hummingbird
/
fastNLP

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "# 快速入门"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'raw_sentence': A series of escapades demonstrating the adage that what is good for the goose is also good for the gander , some of which occasionally amuses but none of which amounts to much of a story . type=str,\n",
       "'label': 1 type=str}"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from fastNLP.io import CSVLoader\n",
    "\n",
    "loader = CSVLoader(headers=('raw_sentence', 'label'), sep='\\t')\n",
    "dataset = loader.load(\"./sample_data/tutorial_sample_dataset.csv\")\n",
    "dataset[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'raw_sentence': A series of escapades demonstrating the adage that what is good for the goose is also good for the gander , some of which occasionally amuses but none of which amounts to much of a story . type=str,\n",
       "'label': 1 type=str,\n",
       "'sentence': a series of escapades demonstrating the adage that what is good for the goose is also good for the gander , some of which occasionally amuses but none of which amounts to much of a story . type=str,\n",
       "'words': ['a', 'series', 'of', 'escapades', 'demonstrating', 'the', 'adage', 'that', 'what', 'is', 'good', 'for', 'the', 'goose', 'is', 'also', 'good', 'for', 'the', 'gander', ',', 'some', 'of', 'which', 'occasionally', 'amuses', 'but', 'none', 'of', 'which', 'amounts', 'to', 'much', 'of', 'a', 'story', '.'] type=list}"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 将所有字母转为小写, 并所有句子变成单词序列\n",
    "dataset.apply(lambda x: x['raw_sentence'].lower(), new_field_name='sentence')\n",
    "dataset.apply(lambda x: x['sentence'].split(), new_field_name='words', is_input=True)\n",
    "dataset[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'raw_sentence': A series of escapades demonstrating the adage that what is good for the goose is also good for the gander , some of which occasionally amuses but none of which amounts to much of a story . type=str,\n",
       "'label': 1 type=str,\n",
       "'sentence': a series of escapades demonstrating the adage that what is good for the goose is also good for the gander , some of which occasionally amuses but none of which amounts to much of a story . type=str,\n",
       "'words': [4, 1, 6, 1, 1, 2, 1, 11, 153, 10, 28, 17, 2, 1, 10, 1, 28, 17, 2, 1, 5, 154, 6, 149, 1, 1, 23, 1, 6, 149, 1, 8, 30, 6, 4, 35, 3] type=list}"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from fastNLP import Vocabulary\n",
    "\n",
    "# 使用Vocabulary类统计单词，并将单词序列转化为数字序列\n",
    "vocab = Vocabulary(min_freq=2).from_dataset(dataset, field_name='words')\n",
    "vocab.index_dataset(dataset, field_name='words',new_field_name='words')\n",
    "dataset[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'raw_sentence': A series of escapades demonstrating the adage that what is good for the goose is also good for the gander , some of which occasionally amuses but none of which amounts to much of a story . type=str,\n",
       "'label': 1 type=str,\n",
       "'sentence': a series of escapades demonstrating the adage that what is good for the goose is also good for the gander , some of which occasionally amuses but none of which amounts to much of a story . type=str,\n",
       "'words': [4, 1, 6, 1, 1, 2, 1, 11, 153, 10, 28, 17, 2, 1, 10, 1, 28, 17, 2, 1, 5, 154, 6, 149, 1, 1, 23, 1, 6, 149, 1, 8, 30, 6, 4, 35, 3] type=list,\n",
       "'target': 1 type=int}"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 将label转为整数，并设置为 target\n",
    "dataset.apply(lambda x: int(x['label']), new_field_name='target', is_target=True)\n",
    "dataset[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "CNNText(\n",
       "  (embed): Embedding(\n",
       "    177, 50\n",
       "    (dropout): Dropout(p=0.0)\n",
       "  )\n",
       "  (conv_pool): ConvMaxpool(\n",
       "    (convs): ModuleList(\n",
       "      (0): Conv1d(50, 3, kernel_size=(3,), stride=(1,), padding=(2,))\n",
       "      (1): Conv1d(50, 4, kernel_size=(4,), stride=(1,), padding=(2,))\n",
       "      (2): Conv1d(50, 5, kernel_size=(5,), stride=(1,), padding=(2,))\n",
       "    )\n",
       "  )\n",
       "  (dropout): Dropout(p=0.1)\n",
       "  (fc): Linear(in_features=12, out_features=5, bias=True)\n",
       ")"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from fastNLP.models import CNNText\n",
    "model = CNNText((len(vocab),50), num_classes=5, padding=2, dropout=0.1)\n",
    "model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(62, 15)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 分割训练集/验证集\n",
    "train_data, dev_data = dataset.split(0.2)\n",
    "len(train_data), len(dev_data)"
   ]
  },
  {
   "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:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 26]) \n",
      "target fields after batch(if batch size is 2):\n",
      "\ttarget: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2]) \n",
      "\n",
      "training epochs started 2019-05-09-10-59-39\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=20), HTML(value='')), layout=Layout(display='…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Evaluation at Epoch 1/10. Step:2/20. AccuracyMetric: acc=0.333333\n",
      "\n",
      "Evaluation at Epoch 2/10. Step:4/20. AccuracyMetric: acc=0.533333\n",
      "\n",
      "Evaluation at Epoch 3/10. Step:6/20. AccuracyMetric: acc=0.533333\n",
      "\n",
      "Evaluation at Epoch 4/10. Step:8/20. AccuracyMetric: acc=0.533333\n",
      "\n",
      "Evaluation at Epoch 5/10. Step:10/20. AccuracyMetric: acc=0.6\n",
      "\n",
      "Evaluation at Epoch 6/10. Step:12/20. AccuracyMetric: acc=0.8\n",
      "\n",
      "Evaluation at Epoch 7/10. Step:14/20. AccuracyMetric: acc=0.8\n",
      "\n",
      "Evaluation at Epoch 8/10. Step:16/20. AccuracyMetric: acc=0.733333\n",
      "\n",
      "Evaluation at Epoch 9/10. Step:18/20. AccuracyMetric: acc=0.733333\n",
      "\n",
      "Evaluation at Epoch 10/10. Step:20/20. AccuracyMetric: acc=0.733333\n",
      "\n",
      "\n",
      "In Epoch:6/Step:12, got best dev performance:AccuracyMetric: acc=0.8\n",
      "Reloaded the best model.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'best_eval': {'AccuracyMetric': {'acc': 0.8}},\n",
       " 'best_epoch': 6,\n",
       " 'best_step': 12,\n",
       " 'seconds': 0.22}"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from fastNLP import Trainer, CrossEntropyLoss, AccuracyMetric\n",
    "\n",
    "# 定义trainer并进行训练\n",
    "trainer = Trainer(model=model, train_data=train_data, dev_data=dev_data,\n",
    "                  loss=CrossEntropyLoss(), metrics=AccuracyMetric())\n",
    "trainer.train()"
   ]
  }
 ],
 "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
}