{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "# 详细指南"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 数据读入"
   ]
  },
  {
   "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": "markdown",
   "metadata": {},
   "source": [
    "Instance表示一个样本，由一个或多个field（域，属性，特征）组成，每个field有名字和值。\n",
    "\n",
    "在初始化Instance时即可定义它包含的域，使用 \"field_name=field_value\"的写法。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'raw_sentence': fake data type=str,\n",
       "'label': 0 type=str}"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from fastNLP import Instance\n",
    "\n",
    "dataset.append(Instance(raw_sentence='fake data', label='0'))\n",
    "dataset[-1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 数据处理"
   ]
  },
  {
   "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,\n",
       "'target': 1 type=int}"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from fastNLP import Vocabulary\n",
    "\n",
    "# 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_field(lambda x: x.split(), field_name='sentence', new_field_name='words')\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",
    "\n",
    "# 将label转为整数\n",
    "dataset.apply(lambda x: int(x['label']), new_field_name='target')\n",
    "dataset[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'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,\n",
      "'seq_len': 37 type=int}\n"
     ]
    }
   ],
   "source": [
    "# 增加长度信息\n",
    "dataset.apply_field(lambda x: len(x), field_name='words', new_field_name='seq_len')\n",
    "print(dataset[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 使用内置模块CNNText\n",
    "设置为符合内置模块的名称"
   ]
  },
  {
   "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",
    "\n",
    "model_cnn = CNNText((len(vocab),50), num_classes=5, padding=2, dropout=0.1)\n",
    "model_cnn"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "我们在使用内置模块的时候，还应该使用应该注意把 field 设定成符合内置模型输入输出的名字。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "words\n",
      "seq_len\n",
      "target\n"
     ]
    }
   ],
   "source": [
    "from fastNLP import Const\n",
    "\n",
    "dataset.rename_field('words', Const.INPUT)\n",
    "dataset.rename_field('seq_len', Const.INPUT_LEN)\n",
    "dataset.rename_field('target', Const.TARGET)\n",
    "\n",
    "dataset.set_input(Const.INPUT, Const.INPUT_LEN)\n",
    "dataset.set_target(Const.TARGET)\n",
    "\n",
    "print(Const.INPUT)\n",
    "print(Const.INPUT_LEN)\n",
    "print(Const.TARGET)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 分割训练集/验证集/测试集"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(64, 7, 7)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_dev_data, test_data = dataset.split(0.1)\n",
    "train_data, dev_data = train_dev_data.split(0.1)\n",
    "len(train_data), len(dev_data), len(test_data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 训练(model_cnn)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### loss\n",
    "训练模型需要提供一个损失函数\n",
    "\n",
    "下面提供了一个在分类问题中常用的交叉熵损失。注意它的**初始化参数**。\n",
    "\n",
    "pred参数对应的是模型的forward返回的dict的一个key的名字，这里是\"output\"。\n",
    "\n",
    "target参数对应的是dataset作为标签的field的名字，这里是\"label_seq\"。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastNLP import CrossEntropyLoss\n",
    "\n",
    "# loss = CrossEntropyLoss()\n",
    "# 等价于\n",
    "loss = CrossEntropyLoss(pred=Const.OUTPUT, target=Const.TARGET)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Metric\n",
    "定义评价指标\n",
    "\n",
    "这里使用准确率。参数的“命名规则”跟上面类似。\n",
    "\n",
    "pred参数对应的是模型的predict方法返回的dict的一个key的名字，这里是\"predict\"。\n",
    "\n",
    "target参数对应的是dataset作为标签的field的名字，这里是\"label_seq\"。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastNLP import AccuracyMetric\n",
