fastNLP/tutorials/fastnlp_1min_tutorial.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "# fastNLP 1分钟上手教程"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## step 1\n",
    "读取数据集"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastNLP import DataSet\n",
    "           \n",
    "data_path = \"./sample_data/tutorial_sample_dataset.csv\"\n",
    "ds = DataSet.read_csv(data_path, headers=('raw_sentence', 'label'), sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'raw_sentence': This quiet , introspective and entertaining independent is worth seeking . type=str,\n",
       "'label': 4 type=str}"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ds[1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## step 2\n",
    "数据预处理\n",
    "1. 类型转换\n",
    "2. 切分验证集\n",
    "3. 构建词典"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[['a',\n",
       "  'series',\n",
       "  'of',\n",
       "  'escapades',\n",
       "  'demonstrating',\n",
       "  'the',\n",
       "  'adage',\n",
       "  'that',\n",
       "  'what',\n",
       "  'is',\n",
       "  'good',\n",
       "  'for',\n",
       "  'the',\n",
       "  'goose',\n",
       "  'is',\n",
       "  'also',\n",
       "  'good',\n",
       "  'for',\n",
       "  'the',\n",
       "  'gander',\n",
       "  ',',\n",
       "  'some',\n",
       "  'of',\n",
       "  'which',\n",
       "  'occasionally',\n",
       "  'amuses',\n",
       "  'but',\n",
       "  'none',\n",
       "  'of',\n",
       "  'which',\n",
       "  'amounts',\n",
       "  'to',\n",
       "  'much',\n",
       "  'of',\n",
       "  'a',\n",
       "  'story',\n",
       "  '.'],\n",
       " ['this',\n",
       "  'quiet',\n",
       "  ',',\n",
       "  'introspective',\n",
       "  'and',\n",
       "  'entertaining',\n",
       "  'independent',\n",
       "  'is',\n",
       "  'worth',\n",
       "  'seeking',\n",
       "  '.'],\n",
       " ['even',\n",
       "  'fans',\n",
       "  'of',\n",
       "  'ismail',\n",
       "  'merchant',\n",
       "  \"'s\",\n",
       "  'work',\n",
       "  ',',\n",
       "  'i',\n",
       "  'suspect',\n",
       "  ',',\n",
       "  'would',\n",
       "  'have',\n",
       "  'a',\n",
       "  'hard',\n",
       "  'time',\n",
       "  'sitting',\n",
       "  'through',\n",
       "  'this',\n",
       "  'one',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'positively',\n",
       "  'thrilling',\n",
       "  'combination',\n",
       "  'of',\n",
       "  'ethnography',\n",
       "  'and',\n",
       "  'all',\n",
       "  'the',\n",
       "  'intrigue',\n",
       "  ',',\n",
       "  'betrayal',\n",
       "  ',',\n",
       "  'deceit',\n",
       "  'and',\n",
       "  'murder',\n",
       "  'of',\n",
       "  'a',\n",
       "  'shakespearean',\n",
       "  'tragedy',\n",
       "  'or',\n",
       "  'a',\n",
       "  'juicy',\n",
       "  'soap',\n",
       "  'opera',\n",
       "  '.'],\n",
       " ['aggressive',\n",
       "  'self-glorification',\n",
       "  'and',\n",
       "  'a',\n",
       "  'manipulative',\n",
       "  'whitewash',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'comedy-drama',\n",
       "  'of',\n",
       "  'nearly',\n",
       "  'epic',\n",
       "  'proportions',\n",
       "  'rooted',\n",
       "  'in',\n",
       "  'a',\n",
       "  'sincere',\n",
       "  'performance',\n",
       "  'by',\n",
       "  'the',\n",
       "  'title',\n",
       "  'character',\n",
       "  'undergoing',\n",
       "  'midlife',\n",
       "  'crisis',\n",
       "  '.'],\n",
       " ['narratively',\n",
       "  ',',\n",
       "  'trouble',\n",
       "  'every',\n",
       "  'day',\n",
       "  'is',\n",
       "  'a',\n",
       "  'plodding',\n",
       "  'mess',\n",
       "  '.'],\n",
       " ['the',\n",
       "  'importance',\n",
       "  'of',\n",
       "  'being',\n",
       "  'earnest',\n",
       "  ',',\n",
       "  'so',\n",
       "  'thick',\n",
       "  'with',\n",
       "  'wit',\n",
       "  'it',\n",
       "  'plays',\n",
       "  'like',\n",
       "  'a',\n",
       "  'reading',\n",
       "  'from',\n",
       "  'bartlett',\n",
       "  \"'s\",\n",
       "  'familiar',\n",
       "  'quotations'],\n",
       " ['but', 'it', 'does', \"n't\", 'leave', 'you', 'with', 'much', '.'],\n",
       " ['you', 'could', 'hate', 'it', 'for', 'the', 'same', 'reason', '.'],\n",
       " ['there',\n",
       "  \"'s\",\n",
       "  'little',\n",
       "  'to',\n",
       "  'recommend',\n",
       "  'snow',\n",
       "  'dogs',\n",
       "  ',',\n",
       "  'unless',\n",
       "  'one',\n",
       "  'considers',\n",
       "  'cliched',\n",
       "  'dialogue',\n",
       "  'and',\n",
       "  'perverse',\n",
       "  'escapism',\n",
       "  'a',\n",
       "  'source',\n",
       "  'of',\n",
       "  'high',\n",
       "  'hilarity',\n",
       "  '.'],\n",
       " ['kung',\n",
       "  'pow',\n",
       "  'is',\n",
       "  'oedekerk',\n",
       "  \"'s\",\n",
       "  'realization',\n",
       "  'of',\n",
       "  'his',\n",
       "  'childhood',\n",
       "  'dream',\n",
       "  'to',\n",
       "  'be',\n",
       "  'in',\n",
       "  'a',\n",
       "  'martial-arts',\n",
       "  'flick',\n",
       "  ',',\n",
       "  'and',\n",
       "  'proves',\n",
       "  'that',\n",
       "  'sometimes',\n",
       "  'the',\n",
       "  'dreams',\n",
       "  'of',\n",
       "  'youth',\n",
       "  'should',\n",
       "  'remain',\n",
       "  'just',\n",
       "  'that',\n",
       "  '.'],\n",
       " ['the', 'performances', 'are', 'an', 'absolute', 'joy', '.'],\n",
       " ['fresnadillo',\n",
