{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "1f673859-da9c-41a5-97ff-4f1b21c66f47",
   "metadata": {},
   "source": [
    "# Chapter 6"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ceece285-8718-4bc2-ba0f-9ac3645c7a8e",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\n57g588\\AppData\\Local\\Programs\\Python\\Python313\\Lib\\site-packages\\datascience\\maps.py:13: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.\n",
      "  import pkg_resources\n"
     ]
    }
   ],
   "source": [
    "from datascience import *"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8770f576-cee3-46c6-8bc5-6fe0447bdfa3",
   "metadata": {},
   "source": [
    "## Students Table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "52a17041-0f47-45a2-8166-1ad16dd5c932",
   "metadata": {},
   "outputs": [],
   "source": [
    "students = Table()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9a3a6bc8-d6b2-46fe-b9c2-72f5d02f6c1d",
   "metadata": {},
   "outputs": [],
   "source": [
    "students = students.with_columns(\"First Name\", make_array(\"Cedric\", \"Ashley\", \"Alexis\", \"Lucy\", \"Devon\"))\n",
    "students"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3e6ede5c-46c9-4c35-ba72-33c6bf8c93b4",
   "metadata": {},
   "outputs": [],
   "source": [
    "students = students.with_columns(\n",
    "    \"Last Name\", make_array(\"Jefferson\", \"Juric\", \"Lameres\", \"Lewis\", \"Maurer\"),\n",
    "    \"Major Code\", make_array(\"CSPR\", \"NDGR\", \"CSBA\", \"CSPR\", \"CSPR\"),\n",
    "    \"Age\", make_array(21, 25, 20, 22, 20))\n",
    "students"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f25b3fdb-3dfd-4599-8006-e2344ce3bec4",
   "metadata": {},
   "outputs": [],
   "source": [
    "students.column(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c01a697c-d3f7-434d-9ba2-cf4a1c139171",
   "metadata": {},
   "outputs": [],
   "source": [
    "students.column(\"Major Code\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a8b275c7-38b6-470f-a65f-3f8de8d106b6",
   "metadata": {},
   "outputs": [],
   "source": [
    "students.column(\"Last Name\").item(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cb20ff11-e882-458e-95c9-508546012d9f",
   "metadata": {},
   "outputs": [],
   "source": [
    "students.select(\"Last Name\", \"Major Code\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d5a93926-a162-426a-bc85-ef31c03be6b5",
   "metadata": {},
   "outputs": [],
   "source": [
    "students.drop(\"First Name\", \"Age\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5fb5c7e6-ebf8-416f-8e84-3f471cc0295a",
   "metadata": {},
   "outputs": [],
   "source": [
    "students.sort(\"First Name\").show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eb6a997f-5fe7-4738-aff9-aed45c030e7b",
   "metadata": {},
   "outputs": [],
   "source": [
    "students"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a29ca197-a603-4c66-a0fe-ffcb1199aee8",
   "metadata": {},
   "outputs": [],
   "source": [
    "alphabetically_last = students.sort(\"First Name\", descending=True).column(\"First Name\").item(0)\n",
    "alphabetically_last"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "765c8a2d-0ac3-408e-b28e-b80528e19a8b",
   "metadata": {},
   "outputs": [],
   "source": [
    "students = students.with_column(\"Age\", students.column(\"Age\") + 1)\n",
    "students"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "99939509-cd7c-415c-8115-48ecc9b45d51",
   "metadata": {},
   "outputs": [],
   "source": [
    "tutor_age = 23\n",
    "students = students.with_column(\"Age Percentage\", students.column(\"Age\") / tutor_age).set_format(\"Age Percentage\", PercentFormatter)\n",
    "students"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ce5cf28f-a4da-4d7c-bd3c-8f2223feae4f",
   "metadata": {},
   "outputs": [],
   "source": [
    "help(students.sort)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "49bbd135-a3d5-43d9-8526-ee487d42c065",
   "metadata": {},
   "outputs": [],
   "source": [
    "students.take(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "839080ee-6534-43a2-8cb8-eeb86e59bd8a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "students.take(np.arange(0, students.num_rows, 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "68700cec-9bf2-40fc-b7ad-e72bed524f72",
   "metadata": {},
   "outputs": [],
   "source": [
    "students.where(\"Major Code\", are.equal_to(\"CSPR\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ebf8f1ef-7976-4977-aeb1-904c3b1430c8",
   "metadata": {},
   "outputs": [],
   "source": [
    "students.where(\"Major Code\", \"CSPR\").sort(\"Age\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ce795821-e27b-48eb-a1ba-d5ba46a00bdc",
   "metadata": {},
   "outputs": [],
   "source": [
    "students.where(\"Major Code\", \"CSPR\").where(\"Age\", are.above(21))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4f44adae-fc69-454a-9731-cfd8fcad1a5b",
   "metadata": {},
   "source": [
    "## Predicates: \n",
    "- are.equal_to (also are.not_equal_to)\n",
    "- are.above\n",
    "- are.above_or_equal_to\n",
    "- are.below\n",
    "- are.below_or_equal_to\n",
    "- are.between\n",
    "- are.strictly_between\n",
    "- are.between_or_equal_to\n",
    "- are_containing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b3d474a5-6684-4d8d-85d4-d92d6e6a484b",
   "metadata": {},
   "outputs": [],
   "source": [
    "students.where(\"Major Code\", are.containing(\"CS\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7b959290-d276-4065-a1da-71e33f27aec0",
   "metadata": {},
   "source": [
    "## Actors Table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a944bad6-02c4-4e8f-9e01-ad58b3a8a500",
   "metadata": {},
   "outputs": [],
   "source": [
    "actors = Table.read_table(\"actors.csv\")\n",
    "actors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bfbff5ff-5450-4c18-b8d7-27d48ff9c330",
   "metadata": {},
   "outputs": [],
   "source": [
    "actors.show(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ce587285-8cf2-49df-83a7-014e241e2179",
   "metadata": {},
   "outputs": [],
   "source": [
    "actors.num_columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "db2d1c1d-26f6-46eb-8fac-214f9fa69163",
   "metadata": {},
   "outputs": [],
   "source": [
    "actors.num_rows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "baf6aecd-f0eb-40bd-9d2f-585a2f784b39",
   "metadata": {},
   "outputs": [],
   "source": [
    "actors.labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e79c939c-e8aa-4cbd-9ccb-3b4b11683fdb",
   "metadata": {},
   "outputs": [],
   "source": [
    "actors = actors.relabeled(\"#1 Movie\", \"Highest Grossing\")\n",
    "actors"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1b27cb11-1159-48b1-9a44-64bbaecf597e",
   "metadata": {},
   "source": [
    "## Active Learning - Use the Actors Table for these questions"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d38bbe05-093d-48db-b222-5bfe8164fd97",
   "metadata": {},
   "source": [
    "1. Print the name of the actor who has been in the most movies, as well as the number of movies.\n",
    "2. Add a column named \"Movie Percentage\" that shows the percentage of movies each actor has been in, relative to the actor in #1.  Format this column and sort it from highest to lowest."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.13.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}