def test_cnn_train(self):
# Get them labels!
print(PROJECT_DIR)
print(DATA_DIR)
with io.open(DATA_DIR + '.labels', 'r') as f:
labels = [line.rstrip('\n') for line in f]
labels = list(set(labels))
# Run the model
model = Magpie()
a = model.train_word2vec(DATA_DIR, vec_dim=300)
print("done2")
print("done3")
model.init_word_vectors(DATA_DIR, vec_dim=300)
model.train(DATA_DIR,
labels,
nn_model='cnn',
test_ratio=0.2,
epochs=30)
path1 = PROJECT_DIR + '/here1.h5'
path2 = PROJECT_DIR + '/embedinghere'
path3 = PROJECT_DIR + '/scaler'
model.save_word2vec_model(path2)
model.save_scaler(path3, overwrite=True)
model.save_model(path1)
print("thuc hien test")
# Do a simple prediction
print(
model.predict_from_text(
'cho em hỏi về lịch khám của bác_sỹ đào việt_hằng và số điện_thoại'
))
]
#train_dir = 'C:\\magpie-master\\data\\hep-categories'
#train_dir = 'C:\\data\\Railway_Passenger_Transport'
train_dir = 'C:\\data\\nlp_chinese_corpus'
Success = 'Success:'
error = 'error:'
magpie = Magpie()
lossHistory = LossHistory()
for EMBEDDING_SIZE in [250, 500]:
for MIN_WORD_COUNT in [5, 10]:
for WORD2VEC_CONTEXT in [5, 10]:
magpie.train_word2vec(train_dir,
vec_dim=EMBEDDING_SIZE,
MWC=MIN_WORD_COUNT,
w2vc=WORD2VEC_CONTEXT)
magpie.fit_scaler('C:\\magpie-master\\data\\hep-categories')
magpie.train('C:\\magpie-master\\data\\hep-categories',
labels,
callbacks=[lossHistory],
test_ratio=0.1,
epochs=20) # 训练，20%数据作为测试数据，20轮
lossHistory.loss_plot(
'epoch', 'C:\\magpie-master\\' + train_dir[-3:] + '_' +
str(EMBEDDING_SIZE) + '_' + str(MIN_WORD_COUNT) + '_' +
str(WORD2VEC_CONTEXT) + '.jpg')
magpie.save_word2vec_model(
'C:\\magpie-master\\save\\embeddings\\' + train_dir[-3:] +
'_' + str(EMBEDDING_SIZE) + '_' + str(MIN_WORD_COUNT) + '_' +
str(WORD2VEC_CONTEXT))
from magpie import Magpie
#train_dir = 'C:\\data\\Railway_Passenger_Transport'
train_dir = 'data/hep-categories'
magpie = Magpie()
magpie.train_word2vec(train_dir, vec_dim=100, MWC=1, w2vc=5)
magpie.fit_scaler('data/hep-categories')
magpie.init_word_vectors('data/hep-categories')
#定义所有类别
labels = [
'1111', '1112', '1113', '1114', '1115', '1116', '1117', '1118', '1121',
'1122', '1123', '1124', '1131', '1132', '1133', '1134', '1135', '1141',
'1142', '1143', '1144', '1151', '1152', '1153', '1154', '1211', '1212',
'1213', '1214', '1215', '1216', '1217', '1218', '1219', '1221', '1222',
'1223', '1231', '1232', '1233', '1234', '1235', '1241', '1242', '1243',
'1251', '1311', '1312', '1313', '1314', '1321', '1322', '1323', '1331',
'1332', '1333', '1334', '1341', '1342', '1343', '1344', '1345', '1351',
'1411', '1421', '1431', '1441', '15', '2111', '2112', '2113', '2114',
'2115', '2116', '2117', '2121', '2122', '2123', '2124', '2131', '2132',
'2133', '2134', '2141', '2142', '2143', '2144', '2145', '2146', '2147',
'2148', '2149', '21410', '2151', '2152', '2153', '2154', '2155', '2156',
'2161', '2162', '2163', '2164', '2165', '2166', '2167', '2168', '2171',
'2172', '2173', '2174', '2175', '2176', '2177', '2178', '2179', '21710',
'21711', '2181', '2182', '2183', '2184', '2185', '2186', '2187', '2188',
'2191', '2192', '2193', '2194', '2195', '2196', '221', '222', '223', '224',
'2311', '2312', '2313', '2314', '2315', '2316', '2321', '2322', '2323',
'2324', '24', '31', '32', '33', '34', '41', '42', '43', '51', '52', '53',
'54', '55', '56', '57', '58', '61', '7111', '7112', '7113', '7114', '7115',
'7116', '7117', '7118', '7119', '71110', '71111', '7121', '7122', '7123',
'7124', '7125', '7126', '7127', '7128', '7129', '7131', '7132', '7133',
from magpie import Magpie
import time
count = 10
magpie = Magpie()
while (count <= 500):
start = time.clock()
magpie.train_word2vec('data/hep-categories', vec_dim=count)
magpie.save_word2vec_model('save/embeddings/here' + str(count),
overwrite=True)
end = time.clock()
runtime = end - start
print(str(count) + ',' + str(runtime))
file = open('save/embeddings/here.txt', 'a')
file.write('\n' + str(count) + ',' + str(runtime))
file.close()
count = count + 10
file.write(label)
print("Data generation finished.")