       "  'has',\n",
       "  'something',\n",
       "  'serious',\n",
       "  'to',\n",
       "  'say',\n",
       "  'about',\n",
       "  'the',\n",
       "  'ways',\n",
       "  'in',\n",
       "  'which',\n",
       "  'extravagant',\n",
       "  'chance',\n",
       "  'can',\n",
       "  'distort',\n",
       "  'our',\n",
       "  'perspective',\n",
       "  'and',\n",
       "  'throw',\n",
       "  'us',\n",
       "  'off',\n",
       "  'the',\n",
       "  'path',\n",
       "  'of',\n",
       "  'good',\n",
       "  'sense',\n",
       "  '.'],\n",
       " ['i',\n",
       "  'still',\n",
       "  'like',\n",
       "  'moonlight',\n",
       "  'mile',\n",
       "  ',',\n",
       "  'better',\n",
       "  'judgment',\n",
       "  'be',\n",
       "  'damned',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'welcome',\n",
       "  'relief',\n",
       "  'from',\n",
       "  'baseball',\n",
       "  'movies',\n",
       "  'that',\n",
       "  'try',\n",
       "  'too',\n",
       "  'hard',\n",
       "  'to',\n",
       "  'be',\n",
       "  'mythic',\n",
       "  ',',\n",
       "  'this',\n",
       "  'one',\n",
       "  'is',\n",
       "  'a',\n",
       "  'sweet',\n",
       "  'and',\n",
       "  'modest',\n",
       "  'and',\n",
       "  'ultimately',\n",
       "  'winning',\n",
       "  'story',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'bilingual',\n",
       "  'charmer',\n",
       "  ',',\n",
       "  'just',\n",
       "  'like',\n",
       "  'the',\n",
       "  'woman',\n",
       "  'who',\n",
       "  'inspired',\n",
       "  'it'],\n",
       " ['like',\n",
       "  'a',\n",
       "  'less',\n",
       "  'dizzily',\n",
       "  'gorgeous',\n",
       "  'companion',\n",
       "  'to',\n",
       "  'mr.',\n",
       "  'wong',\n",
       "  \"'s\",\n",
       "  'in',\n",
       "  'the',\n",
       "  'mood',\n",
       "  'for',\n",
       "  'love',\n",
       "  '--',\n",
       "  'very',\n",
       "  'much',\n",
       "  'a',\n",
       "  'hong',\n",
       "  'kong',\n",
       "  'movie',\n",
       "  'despite',\n",
       "  'its',\n",
       "  'mainland',\n",
       "  'setting',\n",
       "  '.'],\n",
       " ['as',\n",
       "  'inept',\n",
       "  'as',\n",
       "  'big-screen',\n",
       "  'remakes',\n",
       "  'of',\n",
       "  'the',\n",
       "  'avengers',\n",
       "  'and',\n",
       "  'the',\n",
       "  'wild',\n",
       "  'wild',\n",
       "  'west',\n",
       "  '.'],\n",
       " ['it',\n",
       "  \"'s\",\n",
       "  'everything',\n",
       "  'you',\n",
       "  \"'d\",\n",
       "  'expect',\n",
       "  '--',\n",
       "  'but',\n",
       "  'nothing',\n",
       "  'more',\n",
       "  '.'],\n",
       " ['best', 'indie', 'of', 'the', 'year', ',', 'so', 'far', '.'],\n",
       " ['hatfield',\n",
       "  'and',\n",
       "  'hicks',\n",
       "  'make',\n",
       "  'the',\n",
       "  'oddest',\n",
       "  'of',\n",
       "  'couples',\n",
       "  ',',\n",
       "  'and',\n",
       "  'in',\n",
       "  'this',\n",
       "  'sense',\n",
       "  'the',\n",
       "  'movie',\n",
       "  'becomes',\n",
       "  'a',\n",
       "  'study',\n",
       "  'of',\n",
       "  'the',\n",
       "  'gambles',\n",
       "  'of',\n",
       "  'the',\n",
       "  'publishing',\n",
       "  'world',\n",
       "  ',',\n",
       "  'offering',\n",
       "  'a',\n",
       "  'case',\n",
       "  'study',\n",
       "  'that',\n",
       "  'exists',\n",
       "  'apart',\n",
       "  'from',\n",
       "  'all',\n",
       "  'the',\n",
       "  'movie',\n",
       "  \"'s\",\n",
       "  'political',\n",
       "  'ramifications',\n",
       "  '.'],\n",
       " ['it',\n",
       "  \"'s\",\n",
       "  'like',\n",
       "  'going',\n",
       "  'to',\n",
       "  'a',\n",
       "  'house',\n",
       "  'party',\n",
       "  'and',\n",
       "  'watching',\n",
       "  'the',\n",
       "  'host',\n",
       "  'defend',\n",
       "  'himself',\n",
       "  'against',\n",
       "  'a',\n",
       "  'frothing',\n",
       "  'ex-girlfriend',\n",
       "  '.'],\n",
       " ['that',\n",
       "  'the',\n",
       "  'chuck',\n",
       "  'norris',\n",
       "  '``',\n",
       "  'grenade',\n",
       "  'gag',\n",
       "  \"''\",\n",
       "  'occurs',\n",
       "  'about',\n",
       "  '7',\n",
       "  'times',\n",
       "  'during',\n",
       "  'windtalkers',\n",
       "  'is',\n",
       "  'a',\n",
       "  'good',\n",
       "  'indication',\n",
       "  'of',\n",
       "  'how',\n",
       "  'serious-minded',\n",
       "  'the',\n",
       "  'film',\n",
       "  'is',\n",
       "  '.'],\n",
       " ['the',\n",
       "  'plot',\n",
       "  'is',\n",
       "  'romantic',\n",
       "  'comedy',\n",
       "  'boilerplate',\n",
       "  'from',\n",
       "  'start',\n",
       "  'to',\n",
       "  'finish',\n",
       "  '.'],\n",
       " ['it',\n",
       "  'arrives',\n",
       "  'with',\n",
       "  'an',\n",
       "  'impeccable',\n",
       "  'pedigree',\n",
       "  ',',\n",
       "  'mongrel',\n",
       "  'pep',\n",
       "  ',',\n",
       "  'and',\n",
       "  'almost',\n",
       "  'indecipherable',\n",
       "  'plot',\n",
       "  'complications',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'film',\n",
       "  'that',\n",
       "  'clearly',\n",
       "  'means',\n",
       "  'to',\n",
       "  'preach',\n",
       "  'exclusively',\n",
       "  'to',\n",
       "  'the',\n",
       "  'converted',\n",
       "  '.'],\n",
       " ['while',\n",
       "  'the',\n",
