Skip to content

Instantly share code, notes, and snippets.

@ashutoshsahu2015

ashutoshsahu2015/Probability Ratio Encoding.ipynb

Created March 20, 2021 08:07
Show Gist options
  • Save ashutoshsahu2015/e706aa5ab88194443ae12c0b74054057 to your computer and use it in GitHub Desktop.
Save ashutoshsahu2015/e706aa5ab88194443ae12c0b74054057 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
Probability Ratio Encoding.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 5,
"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>Survived</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Cabin</th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>0.466667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>0.744681</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>0.593220</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>0.757576</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>0.750000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>0.615385</td>\n",
" </tr>\n",
" <tr>\n",
" <th>G</th>\n",
" <td>0.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>M</th>\n",
" <td>0.299854</td>\n",
" </tr>\n",
" <tr>\n",
" <th>T</th>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Survived\n",
"Cabin \n",
"A 0.466667\n",
"B 0.744681\n",
"C 0.593220\n",
"D 0.757576\n",
"E 0.750000\n",
"F 0.615385\n",
"G 0.500000\n",
"M 0.299854\n",
"T 0.000000"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prob=dataset.groupby(['Cabin'])['Survived'].mean()\n",
"prob_df=pd.DataFrame(prob)\n",
"prob_df"
]
},
{
"cell_type": "code",
"execution_count": 6,
"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>Survived</th>\n",
" <th>Died</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Cabin</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>0.466667</td>\n",
" <td>0.533333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>0.744681</td>\n",
" <td>0.255319</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>0.593220</td>\n",
" <td>0.406780</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>0.757576</td>\n",
" <td>0.242424</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>0.750000</td>\n",
" <td>0.250000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>0.615385</td>\n",
" <td>0.384615</td>\n",
" </tr>\n",
" <tr>\n",
" <th>G</th>\n",
" <td>0.500000</td>\n",
" <td>0.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>M</th>\n",
" <td>0.299854</td>\n",
" <td>0.700146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>T</th>\n",
" <td>0.000000</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Survived Died\n",
"Cabin \n",
"A 0.466667 0.533333\n",
"B 0.744681 0.255319\n",
"C 0.593220 0.406780\n",
"D 0.757576 0.242424\n",
"E 0.750000 0.250000\n",
"F 0.615385 0.384615\n",
"G 0.500000 0.500000\n",
"M 0.299854 0.700146\n",
"T 0.000000 1.000000"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prob_df['Died']=1-prob_df['Survived']\n",
"prob_df"
]
},
{
"cell_type": "code",
"execution_count": 7,
"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>Survived</th>\n",
" <th>Died</th>\n",
" <th>Probability Ratio</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Cabin</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>0.466667</td>\n",
" <td>0.533333</td>\n",
" <td>0.875000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>0.744681</td>\n",
" <td>0.255319</td>\n",
" <td>2.916667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>0.593220</td>\n",
" <td>0.406780</td>\n",
" <td>1.458333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>0.757576</td>\n",
" <td>0.242424</td>\n",
" <td>3.125000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>0.750000</td>\n",
" <td>0.250000</td>\n",
" <td>3.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>F</th>\n",
" <td>0.615385</td>\n",
" <td>0.384615</td>\n",
" <td>1.600000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>G</th>\n",
" <td>0.500000</td>\n",
" <td>0.500000</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>M</th>\n",
" <td>0.299854</td>\n",
" <td>0.700146</td>\n",
" <td>0.428274</td>\n",
" </tr>\n",
" <tr>\n",
" <th>T</th>\n",
" <td>0.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Survived Died Probability Ratio\n",
"Cabin \n",
"A 0.466667 0.533333 0.875000\n",
"B 0.744681 0.255319 2.916667\n",
"C 0.593220 0.406780 1.458333\n",
"D 0.757576 0.242424 3.125000\n",
"E 0.750000 0.250000 3.000000\n",
"F 0.615385 0.384615 1.600000\n",
"G 0.500000 0.500000 1.000000\n",
"M 0.299854 0.700146 0.428274\n",
"T 0.000000 1.000000 0.000000"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prob_df['Probability Ratio']=prob_df['Survived']/prob_df['Died']\n",
"prob_df"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'A': 0.875,\n",
" 'B': 2.916666666666666,\n",
" 'C': 1.4583333333333333,\n",
" 'D': 3.125,\n",
" 'E': 3.0,\n",
" 'F': 1.6000000000000003,\n",
" 'G': 1.0,\n",
" 'M': 0.42827442827442824,\n",
" 'T': 0.0}"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prob_encod_dictionary=prob_df['Probability Ratio'].to_dict()\n",
"prob_encod_dictionary"
]
},
{
"cell_type": "code",
"execution_count": 9,
"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>Survived</th>\n",
" <th>Cabin</th>\n",
" <th>Cabin_probabilty_ratio</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>M</td>\n",
" <td>0.428274</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>C</td>\n",
" <td>1.458333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>M</td>\n",
" <td>0.428274</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>C</td>\n",
" <td>1.458333</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>M</td>\n",
" <td>0.428274</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Survived Cabin Cabin_probabilty_ratio\n",
"0 0 M 0.428274\n",
"1 1 C 1.458333\n",
"2 1 M 0.428274\n",
"3 1 C 1.458333\n",
"4 0 M 0.428274"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dataset['Cabin_probabilty_ratio']=dataset['Cabin'].map(prob_encod_dictionary)\n",
"dataset.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment