convert iris species to numbers

convert iris species to numbers.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "using DataFrames, CSV\niris_csv = joinpath(dirname(pathof(DataFrames)), \"..\", \"docs\", \"src\", \"assets\", \"iris.csv\")",
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 1,
          "data": {
            "text/plain": "\"C:\\\\Users\\\\genkuroki\\\\.julia\\\\packages\\\\DataFrames\\\\nxjiD\\\\src\\\\..\\\\docs\\\\src\\\\assets\\\\iris.csv\""
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "iris = CSV.read(iris_csv, DataFrame)\nfirst(iris, 5)",
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 2,
          "data": {
            "text/plain": "\u001b[1m5×5 DataFrame\u001b[0m\n\u001b[1m Row \u001b[0m│\u001b[1m SepalLength \u001b[0m\u001b[1m SepalWidth \u001b[0m\u001b[1m PetalLength \u001b[0m\u001b[1m PetalWidth \u001b[0m\u001b[1m Species     \u001b[0m\n\u001b[1m     \u001b[0m│\u001b[90m Float64     \u001b[0m\u001b[90m Float64    \u001b[0m\u001b[90m Float64     \u001b[0m\u001b[90m Float64    \u001b[0m\u001b[90m String      \u001b[0m\n─────┼───────────────────────────────────────────────────────────────\n   1 │         5.1         3.5          1.4         0.2  Iris-setosa\n   2 │         4.9         3.0          1.4         0.2  Iris-setosa\n   3 │         4.7         3.2          1.3         0.2  Iris-setosa\n   4 │         4.6         3.1          1.5         0.2  Iris-setosa\n   5 │         5.0         3.6          1.4         0.2  Iris-setosa",
            "text/html": "<table class=\"data-frame\"><thead><tr><th></th><th>SepalLength</th><th>SepalWidth</th><th>PetalLength</th><th>PetalWidth</th><th>Species</th></tr><tr><th></th><th>Float64</th><th>Float64</th><th>Float64</th><th>Float64</th><th>String</th></tr></thead><tbody><p>5 rows × 5 columns</p><tr><th>1</th><td>5.1</td><td>3.5</td><td>1.4</td><td>0.2</td><td>Iris-setosa</td></tr><tr><th>2</th><td>4.9</td><td>3.0</td><td>1.4</td><td>0.2</td><td>Iris-setosa</td></tr><tr><th>3</th><td>4.7</td><td>3.2</td><td>1.3</td><td>0.2</td><td>Iris-setosa</td></tr><tr><th>4</th><td>4.6</td><td>3.1</td><td>1.5</td><td>0.2</td><td>Iris-setosa</td></tr><tr><th>5</th><td>5.0</td><td>3.6</td><td>1.4</td><td>0.2</td><td>Iris-setosa</td></tr></tbody></table>",
            "text/latex": "\\begin{tabular}{r|ccccc}\n\t& SepalLength & SepalWidth & PetalLength & PetalWidth & Species\\\\\n\t\\hline\n\t& Float64 & Float64 & Float64 & Float64 & String\\\\\n\t\\hline\n\t1 & 5.1 & 3.5 & 1.4 & 0.2 & Iris-setosa \\\\\n\t2 & 4.9 & 3.0 & 1.4 & 0.2 & Iris-setosa \\\\\n\t3 & 4.7 & 3.2 & 1.3 & 0.2 & Iris-setosa \\\\\n\t4 & 4.6 & 3.1 & 1.5 & 0.2 & Iris-setosa \\\\\n\t5 & 5.0 & 3.6 & 1.4 & 0.2 & Iris-setosa \\\\\n\\end{tabular}\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "vec_species = unique(iris.Species)",
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 3,
          "data": {
            "text/plain": "3-element Vector{String}:\n \"Iris-setosa\"\n \"Iris-versicolor\"\n \"Iris-virginica\""
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "dict_species = Dict((v => k for (k, v) in enumerate(vec_species)))",
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 4,
          "data": {
            "text/plain": "Dict{String, Int64} with 3 entries:\n  \"Iris-virginica\"  => 3\n  \"Iris-setosa\"     => 1\n  \"Iris-versicolor\" => 2"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "num_species = (v -> dict_species[v]).(iris.Species)\nfirst(num_species, 5)",
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 5,
          "data": {
            "text/plain": "5-element Vector{Int64}:\n 1\n 1\n 1\n 1\n 1"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "(k -> vec_species[k]).(num_species) == iris.Species",
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 6,
          "data": {
            "text/plain": "true"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df = copy(iris)\ndf.NumSpecies = num_species\nfirst(df, 5)",
