Mushroom_predict.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "0e7eb2c3-e624-23c6-790a-27f89454c85a"
   },
   "source": [
    "# Comparing machine learning algorithms on predicting edible/poisonous mushrooms\n",
    "\n",
    "## Let's start with our imports!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "_cell_guid": "2f6f923e-6216-f053-3030-96635dc3bc22"
   },
   "outputs": [],
   "source": [
    "# Imports\n",
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "from matplotlib import pyplot as plt\n",
    "import seaborn as sns\n",
    "from sklearn import preprocessing\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.metrics import confusion_matrix, classification_report, accuracy_score\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "_cell_guid": "a452e740-1437-c657-d7e1-4df7742802bf"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>class</th>\n",
       "      <th>cap-shape</th>\n",
       "      <th>cap-surface</th>\n",
       "      <th>cap-color</th>\n",
       "      <th>bruises</th>\n",
       "      <th>odor</th>\n",
       "      <th>gill-attachment</th>\n",
       "      <th>gill-spacing</th>\n",
       "      <th>gill-size</th>\n",
       "      <th>gill-color</th>\n",
       "      <th>...</th>\n",
       "      <th>stalk-surface-below-ring</th>\n",
       "      <th>stalk-color-above-ring</th>\n",
       "      <th>stalk-color-below-ring</th>\n",
       "      <th>veil-type</th>\n",
       "      <th>veil-color</th>\n",
       "      <th>ring-number</th>\n",
       "      <th>ring-type</th>\n",
       "      <th>spore-print-color</th>\n",
       "      <th>population</th>\n",
       "      <th>habitat</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>p</td>\n",
       "      <td>x</td>\n",
       "      <td>s</td>\n",
       "      <td>n</td>\n",
       "      <td>t</td>\n",
       "      <td>p</td>\n",
       "      <td>f</td>\n",
       "      <td>c</td>\n",
       "      <td>n</td>\n",
       "      <td>k</td>\n",
       "      <td>...</td>\n",
       "      <td>s</td>\n",
       "      <td>w</td>\n",
       "      <td>w</td>\n",
       "      <td>p</td>\n",
       "      <td>w</td>\n",
       "      <td>o</td>\n",
       "      <td>p</td>\n",
       "      <td>k</td>\n",
       "      <td>s</td>\n",
       "      <td>u</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>e</td>\n",
       "      <td>x</td>\n",
       "      <td>s</td>\n",
       "      <td>y</td>\n",
       "      <td>t</td>\n",
       "      <td>a</td>\n",
       "      <td>f</td>\n",
       "      <td>c</td>\n",
       "      <td>b</td>\n",
       "      <td>k</td>\n",
       "      <td>...</td>\n",
       "      <td>s</td>\n",
       "      <td>w</td>\n",
       "      <td>w</td>\n",
       "      <td>p</td>\n",
       "      <td>w</td>\n",
       "      <td>o</td>\n",
       "      <td>p</td>\n",
       "      <td>n</td>\n",
       "      <td>n</td>\n",
       "      <td>g</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>e</td>\n",
       "      <td>b</td>\n",
       "      <td>s</td>\n",
       "      <td>w</td>\n",
       "      <td>t</td>\n",
       "      <td>l</td>\n",
       "      <td>f</td>\n",
       "      <td>c</td>\n",
       "      <td>b</td>\n",
       "      <td>n</td>\n",
       "      <td>...</td>\n",
       "      <td>s</td>\n",
       "      <td>w</td>\n",
       "      <td>w</td>\n",
       "      <td>p</td>\n",
       "      <td>w</td>\n",
       "      <td>o</td>\n",
       "      <td>p</td>\n",
       "      <td>n</td>\n",
       "      <td>n</td>\n",
       "      <td>m</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>p</td>\n",
       "      <td>x</td>\n",
       "      <td>y</td>\n",
       "      <td>w</td>\n",
       "      <td>t</td>\n",
       "      <td>p</td>\n",
       "      <td>f</td>\n",
       "      <td>c</td>\n",
       "      <td>n</td>\n",
       "      <td>n</td>\n",
       "      <td>...</td>\n",
       "      <td>s</td>\n",
       "      <td>w</td>\n",
       "      <td>w</td>\n",
       "      <td>p</td>\n",
       "      <td>w</td>\n",
       "      <td>o</td>\n",
       "      <td>p</td>\n",
       "      <td>k</td>\n",
       "      <td>s</td>\n",
       "      <td>u</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>e</td>\n",
       "      <td>x</td>\n",
       "      <td>s</td>\n",
       "      <td>g</td>\n",
       "      <td>f</td>\n",
       "      <td>n</td>\n",
       "      <td>f</td>\n",
       "      <td>w</td>\n",
       "      <td>b</td>\n",
       "      <td>k</td>\n",
       "      <td>...</td>\n",
       "      <td>s</td>\n",
       "      <td>w</td>\n",
       "      <td>w</td>\n",
       "      <td>p</td>\n",
       "      <td>w</td>\n",
       "      <td>o</td>\n",
       "      <td>e</td>\n",
       "      <td>n</td>\n",
       "      <td>a</td>\n",
       "      <td>g</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  class cap-shape cap-surface cap-color bruises odor gill-attachment  \\\n",
