fastNLP/tutorials/fastnlp_test_tutorial.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## fastNLP测试说明\n",
    "### 测试环境\n",
    "fastNLP使用pytest对代码进行单元测试，测试代码在test文件夹下，测试所需数据在test/data_for_tests文件夹下\n",
    "测试的步骤主要分为准备数据，执行测试，比对结果，清除环境四步\n",
    "测试代码以test_xxx.py命名，以DataSet的测试代码为例，测试代码文件名为test_dataset.py"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import unittest # 单元测试需要用到unittest\n",
    "\n",
    "from fastNLP.core.dataset import DataSet\n",
    "from fastNLP.core.fieldarray import FieldArray\n",
    "from fastNLP.core.instance import Instance\n",
    "# 在这个单元测试文件中，需要测试DataSet、FieldArray、以及Instance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "class TestDataSet(unittest.TestCase):  # 类名字以Test打头，继承unittest.TestCase\n",
    "\n",
    "    def test_init_v1(self):  # 测试样例1， 函数名称以test_打头\n",
    "        # 该测试样例测试的是DataSet的初始化\n",
    "        ins = Instance(x=[1, 2, 3, 4], y=[5, 6]) # 准备数据\n",
    "        ds = DataSet([ins] * 40) # 执行测试（调用DataSet的初始化函数）\n",
    "        self.assertTrue(\"x\" in ds.field_arrays and \"y\" in ds.field_arrays) # 比对结果：'x'跟'y'都是ds的field\n",
    "        self.assertEqual(ds.field_arrays[\"x\"].content, [[1, 2, 3, 4], ] * 40) # 比对结果： field 'x'的内容正确\n",
    "        self.assertEqual(ds.field_arrays[\"y\"].content, [[5, 6], ] * 40) # 比对结果： field 'y'的内容正确\n",
    "        \n",
    "    def test_init_v2(self): # 测试样例2，该样例测试DataSet的另一种初始化方式\n",
    "        ds = DataSet({\"x\": [[1, 2, 3, 4]] * 40, \"y\": [[5, 6]] * 40})\n",
    "        self.assertTrue(\"x\" in ds.field_arrays and \"y\" in ds.field_arrays)\n",
    "        self.assertEqual(ds.field_arrays[\"x\"].content, [[1, 2, 3, 4], ] * 40)\n",
    "        self.assertEqual(ds.field_arrays[\"y\"].content, [[5, 6], ] * 40)\n",
    "    \n",
    "    def test_init_assert(self): # 测试样例3，该样例测试不规范初始化DataSet时是否会报正确错误\n",
    "        with self.assertRaises(AssertionError):\n",
    "            _ = DataSet({\"x\": [[1, 2, 3, 4]] * 40, \"y\": [[5, 6]] * 100})\n",
    "        with self.assertRaises(AssertionError):\n",
    "            _ = DataSet([[1, 2, 3, 4]] * 10)\n",
    "        with self.assertRaises(ValueError):\n",
    "            _ = DataSet(0.00001)\n",
    "    \n",
    "    def test_contains(self): # 测试样例4，该样例测试DataSet的contains函数，是功能测试\n",
    "        ds = DataSet({\"x\": [[1, 2, 3, 4]] * 40, \"y\": [[5, 6]] * 40})\n",
    "        self.assertTrue(\"x\" in ds)\n",
    "        self.assertTrue(\"y\" in ds)\n",
    "        self.assertFalse(\"z\" in ds)\n",
    "    \n",
    "    # 更多测试样例见test/core/test_dataset.py"
   ]
  },
  {
   "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
}