{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## CSV Input/Output in Python"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Creating a list of lists from scratch\n",
    "# Each 'row' contains a number, its square, and its cube.\n",
    "\n",
    "exponent_table = []\n",
    "\n",
    "for i in range(10):\n",
    "    row = [i, i**2, i**3]\n",
    "    exponent_table.append(row)\n",
    "\n",
    "exponent_table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Writing the list of lists to a CSV file\n",
    "\n",
    "import csv\n",
    "\n",
    "out_path = \"Exponent_table.csv\"\n",
    "\n",
    "header = ['Number', 'Squared', 'Cubed']\n",
    "\n",
    "with open(out_path, 'w') as fo:\n",
    "    csv_writer = csv.writer(fo)\n",
    "    csv_writer.writerow(header)\n",
    "    csv_writer.writerows(exponent_table)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Viewing the contents of the CSV file we just created\n",
    "\n",
    "!cat Exponent_table.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Downloading a CSV containing The Guardian's top 10 'Greatest Arthouse and Drama' films\n",
    "## https://www.theguardian.com/news/datablog/2010/oct/16/greatest-films-of-all-time\n",
    "\n",
    "!wget https://raw.githubusercontent.com/pcda17/pcda17.github.io/master/week/7/Greatest_Arthouse_Drama_Films.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Loading the CSV as a list of lists\n",
    "\n",
    "import csv\n",
    "\n",
    "csv_path = \"Greatest_Arthouse_Drama_Films.csv\"\n",
    "list_of_lists = []\n",
    "\n",
    "with open(csv_path) as fi:\n",
    "    csv_input = csv.reader(fi)\n",
    "    for row in csv_input:\n",
    "        list_of_lists.append(row)\n",
    "\n",
    "list_of_lists"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "len(list_of_lists)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Viewing the header row\n",
    "\n",
    "list_of_lists[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Viewing a single record's row\n",
    "\n",
    "list_of_lists[8]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Viewing the 'director' field in the row we viewed above\n",
    "\n",
    "row = list_of_lists[8]\n",
    "\n",
    "row[2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Viewing the header row alongside each field's index\n",
    "\n",
    "list(enumerate(list_of_lists[0]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Creating a reduced version of a single row, containing 4 selected fields\n",
    "\n",
    "row = list_of_lists[9]\n",
    "\n",
    "film = row[1]\n",
    "director = row[2]\n",
    "year = row[4]\n",
    "country = row[8]\n",
    "\n",
    "reduced_row = [film, director, year, country]\n",
    "\n",
    "reduced_row"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Creating a new list of lists containing reduced versions of each row\n",
    "\n",
    "reduced_list_of_lists = []\n",
    "\n",
    "for row in list_of_lists:\n",
    "    film = row[1]\n",
    "    director = row[2]\n",
    "    year = row[4]\n",
    "    country = row[8]\n",
    "    reduced_row = [film, director, year, country]\n",
    "    reduced_list_of_lists.append(reduced_row)\n",
    "\n",
    "reduced_list_of_lists"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Writing the reduced list of lists to a CSV\n",
    "\n",
    "out_path = \"Greatest_Arthouse_Drama_Films_reduced.csv\"\n",
    "\n",
    "with open(out_path, 'w') as fo:\n",
    "    csv_writer = csv.writer(fo)\n",
    "    csv_writer.writerows(reduced_list_of_lists)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Viewing the contents of the CSV file we just created\n",
    "\n",
    "!cat Greatest_Arthouse_Drama_Films_reduced.csv"
   ]
  },
  {
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}