       "0     p         x           s         n       t    p               f   \n",
       "1     e         x           s         y       t    a               f   \n",
       "2     e         b           s         w       t    l               f   \n",
       "3     p         x           y         w       t    p               f   \n",
       "4     e         x           s         g       f    n               f   \n",
       "\n",
       "  gill-spacing gill-size gill-color   ...   stalk-surface-below-ring  \\\n",
       "0            c         n          k   ...                          s   \n",
       "1            c         b          k   ...                          s   \n",
       "2            c         b          n   ...                          s   \n",
       "3            c         n          n   ...                          s   \n",
       "4            w         b          k   ...                          s   \n",
       "\n",
       "  stalk-color-above-ring stalk-color-below-ring veil-type veil-color  \\\n",
       "0                      w                      w         p          w   \n",
       "1                      w                      w         p          w   \n",
       "2                      w                      w         p          w   \n",
       "3                      w                      w         p          w   \n",
       "4                      w                      w         p          w   \n",
       "\n",
       "  ring-number ring-type spore-print-color population habitat  \n",
       "0           o         p                 k          s       u  \n",
       "1           o         p                 n          n       g  \n",
       "2           o         p                 n          n       m  \n",
       "3           o         p                 k          s       u  \n",
       "4           o         e                 n          a       g  \n",
       "\n",
       "[5 rows x 23 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's import the data and start exploring it\n",
    "data = pd.read_csv('../input/mushrooms.csv')\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "_cell_guid": "ce042608-63f7-643b-03ca-0d6f1f51bfc8"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 8124 entries, 0 to 8123\n",
      "Data columns (total 23 columns):\n",
      "class                       8124 non-null object\n",
      "cap-shape                   8124 non-null object\n",
      "cap-surface                 8124 non-null object\n",
      "cap-color                   8124 non-null object\n",
      "bruises                     8124 non-null object\n",
      "odor                        8124 non-null object\n",
      "gill-attachment             8124 non-null object\n",
      "gill-spacing                8124 non-null object\n",
      "gill-size                   8124 non-null object\n",
      "gill-color                  8124 non-null object\n",
      "stalk-shape                 8124 non-null object\n",
      "stalk-root                  8124 non-null object\n",
      "stalk-surface-above-ring    8124 non-null object\n",
      "stalk-surface-below-ring    8124 non-null object\n",
      "stalk-color-above-ring      8124 non-null object\n",
      "stalk-color-below-ring      8124 non-null object\n",
      "veil-type                   8124 non-null object\n",
      "veil-color                  8124 non-null object\n",
      "ring-number                 8124 non-null object\n",
      "ring-type                   8124 non-null object\n",
      "spore-print-color           8124 non-null object\n",
      "population                  8124 non-null object\n",
      "habitat                     8124 non-null object\n",
      "dtypes: object(23)\n",
      "memory usage: 1.4+ MB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "_cell_guid": "c0966bc9-2244-d8be-a3da-a772ba8ac9d7"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>class</th>\n",
       "      <th>cap-shape</th>\n",
       "      <th>cap-surface</th>\n",
       "      <th>cap-color</th>\n",
       "      <th>bruises</th>\n",
       "      <th>odor</th>\n",
       "      <th>gill-attachment</th>\n",
       "      <th>gill-spacing</th>\n",
       "      <th>gill-size</th>\n",
       "      <th>gill-color</th>\n",
       "      <th>...</th>\n",
       "      <th>stalk-surface-below-ring</th>\n",
       "      <th>stalk-color-above-ring</th>\n",
       "      <th>stalk-color-below-ring</th>\n",
       "      <th>veil-type</th>\n",
       "      <th>veil-color</th>\n",
       "      <th>ring-number</th>\n",
       "      <th>ring-type</th>\n",
       "      <th>spore-print-color</th>\n",
       "      <th>population</th>\n",
       "      <th>habitat</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>...</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "      <td>8124</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>12</td>\n",
       "      <td>...</td>\n",
       "      <td>4</td>\n",
       "      <td>9</td>\n",
       "      <td>9</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>e</td>\n",