address = "/home/ubuntu/toxic/magpie_data"
#data_prep("/Users/wangergou/Downloads/kaggle/Toxic_Comment_Classification/Magpie/data/")
data_prep(address)
magpie = Magpie()
print("Loading word vector... \n")
magpie.train_word2vec(address, vec_dim=100)
print("Initializing data... \n")
magpie.init_word_vectors(address, vec_dim=100)
labels = [
'toxic', 'severe_toxic', 'obscene', 'threat', 'insult', 'identity_hate'
]
print("Training starts... \n")
magpie.train(address, labels, test_ratio=0.2, epochs=30)
magpie.save_model('/home/ubuntu/toxic/magpie_model.h5')
import os
import sys
sys.path.append(os.path.realpath(os.getcwd()))
sys.path.append("..")
from magpie import Magpie
magpie = Magpie()
magpie.train_word2vec('../data/hep-categories', vec_dim=3) #训练一个word2vec
magpie.fit_scaler('../data/hep-categories') #生成scaler
magpie.init_word_vectors('../data/hep-categories', vec_dim=3) #初始化词向量
labels = ['军事', '旅游', '政治'] #定义所有类别
magpie.train('../data/hep-categories', labels, test_ratio=0.2,
epochs=20) #训练，20%数据作为测试数据，5轮
#保存训练后的模型文件
magpie.save_word2vec_model('../workspace/embeddings', overwrite=True)
magpie.save_scaler('../workspace/scaler', overwrite=True)
magpie.save_model('../workspace/model.h5')
'2161', '2162', '2163', '2164', '2165', '2166', '2167', '2168', '2171',
'2172', '2173', '2174', '2175', '2176', '2177', '2178', '2179', '21710',
'21711', '2181', '2182', '2183', '2184', '2185', '2186', '2187', '2188',
'2191', '2192', '2193', '2194', '2195', '2196', '221', '222', '223', '224',
'2311', '2312', '2313', '2314', '2315', '2316', '2321', '2322', '2323',
'2324', '24', '31', '32', '33', '34', '41', '42', '43', '51', '52', '53',
'54', '55', '56', '57', '58', '61', '7111', '7112', '7113', '7114', '7115',
'7116', '7117', '7118', '7119', '71110', '71111', '7121', '7122', '7123',
'7124', '7125', '7126', '7127', '7128', '7129', '7131', '7132', '7133',
'7134', '7135', '7136', '7137', '7138', '7139', '71310', '71311', '71312',
'7141', '7142', '7151', '721', '722', '723', '724', '7311', '7312', '7313',
'7314', '7315', '7316', '7321', '7322', '7323', '7324', '7325', '7326',
'7331', '7332', '7333', '7334', '7335', '7336', '734', '74'
]
magpie.train_word2vec('C:\\data\\Railway_Passenger_Transport',
vec_dim=300,
MWC=8,
w2vc=6)
magpie.fit_scaler('data/hep-categories')
magpie.init_word_vectors('data/hep-categories')
'''
保存在验证集上最好的模型。
filename：字符串，保存模型的路径
monitor：需要监视的值
verbose：信息展示模式，0或1
save_best_only：当设置为True时，将只保存在验证集上性能最好的模型
mode：‘auto’，‘min’，‘max’之一，在save_best_only=True时决定性能最佳模型的评判准则，
例如，当监测值为val_acc时，模式应为max，
当检测值为val_loss时，模式应为min。在auto模式下，评价准则由被监测值的名字自动推断。
save_weights_only：若设置为True，则只保存模型权重，否则将保存整个模型（包括模型结构，配置信息等）
period：CheckPoint之间的间隔的epoch数
https://keras.io/zh/callbacks/#history
