环境
基于pycharm,anaconda,TensorFlow2.0
数据源
对蜡油加氢报警.xlsx表格进行预处理:
- 筛选:只使用“源”、“条件名”这两列;
- 合并:将这两列内容合并;
- 格式:将xlsx文件转化为txt格式,命名为yuchuli;
代码
进行skip-gram建模,经过200000次迭代,输出每个词的词向量,储存在vector4中(这是第四次测试),(与第一次测试生成的vector2相比,生产词向量不同,考虑这样是否会影响最后的结果?)
代码片如下
#!usr/bin/env python
# -*- coding:utf-8 -*-
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import collections
import math
import random
import jieba
import numpy as np
from six.moves import xrange
import tensorflow.compat.v1 as tf
# Step 1: Download the data.
# Read the data into a list of strings.
def read_data():
"""
对要训练的文本进行处理,最后把文本的内容的所有词放在一个列表中
"""
# 读取停用词
stop_words = []
with open("stop_words.txt", encoding='gb18030', errors='ignore') as f:
line = f.readline()
while line:
stop_words.append(line[:-1])
line = f.readline()
stop_words = set(stop_words)
print('停用词读取完毕,共{n}个词'.format(n=len(stop_words)))
# 读取文本,预处理,分词,得到
raw_word_list = []
with open('yuchuli2.txt', "r", encoding='gb18030') as f:
line = f.readline()
while line:
while '\n' in line:
line = line.replace('\n', '')
while ' ' in line:
line = line.replace(' ', '')
if len(line) > 0: # 如果句子非空
raw_words = list(jieba.cut(line, cut_all=False))
raw_word_list.extend(raw_words)
line = f.readline()
return raw_word_list
# step 1:读取文件中的内容组成一个列表
words = read_data()
print('Data size', len(words))
# Step 2: Build the dictionary and replace rare words with UNK token.创建字典代替稀有词
vocabulary_size = 50000
def build_dataset(words):
count = [['UNK', -1]]
count.extend(collections.Counter(words).most_common(vocabulary_size - 1))
print("count", len(count))
dictionary = dict()
for word, _ in count:
dictionary[word] = len(dictionary)
data = list()
unk_count = 0
for word in words:
if word in dictionary:
index = dictionary[word]
else:
index = 0
unk_count += 1
data.append(index)
count[0][1] = unk_count
reverse_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
return data, count, dictionary, reverse_dictionary
data, count, dictionary, reverse_dictionary = build_dataset(words)
# 删除words节省内存
#del words
print('Most common words (+UNK)', count[:5])
print('Sample data', data[:10], [reverse_dictionary[i] for i in data[:10]])
data_index = 0
# Step 3: Function to generate a training batch for the skip-gram model.
def generate_batch(batch_size, num_skips, skip_window):
global data_index
assert batch_size % num_skips == 0
assert num_skips <= 2 * skip_window
batch = np.ndarray(shape=(batch_size), dtype=np.int32)
labels = np.ndarray(shape=(batch_size, 1), dtype=np.int32)
span = 2 * skip_window + 1 # [ skip_window target skip_window ]
buffer = collections.deque(maxlen=span)
for _ in range(span):
buffer.append(data[data_index])
data_index = (data_index + 1) % len(data)
for i in range(batch_size // num_skips):
target = skip_window # target label at the center of the buffer
targets_to_avoid = [skip_window]
for j in range(num_skips):
while target in targets_to_avoid:
target = random.randint(0, span - 1)
targets_to_avoid.append(target)
batch[i * num_skips + j] = buffer[skip_window]
labels[i * num_skips + j, 0] = buffer[target]
buffer.append(data[data_index])
data_index = (data_index + 1) % len(data)
return batch, labels
batch, labels = generate_batch(batch_size=8, num_skips=2, skip_window=1)
for i in range(8):
print(batch[i], reverse_dictionary[batch[i]], '->', labels[i, 0], reverse_dictionary[labels[i, 0]])
# Step 4: Build and train a skip-gram model.
batch_size = 128
embedding_size = 128
skip_window = 1
num_skips = 2
valid_size = 1 # 切记这个数字要和len(valid_word)对应,要不然会报错哦
valid_window = 100
num_sampled = 64 # Number of negative examples to sample.
# 验证集
valid_word = ['120TI2038HI']
valid_examples = [dictionary[li] for li in valid_word]
graph = tf.Graph()
with graph.as_default():
# Input data.
train_inputs = tf.placeholder(tf.int32, shape=[batch_size])
train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])
valid_dataset = tf.constant(valid_examples, dtype=tf.int32)
# Ops and variables pinned to the CPU because of missing GPU implementation
with tf.device('/cpu:0'):
# Look up embeddings for inputs.
embeddings = tf.Variable(
tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
embed = tf.nn.embedding_lookup(embeddings, train_inputs)
# Construct the variables for the NCE loss
nce_weights = tf.Variable(
tf.truncated_normal([vocabulary_size, embedding_size],
stddev=1.0 / math.sqrt(embedding_size)))
nce_biases = tf.Variable(tf.zeros([vocabulary_size]), dtype=tf.float32)