       "      <td>x</td>\n",
       "      <td>y</td>\n",
       "      <td>n</td>\n",
       "      <td>f</td>\n",
       "      <td>n</td>\n",
       "      <td>f</td>\n",
       "      <td>c</td>\n",
       "      <td>b</td>\n",
       "      <td>b</td>\n",
       "      <td>...</td>\n",
       "      <td>s</td>\n",
       "      <td>w</td>\n",
       "      <td>w</td>\n",
       "      <td>p</td>\n",
       "      <td>w</td>\n",
       "      <td>o</td>\n",
       "      <td>p</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>4208</td>\n",
       "      <td>3656</td>\n",
       "      <td>3244</td>\n",
       "      <td>2284</td>\n",
       "      <td>4748</td>\n",
       "      <td>3528</td>\n",
       "      <td>7914</td>\n",
       "      <td>6812</td>\n",
       "      <td>5612</td>\n",
       "      <td>1728</td>\n",
       "      <td>...</td>\n",
       "      <td>4936</td>\n",
       "      <td>4464</td>\n",
       "      <td>4384</td>\n",
       "      <td>8124</td>\n",
       "      <td>7924</td>\n",
       "      <td>7488</td>\n",
       "      <td>3968</td>\n",
       "      <td>2388</td>\n",
       "      <td>4040</td>\n",
       "      <td>3148</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       class cap-shape cap-surface cap-color bruises  odor gill-attachment  \\\n",
       "count   8124      8124        8124      8124    8124  8124            8124   \n",
       "unique     2         6           4        10       2     9               2   \n",
       "top        e         x           y         n       f     n               f   \n",
       "freq    4208      3656        3244      2284    4748  3528            7914   \n",
       "\n",
       "       gill-spacing gill-size gill-color   ...   stalk-surface-below-ring  \\\n",
       "count          8124      8124       8124   ...                       8124   \n",
       "unique            2         2         12   ...                          4   \n",
       "top               c         b          b   ...                          s   \n",
       "freq           6812      5612       1728   ...                       4936   \n",
       "\n",
       "       stalk-color-above-ring stalk-color-below-ring veil-type veil-color  \\\n",
       "count                    8124                   8124      8124       8124   \n",
       "unique                      9                      9         1          4   \n",
       "top                         w                      w         p          w   \n",
       "freq                     4464                   4384      8124       7924   \n",
       "\n",
       "       ring-number ring-type spore-print-color population habitat  \n",
       "count         8124      8124              8124       8124    8124  \n",
       "unique           3         5                 9          6       7  \n",
       "top              o         p                 w          v       d  \n",
       "freq          7488      3968              2388       4040    3148  \n",
       "\n",
       "[4 rows x 23 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "22e61fbf-b376-2e8d-54c0-7e23d762d2b9"
   },
   "source": [
    "It becomes clear that we are dealing with all categorical variables here.\n",
    "We can use sci-kit learn's Label Encoder to deal with these categorical variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "_cell_guid": "b9061cc5-dbd6-bd75-01bd-7727a999b974"
   },
   "outputs": [],
   "source": [
    "labelEncoder = preprocessing.LabelEncoder()\n",
    "for col in data.columns:\n",
    "    data[col] = labelEncoder.fit_transform(data[col])\n",
    "    \n",
    "# Train Test Split\n",
    "X = data.drop('class', axis=1)\n",
    "y = data['class']\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=101)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "b6f9446d-9da7-921d-9ac0-12e31f6ff8a2"
   },
   "source": [
    "Time to compare some Machine Learning models\n",
    "We use a for loop to loop throuh the different models. The empty lists are made to create \n",
    "the overview table at the end."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "_cell_guid": "bff1e945-9583-c4f5-c324-b546f5282cb9"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Results for: Logistic Regression\n",
      "\n",
      "[[1217   57]\n",
      " [  73 1091]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          0       0.94      0.96      0.95      1274\n",
      "          1       0.95      0.94      0.94      1164\n",
      "\n",
      "avg / total       0.95      0.95      0.95      2438\n",
      "\n",
      "0.946677604594\n",
      "\n",
      "\n",
      "\n",
      "Results for: Decision Tree\n",
      "\n",
      "[[1274    0]\n",
      " [   0 1164]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          0       1.00      1.00      1.00      1274\n",
      "          1       1.00      1.00      1.00      1164\n",
      "\n",
      "avg / total       1.00      1.00      1.00      2438\n",
