{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "fastNLP10 分钟上手教程\n", "-------\n", "\n", "fastNLP提供方便的数据预处理，训练和测试模型的功能" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "如果您还没有通过pip安装fastNLP，可以执行下面的操作加载当前模块" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "import sys\n", "sys.path.append(\"../\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "DataSet & Instance\n", "------\n", "\n", "fastNLP用DataSet和Instance保存和处理数据。每个DataSet表示一个数据集，每个Instance表示一个数据样本。一个DataSet存有多个Instance，每个Instance可以自定义存哪些内容。\n", "\n", "有一些read_*方法，可以轻松从文件读取数据，存成DataSet。" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "77\n" ] } ], "source": [ "from fastNLP import DataSet\n", "from fastNLP import Instance\n", "\n", "# 从csv读取数据到DataSet\n", "dataset = DataSet.read_csv('sample_data/tutorial_sample_dataset.csv', headers=('raw_sentence', 'label'), sep='\\t')\n", "print(len(dataset))" ] }, { "cell_type": "code", "execution_count": 7, "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", "{'raw_sentence': The plot is romantic comedy boilerplate from start to finish . type=str,\n", "'label': 2 type=str}\n" ] } ], "source": [ "# 使用数字索引[k]，获取第k个样本\n", "print(dataset[0])\n", "\n", "# 索引也可以是负数\n", "print(dataset[-3])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Instance\n", "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": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'raw_sentence': fake data type=str,\n", "'label': 0 type=str}" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# DataSet.append(Instance)加入新数据\n", "dataset.append(Instance(raw_sentence='fake data', label='0'))\n", "dataset[-1]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## DataSet.apply方法\n", "数据预处理利器" ] }, { "cell_type": "code", "execution_count": 9, "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" ] } ], "source": [ "# 将所有数字转为小写\n", "dataset.apply(lambda x: x['raw_sentence'].lower(), new_field_name='raw_sentence')\n", "print(dataset[0])" ] }, { "cell_type": "code", "execution_count": 10, "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=int}\n" ] } ], "source": [ "# label转int\n", "dataset.apply(lambda x: int(x['label']), new_field_name='label')\n", "print(dataset[0])" ] }, { "cell_type": "code", "execution_count": 11, "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=int,\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}\n" ] } ], "source": [ "# 使用空格分割句子\n", "def split_sent(ins):\n", " return ins['raw_sentence'].split()\n", "dataset.apply(split_sent, new_field_name='words')\n", "print(dataset[0])" ] }, { "cell_type": "code", "execution_count": 12, "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=int,\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,\n", "'seq_len': 37 type=int}\n" ] } ], "source": [ "# 增加长度信息\n", "dataset.apply(lambda x: len(x['words']), new_field_name='seq_len')\n", "print(dataset[0])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## DataSet.drop\n", "筛选数据" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "77\n" ] } ], "source": [ "# 删除低于某个长度的词语\n", "dataset.drop(lambda x: x['seq_len'] <= 3)\n", "print(len(dataset))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 配置DataSet\n", "1. 哪些域是特征，哪些域是标签\n", "2. 切分训练集/验证集" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "# 设置DataSet中，哪些field要转为tensor\n", "\n", "# set target，loss或evaluate中的golden，计算loss，模型评估时使用\n", "dataset.set_target(\"label\")\n", "# set input，模型forward时使用\n", "dataset.set_input(\"words\")" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "54\n", "23\n" ] } ], "source": [ "# 分出测试集、训练集\n", "\n", "test_data, train_data = dataset.split(0.3)\n", "print(len(test_data))\n", "print(len(train_data))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Vocabulary\n", "------\n", "\n", "fastNLP中的Vocabulary轻松构建词表，将词转成数字" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{'raw_sentence': a welcome relief from baseball movies that try too hard to be mythic , this one is a sweet and modest and ultimately winning story . type=str,\n", "'label': 3 type=int,\n", "'words': [4, 1, 1, 18, 1, 1, 13, 1, 1, 1, 8, 26, 1, 5, 35, 1, 11, 4, 1, 10, 1, 10, 1, 1, 1, 2] type=list,\n", "'seq_len': 26 type=int}\n" ] } ], "source": [ "from fastNLP import Vocabulary\n", "\n", "# 构建词表, Vocabulary.add(word)\n", "vocab = Vocabulary(min_freq=2)\n", "train_data.apply(lambda x: [vocab.add(word) for word in