def train_dl(save, vec_dim, epochs):
"""
train process
"""
magpie = Magpie()
# magpie.train_word2vec('/Users/sunxuan/Documents/PycharmProjects/ImpactPool/data/categories', vec_dim=100)
# magpie.fit_scaler('/Users/sunxuan/Documents/PycharmProjects/ImpactPool/data/categories')
magpie.init_word_vectors(
'/Users/sunxuan/Documents/PycharmProjects/ImpactPool/data/categories',
vec_dim=vec_dim)
with open('data/categories.labels') as f:
labels = f.readlines()
labels = [x.strip() for x in labels]
magpie.train(
'/Users/sunxuan/Documents/PycharmProjects/ImpactPool/data/categories',
labels,
test_ratio=0.0,
epochs=epochs)
if save:
"""
Save model
"""
magpie.save_word2vec_model(
'/Users/sunxuan/Documents/PycharmProjects/ImpactPool/data/save/embeddings/here'
)
magpie.save_scaler(
'/Users/sunxuan/Documents/PycharmProjects/ImpactPool/data/save/scaler/here',
overwrite=True)
magpie.save_model(
'/Users/sunxuan/Documents/PycharmProjects/ImpactPool/data/save/model/here.h5'
)
return magpie
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'
))
labels4 = sys.argv[9]
labels = [ labels1, labels2, labels3, labels4 ]
#print (labels)
dirName = 'D:\\xampp\\htdocs\\mtlbl\\webpage\\admin\\models\\' + model_name
os.mkdir(dirName)
model_path = dirName + '\\' + model_name
scaler_path = dirName + '\\scaler_' + model_name
keras_path = dirName + '\\keras_'+ model_name + '.h5'
#print (model_path)
#print (keras_path)
from magpie import Magpie
magpie = Magpie()
magpie.init_word_vectors(data, vec_dim=vec_num)
magpie.train(data, labels, test_ratio= test_rat, epochs = ep)
#more epoch = more understanding of vector and lower lose rate
#magpie.predict_from_text('ECB to reveal bad loan hurdles for euro zone bank test') #test
magpie.save_word2vec_model(model_path)
magpie.save_scaler(scaler_path, overwrite=True)
magpie.save_model(keras_path)
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))
magpie.save_scaler('C:\\magpie-master\\save\\scaler\\' +
train_dir[-3:] + '_' + str(EMBEDDING_SIZE) +
'_' + str(MIN_WORD_COUNT) + '_' +
str(WORD2VEC_CONTEXT))
magpie.save_model('C:\\magpie-master\\save\\model\\' +
train_dir[-3:] + '_' + str(EMBEDDING_SIZE) +
'_' + str(MIN_WORD_COUNT) + '_' +
str(WORD2VEC_CONTEXT) + '.h5')
print(Success + '\n' + train_dir[-3:] + '_' + str(EMBEDDING_SIZE) +
'_' + str(MIN_WORD_COUNT) + '_' + str(WORD2VEC_CONTEXT) +
' Success!!!')
'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',
'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('data/hep-categories', labels, test_ratio=0.2,
epochs=20) #训练，20%数据作为测试数据，20轮 根据给定数据训练模型
'''
#保存训练后的模型文件
magpie.save_word2vec_model('save/embeddings/best', overwrite=True)
magpie.save_scaler('save/scaler/best', overwrite=True)
magpie.save_model('save/model/best.h5')
'''
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
from magpie import Magpie
magpie = Magpie()
#train_dir = 'data/hep-categories'
train_dir = 'C:\\data\\Railway_Passenger_Transport'
#train_dir = 'C:\\data\\Railway_Passenger_Transport'
EMBEDDING_SIZE = 50
MIN_WORD_COUNT = 1
WORD2VEC_CONTEXT = 1
magpie.train_word2vec(train_dir,
vec_dim=EMBEDDING_SIZE,
MWC=MIN_WORD_COUNT,
w2vc=WORD2VEC_CONTEXT)
magpie.save_word2vec_model('save/embeddings/' + train_dir[-3:] + '_' +
str(EMBEDDING_SIZE) + '_' + str(MIN_WORD_COUNT) +
'_' + str(WORD2VEC_CONTEXT),
overwrite=True)
print(train_dir[-3:] + '_' + str(EMBEDDING_SIZE) + '_' + str(MIN_WORD_COUNT) +
'_' + str(WORD2VEC_CONTEXT) + ' Success!!!')