    "\n",
    "# metrics=AccuracyMetric()\n",
    "# 等价于\n",
    "metrics=AccuracyMetric(pred=Const.OUTPUT, target=Const.TARGET)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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, 16]) \n",
      "\tseq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2]) \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 2019-05-12-21-38-34\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=0.285714\n",
      "\n",
      "Evaluation at Epoch 2/10. Step:4/20. AccuracyMetric: acc=0.428571\n",
      "\n",
      "Evaluation at Epoch 3/10. Step:6/20. AccuracyMetric: acc=0.428571\n",
      "\n",
      "Evaluation at Epoch 4/10. Step:8/20. AccuracyMetric: acc=0.428571\n",
      "\n",
      "Evaluation at Epoch 5/10. Step:10/20. AccuracyMetric: acc=0.428571\n",
      "\n",
      "Evaluation at Epoch 6/10. Step:12/20. AccuracyMetric: acc=0.428571\n",
      "\n",
      "Evaluation at Epoch 7/10. Step:14/20. AccuracyMetric: acc=0.428571\n",
      "\n",
      "Evaluation at Epoch 8/10. Step:16/20. AccuracyMetric: acc=0.857143\n",
      "\n",
      "Evaluation at Epoch 9/10. Step:18/20. AccuracyMetric: acc=0.857143\n",
      "\n",
      "Evaluation at Epoch 10/10. Step:20/20. AccuracyMetric: acc=0.857143\n",
      "\n",
      "\n",
      "In Epoch:8/Step:16, got best dev performance:AccuracyMetric: acc=0.857143\n",
      "Reloaded the best model.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'best_eval': {'AccuracyMetric': {'acc': 0.857143}},\n",
       " 'best_epoch': 8,\n",
       " 'best_step': 16,\n",
       " 'seconds': 0.21}"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from fastNLP import Trainer\n",
    "\n",
    "trainer = Trainer(model=model_cnn, train_data=train_data, dev_data=dev_data, loss=loss, metrics=metrics)\n",
    "trainer.train()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 测试(model_cnn)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[tester] \n",
      "AccuracyMetric: acc=0.857143\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'AccuracyMetric': {'acc': 0.857143}}"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from fastNLP import Tester\n",
    "\n",
    "tester = Tester(test_data, model_cnn, metrics=AccuracyMetric())\n",
    "tester.test()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 编写自己的模型\n",
    "\n",
    "完全支持 pytorch 的模型，与 pytorch 唯一不同的是返回结果是一个字典，字典中至少需要包含 \"pred\" 这个字段"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import torch.nn as nn\n",
    "\n",
    "class LSTMText(nn.Module):\n",
    "    def __init__(self, vocab_size, embedding_dim, output_dim, hidden_dim=64, num_layers=2, dropout=0.5):\n",
    "        super().__init__()\n",
    "\n",
    "        self.embedding = nn.Embedding(vocab_size, embedding_dim)\n",
    "        self.lstm = nn.LSTM(embedding_dim, hidden_dim, num_layers=num_layers, bidirectional=True, dropout=dropout)\n",
    "        self.fc = nn.Linear(hidden_dim * 2, output_dim)\n",
    "        self.dropout = nn.Dropout(dropout)\n",
    "\n",
    "    def forward(self, words):\n",
    "        # (input) words : (batch_size, seq_len)\n",
    "        words = words.permute(1,0)\n",
    "        # words : (seq_len, batch_size)\n",
    "\n",
    "        embedded = self.dropout(self.embedding(words))\n",
    "        # embedded : (seq_len, batch_size, embedding_dim)\n",
    "        output, (hidden, cell) = self.lstm(embedded)\n",
    "        # output: (seq_len, batch_size, hidden_dim * 2)\n",
    "        # hidden: (num_layers * 2, batch_size, hidden_dim)\n",
    "        # cell: (num_layers * 2, batch_size, hidden_dim)\n",
    "\n",
