data-science-ipython-notebooks/commands/linux.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:67c67b0d98088d4c0573bea23d46b8ed9372b679f9664a24756eece3d42f6ca2"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Linux Commands\n",
      "\n",
      "* Disk Usage\n",
      "* Splitting Files\n",
      "* Grep\n",
      "* Compression\n",
      "* Terminal Syntax Highlighting\n",
      "* Vim"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Disk Usage"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Display human-readable (-h) free disk space:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df -h"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Display human-readable (-h) disk usage statistics:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "du -h ./"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Display human-readable (-h) disk usage statistics, showing only the total usage (-s):"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "du -sh ../"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Display the human-readable (-h) disk usage statistics, showing also the grand total for all file types (-c):"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "du -csh ./"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Splitting Files"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Count number of lines in a file with wc:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "wc -l < file.txt"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Count the number of lines in a file with grep:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "grep -c \".\" file.txt"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Split a file into multiple files based on line count:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "split -l 20 file.txt new"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Split a file into multiple files based on line count, use suffix of length 1:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "split -l 802 -a 1 file.csv dir/part-user-csv.tbl-"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Grep"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Check number of files matching \u201c.txt\":"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ls -1 | grep .txt | wc -l"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Check number of MapReduce records processed, outputting the results to the terminal:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "cat * | grep -c \"foo\" folder/part*"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Compression"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Uncompress all tar.gz in current directory to another directory"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "for i in *.tar.gz; do echo working on $i; tar xvzf $i -C directory/ ; done"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Terminal Syntax Highlighting"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Add the following to your ~/.bash_profile:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "export PS1='\\[\\033[01;32m\\]\\u@\\h\\[\\033[00m\\]:\\[\\033[01;34m\\]\\W\\[\\033[00m\\]\\$ '\n",
      "export CLICOLOR=1\n",
      "export LSCOLORS=ExFxBxDxCxegedabagacad\n",
      "alias ls='ls -GFh'"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Reload .bash_profile:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "source ~/.bash_profile"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Vim"
     ]
    },
    {
     "cell_type": "raw",
     "metadata": {},
     "source": [
      "Normal mode:  esc\n",
      "\n",
      "Basic movement:  h, j, k, l\n",
      "Word movement:  w, W, e, E, b, B\n",
      "\n",
      "Go to matching parenthesis:  %\n",
      "Go to start of the line:  0\n",
      "Go to end of the line:  $\n",
      "\n",
      "Find character:  f\n",
      "\n",
      "Insert mode:  i\n",
      "Append to line:  A\n",
      "\n",
      "Delete character:  x\n",
      "Delete command:  d\n",
      "Delete line:  dd\n",
      "\n",
      "Replace command:  r\n",
      "Change command:  c\n",
      "\n",
      "Undo:  u (U for all changes on a line)\n",
      "Redo:  CTRL-R\n",
      "\n",
      "Copy the current line:  yy\n",
      "Paste the current line:  p (P for paste above cursor)\n",
      "\n",
      "Quit without saving changes:  q!\n",
      "Write the current file and quit:  :wq\n",
      "\n",
      "# Run the following command to enable the tutorial\n",
      "vimtutor\n",
      "\n",
      "# Run the following commands to enable syntax colors\n",
      "cd ~\n",
      "vim .vimrc\n",
      "syntax on\n",
      ":wq"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}