{
 "cells": [
  {
   "cell_type": "code",
   "id": "initial_id",
   "metadata": {
    "collapsed": true,
    "jupyter": {
     "is_executing": true
    }
   },
   "source": [
    "#第2章/加载编码工具\n",
    "from transformers import BertTokenizer\n",
    "tokenizer = BertTokenizer.from_pretrained(\n",
    "pretrained_model_name_or_path='bert-base-chinese',\n",
    "cache_dir=None,\n",
    "force_download=False,\n",
    ")\n",
    "\n",
    "#第2章/准备实验数据\n",
    "sents = [\n",
    "'你站在桥上看风景',\n",
    "'看风景的人在楼上看你',\n",
    "'明月装饰了你的窗子',\n",
    "'你装饰了别人的梦',\n",
    "]\n",
    "\n",
    "#第2章/基本的编码函数\n",
    "out = tokenizer.encode(\n",
    "text=sents[0],\n",
    "text_pair=sents[1],\n",
    "#当句子长度大于max_length时截断\n",
    "truncation=True,\n",
    "#一律补PAD，直到max_length长度\n",
    "padding='max_length',\n",
    "add_special_tokens=True,\n",
    "max_length=25,\n",
    "return_tensors=None,\n",
    ")\n",
    "print(out)\n",
    "print(tokenizer.decode(out))"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "metadata": {},
   "cell_type": "code",
   "outputs": [],
   "execution_count": null,
   "source": "",
   "id": "1c21ec1248b8a72a"
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}