features = ['user_id', 'movie_id', 'gender', 'age', 'occupation', 'zip']
feature_max_idx = {}
for feature in features:
lbe = LabelEncoder()
data[feature] = lbe.fit_transform(data[feature]) + 1
feature_max_idx[feature] = data[feature].max() + 1
user_profile = data[["user_id", "gender", "age", "occupation",
"zip"]].drop_duplicates('user_id')
item_profile = data[["movie_id"]].drop_duplicates('movie_id')
user_profile.set_index("user_id", inplace=True)
user_item_list = data.groupby("user_id")['movie_id'].apply(list)
train_set, test_set = gen_data_set(data, negsample)
train_model_input, train_label = gen_model_input(train_set, user_profile,
SEQ_LEN)
test_model_input, test_label = gen_model_input(test_set, user_profile, SEQ_LEN)
# 3. Create neg samples
import random
from tqdm import tqdm
train_neg_sample_list = []
test_neg_sample_list = []
all_movie_list = set(data['movie_id'])
neg_sample_num = 10
for i in tqdm(range(len(train_label))):
feature_max_idx = {}
for feature in features:
lbe = LabelEncoder()
data[feature] = lbe.fit_transform(data[feature]) + 1
feature_max_idx[feature] = data[feature].max() + 1
user_profile = data[["user_id", "gender", "age", "occupation",
"zip"]].drop_duplicates('user_id')
item_profile = data[["movie_id"]].drop_duplicates('movie_id')
user_profile.set_index("user_id", inplace=True)
user_item_list = data.groupby("user_id")['movie_id'].apply(list)
train_set, test_set = gen_data_set(data, 0)
train_model_input, train_label = gen_model_input(train_set, user_profile,
SEQ_LEN)
test_model_input, test_label = gen_model_input(test_set, user_profile,
SEQ_LEN)
# 2.count #unique features for each sparse field and generate feature config for sequence feature
embedding_dim = 16
user_feature_columns = [
SparseFeat('user_id', feature_max_idx['user_id'], embedding_dim),
SparseFeat("gender", feature_max_idx['gender'], embedding_dim),
SparseFeat("age", feature_max_idx['age'], embedding_dim),
SparseFeat("occupation", feature_max_idx['occupation'], embedding_dim),