#!/usr/bin/python
# -*- coding: UTF-8 -*-
"""
@Author: njuselhx
@Time: 2021/1/21 下午7:01
@File: train.py
@Software: PyCharm
"""
from magpie import Magpie
magpie = Magpie()
'''
magpie.init_word_vectors('data/hep-categories-zh', vec_dim=100)
labels = ['军事', '旅游', '政治']
magpie.train('data/hep-categories-zh', labels, test_ratio=0.2, epochs=100)
magpie.save_model('save/keras_model_zh.h5')
magpie.save_word2vec_model('save/word2vec_model_zh', overwrite=True)
magpie.save_scaler('save/scaler_zh', overwrite=True)
print(magpie.predict_from_text('特朗普在联合国大会发表演讲谈到这届美国政府成绩时，称他已经取得了美国历史上几乎最大的成就。随后大会现场传出了嘲笑声，特朗普立即回应道：“这是真的。”'))
'''
magpie.init_word_vectors('data/emotion-categories', vec_dim=100)
labels = ['满意', '喜悦', '乐观', '愤怒', '悲哀', '恐惧', '厌恶', '焦虑', '怀疑']
magpie.train('data/emotion-categories', labels, test_ratio=0.2, epochs=2333)
magpie.save_model('save/emotion_keras_model.h5')
magpie.save_word2vec_model('save/emotion_word2vec_model', overwrite=True)
magpie.save_scaler('save/emotion_scaler', overwrite=True)
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')
# keras_model='/home/ydm/ren/remote/multiLabel/data/here.h5',
# word2vec_model='/home/ydm/ren/remote/multiLabel/data/word2vec_mode',
# scaler='/home/ydm/ren/remote/multiLabel/data/scaler',
# labels=labels
# )
magpie = Magpie()
magpie.init_word_vectors(
'/home/ydm/ren/remote/multiLabel/data/hep-categories', vec_dim=100)
print(len(labels))
magpie.train('/home/ydm/ren/remote/multiLabel/data/hep-categories',
labels,
epochs=30,
batch_size=128)
magpie.save_word2vec_model(
'/home/ydm/ren/remote/multiLabel/data/word2vec_mode_place')
magpie.save_scaler('/home/ydm/ren/remote/multiLabel/data/scaler_place',
overwrite=True)
magpie.save_model('/home/ydm/ren/remote/multiLabel/data/model_place.h5')
alltest = getlabel(
'/home/ydm/ren/remote/multiLabel/data/allsents_test.txt')
# alltest = [alltest]
writes = open('/home/ydm/ren/remote/multiLabel/data/result_place.txt',
'w',
encoding='utf-8')
for sent in alltest:
# print(sent)
pre_result = magpie.predict_from_text(sent)[:30]
# print(pre_result)
min_lr=0)
'''
#调参
for optimizer in ['SGD', 'RMSprop', 'Adagrad', 'Adadelta', 'Adam', 'Adamax', 'Nadam']:
for BATCH_SIZE in [16, 32, 64, 128, 256]:
print(optimizer+str(BATCH_SIZE))
magpie.train('data/hep-categories',
labels,
batch_size=BATCH_SIZE,
callbacks=[checkpoint, reduceLROnPlateau],
test_ratio=0.1,
epochs=60,
verbose=1,
optimizer=optimizer,
logdir='C:\\magpie-master\\trainlog\\' + optimizer + '_' + str(BATCH_SIZE) + '.txt'
)
'''
#形成最终模型
magpie.train(
'data/hep-categories',
labels,
batch_size=16,
callbacks=[checkpoint, reduceLROnPlateau],
test_ratio=0.0,
epochs=60,
verbose=1,
optimizer='Adam',
)
magpie.save_word2vec_model('save/embeddings/best', overwrite=True)
magpie.save_scaler('save/scaler/best', overwrite=True)
magpie.save_model('save/model/best.h5')