Skip to content

Instantly share code, notes, and snippets.

@executed

executed/lab2_ml.ipynb

Created December 14, 2021 09:57
Show Gist options
  • Save executed/80bd8ad250e460dc07eb8caeed8d4d16 to your computer and use it in GitHub Desktop.
Save executed/80bd8ad250e460dc07eb8caeed8d4d16 to your computer and use it in GitHub Desktop.
Download ZIP
lab2_ML.ipynb
Display the source blob
Display the rendered blob
Raw
lab2_ml.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "lab2_ML.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyPjUzHROzAv1kxW6FzZDrLc",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/executed/80bd8ad250e460dc07eb8caeed8d4d16/lab2_ml.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"source": [
"Importing the Libraries"
],
"metadata": {
"id": "TIugzd00K2sQ"
}
},
{
"cell_type": "code",
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import pandas as pd\n",
"from sklearn.metrics import confusion_matrix\n",
"from sklearn.metrics import accuracy_score \n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.naive_bayes import GaussianNB\n",
"from sklearn.preprocessing import StandardScaler"
],
"metadata": {
"id": "ZybPdN33K1BC"
},
"execution_count": 33,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Naive Bayes Classification on Iris dataset"
],
"metadata": {
"id": "JCnY0xK0KrvL"
}
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "D_44JWCSKjYL",
"outputId": "cb50981f-0493-47ab-9356-e8ff0d70e4d1"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>sepal_length</th>\n",
" <th>sepal_width</th>\n",
" <th>petal_length</th>\n",
" <th>petal_width</th>\n",
" <th>species</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5.0</td>\n",
" <td>3.6</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" sepal_length sepal_width petal_length petal_width species\n",
"0 5.1 3.5 1.4 0.2 setosa\n",
"1 4.9 3.0 1.4 0.2 setosa\n",
"2 4.7 3.2 1.3 0.2 setosa\n",
"3 4.6 3.1 1.5 0.2 setosa\n",
"4 5.0 3.6 1.4 0.2 setosa"
]
},
"metadata": {},
"execution_count": 34
}
],
"source": [
"dataset = pd.read_csv('https://raw.githubusercontent.com/mk-gurucharan/Classification/master/IrisDataset.csv')\n",
"\n",
"X = dataset.iloc[:,:4].values\n",
"y = dataset['species'].values\n",
"\n",
"dataset.head(5)"
]
},
{
"cell_type": "markdown",
"source": [
"Splitting the dataset into the Training set and Test set"
],
"metadata": {
"id": "p5XnMpc_LAsp"
}
},
{
"cell_type": "code",
"source": [
"\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)"
],
"metadata": {
"id": "ye1gWl5aLCM8"
},
"execution_count": 35,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Feature Scaling"
],
"metadata": {
"id": "cilubRzpLFir"
}
},
{
"cell_type": "code",
"source": [
"\n",
"\n",
"sc = StandardScaler()\n",
"X_train = sc.fit_transform(X_train)\n",
"X_test = sc.transform(X_test)"
],
"metadata": {
"id": "Cej4uIYzLHAU"
},
"execution_count": 36,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Training the Naive Bayes Classification model on the Training Set"
],
"metadata": {
"id": "6LItoI0HLL3q"
}
},
{
"cell_type": "code",
"source": [
"\n",
"\n",
"classifier = GaussianNB()\n",
"classifier.fit(X_train, y_train)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "kKbDSNH3LOLu",
"outputId": "3cd647ea-4d53-4b3b-e4e6-d684e15f70cd"
},
"execution_count": 37,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"GaussianNB()"
]
},
"metadata": {},
"execution_count": 37
}
]
},
{
"cell_type": "markdown",
"source": [
"Predicting the Test set results"
],
"metadata": {
"id": "drasHvdPLQTo"
}
},
{
"cell_type": "code",
"source": [
"y_pred = classifier.predict(X_test) \n",
"y_pred"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "LdFuzce5LSSG",
"outputId": "89d86c70-e1d7-48a1-eca1-3e405a447409"
},
"execution_count": 38,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array(['virginica', 'virginica', 'versicolor', 'setosa', 'versicolor',\n",
" 'versicolor', 'versicolor', 'setosa', 'versicolor', 'virginica',\n",
" 'setosa', 'versicolor', 'versicolor', 'virginica', 'versicolor',\n",
" 'versicolor', 'virginica', 'virginica', 'setosa', 'setosa',\n",
" 'versicolor', 'versicolor', 'setosa', 'virginica', 'virginica',\n",
" 'versicolor', 'setosa', 'setosa', 'versicolor', 'setosa'],\n",
" dtype='<U10')"
]
},
"metadata": {},
"execution_count": 38
}
]
},
{
"cell_type": "markdown",
"source": [
"Confusion Matrix and Accuracy"
],
"metadata": {
"id": "O4qEPDsLLWwh"
}
},
{
"cell_type": "code",
"source": [
"cm = confusion_matrix(y_test, y_pred)\n",
"\n",
"print (\"Accuracy : \", accuracy_score(y_test, y_pred))\n",
"cm"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "POZWELk4LXMI",
"outputId": "81bf9715-3b78-43d1-bb9f-289678f3cdc0"
},
"execution_count": 39,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Accuracy : 0.8666666666666667\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([[ 9, 0, 0],\n",
" [ 0, 11, 2],\n",
" [ 0, 2, 6]])"
]
},
"metadata": {},