# Compute the average NCE loss for the batch.
# tf.nce_loss automatically draws a new sample of the negative labels each
# time we evaluate the loss.
loss = tf.reduce_mean(tf.nn.nce_loss(weights=nce_weights,
biases=nce_biases,
inputs=embed,
labels=train_labels,
num_sampled=num_sampled,
num_classes=vocabulary_size))
# Construct the SGD optimizer using a learning rate of 1.0.
optimizer = tf.train.GradientDescentOptimizer(1.0).minimize(loss)
# Compute the cosine similarity between minibatch examples and all embeddings.
norm = tf.sqrt(tf.reduce_sum(tf.square(embeddings), 1, keep_dims=True))
normalized_embeddings = embeddings / norm
#valid_embeddings = tf.nn.embedding_lookup(normalized_embeddings)
valid_embeddings = tf.nn.embedding_lookup(normalized_embeddings, valid_dataset)
similarity = tf.matmul(valid_embeddings, normalized_embeddings, transpose_b=True)
#similarity = tf.matmul(normalized_embeddings, transpose_b=True)
# Add variable initializer.
init = tf.global_variables_initializer()
# Step 5: Begin training.
num_steps = 200000
with tf.Session(graph=graph) as session:
# We must initialize all variables before we use them.
init.run()
print("Initialized")
average_loss = 0
for step in xrange(num_steps):
batch_inputs, batch_labels = generate_batch(batch_size, num_skips, skip_window)
feed_dict = {train_inputs: batch_inputs, train_labels: batch_labels}
# We perform one update step by evaluating the optimizer op (including it
# in the list of returned values for session.run()
_, loss_val = session.run([optimizer, loss], feed_dict=feed_dict)
average_loss += loss_val
if step % 2000 == 0:
if step > 0:
average_loss /= 2000
# The average loss is an estimate of the loss over the last 2000 batches.
print("Average loss at step ", step, ": ", average_loss)
average_loss = 0
# Note that this is expensive (~20% slowdown if computed every 500 steps)
if step % 10000 == 0:
sim = similarity.eval()
for i in xrange(valid_size):
valid_word = reverse_dictionary[valid_examples[i]]
top_k = 8 # number of nearest neighbors
nearest = (-sim[i, :]).argsort()[:top_k]
log_str = "Nearest to %s:" % valid_word
# for k in xrange(top_k):
# close_word = reverse_dictionary[nearest[k]]
# log_str = "%s %s," % (log_str, close_word)
print(log_str)
final_embeddings = normalized_embeddings.eval()
# 训练得到最后的词向量矩阵
print(final_embeddings)
fp = open('vector4.txt', 'w', encoding='utf8')
for k, v in reverse_dictionary.items():
t = tuple(final_embeddings[k])
s = ''
for i in t:
i = str(i)
s += i + " "
fp.write(v + " " + s + "\n")
# s为'0.031514477 0.059997283 ...' , 对于每一个词的词向量中的300个数字,用空格把他们连接成字符串。
# 把词向量写入文本文档中。不过这样就成了字符串,我之前试过用np保存为ndarray格式,这里是按源码的保存方式。
fp.close()
# Step 6: Visualize the embeddings.
def plot_with_labels(low_dim_embs, labels, filename='images/tsne4.png', fonts=None):
assert low_dim_embs.shape[0] >= len(labels), "More labels than embeddings"
plt.figure(figsize=(18, 18)) # in inches
for i, label in enumerate(labels):
x, y = low_dim_embs[i, :]
plt.scatter(x, y) # 显示散点图
plt.annotate(label,
fontproperties=fonts,
xy=(x, y), # 添加注释, xytest是注释的位置。然后添加显示的字体。
xytext=(5, 2),
textcoords='offset points',
ha='right',
va='bottom')
plt.savefig(filename, dpi=800)
plt.show()
try:
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
# 这个库很重要,因为需要加载字体,原开源代码里是没有的。
# 为了在图片上能显示出中文
font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=14)
tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
plot_only = 50
low_dim_embs = tsne.fit_transform(final_embeddings[:plot_only, :])
labels = []
labels = [reverse_dictionary[i] for i in xrange(plot_only)]
# tsne: 一个降维的方法,降维后维度是2维,使用'pca'来初始化。
# 取出了前500个词的词向量,把300维减低到2维。
plot_with_labels(low_dim_embs, labels,fonts=font)
except ImportError:
print("Please install sklearn, matplotlib, and scipy to visualize embeddings.")
运行结果
-
词向量储存在vector4中;
-
可视化结果(结果不是很好,思考原因中= ̄へ ̄=)
没有发现太接近的报警
问题
- 是否需要解决可视化不好的问题,毕竟要利用的是词向量来做聚类分析;
- 如果需要解决可视化结果的问题,怎么解决?
- 值得一提的是每次生成的词向量都不一样,有什么含义?
- txt文件是分行的,试试不分行的话分词会怎么样?
- 不是中文(英文+数字)需要分词吗?