    "        hidden = torch.cat((hidden[-2, :, :], hidden[-1, :, :]), dim=1)\n",
    "        hidden = self.dropout(hidden)\n",
    "        # hidden: (batch_size, hidden_dim * 2)\n",
    "\n",
    "        pred = self.fc(hidden.squeeze(0))\n",
    "        # result: (batch_size, output_dim)\n",
    "        return {\"pred\":pred}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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, 16]) \n",
      "\tseq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2]) \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 2019-05-12-21-38-36\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=0.571429\n",
      "\n",
      "Evaluation at Epoch 2/10. Step:4/20. AccuracyMetric: acc=0.571429\n",
      "\n",
      "Evaluation at Epoch 3/10. Step:6/20. AccuracyMetric: acc=0.571429\n",
      "\n",
      "Evaluation at Epoch 4/10. Step:8/20. AccuracyMetric: acc=0.571429\n",
      "\n",
      "Evaluation at Epoch 5/10. Step:10/20. AccuracyMetric: acc=0.714286\n",
      "\n",
      "Evaluation at Epoch 6/10. Step:12/20. AccuracyMetric: acc=0.857143\n",
      "\n",
      "Evaluation at Epoch 7/10. Step:14/20. AccuracyMetric: acc=0.857143\n",
      "\n",
      "Evaluation at Epoch 8/10. Step:16/20. AccuracyMetric: acc=0.857143\n",
      "\n",
      "Evaluation at Epoch 9/10. Step:18/20. AccuracyMetric: acc=0.857143\n",
      "\n",
      "Evaluation at Epoch 10/10. Step:20/20. AccuracyMetric: acc=0.857143\n",
      "\n",
      "\n",
      "In Epoch:6/Step:12, got best dev performance:AccuracyMetric: acc=0.857143\n",
      "Reloaded the best model.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'best_eval': {'AccuracyMetric': {'acc': 0.857143}},\n",
       " 'best_epoch': 6,\n",
       " 'best_step': 12,\n",
       " 'seconds': 2.15}"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_lstm = LSTMText(len(vocab),50,5)\n",
    "trainer = Trainer(model=model_lstm, train_data=train_data, dev_data=dev_data, loss=loss, metrics=metrics)\n",
    "trainer.train()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[tester] \n",
      "AccuracyMetric: acc=0.857143\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'AccuracyMetric': {'acc': 0.857143}}"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tester = Tester(test_data, model_lstm, metrics=AccuracyMetric())\n",
    "tester.test()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 使用 Batch编写自己的训练过程"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 0 Avg Loss: 3.11 18ms\n",
      "Epoch 1 Avg Loss: 2.88 30ms\n",
      "Epoch 2 Avg Loss: 2.69 42ms\n",
      "Epoch 3 Avg Loss: 2.47 54ms\n",
      "Epoch 4 Avg Loss: 2.38 67ms\n",
      "Epoch 5 Avg Loss: 2.10 78ms\n",
      "Epoch 6 Avg Loss: 2.06 91ms\n",
      "Epoch 7 Avg Loss: 1.92 103ms\n",
      "Epoch 8 Avg Loss: 1.91 114ms\n",
      "Epoch 9 Avg Loss: 1.76 126ms\n",
      "[tester] \n",
      "AccuracyMetric: acc=0.571429\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'AccuracyMetric': {'acc': 0.571429}}"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from fastNLP import BucketSampler\n",
    "from fastNLP import Batch\n",
    "import torch\n",
    "import time\n",
    "\n",
    "model = CNNText((len(vocab),50), num_classes=5, padding=2, dropout=0.1)\n",
    "\n",
    "def train(epoch, data):\n",
    "    optim = torch.optim.Adam(model.parameters(), lr=0.001)\n",
    "    lossfunc = torch.nn.CrossEntropyLoss()\n",
    "    batch_size = 32\n",
    "\n",
    "    # 定义一个Batch，传入DataSet，规定batch_size和去batch的规则。\n",
    "    # 顺序（Sequential），随机（Random），相似长度组成一个batch（Bucket）\n",
    "    train_sampler = BucketSampler(batch_size=batch_size, seq_len_field_name='seq_len')\n",
