Lesson08.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "homeless-wisconsin",
   "metadata": {},
   "source": [
    "## Наука о данных\n",
    "### Совместный бакалавриат ВШЭ-РЭШ, 2021-2022 учебный год\n",
    "_Илья Щуров_\n",
    "\n",
    "[Страница курса](http://math-info.hse.ru/s21/j)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "collected-september",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[[100, 2, 3], [10, 20, 30]]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "table = [[1, 2, 3],\n",
    "         [10, 20, 30]]\n",
    "backup_table = table.copy()\n",
    "table[0][0] = 100\n",
    "backup_table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "listed-termination",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Overwriting testfile.txt\n"
     ]
    }
   ],
   "source": [
    "%%file testfile.txt\n",
    "Hello, world!\n",
    "This is a test."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "pleasant-recruitment",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class '_io.TextIOWrapper'>\n",
      "Hello, world!\n",
      "\n",
      "This is a test.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "f = open(\"testfile.txt\")\n",
    "print(type(f))\n",
    "for line in f:\n",
    "    print(line)\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "sublime-anxiety",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Hello, world!\\n', 'This is a test.\\n']\n"
     ]
    }
   ],
   "source": [
    "f = open(\"testfile.txt\")\n",
    "print(list(f))\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "united-dodge",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class '_io.TextIOWrapper'>\n",
      "Hello, world!\n",
      "This is a test.\n"
     ]
    }
   ],
   "source": [
    "f = open(\"testfile.txt\")\n",
    "for line in f:\n",
    "    print(line, end=\"\")\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "international-scale",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello, world!\n",
      "This is a test.\n"
     ]
    }
   ],
   "source": [
    "f = open(\"testfile.txt\")\n",
    "for line in f:\n",
    "    print(line.rstrip())\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "indian-compound",
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "I/O operation on closed file.",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m/var/folders/h2/9nyrt4p55kq6pdvqg02_zmj40000gn/T/ipykernel_32950/3271805783.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0mline\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m     \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mline\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: I/O operation on closed file."
     ]
    }
   ],
   "source": [
    "for line in f:\n",
    "    print(line)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "surprising-label",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello, world!\n",
      "This is a test.\n",
      "Inside with\n",
      "Is file closed? False\n",
      "Outwide of with\n",
      "Is file closed? True\n"
     ]
    }
   ],
   "source": [
    "with open(\"testfile.txt\") as f:\n",
    "    for line in f:\n",
    "        print(line.rstrip())\n",
    "    print(\"Inside with\")\n",
    "    print(\"Is file closed?\", f.closed)\n",
    "print(\"Outwide of with\")\n",
    "print(\"Is file closed?\", f.closed)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "coastal-economy",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello, world!\n",
      "This is a test.\n",
      "Once again\n"
     ]
    }
   ],
   "source": [
    "with open(\"testfile.txt\") as f:\n",
    "    for line in f:\n",
    "        print(line.rstrip())\n",
    "    print(\"Once again\")\n",
    "    for line in f:\n",
    "        print(line.rstrip())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "congressional-circular",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello, world!\n",
      "This is a test.\n",
      "Once again\n",
      "Hello, world!\n",
      "This is a test.\n"
     ]
    }
   ],
   "source": [
    "with open(\"testfile.txt\") as f:\n",
    "    for line in f:\n",
    "        print(line.rstrip())\n",
    "    print(\"Once again\")\n",
    "    f.seek(0)\n",
    "    for line in f:\n",
    "        print(line.rstrip())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "equipped-affair",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello, world!\n",
      "This is a test.\n",
      "Once again\n",
      "ello, world!\n",
      "This is a test.\n"
     ]
    }
   ],
   "source": [
    "with open(\"testfile.txt\") as f:\n",
    "    for line in f:\n",
    "        print(line.rstrip())\n",
    "    print(\"Once again\")\n",
    "    f.seek(1)\n",
    "    for line in f:\n",
    "        print(line.rstrip())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "relative-memorabilia",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing cyrillic.txt\n"
     ]
    }
   ],
   "source": [
    "%%file cyrillic.txt\n",
    "Доброе утро, страна!\n",
    "Говорит Москва!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "radical-lying",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"\n",