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 7,
          "data": {
            "text/plain": "\u001b[1m5×6 DataFrame\u001b[0m\n\u001b[1m Row \u001b[0m│\u001b[1m SepalLength \u001b[0m\u001b[1m SepalWidth \u001b[0m\u001b[1m PetalLength \u001b[0m\u001b[1m PetalWidth \u001b[0m\u001b[1m Species     \u001b[0m\u001b[1m NumSpeci\u001b[0m ⋯\n\u001b[1m     \u001b[0m│\u001b[90m Float64     \u001b[0m\u001b[90m Float64    \u001b[0m\u001b[90m Float64     \u001b[0m\u001b[90m Float64    \u001b[0m\u001b[90m String      \u001b[0m\u001b[90m Int64   \u001b[0m ⋯\n─────┼──────────────────────────────────────────────────────────────────────────\n   1 │         5.1         3.5          1.4         0.2  Iris-setosa           ⋯\n   2 │         4.9         3.0          1.4         0.2  Iris-setosa\n   3 │         4.7         3.2          1.3         0.2  Iris-setosa\n   4 │         4.6         3.1          1.5         0.2  Iris-setosa\n   5 │         5.0         3.6          1.4         0.2  Iris-setosa           ⋯\n\u001b[36m                                                                1 column omitted\u001b[0m",
            "text/html": "<table class=\"data-frame\"><thead><tr><th></th><th>SepalLength</th><th>SepalWidth</th><th>PetalLength</th><th>PetalWidth</th><th>Species</th><th>NumSpecies</th></tr><tr><th></th><th>Float64</th><th>Float64</th><th>Float64</th><th>Float64</th><th>String</th><th>Int64</th></tr></thead><tbody><p>5 rows × 6 columns</p><tr><th>1</th><td>5.1</td><td>3.5</td><td>1.4</td><td>0.2</td><td>Iris-setosa</td><td>1</td></tr><tr><th>2</th><td>4.9</td><td>3.0</td><td>1.4</td><td>0.2</td><td>Iris-setosa</td><td>1</td></tr><tr><th>3</th><td>4.7</td><td>3.2</td><td>1.3</td><td>0.2</td><td>Iris-setosa</td><td>1</td></tr><tr><th>4</th><td>4.6</td><td>3.1</td><td>1.5</td><td>0.2</td><td>Iris-setosa</td><td>1</td></tr><tr><th>5</th><td>5.0</td><td>3.6</td><td>1.4</td><td>0.2</td><td>Iris-setosa</td><td>1</td></tr></tbody></table>",
            "text/latex": "\\begin{tabular}{r|cccccc}\n\t& SepalLength & SepalWidth & PetalLength & PetalWidth & Species & NumSpecies\\\\\n\t\\hline\n\t& Float64 & Float64 & Float64 & Float64 & String & Int64\\\\\n\t\\hline\n\t1 & 5.1 & 3.5 & 1.4 & 0.2 & Iris-setosa & 1 \\\\\n\t2 & 4.9 & 3.0 & 1.4 & 0.2 & Iris-setosa & 1 \\\\\n\t3 & 4.7 & 3.2 & 1.3 & 0.2 & Iris-setosa & 1 \\\\\n\t4 & 4.6 & 3.1 & 1.5 & 0.2 & Iris-setosa & 1 \\\\\n\t5 & 5.0 & 3.6 & 1.4 & 0.2 & Iris-setosa & 1 \\\\\n\\end{tabular}\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df2 = copy(iris)\ndf2.Species = num_species\nfirst(df2, 5)",
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 8,
          "data": {
            "text/plain": "\u001b[1m5×5 DataFrame\u001b[0m\n\u001b[1m Row \u001b[0m│\u001b[1m SepalLength \u001b[0m\u001b[1m SepalWidth \u001b[0m\u001b[1m PetalLength \u001b[0m\u001b[1m PetalWidth \u001b[0m\u001b[1m Species \u001b[0m\n\u001b[1m     \u001b[0m│\u001b[90m Float64     \u001b[0m\u001b[90m Float64    \u001b[0m\u001b[90m Float64     \u001b[0m\u001b[90m Float64    \u001b[0m\u001b[90m Int64   \u001b[0m\n─────┼───────────────────────────────────────────────────────────\n   1 │         5.1         3.5          1.4         0.2        1\n   2 │         4.9         3.0          1.4         0.2        1\n   3 │         4.7         3.2          1.3         0.2        1\n   4 │         4.6         3.1          1.5         0.2        1\n   5 │         5.0         3.6          1.4         0.2        1",
            "text/html": "<table class=\"data-frame\"><thead><tr><th></th><th>SepalLength</th><th>SepalWidth</th><th>PetalLength</th><th>PetalWidth</th><th>Species</th></tr><tr><th></th><th>Float64</th><th>Float64</th><th>Float64</th><th>Float64</th><th>Int64</th></tr></thead><tbody><p>5 rows × 5 columns</p><tr><th>1</th><td>5.1</td><td>3.5</td><td>1.4</td><td>0.2</td><td>1</td></tr><tr><th>2</th><td>4.9</td><td>3.0</td><td>1.4</td><td>0.2</td><td>1</td></tr><tr><th>3</th><td>4.7</td><td>3.2</td><td>1.3</td><td>0.2</td><td>1</td></tr><tr><th>4</th><td>4.6</td><td>3.1</td><td>1.5</td><td>0.2</td><td>1</td></tr><tr><th>5</th><td>5.0</td><td>3.6</td><td>1.4</td><td>0.2</td><td>1</td></tr></tbody></table>",
