{ "cells": [ { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "# Import libraries\n", "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "from sklearn.preprocessing import LabelEncoder\n", "from sklearn.ensemble import RandomForestClassifier\n", "import lightgbm as lgb\n", "import scipy.stats\n", "\n", "datapath='Data/'" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "# Import data\n", "train_df=pd.read_csv(datapath+'train_u6lujuX_CVtuZ9i.csv')\n", "test_df=pd.read_csv(datapath+'test_Y3wMUE5_7gLdaTN.csv')" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | Loan_ID | \n", "Gender | \n", "Married | \n", "Dependents | \n", "Education | \n", "Self_Employed | \n", "ApplicantIncome | \n", "CoapplicantIncome | \n", "LoanAmount | \n", "Loan_Amount_Term | \n", "Credit_History | \n", "Property_Area | \n", "Loan_Status | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "LP001002 | \n", "Male | \n", "No | \n", "0 | \n", "Graduate | \n", "No | \n", "5849 | \n", "0.0 | \n", "NaN | \n", "360.0 | \n", "1.0 | \n", "Urban | \n", "Y | \n", "
1 | \n", "LP001003 | \n", "Male | \n", "Yes | \n", "1 | \n", "Graduate | \n", "No | \n", "4583 | \n", "1508.0 | \n", "128.0 | \n", "360.0 | \n", "1.0 | \n", "Rural | \n", "N | \n", "
2 | \n", "LP001005 | \n", "Male | \n", "Yes | \n", "0 | \n", "Graduate | \n", "Yes | \n", "3000 | \n", "0.0 | \n", "66.0 | \n", "360.0 | \n", "1.0 | \n", "Urban | \n", "Y | \n", "
3 | \n", "LP001006 | \n", "Male | \n", "Yes | \n", "0 | \n", "Not Graduate | \n", "No | \n", "2583 | \n", "2358.0 | \n", "120.0 | \n", "360.0 | \n", "1.0 | \n", "Urban | \n", "Y | \n", "
4 | \n", "LP001008 | \n", "Male | \n", "No | \n", "0 | \n", "Graduate | \n", "No | \n", "6000 | \n", "0.0 | \n", "141.0 | \n", "360.0 | \n", "1.0 | \n", "Urban | \n", "Y | \n", "