LDA主题模型

在 上张贴 由 孔 祥博发表回复

Python
1
2
3
4
5
6
7
8
9
10
11
from gensim import corpora, models, similarities
import gensim
 
#做映射，相当于词袋
dictionary = corpora.Dictionary(contents_clean)
corpus = [dictionary.doc2bow(sentence) for sentence in contents_clean]
 
lda = gensim.models.ldamodel.LdaModel(corpus=corpus, id2word=dictionary, num_topics=20) #类似Kmeans自己指定K值
 
#一号分类结果
print (lda.print_topic(1, topn=5))

[crayon-5e25561d3e4139…

新闻分类1关键词提取

在 上张贴 由 孔 祥博发表回复

Python
1
2
3
4
5
6
import pandas as pd
import jieba
#pip install jieba
df_news=pd.read_table('val.txt',names=['category','theme','URL','content'],encoding='utf-8')
df_news=df_news.dropna()
print(df_news.head())

[crayon-5e25561d3f6db5…

卷积神经网络CNN

在 上张贴 由 孔 祥博发表回复

首先还是导入mnist数据集，

Python
1
2
3
4
5
6
7
8
import tensorflow as tf
import random
import numpy as np
import matplotlib.pyplot as plt
import datetime
 
from tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets("data/",one_hot="True")

多加了卷积层…

TensorFlow神经网络

在 上张贴 由 孔 祥博发表回复

Python
1
2
3
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets("data/",one_hot=True)

  [crayon-5e25561…

TensorFlow-逻辑回归算法

在 上张贴 由 孔 祥博发表回复

Python
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
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
 
mnist=input_data.read_data_sets('data/',one_hot=True)
 
#设置参数
numClasses=10
inputSize=784
trainingIterations=50000
batchSize=64
 
#制定好x和y的大小
X=tf.placeholder(tf.float32,shape=[None,inputSize])
y=tf.placeholder(tf.float32,shape=[None,numClasses])
 
#参数初始化
W1=tf.Variable(tf.random_normal([inputSize,numClasses],stddev=0.1))
B1=tf.Variable(tf.constant(0.1),[numClasses])
 
#构造模型
y_pred=tf.nn.softmax(tf.matmul(X,W1)+B1)
 
loss=tf.reduce_mean(tf.square(y-y_pred))
opt=tf.train.GradientDescentOptimizer(learning_rate=0.5).minimize(loss)
correct_prediction=tf.equal(tf.argmax(y_pred,1),tf.argmax(y,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,"float"))
 
sess=tf.Session()
init=tf.global_variables_initializer()
sess.run(init)
 
#迭代计算
for i in range(trainingIterations):
batch=mnist.train.next_batch(batchSize)
batchInput=batch[0]
batchLabels=batch[1]
_,trainingLoss=sess.run([opt,loss],feed_dict={X:batchInput,y:batchLabels})
if i%1000==0:
train_accuracy=accuracy.eval(session=sess,feed_dict={X:batchInput,y:batchLabels})
print("step %d,training accuracy %g"%(i,train_accuracy))
 
#测试结果
batch=mnist.test.next_batch(batchSize)
testAccuracy=sess.run(accuracy,feed_dict={X:batch[0],y:batch[1]})
print("test accuracy %g"%(testAccuracy))

…