def __init__(self, args, label2index_map, input_size, paths, config):
self.batch_size = args.batch_size
self.epoch_num = args.epoch
self.optimier = args.optimizer
self.hidden_dim1 = args.hidden_dim1
self.hidden_dim2 = args.hidden_dim2
self.hidden_dim3 = args.hidden_dim3
self.dropout_keep_prob = args.dropout
self.beta = args.beta
self.lr = args.lr
self.clip_grad = args.clip
self.optimizer = args.optimizer
self.test_data_path = args.test_data
self.tag2label = label2index_map
self.num_tags = len(label2index_map)
self.input_size = input_size
self.config = config
self.model_path = paths['model_path']
self.summary_path = paths['summary_path']
self.logger = base_util.get_logger(paths['log_path'])
self.result_path = paths['result_path']
time.time())) if args.mode == 'train' else args.demo_model
output_path = os.path.join(args.result, "dnn_save", tag_timestamp)
if not os.path.exists(output_path): os.makedirs(output_path)
summary_path = os.path.join(output_path, "summaries")
paths['summary_path'] = summary_path
if not os.path.exists(summary_path): os.makedirs(summary_path)
model_path = os.path.join(output_path, "checkpoints/")
if not os.path.exists(model_path): os.makedirs(model_path)
ckpt_prefix = os.path.join(model_path, "model")
paths['model_path'] = ckpt_prefix
result_path = os.path.join(output_path, "results")
paths['result_path'] = result_path
if not os.path.exists(result_path): os.makedirs(result_path)
log_path = os.path.join(result_path, "log.txt")
paths['log_path'] = log_path
get_logger(log_path).info(str(args))
os.environ['CUDA_VISIBLE_DEVICES'] = '1'
_, label_list = load_label2index()
print(label_list)
# training model
train_path = os.path.join(args.train_data, 'train_modified.csv')
test_path = os.path.join(args.test_data, 'test_modified.csv')
if args.mode == 'train':
ids, train_data = read_corpus(train_path, shuffle=False)
print("train data: {}".format(len(train_data)))
train = train_data[:1000]
val = train_data[1000:1050]
input_size = len(train.columns) - 1
print('input_size', input_size)
import pandas as pd
import numpy as np
from sklearn import preprocessing
from code.util.base_util import get_logger
from code.util.base_util import pickle_load
from code.util.base_util import pickle_dump
from code.util.base_util import timer
import os
import pickle
LABEL = 'current_service'
ID = 'user_id'
log = get_logger()
category_list = [
'gender', 'service_type', 'is_mix_service', 'contract_type', 'net_service',
'complaint_level', 'age_group', 'ctims'
]
def __get_dir(dir):
if not os.getcwd().endswith('code'):
return '../' + dir
return dir
def base_data_prepare(age2group=True, one_hot=True):
df_train = pd.read_csv(__get_dir('../origin_data/train.csv'))
df_test = pd.read_csv(__get_dir('../origin_data/test.csv'))
import pandas as pd
import numpy as np
from sklearn.metrics import f1_score
from sklearn.model_selection import KFold, StratifiedKFold
from code.util.base_util import timer
import os
from code import base_data_process
import tensorflow as tf
from code.util import base_util
log = base_util.get_logger()
ID_COLUMN_NAME = 'user_id'
LABEL_COLUMN_NAME = 'current_service'
def nn_model(df_train, df_test):
pass
class FeatureNN():
def __init__(self,
x_train,
y_train,
x_val,
y_val,
epoch=10,
batch_size=30):
self.epoch = epoch