       "  'importance',\n",
       "  'of',\n",
       "  'being',\n",
       "  'earnest',\n",
       "  'offers',\n",
       "  'opportunities',\n",
       "  'for',\n",
       "  'occasional',\n",
       "  'smiles',\n",
       "  'and',\n",
       "  'chuckles',\n",
       "  ',',\n",
       "  'it',\n",
       "  'does',\n",
       "  \"n't\",\n",
       "  'give',\n",
       "  'us',\n",
       "  'a',\n",
       "  'reason',\n",
       "  'to',\n",
       "  'be',\n",
       "  'in',\n",
       "  'the',\n",
       "  'theater',\n",
       "  'beyond',\n",
       "  'wilde',\n",
       "  \"'s\",\n",
       "  'wit',\n",
       "  'and',\n",
       "  'the',\n",
       "  'actors',\n",
       "  \"'\",\n",
       "  'performances',\n",
       "  '.'],\n",
       " ['the',\n",
       "  'latest',\n",
       "  'vapid',\n",
       "  'actor',\n",
       "  \"'s\",\n",
       "  'exercise',\n",
       "  'to',\n",
       "  'appropriate',\n",
       "  'the',\n",
       "  'structure',\n",
       "  'of',\n",
       "  'arthur',\n",
       "  'schnitzler',\n",
       "  \"'s\",\n",
       "  'reigen',\n",
       "  '.'],\n",
       " ['more',\n",
       "  'vaudeville',\n",
       "  'show',\n",
       "  'than',\n",
       "  'well-constructed',\n",
       "  'narrative',\n",
       "  ',',\n",
       "  'but',\n",
       "  'on',\n",
       "  'those',\n",
       "  'terms',\n",
       "  'it',\n",
       "  \"'s\",\n",
       "  'inoffensive',\n",
       "  'and',\n",
       "  'actually',\n",
       "  'rather',\n",
       "  'sweet',\n",
       "  '.'],\n",
       " ['nothing', 'more', 'than', 'a', 'run-of-the-mill', 'action', 'flick', '.'],\n",
       " ['hampered',\n",
       "  '--',\n",
       "  'no',\n",
       "  ',',\n",
       "  'paralyzed',\n",
       "  '--',\n",
       "  'by',\n",
       "  'a',\n",
       "  'self-indulgent',\n",
       "  'script',\n",
       "  '...',\n",
       "  'that',\n",
       "  'aims',\n",
       "  'for',\n",
       "  'poetry',\n",
       "  'and',\n",
       "  'ends',\n",
       "  'up',\n",
       "  'sounding',\n",
       "  'like',\n",
       "  'satire',\n",
       "  '.'],\n",
       " ['ice',\n",
       "  'age',\n",
       "  'is',\n",
       "  'the',\n",
       "  'first',\n",
       "  'computer-generated',\n",
       "  'feature',\n",
       "  'cartoon',\n",
       "  'to',\n",
       "  'feel',\n",
       "  'like',\n",
       "  'other',\n",
       "  'movies',\n",
       "  ',',\n",
       "  'and',\n",
       "  'that',\n",
       "  'makes',\n",
       "  'for',\n",
       "  'some',\n",
       "  'glacial',\n",
       "  'pacing',\n",
       "  'early',\n",
       "  'on',\n",
       "  '.'],\n",
       " ['there',\n",
       "  \"'s\",\n",
       "  'very',\n",
       "  'little',\n",
       "  'sense',\n",
       "  'to',\n",
       "  'what',\n",
       "  \"'s\",\n",
       "  'going',\n",
       "  'on',\n",
       "  'here',\n",
       "  ',',\n",
       "  'but',\n",
       "  'the',\n",
       "  'makers',\n",
       "  'serve',\n",
       "  'up',\n",
       "  'the',\n",
       "  'cliches',\n",
       "  'with',\n",
       "  'considerable',\n",
       "  'dash',\n",
       "  '.'],\n",
       " ['cattaneo',\n",
       "  'should',\n",
       "  'have',\n",
       "  'followed',\n",
       "  'the',\n",
       "  'runaway',\n",
       "  'success',\n",
       "  'of',\n",
       "  'his',\n",
       "  'first',\n",
       "  'film',\n",
       "  ',',\n",
       "  'the',\n",
       "  'full',\n",
       "  'monty',\n",
       "  ',',\n",
       "  'with',\n",
       "  'something',\n",
       "  'different',\n",
       "  '.'],\n",
       " ['they',\n",
       "  \"'re\",\n",
       "  'the',\n",
       "  'unnamed',\n",
       "  ',',\n",
       "  'easily',\n",
       "  'substitutable',\n",
       "  'forces',\n",
       "  'that',\n",
       "  'serve',\n",
       "  'as',\n",
       "  'whatever',\n",
       "  'terror',\n",
       "  'the',\n",
       "  'heroes',\n",
       "  'of',\n",
       "  'horror',\n",
       "  'movies',\n",
       "  'try',\n",
       "  'to',\n",
       "  'avoid',\n",
       "  '.'],\n",
       " ['it',\n",
       "  'almost',\n",
       "  'feels',\n",
       "  'as',\n",
       "  'if',\n",
       "  'the',\n",
       "  'movie',\n",
       "  'is',\n",
       "  'more',\n",
       "  'interested',\n",
       "  'in',\n",
       "  'entertaining',\n",
       "  'itself',\n",
       "  'than',\n",
       "  'in',\n",
       "  'amusing',\n",
       "  'us',\n",
       "  '.'],\n",
       " ['the',\n",
       "  'movie',\n",
       "  \"'s\",\n",
       "  'progression',\n",
       "  'into',\n",
       "  'rambling',\n",
       "  'incoherence',\n",
       "  'gives',\n",
       "  'new',\n",
       "  'meaning',\n",
       "  'to',\n",
       "  'the',\n",
       "  'phrase',\n",
       "  '`',\n",
       "  'fatal',\n",
       "  'script',\n",
       "  'error',\n",
       "  '.',\n",
       "  \"'\"],\n",
       " ['i',\n",
       "  'still',\n",
       "  'like',\n",
       "  'moonlight',\n",
       "  'mile',\n",
       "  ',',\n",
       "  'better',\n",
       "  'judgment',\n",
       "  'be',\n",
       "  'damned',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'welcome',\n",
       "  'relief',\n",
       "  'from',\n",
       "  'baseball',\n",
       "  'movies',\n",
       "  'that',\n",
       "  'try',\n",
       "  'too',\n",
       "  'hard',\n",
       "  'to',\n",
       "  'be',\n",
       "  'mythic',\n",
       "  ',',\n",
       "  'this',\n",
       "  'one',\n",
       "  'is',\n",
       "  'a',\n",
       "  'sweet',\n",
       "  'and',\n",
       "  'modest',\n",
       "  'and',\n",