    "Здравствуй, страна!\n",
    "Once again\n",
    "Здравствуй, страна!\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "rational-olive",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Доброе утро, страна!\n",
      "Говорит Москва!\n",
      "Once again\n",
      "оброе утро, страна!\n",
      "Говорит Москва!\n"
     ]
    }
   ],
   "source": [
    "with open(\"cyrillic.txt\", encoding='utf-8') as f:\n",
    "    for line in f:\n",
    "        print(line.rstrip())\n",
    "    print(\"Once again\")\n",
    "    f.seek(2)\n",
    "    for line in f:\n",
    "        print(line.rstrip())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "falling-regulation",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "b'\\xd0\\x94\\xd0\\xbe\\xd0\\xb1\\xd1\\x80\\xd0\\xbe\\xd0\\xb5 \\xd1\\x83\\xd1\\x82\\xd1\\x80\\xd0\\xbe'"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"Доброе утро\".encode('utf-8')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "strong-telling",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "b'\\xc4\\xee\\xe1\\xf0\\xee\\xe5 \\xf3\\xf2\\xf0\\xee'"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"Доброе утро\".encode('CP1251')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "lasting-prediction",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Доброе утро'"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"Доброе утро\".encode('utf-8').decode('cp1251')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "polished-powder",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Äîáðîå óòðî'"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"Доброе утро\".encode('cp1251').decode('latin-1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "frank-sheriff",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Доброе утро'"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'Äîáðîå óòðî'.encode('latin-1').decode('cp1251')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "hawaiian-conference",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "b'Hello, world!'"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "b'Hello, world!'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "every-maple",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Этот файл создан искусственным интеллектом\n",
      "\n",
      "Его удаление приведёт к краху цивилизации\n",
      "\n"
     ]
    }
   ],
   "source": [
    "with open(\"newfile.txt\", \"w\") as f:\n",
    "    print(\"Этот файл создан искусственным интеллектом\", file=f)\n",
    "    print(\"Его удаление приведёт к краху цивилизации\", file=f)\n",
    "\n",
    "with open(\"newfile.txt\", encoding='utf-8') as f:\n",
    "    for line in f:\n",
    "        print(line)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "necessary-tamil",
   "metadata": {},
   "outputs": [],
   "source": [
    "f = open(\"anotherfile.txt\", \"w\")\n",
    "print(\"Hello, world!\", file=f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "considerable-costume",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f.closed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "identified-ferry",
   "metadata": {},
   "outputs": [],
   "source": [
    "f.flush()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "liberal-amount",
   "metadata": {},
   "outputs": [],
   "source": [
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "occasional-seeking",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"anotherfile.txt\", \"w\") as f:\n",
    "    print(\"Hello, world!\", file=f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "modified-speaker",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Этот файл создан искусственным интеллектом\n",
      "\n",
      "Его удаление приведёт к краху цивилизации\n",
      "\n",
      "α² + β² = γ²\n",
      "\n"
     ]
    }
   ],
   "source": [
    "with open(\"newfile.txt\", \"w\", encoding='UTF-8') as f:\n",
    "    print(\"Этот файл создан искусственным интеллектом\", file=f)\n",
    "    print(\"Его удаление приведёт к краху цивилизации\", file=f)\n",
    "    print(\"α² + β² = γ²\", file=f)\n",
    "\n",
    "with open(\"newfile.txt\", encoding='UTF-8') as f:\n",
    "    for line in f:\n",
    "        print(line)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "focal-hybrid",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"newfile.txt\", \"w\", encoding='UTF-8') as f:\n",
    "    print(\"New content\", file=f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "prepared-variance",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "New content\n",
      "\n"
     ]
    }
   ],
   "source": [
    "with open(\"newfile.txt\") as f:\n",
    "    for line in f:\n",
    "        print(line)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "martial-evans",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"newfile.txt\", \"a\") as f:\n",
    "    print(\"More content\", file=f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "express-pakistan",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "New content\n",
      "More content\n"
     ]
    }
   ],
   "source": [
    "with open(\"newfile.txt\") as f:\n",
    "    for line in f:\n",