            "text/latex": "\\begin{tabular}{r|ccccc}\n\t& SepalLength & SepalWidth & PetalLength & PetalWidth & Species\\\\\n\t\\hline\n\t& Float64 & Float64 & Float64 & Float64 & Int64\\\\\n\t\\hline\n\t1 & 5.1 & 3.5 & 1.4 & 0.2 & 1 \\\\\n\t2 & 4.9 & 3.0 & 1.4 & 0.2 & 1 \\\\\n\t3 & 4.7 & 3.2 & 1.3 & 0.2 & 1 \\\\\n\t4 & 4.6 & 3.1 & 1.5 & 0.2 & 1 \\\\\n\t5 & 5.0 & 3.6 & 1.4 & 0.2 & 1 \\\\\n\\end{tabular}\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df3 = copy(iris)\ndf3.Species = float(num_species)\nfirst(df3, 5)",
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 9,
          "data": {
            "text/plain": "\u001b[1m5×5 DataFrame\u001b[0m\n\u001b[1m Row \u001b[0m│\u001b[1m SepalLength \u001b[0m\u001b[1m SepalWidth \u001b[0m\u001b[1m PetalLength \u001b[0m\u001b[1m PetalWidth \u001b[0m\u001b[1m Species \u001b[0m\n\u001b[1m     \u001b[0m│\u001b[90m Float64     \u001b[0m\u001b[90m Float64    \u001b[0m\u001b[90m Float64     \u001b[0m\u001b[90m Float64    \u001b[0m\u001b[90m Float64 \u001b[0m\n─────┼───────────────────────────────────────────────────────────\n   1 │         5.1         3.5          1.4         0.2      1.0\n   2 │         4.9         3.0          1.4         0.2      1.0\n   3 │         4.7         3.2          1.3         0.2      1.0\n   4 │         4.6         3.1          1.5         0.2      1.0\n   5 │         5.0         3.6          1.4         0.2      1.0",
            "text/html": "<table class=\"data-frame\"><thead><tr><th></th><th>SepalLength</th><th>SepalWidth</th><th>PetalLength</th><th>PetalWidth</th><th>Species</th></tr><tr><th></th><th>Float64</th><th>Float64</th><th>Float64</th><th>Float64</th><th>Float64</th></tr></thead><tbody><p>5 rows × 5 columns</p><tr><th>1</th><td>5.1</td><td>3.5</td><td>1.4</td><td>0.2</td><td>1.0</td></tr><tr><th>2</th><td>4.9</td><td>3.0</td><td>1.4</td><td>0.2</td><td>1.0</td></tr><tr><th>3</th><td>4.7</td><td>3.2</td><td>1.3</td><td>0.2</td><td>1.0</td></tr><tr><th>4</th><td>4.6</td><td>3.1</td><td>1.5</td><td>0.2</td><td>1.0</td></tr><tr><th>5</th><td>5.0</td><td>3.6</td><td>1.4</td><td>0.2</td><td>1.0</td></tr></tbody></table>",
            "text/latex": "\\begin{tabular}{r|ccccc}\n\t& SepalLength & SepalWidth & PetalLength & PetalWidth & Species\\\\\n\t\\hline\n\t& Float64 & Float64 & Float64 & Float64 & Float64\\\\\n\t\\hline\n\t1 & 5.1 & 3.5 & 1.4 & 0.2 & 1.0 \\\\\n\t2 & 4.9 & 3.0 & 1.4 & 0.2 & 1.0 \\\\\n\t3 & 4.7 & 3.2 & 1.3 & 0.2 & 1.0 \\\\\n\t4 & 4.6 & 3.1 & 1.5 & 0.2 & 1.0 \\\\\n\t5 & 5.0 & 3.6 & 1.4 & 0.2 & 1.0 \\\\\n\\end{tabular}\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "julia-1.7-depwarn-o3",
      "display_name": "Julia 1.7.0-DEV depwarn -O3",
      "language": "julia"
    },
    "toc": {
      "nav_menu": {},
      "number_sections": true,
      "sideBar": true,
      "skip_h1_title": false,
      "base_numbering": 1,
      "title_cell": "Table of Contents",
      "title_sidebar": "Contents",
      "toc_cell": false,
      "toc_position": {},
      "toc_section_display": true,
      "toc_window_display": false
    },
    "language_info": {
      "file_extension": ".jl",
      "name": "julia",
      "mimetype": "application/julia",
      "version": "1.7.0"
    },
    "@webio": {
      "lastKernelId": null,
      "lastCommId": null
    },
    "gist": {
      "id": "40efed65a6d5639ff6aca2419a8d947d",
      "data": {
        "description": "convert iris species to numbers",
        "public": true
      }
    },
    "_draft": {
      "nbviewer_url": "https://gist.github.com/40efed65a6d5639ff6aca2419a8d947d"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}