       "  'ultimately',\n",
       "  'winning',\n",
       "  'story',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'bilingual',\n",
       "  'charmer',\n",
       "  ',',\n",
       "  'just',\n",
       "  'like',\n",
       "  'the',\n",
       "  'woman',\n",
       "  'who',\n",
       "  'inspired',\n",
       "  'it'],\n",
       " ['like',\n",
       "  'a',\n",
       "  'less',\n",
       "  'dizzily',\n",
       "  'gorgeous',\n",
       "  'companion',\n",
       "  'to',\n",
       "  'mr.',\n",
       "  'wong',\n",
       "  \"'s\",\n",
       "  'in',\n",
       "  'the',\n",
       "  'mood',\n",
       "  'for',\n",
       "  'love',\n",
       "  '--',\n",
       "  'very',\n",
       "  'much',\n",
       "  'a',\n",
       "  'hong',\n",
       "  'kong',\n",
       "  'movie',\n",
       "  'despite',\n",
       "  'its',\n",
       "  'mainland',\n",
       "  'setting',\n",
       "  '.'],\n",
       " ['as',\n",
       "  'inept',\n",
       "  'as',\n",
       "  'big-screen',\n",
       "  'remakes',\n",
       "  'of',\n",
       "  'the',\n",
       "  'avengers',\n",
       "  'and',\n",
       "  'the',\n",
       "  'wild',\n",
       "  'wild',\n",
       "  'west',\n",
       "  '.'],\n",
       " ['it',\n",
       "  \"'s\",\n",
       "  'everything',\n",
       "  'you',\n",
       "  \"'d\",\n",
       "  'expect',\n",
       "  '--',\n",
       "  'but',\n",
       "  'nothing',\n",
       "  'more',\n",
       "  '.'],\n",
       " ['best', 'indie', 'of', 'the', 'year', ',', 'so', 'far', '.'],\n",
       " ['hatfield',\n",
       "  'and',\n",
       "  'hicks',\n",
       "  'make',\n",
       "  'the',\n",
       "  'oddest',\n",
       "  'of',\n",
       "  'couples',\n",
       "  ',',\n",
       "  'and',\n",
       "  'in',\n",
       "  'this',\n",
       "  'sense',\n",
       "  'the',\n",
       "  'movie',\n",
       "  'becomes',\n",
       "  'a',\n",
       "  'study',\n",
       "  'of',\n",
       "  'the',\n",
       "  'gambles',\n",
       "  'of',\n",
       "  'the',\n",
       "  'publishing',\n",
       "  'world',\n",
       "  ',',\n",
       "  'offering',\n",
       "  'a',\n",
       "  'case',\n",
       "  'study',\n",
       "  'that',\n",
       "  'exists',\n",
       "  'apart',\n",
       "  'from',\n",
       "  'all',\n",
       "  'the',\n",
       "  'movie',\n",
       "  \"'s\",\n",
       "  'political',\n",
       "  'ramifications',\n",
       "  '.'],\n",
       " ['it',\n",
       "  \"'s\",\n",
       "  'like',\n",
       "  'going',\n",
       "  'to',\n",
       "  'a',\n",
       "  'house',\n",
       "  'party',\n",
       "  'and',\n",
       "  'watching',\n",
       "  'the',\n",
       "  'host',\n",
       "  'defend',\n",
       "  'himself',\n",
       "  'against',\n",
       "  'a',\n",
       "  'frothing',\n",
       "  'ex-girlfriend',\n",
       "  '.'],\n",
       " ['that',\n",
       "  'the',\n",
       "  'chuck',\n",
       "  'norris',\n",
       "  '``',\n",
       "  'grenade',\n",
       "  'gag',\n",
       "  \"''\",\n",
       "  'occurs',\n",
       "  'about',\n",
       "  '7',\n",
       "  'times',\n",
       "  'during',\n",
       "  'windtalkers',\n",
       "  'is',\n",
       "  'a',\n",
       "  'good',\n",
       "  'indication',\n",
       "  'of',\n",
       "  'how',\n",
       "  'serious-minded',\n",
       "  'the',\n",
       "  'film',\n",
       "  'is',\n",
       "  '.'],\n",
       " ['the',\n",
       "  'plot',\n",
       "  'is',\n",
       "  'romantic',\n",
       "  'comedy',\n",
       "  'boilerplate',\n",
       "  'from',\n",
       "  'start',\n",
       "  'to',\n",
       "  'finish',\n",
       "  '.'],\n",
       " ['it',\n",
       "  'arrives',\n",
       "  'with',\n",
       "  'an',\n",
       "  'impeccable',\n",
       "  'pedigree',\n",
       "  ',',\n",
       "  'mongrel',\n",
       "  'pep',\n",
       "  ',',\n",
       "  'and',\n",
       "  'almost',\n",
       "  'indecipherable',\n",
       "  'plot',\n",
       "  'complications',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'film',\n",
       "  'that',\n",
       "  'clearly',\n",
       "  'means',\n",
       "  'to',\n",
       "  'preach',\n",
       "  'exclusively',\n",
       "  'to',\n",
       "  'the',\n",
       "  'converted',\n",
       "  '.'],\n",
       " ['i',\n",
       "  'still',\n",
       "  'like',\n",
       "  'moonlight',\n",
       "  'mile',\n",
       "  ',',\n",
       "  'better',\n",
       "  'judgment',\n",
       "  'be',\n",
       "  'damned',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'welcome',\n",
       "  'relief',\n",
       "  'from',\n",
       "  'baseball',\n",
       "  'movies',\n",
       "  'that',\n",
       "  'try',\n",
       "  'too',\n",
       "  'hard',\n",
       "  'to',\n",
       "  'be',\n",
       "  'mythic',\n",
       "  ',',\n",
       "  'this',\n",
       "  'one',\n",
       "  'is',\n",
       "  'a',\n",
       "  'sweet',\n",
       "  'and',\n",
       "  'modest',\n",
       "  'and',\n",
       "  'ultimately',\n",
       "  'winning',\n",
       "  'story',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'bilingual',\n",
       "  'charmer',\n",
       "  ',',\n",
       "  'just',\n",
       "  'like',\n",
       "  'the',\n",
       "  'woman',\n",
       "  'who',\n",
       "  'inspired',\n",
       "  'it'],\n",
       " ['like',\n",
       "  'a',\n",
       "  'less',\n",
       "  'dizzily',\n",
       "  'gorgeous',\n",
       "  'companion',\n",
       "  'to',\n",
       "  'mr.',\n",
       "  'wong',\n",
       "  \"'s\",\n",
       "  'in',\n",
       "  'the',\n",
       "  'mood',\n",