      "\n",
      "1.0\n",
      "\n",
      "\n",
      "\n",
      "Results for: Random Forest\n",
      "\n",
      "[[1274    0]\n",
      " [   0 1164]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          0       1.00      1.00      1.00      1274\n",
      "          1       1.00      1.00      1.00      1164\n",
      "\n",
      "avg / total       1.00      1.00      1.00      2438\n",
      "\n",
      "1.0\n",
      "\n",
      "\n",
      "\n",
      "Results for: K-Nearest Neighbors\n",
      "\n",
      "[[1273    1]\n",
      " [   1 1163]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          0       1.00      1.00      1.00      1274\n",
      "          1       1.00      1.00      1.00      1164\n",
      "\n",
      "avg / total       1.00      1.00      1.00      2438\n",
      "\n",
      "0.999179655455\n",
      "\n",
      "\n",
      "\n",
      "Results for: Linear SVM\n",
      "\n",
      "[[1274    0]\n",
      " [   0 1164]]\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          0       1.00      1.00      1.00      1274\n",
      "          1       1.00      1.00      1.00      1164\n",
      "\n",
      "avg / total       1.00      1.00      1.00      2438\n",
      "\n",
      "1.0\n",
      "\n",
      "\n",
      "\n",
      "   accuracy score                model\n",
      "0        0.946678  Logistic Regression\n",
      "1        1.000000        Decision Tree\n",
      "2        1.000000        Random Forest\n",
      "3        0.999180  K-Nearest Neighbors\n",
      "4        1.000000           Linear SVM\n"
     ]
    }
   ],
   "source": [
    "keys = []\n",
    "scores = []\n",
    "models = {'Logistic Regression': LogisticRegression(), 'Decision Tree': DecisionTreeClassifier(),\n",
    "          'Random Forest': RandomForestClassifier(n_estimators=30), \n",
    "          'K-Nearest Neighbors':KNeighborsClassifier(n_neighbors=1),\n",
    "            'Linear SVM':SVC(kernel='rbf', gamma=.10, C=1.0)}\n",
    "\n",
    "for k,v in models.items():\n",
    "    mod = v\n",
    "    mod.fit(X_train, y_train)\n",
    "    pred = mod.predict(X_test)\n",
    "    print('Results for: ' + str(k) + '\\n')\n",
    "    print(confusion_matrix(y_test, pred))\n",
    "    print(classification_report(y_test, pred))\n",
    "    acc = accuracy_score(y_test, pred)\n",
    "    print(acc)\n",
    "    print('\\n' + '\\n')\n",
    "    keys.append(k)\n",
    "    scores.append(acc)\n",
    "    table = pd.DataFrame({'model':keys, 'accuracy score':scores})\n",
    "\n",
    "print(table)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "286ef9c8-31f9-cded-fead-472ba89dad0c"
   },
   "source": [
    "Logistic Regression clearly performs the poorest of our algorithms. The k-NN classifier comes extremely close to 100% accuracy. The tree-based methods and the linear SVM all achieve 100% accuracy. It looks like these machine learning algorithms have little trouble with this dataset. Let's explore the important features in predicting poisonous mushrooms next."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "_cell_guid": "7394532e-adb2-6e32-be93-5ec027fa290b"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAFZCAYAAABjZm+4AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ncngAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7ff827099c88>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Re-training the Random Forest\n",
    "rfc = RandomForestClassifier(n_estimators = 30)\n",
    "rfc.fit(X_train, y_train)\n",
    "pred_rfc = rfc.predict(X_test)\n",
    "\n",
    "importances = rfc.feature_importances_\n",
    "plot = sns.barplot(x=X.columns, y=importances)\n",
    "\n",
    "for item in plot.get_xticklabels():\n",
    "    item.set_rotation(90)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "c9b2409c-2ab8-0964-df70-9488b4ada7d6"
   },
   "source": [
    "Odor has the highest feature importance in the Random Forest. We can explore the effect of odor on the predicted class a bit further with this next plot."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "_cell_guid": "e05b1150-1a4d-10f7-4800-c3f43068f616"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEGCAYAAAB/+QKOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nK+TjAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7ff83b62ccc0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.countplot(x = 'odor', data = data, hue='class', palette='coolwarm')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_cell_guid": "374e72de-5649-a46a-14b9-c7641aafc14c"
   },
   "source": [
    "From this plot we can see how important odor is in predicting the right classes. Most odor categories are only linked to one outcome class. And for odor #5 almost all mushrooms belong to class 0.\n",
    "This was a very clear dataset where most ML algorithms will not have a problem with."
   ]
  }
 ],
 "metadata": {
  "_change_revision": 51,
  "_is_fork": false,
  "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}