TensorFlow练习2: 对评论进行分类
本帖是前一贴的补充：
- 使用大数据，了解怎么处理数据不能一次全部加载到内存的情况。如果你内存充足，当我没说
- 训练好的模型的保存和使用
- 使用的模型没变，还是简单的feedforward神经网络（update：添加CNN模型）
- 如果你要运行本帖代码，推荐使用GPU版本或强大的VPS，我使用小笔记本差点等吐血
- 后续有关于中文的练习《TensorFlow练习13: 制作一个简单的聊天机器人》《TensorFlow练习7: 基于RNN生成古诗词》《TensorFlow练习18: 根据姓名判断性别》
在正文开始之前，我画了一个机器学习模型的基本开发流程图：
使用的数据集
使用的数据集：http://help.sentiment140.com/for-students/ (情绪分析)
数据集包含1百60万条推特，包含消极、中性和积极tweet。不知道有没有现成的微博数据集。
数据格式：移除表情符号的CSV文件，字段如下：
- 0 – the polarity of the tweet (0 = negative, 2 = neutral, 4 = positive)
- 1 – the id of the tweet (2087)
- 2 – the date of the tweet (Sat May 16 23:58:44 UTC 2009)
- 3 – the query (lyx). If there is no query, then this value is NO_QUERY.
- 4 – the user that tweeted (robotickilldozr)
- 5 – the text of the tweet (Lyx is cool)
training.1600000.processed.noemoticon.csv（238M）
testdata.manual.2009.06.14.csv（74K）
数据预处理
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
|
import nltk
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer
import pickle
import numpy as np
import pandas as pd
from collections import OrderedDict
org_train_file = 'training.1600000.processed.noemoticon.csv'
org_test_file = 'testdata.manual.2009.06.14.csv'
# 提取文件中有用的字段
def usefull_filed(org_file, output_file):
output = open(output_file, 'w')
with open(org_file, buffering=10000, encoding='latin-1') as f:
try:
for line in f: # "4","2193601966","Tue Jun 16 08:40:49 PDT 2009","NO_QUERY","AmandaMarie1028","Just woke up. Having no school is the best feeling ever "
line = line.replace('"', '')
clf = line.split(',')[0] # 4
if clf == '0':
clf = [0, 0, 1] # 消极评论
elif clf == '2':
clf = [0, 1, 0] # 中性评论
elif clf == '4':
clf = [1, 0, 0] # 积极评论
tweet = line.split(',')[-1]
outputline = str(clf) + ':%:%:%:' + tweet
output.write(outputline) # [0, 0, 1]:%:%:%: that's a bummer. You shoulda got David Carr of Third Day to do it. ;D
except Exception as e:
print(e)
output.close() # 处理完成，处理后文件大小127.5M
usefull_filed(org_train_file, 'training.csv')
usefull_filed(org_test_file, 'tesing.csv')
# 创建词汇表
def create_lexicon(train_file):
lex = []
lemmatizer = WordNetLemmatizer()
with open(train_file, buffering=10000, encoding='latin-1') as f:
try:
count_word = {} # 统计单词出现次数
for line in f:
tweet = line.split(':%:%:%:')[1]
words = word_tokenize(line.lower())
for word in words:
word = lemmatizer.lemmatize(word)
if word not in count_word:
count_word[word] = 1
else:
count_word[word] += 1
count_word = OrderedDict(sorted(count_word.items(), key=lambda t: t[1]))
for word in count_word:
if count_word[word] < 100000 and count_word[word] > 100: # 过滤掉一些词
lex.append(word)
except Exception as e:
print(e)
return lex
lex = create_lexicon('training.csv')
with open('lexcion.pickle', 'wb') as f:
pickle.dump(lex, f)
"""
# 把字符串转为向量
def string_to_vector(input_file, output_file, lex):
output_f = open(output_file, 'w')
lemmatizer = WordNetLemmatizer()
with open(input_file, buffering=10000, encoding='latin-1') as f:
for line in f:
label = line.split(':%:%:%:')[0]
tweet = line.split(':%:%:%:')[1]
words = word_tokenize(tweet.lower())
words = [lemmatizer.lemmatize(word) for word in words]
features = np.zeros(len(lex))
for word in words:
if word in lex:
features[lex.index(word)] = 1 # 一个句子中某个词可能出现两次,可以用+=1，其实区别不大
features = list(features)
output_f.write(str(label) + ":" + str(features) + '\n')
output_f.close()
f = open('lexcion.pickle', 'rb')
lex = pickle.load(f)
f.close()
# lexcion词汇表大小112k,training.vec大约112k*1600000 170G 太大，只能边转边训练了
# string_to_vector('training.csv', 'training.vec', lex)
# string_to_vector('tesing.csv', 'tesing.vec', lex)
"""
|