       "  'for',\n",
       "  'love',\n",
       "  '--',\n",
       "  'very',\n",
       "  'much',\n",
       "  'a',\n",
       "  'hong',\n",
       "  'kong',\n",
       "  'movie',\n",
       "  'despite',\n",
       "  'its',\n",
       "  'mainland',\n",
       "  'setting',\n",
       "  '.'],\n",
       " ['as',\n",
       "  'inept',\n",
       "  'as',\n",
       "  'big-screen',\n",
       "  'remakes',\n",
       "  'of',\n",
       "  'the',\n",
       "  'avengers',\n",
       "  'and',\n",
       "  'the',\n",
       "  'wild',\n",
       "  'wild',\n",
       "  'west',\n",
       "  '.'],\n",
       " ['it',\n",
       "  \"'s\",\n",
       "  'everything',\n",
       "  'you',\n",
       "  \"'d\",\n",
       "  'expect',\n",
       "  '--',\n",
       "  'but',\n",
       "  'nothing',\n",
       "  'more',\n",
       "  '.'],\n",
       " ['best', 'indie', 'of', 'the', 'year', ',', 'so', 'far', '.'],\n",
       " ['hatfield',\n",
       "  'and',\n",
       "  'hicks',\n",
       "  'make',\n",
       "  'the',\n",
       "  'oddest',\n",
       "  'of',\n",
       "  'couples',\n",
       "  ',',\n",
       "  'and',\n",
       "  'in',\n",
       "  'this',\n",
       "  'sense',\n",
       "  'the',\n",
       "  'movie',\n",
       "  'becomes',\n",
       "  'a',\n",
       "  'study',\n",
       "  'of',\n",
       "  'the',\n",
       "  'gambles',\n",
       "  'of',\n",
       "  'the',\n",
       "  'publishing',\n",
       "  'world',\n",
       "  ',',\n",
       "  'offering',\n",
       "  'a',\n",
       "  'case',\n",
       "  'study',\n",
       "  'that',\n",
       "  'exists',\n",
       "  'apart',\n",
       "  'from',\n",
       "  'all',\n",
       "  'the',\n",
       "  'movie',\n",
       "  \"'s\",\n",
       "  'political',\n",
       "  'ramifications',\n",
       "  '.'],\n",
       " ['it',\n",
       "  \"'s\",\n",
       "  'like',\n",
       "  'going',\n",
       "  'to',\n",
       "  'a',\n",
       "  'house',\n",
       "  'party',\n",
       "  'and',\n",
       "  'watching',\n",
       "  'the',\n",
       "  'host',\n",
       "  'defend',\n",
       "  'himself',\n",
       "  'against',\n",
       "  'a',\n",
       "  'frothing',\n",
       "  'ex-girlfriend',\n",
       "  '.'],\n",
       " ['that',\n",
       "  'the',\n",
       "  'chuck',\n",
       "  'norris',\n",
       "  '``',\n",
       "  'grenade',\n",
       "  'gag',\n",
       "  \"''\",\n",
       "  'occurs',\n",
       "  'about',\n",
       "  '7',\n",
       "  'times',\n",
       "  'during',\n",
       "  'windtalkers',\n",
       "  'is',\n",
       "  'a',\n",
       "  'good',\n",
       "  'indication',\n",
       "  'of',\n",
       "  'how',\n",
       "  'serious-minded',\n",
       "  'the',\n",
       "  'film',\n",
       "  'is',\n",
       "  '.'],\n",
       " ['the',\n",
       "  'plot',\n",
       "  'is',\n",
       "  'romantic',\n",
       "  'comedy',\n",
       "  'boilerplate',\n",
       "  'from',\n",
       "  'start',\n",
       "  'to',\n",
       "  'finish',\n",
       "  '.'],\n",
       " ['it',\n",
       "  'arrives',\n",
       "  'with',\n",
       "  'an',\n",
       "  'impeccable',\n",
       "  'pedigree',\n",
       "  ',',\n",
       "  'mongrel',\n",
       "  'pep',\n",
       "  ',',\n",
       "  'and',\n",
       "  'almost',\n",
       "  'indecipherable',\n",
       "  'plot',\n",
       "  'complications',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'film',\n",
       "  'that',\n",
       "  'clearly',\n",
       "  'means',\n",
       "  'to',\n",
       "  'preach',\n",
       "  'exclusively',\n",
       "  'to',\n",
       "  'the',\n",
       "  'converted',\n",
       "  '.'],\n",
       " ['i',\n",
       "  'still',\n",
       "  'like',\n",
       "  'moonlight',\n",
       "  'mile',\n",
       "  ',',\n",
       "  'better',\n",
       "  'judgment',\n",
       "  'be',\n",
       "  'damned',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'welcome',\n",
       "  'relief',\n",
       "  'from',\n",
       "  'baseball',\n",
       "  'movies',\n",
       "  'that',\n",
       "  'try',\n",
       "  'too',\n",
       "  'hard',\n",
       "  'to',\n",
       "  'be',\n",
       "  'mythic',\n",
       "  ',',\n",
       "  'this',\n",
       "  'one',\n",
       "  'is',\n",
       "  'a',\n",
       "  'sweet',\n",
       "  'and',\n",
       "  'modest',\n",
       "  'and',\n",
       "  'ultimately',\n",
       "  'winning',\n",
       "  'story',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'bilingual',\n",
       "  'charmer',\n",
       "  ',',\n",
       "  'just',\n",
       "  'like',\n",
       "  'the',\n",
       "  'woman',\n",
       "  'who',\n",
       "  'inspired',\n",
       "  'it'],\n",
       " ['like',\n",
       "  'a',\n",
       "  'less',\n",
       "  'dizzily',\n",
       "  'gorgeous',\n",
       "  'companion',\n",
       "  'to',\n",
       "  'mr.',\n",
       "  'wong',\n",
       "  \"'s\",\n",
       "  'in',\n",
       "  'the',\n",
       "  'mood',\n",
       "  'for',\n",
       "  'love',\n",
       "  '--',\n",
       "  'very',\n",
       "  'much',\n",
       "  'a',\n",
       "  'hong',\n",
       "  'kong',\n",
       "  'movie',\n",
       "  'despite',\n",
       "  'its',\n",
       "  'mainland',\n",
       "  'setting',\n",
       "  '.'],\n",
       " ['as',\n",
       "  'inept',\n",
       "  'as',\n",
       "  'big-screen',\n",
       "  'remakes',\n",
       "  'of',\n",
       "  'the',\n",
       "  'avengers',\n",
       "  'and',\n",
       "  'the',\n",
       "  'wild',\n",
       "  'wild',\n",
       "  'west',\n",
       "  '.'],\n",
