vrajesh26

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import style
style.use("ggplot")
from sklearn import svm
import ggplot as ggp
from sklearn.model_selection import train_test_split
Data_main=pd.read_csv(filepath_or_buffer='D:\loan_data.csv')
np.sum(Data_main.isnull())

vrajesh26

employee<-read.csv("D:/WA_Fn-UseC_-HR-Employee-Attrition.csv")
View(employee)
str(employee)
dim(employee)
colnames(employee)[1]="Age"

library("caTools")
set.seed(12345)
emp <- sample.split(employee$Attrition,SplitRatio = 0.75)
emp_train <- subset(employee,emp==TRUE)

vrajesh26

train<-read.csv("D:/loan prediction/loan_train.csv",na.strings = c(""," ",NA))
test<-read.csv("D:/loan prediction/loan_test.csv",na.strings = c(""," ",NA))
View(train)
colSums(is.na(train))
colSums(is.na(test))
dim(train)
library(mlr)

summarizeColumns(train)
summarizeColumns(train)