"execution_count": 39
}
]
},
{
"cell_type": "markdown",
"source": [
"Comparing the Real Values with Predicted Values"
],
"metadata": {
"id": "nMU65x8jLpgW"
}
},
{
"cell_type": "code",
"source": [
"df = pd.DataFrame({'Real Values':y_test, 'Predicted Values':y_pred})\n",
"df"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 990
},
"id": "AmM4bJS5Lp94",
"outputId": "af6edc49-41bc-42d6-8698-f717f559c7e2"
},
"execution_count": 40,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Real Values</th>\n",
" <th>Predicted Values</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>virginica</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>virginica</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>versicolor</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>setosa</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>virginica</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>versicolor</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>versicolor</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>setosa</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>virginica</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>virginica</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>setosa</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>versicolor</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>versicolor</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>virginica</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>versicolor</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>versicolor</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>virginica</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>versicolor</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>setosa</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>setosa</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>versicolor</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>versicolor</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>setosa</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>virginica</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>versicolor</td>\n",
" <td>virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>versicolor</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>setosa</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>setosa</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>versicolor</td>\n",
" <td>versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>setosa</td>\n",
" <td>setosa</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Real Values Predicted Values\n",
"0 virginica virginica\n",
"1 virginica virginica\n",
"2 versicolor versicolor\n",
"3 setosa setosa\n",
"4 virginica versicolor\n",
"5 versicolor versicolor\n",
"6 versicolor versicolor\n",
"7 setosa setosa\n",
"8 virginica versicolor\n",
"9 virginica virginica\n",
"10 setosa setosa\n",
"11 versicolor versicolor\n",
"12 versicolor versicolor\n",
"13 virginica virginica\n",
"14 versicolor versicolor\n",
"15 versicolor versicolor\n",
"16 virginica virginica\n",
"17 versicolor virginica\n",
"18 setosa setosa\n",
"19 setosa setosa\n",
"20 versicolor versicolor\n",
"21 versicolor versicolor\n",
"22 setosa setosa\n",
"23 virginica virginica\n",
"24 versicolor virginica\n",
"25 versicolor versicolor\n",
"26 setosa setosa\n",
"27 setosa setosa\n",
"28 versicolor versicolor\n",
"29 setosa setosa"
]
},
"metadata": {},
"execution_count": 40
}
]
},
{
"cell_type": "markdown",
"source": [
"# Pima dataset"
],
"metadata": {
"id": "9N6LtQTESUP6"
}
},
{
"cell_type": "code",
"source": [
"dataset = pd.read_csv('https://drive.google.com/uc?id=1aQWzKF2sn8DSy2c9B66C-FFlichp9sv8', header=0)\n",
"\n",
"dataset.head()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "BN1EgOeCSWPY",
"outputId": "eb8c9841-e179-43f2-c4ab-af5902b138e4"
},
"execution_count": 41,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>preg</th>\n",
" <th>plasma</th>\n",
" <th>bpress</th>\n",
" <th>triceps_thick</th>\n",
" <th>insulin</th>\n",
" <th>BMI</th>\n",
" <th>pedigree_fun</th>\n",
" <th>age</th>\n",
" <th>class</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>6</td>\n",
" <td>148</td>\n",
" <td>72</td>\n",
" <td>35</td>\n",
" <td>0</td>\n",
" <td>33.6</td>\n",
" <td>0.627</td>\n",
" <td>50</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>85</td>\n",
" <td>66</td>\n",
" <td>29</td>\n",
" <td>0</td>\n",
" <td>26.6</td>\n",
" <td>0.351</td>\n",
" <td>31</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>8</td>\n",
" <td>183</td>\n",
" <td>64</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>23.3</td>\n",
" <td>0.672</td>\n",
" <td>32</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>89</td>\n",
" <td>66</td>\n",
" <td>23</td>\n",
" <td>94</td>\n",
" <td>28.1</td>\n",
" <td>0.167</td>\n",
" <td>21</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>137</td>\n",
" <td>40</td>\n",
" <td>35</td>\n",