       " ['it',\n",
       "  \"'s\",\n",
       "  'everything',\n",
       "  'you',\n",
       "  \"'d\",\n",
       "  'expect',\n",
       "  '--',\n",
       "  'but',\n",
       "  'nothing',\n",
       "  'more',\n",
       "  '.'],\n",
       " ['best', 'indie', 'of', 'the', 'year', ',', 'so', 'far', '.'],\n",
       " ['hatfield',\n",
       "  'and',\n",
       "  'hicks',\n",
       "  'make',\n",
       "  'the',\n",
       "  'oddest',\n",
       "  'of',\n",
       "  'couples',\n",
       "  ',',\n",
       "  'and',\n",
       "  'in',\n",
       "  'this',\n",
       "  'sense',\n",
       "  'the',\n",
       "  'movie',\n",
       "  'becomes',\n",
       "  'a',\n",
       "  'study',\n",
       "  'of',\n",
       "  'the',\n",
       "  'gambles',\n",
       "  'of',\n",
       "  'the',\n",
       "  'publishing',\n",
       "  'world',\n",
       "  ',',\n",
       "  'offering',\n",
       "  'a',\n",
       "  'case',\n",
       "  'study',\n",
       "  'that',\n",
       "  'exists',\n",
       "  'apart',\n",
       "  'from',\n",
       "  'all',\n",
       "  'the',\n",
       "  'movie',\n",
       "  \"'s\",\n",
       "  'political',\n",
       "  'ramifications',\n",
       "  '.'],\n",
       " ['it',\n",
       "  \"'s\",\n",
       "  'like',\n",
       "  'going',\n",
       "  'to',\n",
       "  'a',\n",
       "  'house',\n",
       "  'party',\n",
       "  'and',\n",
       "  'watching',\n",
       "  'the',\n",
       "  'host',\n",
       "  'defend',\n",
       "  'himself',\n",
       "  'against',\n",
       "  'a',\n",
       "  'frothing',\n",
       "  'ex-girlfriend',\n",
       "  '.'],\n",
       " ['that',\n",
       "  'the',\n",
       "  'chuck',\n",
       "  'norris',\n",
       "  '``',\n",
       "  'grenade',\n",
       "  'gag',\n",
       "  \"''\",\n",
       "  'occurs',\n",
       "  'about',\n",
       "  '7',\n",
       "  'times',\n",
       "  'during',\n",
       "  'windtalkers',\n",
       "  'is',\n",
       "  'a',\n",
       "  'good',\n",
       "  'indication',\n",
       "  'of',\n",
       "  'how',\n",
       "  'serious-minded',\n",
       "  'the',\n",
       "  'film',\n",
       "  'is',\n",
       "  '.'],\n",
       " ['the',\n",
       "  'plot',\n",
       "  'is',\n",
       "  'romantic',\n",
       "  'comedy',\n",
       "  'boilerplate',\n",
       "  'from',\n",
       "  'start',\n",
       "  'to',\n",
       "  'finish',\n",
       "  '.'],\n",
       " ['it',\n",
       "  'arrives',\n",
       "  'with',\n",
       "  'an',\n",
       "  'impeccable',\n",
       "  'pedigree',\n",
       "  ',',\n",
       "  'mongrel',\n",
       "  'pep',\n",
       "  ',',\n",
       "  'and',\n",
       "  'almost',\n",
       "  'indecipherable',\n",
       "  'plot',\n",
       "  'complications',\n",
       "  '.'],\n",
       " ['a',\n",
       "  'film',\n",
       "  'that',\n",
       "  'clearly',\n",
       "  'means',\n",
       "  'to',\n",
       "  'preach',\n",
       "  'exclusively',\n",
       "  'to',\n",
       "  'the',\n",
       "  'converted',\n",
       "  '.']]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 将所有数字转为小写\n",
    "ds.apply(lambda x: x['raw_sentence'].lower(), new_field_name='raw_sentence')\n",
    "# label转int\n",
    "ds.apply(lambda x: int(x['label']), new_field_name='label_seq', is_target=True)\n",
    "\n",
    "def split_sent(ins):\n",
    "    return ins['raw_sentence'].split()\n",
    "ds.apply(split_sent, new_field_name='words', is_input=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train size:  54\n",
      "Test size:  23\n"
     ]
    }
   ],
   "source": [
    "# 分割训练集/验证集\n",
    "train_data, dev_data = ds.split(0.3)\n",
    "print(\"Train size: \", len(train_data))\n",
    "print(\"Test size: \", len(dev_data))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[[120, 121, 6, 2, 122, 5, 72, 123, 3],\n",
       " [14,\n",
       "  4,\n",
       "  152,\n",
       "  153,\n",
       "  154,\n",
       "  155,\n",
       "  8,\n",
       "  156,\n",
       "  157,\n",
       "  9,\n",
       "  16,\n",
       "  2,\n",
       "  158,\n",
       "  21,\n",
       "  159,\n",
       "  30,\n",
       "  98,\n",
       "  57,\n",
       "  4,\n",
       "  160,\n",
       "  161,\n",
       "  13,\n",
       "  162,\n",
       "  163,\n",
       "  164,\n",
       "  165,\n",
       "  3],\n",
       " [4,\n",
       "  112,\n",
       "  113,\n",
       "  15,\n",
       "  114,\n",
       "  35,\n",
       "  10,\n",
       "  68,\n",
       "  115,\n",
       "  69,\n",
       "  8,\n",
       "  23,\n",
       "  116,\n",
       "  5,\n",
       "  18,\n",
       "  36,\n",
       "  11,\n",
       "  4,\n",
       "  70,\n",
       "  7,\n",
       "  117,\n",
       "  7,\n",
       "  118,\n",
       "  119,\n",
       "  71,\n",
       "  3],\n",
       " [4, 1, 1, 5, 138, 14, 2, 1, 1, 1, 12],\n",
       " [2, 27, 11, 139, 140, 141, 15, 142, 8, 143, 3],\n",
       " [12, 9, 14, 32, 8, 4, 59, 60, 7, 61, 2, 62, 63, 64, 65, 4, 66, 67, 3],\n",
       " [97, 145, 14, 146, 147, 5, 148, 149, 23, 150, 3],\n",
       " [4, 1, 1, 5, 138, 14, 2, 1, 1, 1, 12],\n",
       " [4, 1, 1, 5, 138, 14, 2, 1, 1, 1, 12],\n",
       " [14,\n",
       "  4,\n",
       "  152,\n",
       "  153,\n",
       "  154,\n",
       "  155,\n",
       "  8,\n",
       "  156,\n",
       "  157,\n",
       "  9,\n",
       "  16,\n",
       "  2,\n",
       "  158,\n",
       "  21,\n",
       "  159,\n",
       "  30,\n",
       "  98,\n",
       "  57,\n",
       "  4,\n",
       "  160,\n",
       "  161,\n",
       "  13,\n",
       "  162,\n",
       "  163,\n",
       "  164,\n",
       "  165,\n",
