代码语言：python

所属分类：人工智能

代码描述：python使用TensorFlow基于seq2seq实现人工智能中文聊天机器人代码，首先对问答的数据进行训练，然后根据生成的模型进行预测问答。

代码标签： python TensorFlow seq2seq 人工 智能 中文 聊天 机器人 代码

下面为部分代码预览，完整代码请点击下载或在bfwstudio webide中打开

# coding:utf-8
import sys
import numpy as np
import tensorflow as tf
from tensorflow.contrib.legacy_seq2seq.python.ops import seq2seq
from numpy import unicode
import jieba
import random


class WordToken(object):
    def __init__(self):
        # 最小起始id号, 保留的用于表示特殊标记
        self.START_ID = 4
        self.word2id_dict = {}
        self.id2word_dict = {}


    def load_file_list(self, file_list, min_freq):
        """
        加载样本文件列表，全部切词后统计词频，按词频由高到低排序后顺次编号
        并存到self.word2id_dict和self.id2word_dict中
        """
        words_count = {}
        for file in file_list:
            with open(file, 'r',encoding='utf-8') as file_object:
                for line in file_object.readlines():
                    line = line.strip()
                    seg_list = jieba.cut(line)
                    for str in seg_list:
                        if str in words_count:
                            words_count[str] = words_count[str] + 1
                        else:
                            words_count[str] = 1

        sorted_list = [[v[1], v[0]] for v in words_count.items()]
        sorted_list.sort(reverse=True)
        for index, item in enumerate(sorted_list):
            word = item[1]
            if item[0] < min_freq:
                break
            self.word2id_dict[word] = self.START_ID + index
            self.id2word_dict[self.START_ID + index] = word
        return index

    def word2id(self, word):
        if not isinstance(word, unicode):
            print ("Exception: error word not unicode")
            sys.exit(1)
        if word in self.word2id_dict:
            return self.word2id_dict[word]
        else:
            return None

    def id2word(self, id):
        id = int(id)
        if id in self.id2word_dict:
            return self.id2word_dict[id]
        else:
            return None
            
# 输入序列长度
input_seq_len = 5
.........完整代码请登录后点击上方下载按钮下载查看

网友评论0

取消

评论提交中...

提交评论