" <td>168</td>\n",
" <td>43.1</td>\n",
" <td>2.288</td>\n",
" <td>33</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" preg plasma bpress triceps_thick insulin BMI pedigree_fun age class\n",
"0 6 148 72 35 0 33.6 0.627 50 1\n",
"1 1 85 66 29 0 26.6 0.351 31 0\n",
"2 8 183 64 0 0 23.3 0.672 32 1\n",
"3 1 89 66 23 94 28.1 0.167 21 0\n",
"4 0 137 40 35 168 43.1 2.288 33 1"
]
},
"metadata": {},
"execution_count": 41
}
]
},
{
"cell_type": "markdown",
"source": [
"Describe data"
],
"metadata": {
"id": "7asDfrIMTzy0"
}
},
{
"cell_type": "code",
"source": [
"dataset.describe()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 300
},
"id": "999s1jhzT1HR",
"outputId": "0ab7f951-9242-47fd-801b-7f873dd81a71"
},
"execution_count": 42,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>preg</th>\n",
" <th>plasma</th>\n",
" <th>bpress</th>\n",
" <th>triceps_thick</th>\n",
" <th>insulin</th>\n",
" <th>BMI</th>\n",
" <th>pedigree_fun</th>\n",
" <th>age</th>\n",
" <th>class</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>768.000000</td>\n",
" <td>768.000000</td>\n",
" <td>768.000000</td>\n",
" <td>768.000000</td>\n",
" <td>768.000000</td>\n",
" <td>768.000000</td>\n",
" <td>768.000000</td>\n",
" <td>768.000000</td>\n",
" <td>768.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>3.845052</td>\n",
" <td>120.894531</td>\n",
" <td>69.105469</td>\n",
" <td>20.536458</td>\n",
" <td>79.799479</td>\n",
" <td>31.992578</td>\n",
" <td>0.471876</td>\n",
" <td>33.240885</td>\n",
" <td>0.348958</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>3.369578</td>\n",
" <td>31.972618</td>\n",
" <td>19.355807</td>\n",
" <td>15.952218</td>\n",
" <td>115.244002</td>\n",
" <td>7.884160</td>\n",
" <td>0.331329</td>\n",
" <td>11.760232</td>\n",
" <td>0.476951</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.078000</td>\n",
" <td>21.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>1.000000</td>\n",
" <td>99.000000</td>\n",
" <td>62.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>27.300000</td>\n",
" <td>0.243750</td>\n",
" <td>24.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>3.000000</td>\n",
" <td>117.000000</td>\n",
" <td>72.000000</td>\n",
" <td>23.000000</td>\n",
" <td>30.500000</td>\n",
" <td>32.000000</td>\n",
" <td>0.372500</td>\n",
" <td>29.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>6.000000</td>\n",
" <td>140.250000</td>\n",
" <td>80.000000</td>\n",
" <td>32.000000</td>\n",
" <td>127.250000</td>\n",
" <td>36.600000</td>\n",
" <td>0.626250</td>\n",
" <td>41.000000</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>17.000000</td>\n",
" <td>199.000000</td>\n",
" <td>122.000000</td>\n",
" <td>99.000000</td>\n",
" <td>846.000000</td>\n",
" <td>67.100000</td>\n",
" <td>2.420000</td>\n",
" <td>81.000000</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" preg plasma bpress ... pedigree_fun age class\n",
"count 768.000000 768.000000 768.000000 ... 768.000000 768.000000 768.000000\n",
"mean 3.845052 120.894531 69.105469 ... 0.471876 33.240885 0.348958\n",
"std 3.369578 31.972618 19.355807 ... 0.331329 11.760232 0.476951\n",
"min 0.000000 0.000000 0.000000 ... 0.078000 21.000000 0.000000\n",
"25% 1.000000 99.000000 62.000000 ... 0.243750 24.000000 0.000000\n",
"50% 3.000000 117.000000 72.000000 ... 0.372500 29.000000 0.000000\n",
"75% 6.000000 140.250000 80.000000 ... 0.626250 41.000000 1.000000\n",
"max 17.000000 199.000000 122.000000 ... 2.420000 81.000000 1.000000\n",
"\n",
"[8 rows x 9 columns]"
]
},
"metadata": {},
"execution_count": 42
}
]
},
{
"cell_type": "markdown",
"source": [
"Split data"
],
"metadata": {
"id": "yO9trkCoT82t"
}
},
{
"cell_type": "code",
"source": [
"X = dataset.drop(\"class\", axis=1)\n",
"y = dataset[[\"class\"]]\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=1)"
],
"metadata": {
"id": "fRDDKG-iT_aW"
},
"execution_count": 43,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Model"
],
"metadata": {
"id": "dPmrHAUKUrtd"
}
},
{
"cell_type": "code",
"source": [
"model = GaussianNB()\n",
"\n",
"model.fit(X_train, y_train)\n",
"\n",
"y_pred = model.predict(X_test)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "DqulwUdAUsfy",
"outputId": "b651b982-1eb9-460c-9e2e-f9695f0c7ba6"
},
"execution_count": 48,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py:985: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"Evaluation"
],
"metadata": {
"id": "1eL1vGyNU1bp"
}
},
{
"cell_type": "code",
"source": [
"print(\"Train accuracy: \", accuracy_score(y_train, model.predict(X_train)))\n",
"\n",
"print(\"Test accuracy: \", accuracy_score(y_test, y_pred))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2b2lSxpEU3K8",
"outputId": "2b36215f-f493-40a0-a635-bbe5982ee040"
},
"execution_count": 49,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Train accuracy: 0.7616387337057728\n",
"Test accuracy: 0.7835497835497836\n"
]
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment