{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 快速生成假数据"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import faker\n",
    "\n",
    "fake = faker.Faker()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Paul Jones'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.name()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Hong Kong dollar'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.currency_name() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Mosley, Stevens and Cuevas'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.company()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<faker.providers.user_agent.Provider at 0x7f88d87d6130>,\n",
       " <faker.providers.ssn.en_US.Provider at 0x7f88d87d6160>,\n",
       " <faker.providers.python.Provider at 0x7f88d87bfe20>,\n",
       " <faker.providers.profile.Provider at 0x7f88d87bffd0>,\n",
       " <faker.providers.phone_number.en_US.Provider at 0x7f88d87bfee0>,\n",
       " <faker.providers.person.en_US.Provider at 0x7f88d87bfbe0>,\n",
       " <faker.providers.misc.en_US.Provider at 0x7f88d87bfca0>,\n",
       " <faker.providers.lorem.en_US.Provider at 0x7f88d87bfaf0>,\n",
       " <faker.providers.job.en_US.Provider at 0x7f88d87bf940>,\n",
       " <faker.providers.isbn.Provider at 0x7f88d87bf640>,\n",
       " <faker.providers.internet.en_US.Provider at 0x7f88d87bf850>,\n",
       " <faker.providers.geo.en_US.Provider at 0x7f88d87bf580>,\n",
       " <faker.providers.file.Provider at 0x7f88d87bf790>,\n",
       " <faker.providers.date_time.en_US.Provider at 0x7f88d87bf4c0>,\n",
       " <faker.providers.currency.en_US.Provider at 0x7f88d87bf5e0>,\n",
       " <faker.providers.credit_card.en_US.Provider at 0x7f88d87bf400>,\n",
       " <faker.providers.company.en_US.Provider at 0x7f88d879ce20>,\n",
       " <faker.providers.color.en_US.Provider at 0x7f88d879cb20>,\n",
       " <faker.providers.barcode.en_US.Provider at 0x7f88d879c550>,\n",
       " <faker.providers.bank.en_GB.Provider at 0x7f89282f9b50>,\n",
       " <faker.providers.automotive.en_US.Provider at 0x7f88c87f8ee0>,\n",
       " <faker.providers.address.en_US.Provider at 0x7f88d8695b80>]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.providers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Craig Daniels'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.providers[5].name()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 生成本土化数据"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "import faker\n",
    "fake = faker.Faker(locale=\"zh-CN\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'黄丽娟'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.name()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'13918155548'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.phone_number()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'佳禾网络有限公司'"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.company()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'tao68@example.org'"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.email()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 创建多个本土化版本"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "fake = faker.Faker(locale=[\"zh-CN\", \"ja-JP\", \"ko-KR\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'程畅'"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake[\"zh-CN\"].name()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'近藤 稔'"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake[\"ja-JP\"].name()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'구현우'"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake[\"ko-KR\"].name()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['zh_CN', 'ja_JP', 'ko_KR']"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.locales"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<faker.generator.Generator at 0x7f88d88ff580>,\n",
       " <faker.generator.Generator at 0x7f88d88ff550>,\n",
       " <faker.generator.Generator at 0x7f88d88ffa90>]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.factories"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 使用社区生态中补充的 Provider"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "# uncomment below code to install third-party provider\n",
    "# !pip install faker-biology"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "from faker import Faker\n",
    "from faker_biology.bioseq import Bioseq\n",
    "\n",
    "fake = Faker()\n",
    "fake.add_provider(Bioseq)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'TCGACCATCG'"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.dna(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'UAAGGUCGGC'"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.rna(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'MVGFAGGAENV'"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.protein(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 如何实现自己的 Provider"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "import faker\n",
    "\n",
    "from faker.providers import DynamicProvider\n",
    "\n",
    "fake = faker.Faker()\n",
    "\n",
    "locales = DynamicProvider(\n",
    "    provider_name=\"custom_locales\",\n",
    "    elements=[\"zh-CN\", \"en-US\", \"ja-JP\", \"ko-KR\"]\n",
    ")\n",
    "fake.add_provider(locales)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'ko-KR'"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.custom_locales()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "import faker\n",
    "from faker.providers import BaseProvider\n",
    "\n",
    "\n",
    "class MyProvider(BaseProvider):\n",
    "    def custom_locales(self):\n",
    "        choices = [\"zh-CN\", \"en-US\", \"ja-JP\", \"ko-KR\"]\n",
    "        return choices\n",
    "\n",
    "    def custom_programming_languages(self):\n",
    "        langs = [\"Python\", \"Java\", \"Golang\", \"JavaScript\", \"Swift\"]\n",
    "        return langs\n",
    "\n",
    "    def custom_numbers(self, n: int = 10):\n",
    "        if n < 0:\n",
    "            raise ValueError(\"n must be greater than or equal to 0.\")\n",
    "\n",
    "        return list(range(n))\n",
    "\n",
    "\n",
    "fake = faker.Faker()\n",
    "fake.add_provider(MyProvider)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['zh-CN', 'en-US', 'ja-JP', 'ko-KR']"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.custom_locales()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Python', 'Java', 'Golang', 'JavaScript', 'Swift']"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.custom_programming_languages()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.custom_numbers()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 1, 2, 3, 4]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.custom_numbers(n=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "import faker\n",
    "from faker.providers import BaseProvider\n",
    "\n",
    "\n",
    "class MyProvider(BaseProvider):\n",
    "    def custom_locales(self):\n",
    "        choices = [\"zh-CN\", \"en-US\", \"ja-JP\", \"ko-KR\"]\n",
    "        return self.random_element(choices)\n",
    "\n",
    "    def custom_programming_languages(self):\n",
    "        langs = [\"Python\", \"Java\", \"Golang\", \"JavaScript\", \"Swift\"]\n",
    "        return self.random_element(langs)\n",
    "\n",
    "    def custom_numbers(self, n: int = 10):\n",
    "        if n < 0:\n",
    "            raise ValueError(\"n must be greater than or equal to 0.\")\n",
    "\n",
    "        return self.random_element(list(range(n)))\n",
    "\n",
    "fake = faker.Faker()\n",
    "fake.add_provider(MyProvider)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'ko-KR'"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.custom_locales()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Swift'"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.custom_programming_languages()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fake.custom_numbers(n=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.0 ('pandas-startup')",
   "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": "3.9.0"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "13977d4cc82dee5f9d9535ceb495bd0ab12a43c33c664e5f0d53c24cf634b67f"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}