       "  3],\n",
       " [10,\n",
       "  2,\n",
       "  82,\n",
       "  83,\n",
       "  84,\n",
       "  85,\n",
       "  86,\n",
       "  87,\n",
       "  88,\n",
       "  89,\n",
       "  90,\n",
       "  91,\n",
       "  92,\n",
       "  93,\n",
       "  11,\n",
       "  4,\n",
       "  28,\n",
       "  94,\n",
       "  6,\n",
       "  95,\n",
       "  96,\n",
       "  2,\n",
       "  17,\n",
       "  11,\n",
       "  3],\n",
       " [12, 73, 20, 33, 74, 75, 5, 76, 77, 5, 7, 78, 79, 27, 80, 3],\n",
       " [12, 78, 1, 24, 1, 2, 13, 11, 31, 1, 16, 1, 1, 133, 16, 1, 1, 3],\n",
       " [24, 107, 24, 108, 109, 6, 2, 110, 7, 2, 34, 34, 111, 3],\n",
       " [2, 27, 11, 139, 140, 141, 15, 142, 8, 143, 3],\n",
       " [24, 107, 24, 108, 109, 6, 2, 110, 7, 2, 34, 34, 111, 3],\n",
       " [97, 145, 14, 146, 147, 5, 148, 149, 23, 150, 3],\n",
       " [4,\n",
       "  112,\n",
       "  113,\n",
       "  15,\n",
       "  114,\n",
       "  35,\n",
       "  10,\n",
       "  68,\n",
       "  115,\n",
       "  69,\n",
       "  8,\n",
       "  23,\n",
       "  116,\n",
       "  5,\n",
       "  18,\n",
       "  36,\n",
       "  11,\n",
       "  4,\n",
       "  70,\n",
       "  7,\n",
       "  117,\n",
       "  7,\n",
       "  118,\n",
       "  119,\n",
       "  71,\n",
       "  3],\n",
       " [12, 9, 99, 29, 100, 101, 30, 22, 58, 31, 3],\n",
       " [12, 9, 99, 29, 100, 101, 30, 22, 58, 31, 3],\n",
       " [120, 121, 6, 2, 122, 5, 72, 123, 3],\n",
       " [1, 30, 1, 5, 1, 30, 1, 4, 1, 1, 1, 10, 1, 21, 1, 7, 1, 1, 1, 14, 1, 3],\n",
       " [1,\n",
       "  1,\n",
       "  1,\n",
       "  1,\n",
       "  8,\n",
       "  1,\n",
       "  89,\n",
       "  2,\n",
       "  1,\n",
       "  16,\n",
       "  151,\n",
       "  1,\n",
       "  1,\n",
       "  1,\n",
       "  1,\n",
       "  1,\n",
       "  1,\n",
       "  7,\n",
       "  1,\n",
       "  1,\n",
       "  1,\n",
       "  2,\n",
       "  1,\n",
       "  6,\n",
       "  28,\n",
       "  25,\n",
       "  3]]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from fastNLP import Vocabulary\n",
    "vocab = Vocabulary(min_freq=2)\n",
    "train_data.apply(lambda x: [vocab.add(word) for word in x['words']])\n",
    "\n",
    "# index句子, Vocabulary.to_index(word)\n",
    "train_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True)\n",
    "dev_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## step 3\n",
    " 定义模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastNLP.models import CNNText\n",
    "model = CNNText((len(vocab),50), num_classes=5, padding=2, dropout=0.1)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## step 4\n",
    "开始训练"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "input fields after batch(if batch size is 2):\n",
      "\twords: (1)type:numpy.ndarray (2)dtype:object, (3)shape:(2,) \n",
      "\tword_seq: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 11]) \n",
      "target fields after batch(if batch size is 2):\n",
      "\tlabel_seq: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2]) \n",
      "\n"
     ]
    },
    {
     "ename": "AttributeError",
     "evalue": "'numpy.ndarray' object has no attribute 'contiguous'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-7-4b34d005949c>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      4\u001b[0m                   \u001b[0mdev_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdev_data\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m                   \u001b[0mloss\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mCrossEntropyLoss\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m                   \u001b[0mmetrics\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mAccuracyMetric\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      7\u001b[0m                   )\n\u001b[1;32m      8\u001b[0m \u001b[0mtrainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/fdujyn/anaconda3/lib/python3.6/site-packages/fastNLP/core/trainer.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, train_data, model, optimizer, loss, batch_size, sampler, update_every, n_epochs, print_every, dev_data, metrics, metric_key, validate_every, save_path, prefetch, use_tqdm, device, callbacks, check_code_level)\u001b[0m\n\u001b[1;32m    447\u001b[0m             _check_code(dataset=train_data, model=model, losser=losser, metrics=metrics, dev_data=dev_data,\n\u001b[1;32m    448\u001b[0m                         \u001b[0mmetric_key\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmetric_key\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcheck_level\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcheck_code_level\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 449\u001b[0;31m                         batch_size=min(batch_size, DEFAULT_CHECK_BATCH_SIZE))\n\u001b[0m\u001b[1;32m    450\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    451\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/fdujyn/anaconda3/lib/python3.6/site-packages/fastNLP/core/trainer.py\u001b[0m in \u001b[0;36m_check_code\u001b[0;34m(dataset, model, losser, metrics, batch_size, dev_data, metric_key, check_level)\u001b[0m\n\u001b[1;32m    811\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    812\u001b[0m         \u001b[0mrefined_batch_x\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_build_args\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mbatch_x\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 813\u001b[0;31m         \u001b[0mpred_dict\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mrefined_batch_x\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    814\u001b[0m         \u001b[0mfunc_signature\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_get_func_signature\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    815\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpred_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdict\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/fdujyn/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m    489\u001b[0m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_slow_forward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    490\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 491\u001b[0;31m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    492\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0mhook\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_forward_hooks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    493\u001b[0m             \u001b[0mhook_result\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mhook\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/fdujyn/anaconda3/lib/python3.6/site-packages/fastNLP/models/cnn_text_classification.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, words, seq_len)\u001b[0m\n\u001b[1;32m     58\u001b[0m         \u001b[0;34m:\u001b[0m\u001b[0;32mreturn\u001b[0m \u001b[0moutput\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mdict\u001b[0m \u001b[0mof\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mLongTensor\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mbatch_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnum_classes\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     59\u001b[0m         \"\"\"\n\u001b[0;32m---> 60\u001b[0;31m         \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0membed\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mwords\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# [N,L] -> [N,L,C]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     61\u001b[0m         \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconv_pool\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# [N,L,C] -> [N,C]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     62\u001b[0m         \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdropout\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/fdujyn/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m    489\u001b[0m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_slow_forward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    490\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 491\u001b[0;31m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    492\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0mhook\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_forward_hooks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    493\u001b[0m             \u001b[0mhook_result\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mhook\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/fdujyn/anaconda3/lib/python3.6/site-packages/fastNLP/modules/encoder/embedding.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m     33\u001b[0m         \u001b[0;34m:\u001b[0m\u001b[0;32mreturn\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTensor\u001b[0m \u001b[0;34m:\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mseq_len\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0membed_dim\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     34\u001b[0m         \"\"\"\n\u001b[0;32m---> 35\u001b[0;31m         \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     36\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdropout\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/fdujyn/anaconda3/lib/python3.6/site-packages/torch/nn/modules/sparse.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    106\u001b[0m         return F.embedding(\n\u001b[1;32m    107\u001b[0m             \u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mweight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpadding_idx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmax_norm\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 108\u001b[0;31m             self.norm_type, self.scale_grad_by_freq, self.sparse)\n\u001b[0m\u001b[1;32m    109\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    110\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mextra_repr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/fdujyn/anaconda3/lib/python3.6/site-packages/torch/nn/functional.py\u001b[0m in \u001b[0;36membedding\u001b[0;34m(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)\u001b[0m\n\u001b[1;32m   1062\u001b[0m                  [ 0.6262,  0.2438,  0.7471]]])\n\u001b[1;32m   1063\u001b[0m     \"\"\"\n\u001b[0;32m-> 1064\u001b[0;31m     \u001b[0minput\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontiguous\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1065\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mpadding_idx\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1066\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mpadding_idx\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mAttributeError\u001b[0m: 'numpy.ndarray' object has no attribute 'contiguous'"
     ]
    }
   ],
   "source": [
    "from fastNLP import Trainer, CrossEntropyLoss, AccuracyMetric\n",
    "trainer = Trainer(model=model, \n",
    "                  train_data=train_data, \n",
    "                  dev_data=dev_data,\n",
    "                  loss=CrossEntropyLoss(),\n",
    "                  metrics=AccuracyMetric()\n",
    "                  )\n",
    "trainer.train()\n",
    "print('Train finished!')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 本教程结束。更多操作请参考进阶教程。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}