上面代码把原始数据转为training.csv、和tesing.csv，里面只包含label和tweet。lexcion.pickle文件保存了词汇表。
如果数据文件太大，不能一次加载到内存，可以把数据导入数据库
Dask可处理大csv文件
开始漫长的训练
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
|
import os
import random
import tensorflow as tf
import pickle
import numpy as np
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer
f = open('lexcion.pickle', 'rb')
lex = pickle.load(f)
f.close()
def get_random_line(file, point):
file.seek(point)
file.readline()
return file.readline()
# 从文件中随机选择n条记录
def get_n_random_line(file_name, n=150):
lines = []
file = open(file_name, encoding='latin-1')
total_bytes = os.stat(file_name).st_size
for i in range(n):
random_point = random.randint(0, total_bytes)
lines.append(get_random_line(file, random_point))
file.close()
return lines
def get_test_dataset(test_file):
with open(test_file, encoding='latin-1') as f:
test_x = []
test_y = []
lemmatizer = WordNetLemmatizer()
for line in f:
label = line.split(':%:%:%:')[0]
tweet = line.split(':%:%:%:')[1]
words = word_tokenize(tweet.lower())
words = [lemmatizer.lemmatize(word) for word in words]
features = np.zeros(len(lex))
for word in words:
if word in lex:
features[lex.index(word)] = 1
test_x.append(list(features))
test_y.append(eval(label))
return test_x, test_y
test_x, test_y = get_test_dataset('tesing.csv')
#######################################################################
n_input_layer = len(lex) # 输入层
n_layer_1 = 2000 # hide layer
n_layer_2 = 2000 # hide layer(隐藏层)听着很神秘，其实就是除输入输出层外的中间层
n_output_layer = 3 # 输出层
def neural_network(data):
# 定义第一层"神经元"的权重和biases
layer_1_w_b = {'w_':tf.Variable(tf.random_normal([n_input_layer, n_layer_1])), 'b_':tf.Variable(tf.random_normal([n_layer_1]))}
# 定义第二层"神经元"的权重和biases
layer_2_w_b = {'w_':tf.Variable(tf.random_normal([n_layer_1, n_layer_2])), 'b_':tf.Variable(tf.random_normal([n_layer_2]))}
# 定义输出层"神经元"的权重和biases
layer_output_w_b = {'w_':tf.Variable(tf.random_normal([n_layer_2, n_output_layer])), 'b_':tf.Variable(tf.random_normal([n_output_layer]))}
# w·x+b
layer_1 = tf.add(tf.matmul(data, layer_1_w_b['w_']), layer_1_w_b['b_'])
layer_1 = tf.nn.relu(layer_1) # 激活函数
layer_2 = tf.add(tf.matmul(layer_1, layer_2_w_b['w_']), layer_2_w_b['b_'])
layer_2 = tf.nn.relu(layer_2 ) # 激活函数
layer_output = tf.add(tf.matmul(layer_2, layer_output_w_b['w_']), layer_output_w_b['b_'])
return layer_output
X = tf.placeholder('float')
Y = tf.placeholder('float')
batch_size = 90
def train_neural_network(X, Y):
predict = neural_network(X)
cost_func = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(predict, Y))
optimizer = tf.train.AdamOptimizer().minimize(cost_func)
with tf.Session() as session:
session.run(tf.initialize_all_variables())
lemmatizer = WordNetLemmatizer()
saver = tf.train.Saver()
i = 0
pre_accuracy = 0
while True: # 一直训练
batch_x = []
batch_y = []
#if model.ckpt文件已存在:
# saver.restore(session, 'model.ckpt') 恢复保存的session
try:
lines = get_n_random_line('training.csv', batch_size)
for line in lines:
label = line.split(':%:%:%:')[0]
tweet = line.split(':%:%:%:')[1]
words = word_tokenize(tweet.lower())
words = [lemmatizer.lemmatize(word) for word in words]
features = np.zeros(len(lex))
for word in words:
if word in lex:
features[lex.index(word)] = 1 # 一个句子中某个词可能出现两次,可以用+=1，其实区别不大
batch_x.append(list(features))
batch_y.append(eval(label))
session.run([optimizer, cost_func], feed_dict={X:batch_x,Y:batch_y})
except Exception as e:
print(e)
# 准确率
if i > 100:
correct = tf.equal(tf.argmax(predict,1), tf.argmax(Y,1))
accuracy = tf.reduce_mean(tf.cast(correct,'float'))
accuracy = accuracy.eval({X:test_x, Y:test_y})
if accuracy > pre_accuracy: # 保存准确率最高的训练模型
