{

"cells": [
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"from sklearn.impute import KNNImputer,SimpleImputer\n",
"from sklearn.linear_model import LogisticRegression\n",
"\n",
"from sklearn.metrics import accuracy_score"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('train.csv')[['Age','Pclass','Fare','Survived']]"
]
},
{
"cell_type": "code",
"execution_count": 34,
"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>Age</th>\n",
" <th>Pclass</th>\n",
" <th>Fare</th>\n",
" <th>Survived</th>\n",
" </tr>\n",
 " </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>22.0</td>\n",
" <td>3</td>\n",
" <td>7.2500</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>38.0</td>\n",
" <td>1</td>\n",
" <td>71.2833</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>26.0</td>\n",
" <td>3</td>\n",
" <td>7.9250</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>35.0</td>\n",
" <td>1</td>\n",
" <td>53.1000</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>35.0</td>\n",
" <td>3</td>\n",
" <td>8.0500</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Age Pclass Fare Survived\n",
"0 22.0 3 7.2500 0\n",
"1 38.0 1 71.2833 1\n",
"2 26.0 3 7.9250 1\n",
"3 35.0 1 53.1000 1\n",
"4 35.0 3 8.0500 0"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
 {
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Age 19.86532\n",
"Pclass 0.00000\n",
"Fare 0.00000\n",
"Survived 0.00000\n",
"dtype: float64"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.isnull().mean() * 100"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [],
"source": [
"X = df.drop(columns=['Survived'])\n",
"y = df['Survived']"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
"X_train,X_test,y_train,y_test =
train_test_split(X,y,test_size=0.2,random_state=2)"
]
},
{
"cell_type": "code",
"execution_count": 38,
"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>Age</th>\n",
" <th>Pclass</th>\n",
" <th>Fare</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>40.0</td>\n",
" <td>1</td>\n",
" <td>27.7208</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>4.0</td>\n",
" <td>3</td>\n",
" <td>16.7000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>873</th>\n",
" <td>47.0</td>\n",
" <td>3</td>\n",
" <td>9.0000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>182</th>\n",
" <td>9.0</td>\n",
" <td>3</td>\n",
" <td>31.3875</td>\n",
" </tr>\n",
" <tr>\n",
" <th>876</th>\n",
" <td>20.0</td>\n",
" <td>3</td>\n",
" <td>9.8458</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Age Pclass Fare\n",
"30 40.0 1 27.7208\n",
"10 4.0 3 16.7000\n",
"873 47.0 3 9.0000\n",
"182 9.0 3 31.3875\n",
"876 20.0 3 9.8458"
]
 },
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_train.head()"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [],
"source": [
"knn = KNNImputer(n_neighbors=3,weights='distance')\n",
"\n",
"X_train_trf = knn.fit_transform(X_train)\n",
"X_test_trf = knn.transform(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.7150837988826816"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"lr = LogisticRegression()\n",
"\n",
"lr.fit(X_train_trf,y_train)\n",
"\n",
"y_pred = lr.predict(X_test_trf)\n",
"\n",
"accuracy_score(y_test,y_pred)"
]
},
{
"cell_type": "code",
"execution_count": 55,
"metadata": {},
"outputs": [],
"source": [
"# Comparision with Simple Imputer --> mean\n",
"\n",
"si = SimpleImputer()\n",
"\n",
"X_train_trf2 = si.fit_transform(X_train)\n",
 "X_test_trf2 = si.transform(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.6927374301675978"
]
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"lr = LogisticRegression()\n",
"\n",
"lr.fit(X_train_trf2,y_train)\n",
"\n",
"y_pred2 = lr.predict(X_test_trf2)\n",
"\n",
"accuracy_score(y_test,y_pred2)"
]
},
{
"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": "3.8.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}