stark
/
machine_learning
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
main
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '678d608b54'
${ noResults }
machine_learning/decision_tree_9/Untitled.ipynb

299 lines
7.2 KiB
Plaintext
Raw Normal View History Unescape Escape

sklearn
6 months ago
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "4be81fd7",
"metadata": {},
"outputs": [
{
"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>Gender</th>\n",
" <th>Height</th>\n",
" <th>Weight</th>\n",
" <th>Index</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Male</td>\n",
" <td>174</td>\n",
" <td>96</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Male</td>\n",
" <td>189</td>\n",
" <td>87</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Female</td>\n",
" <td>185</td>\n",
" <td>110</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Female</td>\n",
" <td>195</td>\n",
" <td>104</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Male</td>\n",
" <td>149</td>\n",
" <td>61</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Gender Height Weight Index\n",
"0 Male 174 96 4\n",
"1 Male 189 87 2\n",
"2 Female 185 110 4\n",
"3 Female 195 104 3\n",
"4 Male 149 61 3"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"data = pd.read_csv(\"obese.csv\")\n",
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "c90a3afb",
"metadata": {},
"outputs": [],
"source": [
"data['obese'] = (data.Index >= 4).astype('int')\n",
"data.drop('Index', axis = 1, inplace = True)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "d0ad044a",
"metadata": {},
"outputs": [
{
"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>Gender</th>\n",
" <th>Height</th>\n",
" <th>Weight</th>\n",
" <th>obese</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Male</td>\n",
" <td>174</td>\n",
" <td>96</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Male</td>\n",
" <td>189</td>\n",
" <td>87</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Female</td>\n",
" <td>185</td>\n",
" <td>110</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Female</td>\n",
" <td>195</td>\n",
" <td>104</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Male</td>\n",
" <td>149</td>\n",
" <td>61</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Gender Height Weight obese\n",
"0 Male 174 96 1\n",
"1 Male 189 87 0\n",
"2 Female 185 110 1\n",
"3 Female 195 104 0\n",
"4 Male 149 61 0"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "dde37f0d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Misclassified when cutting at 100kg: 18 \n",
" Misclassified when cutting at 80kg: 63\n"
]
}
],
"source": [
"print(\n",
" \" Misclassified when cutting at 100kg:\",\n",
" data.loc[(data['Weight']>=100) & (data['obese']==0),:].shape[0], \"\\n\",\n",
" \"Misclassified when cutting at 80kg:\",\n",
" data.loc[(data['Weight']>=80) & (data['obese']==0),:].shape[0]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "0d2e9b73",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Female 0.51\n",
"Male 0.49\n",
"Name: Gender, dtype: float64\n"
]
},
{
"data": {
"text/plain": [
"0.4998"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def gini_impurity(y):\n",
" '''\n",
" Given a Pandas Series, it calculates the Gini Impurity. \n",
" y: variable with which calculate Gini Impurity.\n",
" '''\n",
" if isinstance(y, pd.Series):\n",
" p = y.value_counts()/y.shape[0]\n",
" print(p)\n",
" gini = 1-np.sum(p**2)\n",
" return(gini)\n",
"\n",
" else:\n",
" raise('Object must be a Pandas Series.')\n",
"\n",
"gini_impurity(data.Gender) "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b60120ac",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.7.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}