print('准确率: ', accuracy)
pre_accuracy = accuracy
saver.save(session, 'model.ckpt') # 保存session
i = 0
i += 1
train_neural_network(X,Y)
|
上面程序占用内存600M，峰值1G。
运行：
训练模型保存为model.ckpt。
使用训练好的模型
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
import tensorflow as tf
import pickle
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer
import numpy as np
f = open('lexcion.pickle', 'rb')
lex = pickle.load(f)
f.close()
n_input_layer = len(lex) # 输入层
n_layer_1 = 2000 # hide layer
n_layer_2 = 2000 # hide layer(隐藏层)听着很神秘，其实就是除输入输出层外的中间层
n_output_layer = 3 # 输出层
def neural_network(data):
# 定义第一层"神经元"的权重和biases
layer_1_w_b = {'w_':tf.Variable(tf.random_normal([n_input_layer, n_layer_1])), 'b_':tf.Variable(tf.random_normal([n_layer_1]))}
# 定义第二层"神经元"的权重和biases
layer_2_w_b = {'w_':tf.Variable(tf.random_normal([n_layer_1, n_layer_2])), 'b_':tf.Variable(tf.random_normal([n_layer_2]))}
# 定义输出层"神经元"的权重和biases
layer_output_w_b = {'w_':tf.Variable(tf.random_normal([n_layer_2, n_output_layer])), 'b_':tf.Variable(tf.random_normal([n_output_layer]))}
# w·x+b
layer_1 = tf.add(tf.matmul(data, layer_1_w_b['w_']), layer_1_w_b['b_'])
layer_1 = tf.nn.relu(layer_1) # 激活函数
layer_2 = tf.add(tf.matmul(layer_1, layer_2_w_b['w_']), layer_2_w_b['b_'])
layer_2 = tf.nn.relu(layer_2 ) # 激活函数
layer_output = tf.add(tf.matmul(layer_2, layer_output_w_b['w_']), layer_output_w_b['b_'])
return layer_output
X = tf.placeholder('float')
def prediction(tweet_text):
predict = neural_network(X)
with tf.Session() as session:
session.run(tf.initialize_all_variables())
saver = tf.train.Saver()
saver.restore(session, 'model.ckpt')
lemmatizer = WordNetLemmatizer()
words = word_tokenize(tweet_text.lower())
words = [lemmatizer.lemmatize(word) for word in words]
features = np.zeros(len(lex))
for word in words:
if word in lex:
features[lex.index(word)] = 1
#print(predict.eval(feed_dict={X:[features]})) [[val1,val2,val3]]
res = session.run(tf.argmax(predict.eval(feed_dict={X:[features]}),1 ))
return res
prediction("I am very happe")
|
上面使用简单的feedfroward模型，下面使用CNN模型
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
|
# https://github.com/Lab41/sunny-side-up
import os
import random
import tensorflow as tf
import pickle
import numpy as np
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer
f = open('lexcion.pickle', 'rb')
lex = pickle.load(f)
f.close()
def get_random_line(file, point):
file.seek(point)
file.readline()
return file.readline()
# 从文件中随机选择n条记录
def get_n_random_line(file_name, n=150):
lines = []
file = open(file_name, encoding='latin-1')
total_bytes = os.stat(file_name).st_size
for i in range(n):
random_point = random.randint(0, total_bytes)
lines.append(get_random_line(file, random_point))
file.close()
return lines
def get_test_dataset(test_file):
with open(test_file, encoding='latin-1') as f:
test_x = []
test_y = []
lemmatizer = WordNetLemmatizer()
for line in f:
label = line.split(':%:%:%:')[0]
tweet = line.split(':%:%:%:')[1]
words = word_tokenize(tweet.lower())
words = [lemmatizer.lemmatize(word) for word in words]
features = np.zeros(len(lex))
for word in words:
if word in lex:
features[lex.index(word)] = 1
test_x.append(list(features))
test_y.append(eval(label))
return test_x, test_y
test_x, test_y = get_test_dataset('tesing.csv')
##############################################################################
input_size = len(lex)
num_classes = 3
X = tf.placeholder(tf.int32, [None, input_size])
Y = tf.placeholder(tf.float32, [None, num_classes])
dropout_keep_prob = tf.placeholder(tf.float32)
batch_size = 90
def neural_network():
# embedding layer
with tf.device('/cpu:0'), tf.name_scope("embedding"):
embedding_size = 128
W = tf.Variable(tf.random_uniform([input_size, embedding_size], -1.0, 1.0))
embedded_chars = tf.nn.embedding_lookup(W, X)
embedded_chars_expanded = tf.expand_dims(embedded_chars, -1)
# convolution + maxpool layer
num_filters = 128
filter_sizes = [3,4,5]
pooled_outputs = []
for i, filter_size in enumerate(filter_sizes):
with tf.name_scope("conv-maxpool-%s" % filter_size):
filter_shape = [filter_size, embedding_size, 1, num_filters]
W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1))
b = tf.Variable(tf.constant(0.1, shape=[num_filters]))
conv = tf.nn.conv2d(embedded_chars_expanded, W, strides=[1, 1, 1, 1], padding="VALID")
h = tf.nn.relu(tf.nn.bias_add(conv, b))
pooled = tf.nn.max_pool(h, ksize=[1, input_size - filter_size + 1, 1, 1], strides=[1, 1, 1, 1], padding='VALID')
pooled_outputs.append(pooled)
num_filters_total = num_filters * len(filter_sizes)
h_pool = tf.concat(3, pooled_outputs)
h_pool_flat = tf.reshape(h_pool, [-1, num_filters_total])
# dropout
with tf.name_scope("dropout"):
h_drop = tf.nn.dropout(h_pool_flat, dropout_keep_prob)
# output
with tf.name_scope("output"):
W = tf.get_variable("W", shape=[num_filters_total, num_classes], initializer=tf.contrib.layers.xavier_initializer())
b = tf.Variable(tf.constant(0.1, shape=[num_classes]))
output = tf.nn.xw_plus_b(h_drop, W, b)
return output
def train_neural_network():
output = neural_network()
optimizer = tf.train.AdamOptimizer(1e-3)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(output, Y))
grads_and_vars = optimizer.compute_gradients(loss)
train_op = optimizer.apply_gradients(grads_and_vars)
saver = tf.train.Saver(tf.global_variables())
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
lemmatizer = WordNetLemmatizer()
i = 0
while True:
batch_x = []
batch_y = []
#if model.ckpt文件已存在:
# saver.restore(session, 'model.ckpt') 恢复保存的session
try:
lines = get_n_random_line('training.csv', batch_size)
for line in lines:
label = line.split(':%:%:%:')[0]
tweet = line.split(':%:%:%:')[1]
words = word_tokenize(tweet.lower())
words = [lemmatizer.lemmatize(word) for word in words]
features = np.zeros(len(lex))
for word in words:
if word in lex:
features[lex.index(word)] = 1 # 一个句子中某个词可能出现两次,可以用+=1，其实区别不大
batch_x.append(list(features))
batch_y.append(eval(label))
_, loss_ = sess.run([train_op, loss], feed_dict={X:batch_x, Y:batch_y, dropout_keep_prob:0.5})
print(loss_)
except Exception as e:
print(e)
if i % 10 == 0:
predictions = tf.argmax(output, 1)
correct_predictions = tf.equal(predictions, tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_predictions, "float"))
accur = sess.run(accuracy, feed_dict={X:test_x[0:50], Y:test_y[0:50], dropout_keep_prob:1.0})
print('准确率:', accur)
i += 1
train_neural_network()
|
使用了CNN模型之后，准确率有了显著提升。
http://blog.topspeedsnail.com/archives/10420
标签:
tensorflow
【推荐】国内首个AI IDE，深度理解中文开发场景，立即下载体验Trae
【推荐】编程新体验，更懂你的AI，立即体验豆包MarsCode编程助手
【推荐】抖音旗下AI助手豆包，你的智能百科全书，全免费不限次数
【推荐】轻量又高性能的 SSH 工具 IShell：AI 加持，快人一步
· Linux系列：如何用 C#调用 C方法造成内存泄露
· AI与.NET技术实操系列（二）：开始使用ML.NET
· 记一次.NET内存居高不下排查解决与启示
· 探究高空视频全景AR技术的实现原理
· 理解Rust引用及其生命周期标识（上）
· 阿里最新开源QwQ-32B，效果媲美deepseek-r1满血版，部署成本又又又降低了！
· 单线程的Redis速度为什么快？
· SQL Server 2025 AI相关能力初探
· 展开说说关于C#中ORM框架的用法！
· AI编程工具终极对决：字节Trae VS Cursor，谁才是开发者新宠？
2016-01-08 Linux概念架构的理解(转)
2016-01-08 Dynamic proxy (good-原创)
2016-01-08 思维导图
2015-01-08 SLF4J warning or error messages and their meanings（转）
2015-01-08 java.lang.ClassNotFoundException与java.lang.NoClassDefFoundError的区别(转)
2015-01-08 java class生成jar包(转)
2015-01-08 package、import、java及javac的相关介绍（转）