x['words']])\n", "vocab.build_vocab()\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='words')\n", "test_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='words')\n", "\n", "\n", "print(test_data[0])" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 如果你们需要做强化学习或者GAN之类的项目，你们也可以使用这些数据预处理的工具\n", "from fastNLP.core.batch import Batch\n", "from fastNLP.core.sampler import RandomSampler\n", "\n", "batch_iterator = Batch(dataset=train_data, batch_size=2, sampler=RandomSampler())\n", "for batch_x, batch_y in batch_iterator:\n", " print(\"batch_x has: \", batch_x)\n", " print(\"batch_y has: \", batch_y)\n", " break" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Model\n", "定义一个PyTorch模型" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "CNNText(\n", " (embed): Embedding(\n", " (embed): Embedding(59, 50, padding_idx=0)\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(\n", " (linear): Linear(in_features=12, out_features=5, bias=True)\n", " )\n", ")" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from fastNLP.models import CNNText\n", "model = CNNText(embed_num=len(vocab), embed_dim=50, num_classes=5, padding=2, dropout=0.1)\n", "model" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "这是上述模型的forward方法。如果你不知道什么是forward方法，请参考我们的PyTorch教程。\n", "\n", "注意两点：\n", "1. forward参数名字叫**word_seq**，请记住。\n", "2. forward的返回值是一个**dict**，其中有个key的名字叫**output**。\n", "\n", "```Python\n", " def forward(self, word_seq):\n", " \"\"\"\n", "\n", " :param word_seq: torch.LongTensor, [batch_size, seq_len]\n", " :return output: dict of torch.LongTensor, [batch_size, num_classes]\n", " \"\"\"\n", " x = self.embed(word_seq) # [N,L] -> [N,L,C]\n", " x = self.conv_pool(x) # [N,L,C] -> [N,C]\n", " x = self.dropout(x)\n", " x = self.fc(x) # [N,C] -> [N, N_class]\n", " return {'output': x}\n", "```" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "这是上述模型的predict方法，是用来直接输出该任务的预测结果，与forward目的不同。\n", "\n", "注意两点：\n", "1. predict参数名也叫**word_seq**。\n", "2. predict的返回值是也一个**dict**，其中有个key的名字叫**predict**。\n", "\n", "```\n", " def predict(self, word_seq):\n", " \"\"\"\n", "\n", " :param word_seq: torch.LongTensor, [batch_size, seq_len]\n", " :return predict: dict of torch.LongTensor, [batch_size, seq_len]\n", " \"\"\"\n", " output = self(word_seq)\n", " _, predict = output['output'].max(dim=1)\n", " return {'predict': predict}\n", "```" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Trainer & Tester\n", "------\n", "\n", "使用fastNLP的Trainer训练模型" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "from fastNLP import Trainer\n", "from copy import deepcopy\n", "from fastNLP.core.losses import CrossEntropyLoss\n", "from fastNLP.core.metrics import AccuracyMetric\n", "\n", "\n", "# 更改DataSet中对应field的名称，与模型的forward的参数名一致\n", "# 因为forward的参数叫word_seq, 所以要把原本叫words的field改名为word_seq\n", "# 这里的演示是让你了解这种**命名规则**\n", "train_data.rename_field('words', 'word_seq')\n", "test_data.rename_field('words', 'word_seq')\n", "\n", "# 顺便把label换名为label_seq\n", "train_data.rename_field('label', 'label_seq')\n", "test_data.rename_field('label', 'label_seq')" ] }, { "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": 19, "metadata": {}, "outputs": [], "source": [ "loss = CrossEntropyLoss(pred=\"output\", target=\"label_seq\")" ] }, { "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": 20, "metadata": {}, "outputs": [], "source": [ "metric = AccuracyMetric(pred=\"predict\", target=\"label_seq\")" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "input fields after batch(if batch size is 2):\n", "\tword_seq: (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", "\tlabel_seq: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2]) \n", "\n", "training epochs started 2019-01-12 17-07-51\n" ] }, { "data": { "text/plain": [ "HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=10), HTML(value='')), layout=Layout(display='…" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Evaluation at Epoch 1/5. Step:2/10. AccuracyMetric: acc=0.425926\n", "Evaluation at Epoch 2/5. Step:4/10. AccuracyMetric: acc=0.425926\n", "Evaluation at Epoch 3/5. Step:6/10. AccuracyMetric: acc=0.611111\n", "Evaluation at Epoch 4/5. Step:8/10. AccuracyMetric: acc=0.648148\n", "Evaluation at Epoch 5/5. Step:10/10. AccuracyMetric: acc=0.703704\n", "\n", "In Epoch:5/Step:10, got best dev performance:AccuracyMetric: acc=0.703704\n", "Reloaded the best model.\n" ] }, { "data": { "text/plain": [ "{'best_eval': {'AccuracyMetric': {'acc': 0.703704}},\n", " 'best_epoch': 5,\n", " 'best_step': 10,\n", " 'seconds': 0.62}" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 实例化Trainer，传入模型和数据，进行训练\n", "# 先在test_data拟合（确保模型的实现是正确的）\n", "copy_model = deepcopy(model)\n", "overfit_trainer = Trainer(model=copy_model, train_data=test_data, dev_data=test_data,\n", " loss=loss,\n", " metrics=metric,\n", " save_path=None,\n", " batch_size=32,\n", " n_epochs=5)\n", "overfit_trainer.train()" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "input fields after batch(if batch size is 2):\n", "\tword_seq: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 20]) \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", "training epochs started 2019-01-12 17-09-05\n" ] }, { "data": { "text/plain": [ "HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=5), HTML(value='')), layout=Layout(display='i…" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Evaluation at Epoch 1/5. Step:1/5. AccuracyMetric: acc=0.37037\n", "Evaluation at Epoch 2/5. Step:2/5. AccuracyMetric: acc=0.37037\n", "Evaluation at Epoch 3/5. Step:3/5. AccuracyMetric: acc=0.462963\n", "Evaluation at Epoch 4/5. Step:4/5. AccuracyMetric: acc=0.425926\n", "Evaluation at Epoch 5/5. Step:5/5. AccuracyMetric: acc=0.481481\n", "\n", "In Epoch:5/Step:5, got best dev performance:AccuracyMetric: acc=0.481481\n", "Reloaded the best model.\n", "Train finished!\n" ] } ], "source": [ "# 用train_data训练，在test_data验证\n", "trainer = Trainer(model=model, train_data=train_data, dev_data=test_data,\n", " loss=CrossEntropyLoss(pred=\"output\", target=\"label_seq\"),\n", " metrics=AccuracyMetric(pred=\"predict\", target=\"label_seq\"),\n", " save_path=None,\n", " batch_size=32,\n", " n_epochs=5)\n", "trainer.train()\n", "print('Train finished!')" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[tester] \n", "AccuracyMetric: acc=0.481481\n", "{'AccuracyMetric': {'acc': 0.481481}}\n" ] } ], "source": [ "# 调用Tester在test_data上评价效果\n", "from fastNLP import Tester\n", "\n", "tester = Tester(data=test_data, model=model, metrics=AccuracyMetric(pred=\"predict\", target=\"label_seq\"),\n", " batch_size=4)\n", "acc = tester.test()\n", "print(acc)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# In summary\n", "\n", "## fastNLP Trainer的伪代码逻辑\n", "### 1. 准备DataSet，假设DataSet中共有如下的fields\n", " ['raw_sentence', 'word_seq1', 'word_seq2', 'raw_label','label']\n", " 通过\n", " DataSet.set_input('word_seq1', word_seq2', flag=True)将'word_seq1', 'word_seq2'设置为input\n", " 通过\n", " DataSet.set_target('label', flag=True)将'label'设置为target\n", "### 2. 初始化模型\n", " class Model(nn.Module):\n", " def __init__(self):\n", " xxx\n", " def forward(self, word_seq1, word_seq2):\n", " # (1) 这里使用的形参名必须和DataSet中的input field的名称对应。因为我们是通过形参名, 进行赋值的\n", " # (2) input field的数量可以多于这里的形参数量。但是不能少于。\n", " xxxx\n", " # 输出必须是一个dict\n", "### 3. Trainer的训练过程\n", " (1) 从DataSet中按照batch_size取出一个batch，调用Model.forward\n", " (2) 将 Model.forward的结果 与 标记为target的field 传入Losser当中。\n", " 由于每个人写的Model.forward的output的dict可能key并不一样，比如有人是{'pred':xxx}, {'output': xxx}; \n", " 另外每个人将target可能也会设置为不同的名称, 比如有人是label, 有人设置为target；\n", " 为了解决以上的问题，我们的loss提供映射机制\n", " 比如CrossEntropyLosser的需要的输入是(prediction, target)。但是forward的output是{'output': xxx}; 'label'是target\n", " 那么初始化losser的时候写为CrossEntropyLosser(prediction='output', target='label')即可\n", " (3) 对于Metric是同理的\n", " Metric计算也是从 forward的结果中取值 与 设置target的field中取值。 也是可以通过映射找到对应的值 \n", " \n", " \n", "\n", "## 一些问题.\n", "### 1. DataSet中为什么需要设置input和target\n", " 只有被设置为input或者target的数据才会在train的过程中被取出来\n", " (1.1) 我们只会在设置为input的field中寻找传递给Model.forward的参数。\n", " (1.2) 我们在传递值给losser或者metric的时候会使用来自: \n", " (a)Model.forward的output\n", " (b)被设置为target的field\n", " \n", "\n", "### 2. 我们是通过forwad中的形参名将DataSet中的field赋值给对应的参数\n", " (1.1) 构建模型过程中，\n", " 例如:\n", " DataSet中x，seq_lens是input，那么forward就应该是\n", " def forward(self, x, seq_lens):\n", " pass\n", " 我们是通过形参名称进行匹配的field的\n", " \n", "\n", "\n", "### 1. 加载数据到DataSet\n", "### 2. 使用apply操作对DataSet进行预处理\n", " (2.1) 处理过程中将某些field设置为input，某些field设置为target\n", "### 3. 构建模型\n", " (3.1) 构建模型过程中，需要注意forward函数的形参名需要和DataSet中设置为input的field名称是一致的。\n", " 例如:\n", " DataSet中x，seq_lens是input，那么forward就应该是\n", " def forward(self, x, seq_lens):\n", " pass\n", " 我们是通过形参名称进行匹配的field的\n", " (3.2) 模型的forward的output需要是dict类型的。\n", " 建议将输出设置为{\"pred\": xx}.\n", " \n" ] }, { "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": 2 }