    "    train_batch = Batch(batch_size=batch_size, dataset=data, sampler=train_sampler)\n",
    "    \n",
    "    start_time = time.time()\n",
    "    for i in range(epoch):\n",
    "        loss_list = []\n",
    "        for batch_x, batch_y in train_batch:\n",
    "            optim.zero_grad()\n",
    "            output = model(batch_x['words'])\n",
    "            loss = lossfunc(output['pred'], batch_y['target'])\n",
    "            loss.backward()\n",
    "            optim.step()\n",
    "            loss_list.append(loss.item())\n",
    "        print('Epoch {:d} Avg Loss: {:.2f}'.format(i, sum(loss_list) / len(loss_list)),end=\" \")\n",
    "        print('{:d}ms'.format(round((time.time()-start_time)*1000)))\n",
    "        loss_list.clear()\n",
    "            \n",
    "train(10, train_data)\n",
    "tester = Tester(test_data, model, metrics=AccuracyMetric())\n",
    "tester.test()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 使用 Callback 实现自己想要的效果"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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, 16]) \n",
      "\tseq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2]) \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 2019-05-12-21-38-40\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=0.285714\n",
      "\n",
      "Sum Time: 51ms\n",
      "\n",
      "\n",
      "Evaluation at Epoch 2/10. Step:4/20. AccuracyMetric: acc=0.285714\n",
      "\n",
      "Sum Time: 69ms\n",
      "\n",
      "\n",
      "Evaluation at Epoch 3/10. Step:6/20. AccuracyMetric: acc=0.285714\n",
      "\n",
      "Sum Time: 91ms\n",
      "\n",
      "\n",
      "Evaluation at Epoch 4/10. Step:8/20. AccuracyMetric: acc=0.571429\n",
      "\n",
      "Sum Time: 107ms\n",
      "\n",
      "\n",
      "Evaluation at Epoch 5/10. Step:10/20. AccuracyMetric: acc=0.571429\n",
      "\n",
      "Sum Time: 125ms\n",
      "\n",
      "\n",
      "Evaluation at Epoch 6/10. Step:12/20. AccuracyMetric: acc=0.571429\n",
      "\n",
      "Sum Time: 142ms\n",
      "\n",
      "\n",
      "Evaluation at Epoch 7/10. Step:14/20. AccuracyMetric: acc=0.571429\n",
      "\n",
      "Sum Time: 158ms\n",
      "\n",
      "\n",
      "Evaluation at Epoch 8/10. Step:16/20. AccuracyMetric: acc=0.571429\n",
      "\n",
      "Sum Time: 176ms\n",
      "\n",
      "\n",
      "Evaluation at Epoch 9/10. Step:18/20. AccuracyMetric: acc=0.714286\n",
      "\n",
      "Sum Time: 193ms\n",
      "\n",
      "\n",
      "Evaluation at Epoch 10/10. Step:20/20. AccuracyMetric: acc=0.857143\n",
      "\n",
      "Sum Time: 212ms\n",
      "\n",
      "\n",
      "\n",
      "In Epoch:10/Step:20, got best dev performance:AccuracyMetric: acc=0.857143\n",
      "Reloaded the best model.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'best_eval': {'AccuracyMetric': {'acc': 0.857143}},\n",
       " 'best_epoch': 10,\n",
       " 'best_step': 20,\n",
       " 'seconds': 0.2}"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from fastNLP import Callback\n",
    "\n",
    "start_time = time.time()\n",
    "\n",
    "class MyCallback(Callback):\n",
    "    def on_epoch_end(self):\n",
    "        print('Sum Time: {:d}ms\\n\\n'.format(round((time.time()-start_time)*1000)))\n",
    "        \n",
    "\n",
    "model = CNNText((len(vocab),50), num_classes=5, padding=2, dropout=0.1)\n",
    "trainer = Trainer(model=model, train_data=train_data, dev_data=dev_data,\n",
    "                  loss=CrossEntropyLoss(), metrics=AccuracyMetric(), callbacks=[MyCallback()])\n",
    "trainer.train()"
   ]
  },
  {
   "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
}