    "        print(line.rstrip())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "legal-cutting",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"newfile.txt\") as f:\n",
    "    lines = f.readlines()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "central-planning",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['New content\\n', 'More content\\n']"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "vanilla-invalid",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"newfile.txt\") as f:\n",
    "    contents = f.read()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "posted-woman",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'New content\\nMore content\\n'"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "contents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "tutorial-remark",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "still-swing",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'/Users/user/prj/svn.math-hse.info/repo/2021-22/nes-datascience'"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.getcwd()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "demonstrated-collar",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "unknown-institution",
   "metadata": {},
   "outputs": [],
   "source": [
    "new_folder = Path(\"new_folder\")\n",
    "new_folder.mkdir(exist_ok=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "contained-ranking",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(new_folder / \"newfile.txt\", \"w\") as f:\n",
    "    print(\"New file\", file=f)\n",
    "    print(\"In new folder\", file=f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "lesbian-channels",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PosixPath('new_folder/newfile.txt')"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_folder / \"newfile.txt\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "jewish-twist",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PosixPath('new_folder/../newfile.txt')"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_folder / \"..\" / \"newfile.txt\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "played-invite",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "New content\n",
      "More content\n"
     ]
    }
   ],
   "source": [
    "with open(new_folder / \"..\" / \"newfile.txt\") as f:\n",
    "    for line in f:\n",
    "        print(line.rstrip())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "polyphonic-sustainability",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'New content\\nMore content\\n'"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Path(\"newfile.txt\").read_text()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "hybrid-rates",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "new_folder\n",
      "rsconnect\n",
      "first-lesson.Rmd\n",
      "assignments\n",
      ".DS_Store\n",
      "var1_mehweb.csv\n",
      "Untitled.ipynb\n",
      "second-lesson.html\n",
      "anotherfile.txt\n",
      "cyrillic.txt\n",
      "first-lesson.html\n",
      "second-class.nb.html\n",
      "Lesson02.ipynb\n",
      "first-class.nb.html\n",
      "newfile.txt\n",
      "Lesson04.ipynb\n",
      "Lesson06.ipynb\n",
      "second-lesson.Rmd\n",
      ".ipynb_checkpoints\n",
      "Lesson01.ipynb\n",
      "Lesson03.ipynb\n",
      "testfile.txt\n",
      "ps01.ipynb\n",
      "second-lesson.nb.html\n",
      "Lesson07.ipynb\n",
      "Lesson05.ipynb\n"
     ]
    }
   ],
   "source": [
    "for file in Path(\"\").iterdir():\n",
    "    print(file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "smaller-wales",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Lesson02.ipynb\n",
      "Lesson04.ipynb\n",
      "Lesson06.ipynb\n",
      "Lesson01.ipynb\n",
      "Lesson03.ipynb\n",
      "Lesson07.ipynb\n",
      "Lesson05.ipynb\n"
     ]
    }
   ],
   "source": [
    "for file in Path(\"\").glob(\"Lesson??.ipynb\"):\n",
    "    print(file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "mediterranean-friendship",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[PosixPath('/../home'),\n",
       " PosixPath('/../usr'),\n",
       " PosixPath('/../.DS_Store'),\n",
       " PosixPath('/../.PKInstallSandboxManager-SystemSoftware'),\n",
       " PosixPath('/../bin'),\n",
       " PosixPath('/../sbin'),\n",
       " PosixPath('/../.file'),\n",
       " PosixPath('/../etc'),\n",
       " PosixPath('/../var'),\n",
       " PosixPath('/../Library'),\n",
       " PosixPath('/../System'),\n",
       " PosixPath('/../.VolumeIcon.icns'),\n",
       " PosixPath('/../.fseventsd'),\n",
       " PosixPath('/../private'),\n",
       " PosixPath('/../.vol'),\n",
       " PosixPath('/../Users'),\n",
       " PosixPath('/../Applications'),\n",
       " PosixPath('/../opt'),\n",
       " PosixPath('/../dev'),\n",
       " PosixPath('/../Volumes'),\n",
       " PosixPath('/../tmp'),\n",
       " PosixPath('/../cores')]"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(Path(\"/../\").iterdir())"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.10",
   "language": "python",
   "name": "py3.10"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}