ANN

This data set contains details of a bank’s customers and the target variable is a binary variable reflecting the fact whether the customer left the bank (closed his account) or he continues to be a customer.

Dataset

data <- read.csv('Churn_Modelling.csv')
data <- data[4:14]

converting as factors

data$Gender <- as.numeric(factor(data$Gender),levels=c('Female','male'),labels=c(1,2))
data$Geography <- as.numeric(factor(data$Geography),levels=c('Franch','spain','germany'),labels=c(1,2,3))

build and train and test data

library(caTools)
set.seed(101)
sample = sample.split(data$Exited,SplitRatio = 0.80)
train_data = subset(data,sample==T)
test_data = subset(data,sample==F)

Standrazing

train_data[-11] <- scale(train_data[-11])
test_data[-11] <- scale(test_data[-11])

Connnecting with h20 server

library(h2o)

## 
## ----------------------------------------------------------------------
## 
## Your next step is to start H2O:
##     > h2o.init()
## 
## For H2O package documentation, ask for help:
##     > ??h2o
## 
## After starting H2O, you can use the Web UI at http://localhost:54321
## For more information visit http://docs.h2o.ai
## 
## ----------------------------------------------------------------------

## 
## Attaching package: 'h2o'

## The following objects are masked from 'package:stats':
## 
##     cor, sd, var

## The following objects are masked from 'package:base':
## 
##     %*%, %in%, &&, ||, apply, as.factor, as.numeric, colnames,
##     colnames<-, ifelse, is.character, is.factor, is.numeric, log,
##     log10, log1p, log2, round, signif, trunc

h2o.init(nthreads = -1)

##  Connection successful!
## 
## R is connected to the H2O cluster: 
##     H2O cluster uptime:         6 minutes 53 seconds 
##     H2O cluster timezone:       Asia/Kolkata 
##     H2O data parsing timezone:  UTC 
##     H2O cluster version:        3.30.0.7 
##     H2O cluster version age:    19 days  
##     H2O cluster name:           H2O_started_from_R_manor_lpc090 
##     H2O cluster total nodes:    1 
##     H2O cluster total memory:   1.47 GB 
##     H2O cluster total cores:    8 
##     H2O cluster allowed cores:  8 
##     H2O cluster healthy:        TRUE 
##     H2O Connection ip:          localhost 
##     H2O Connection port:        54321 
##     H2O Connection proxy:       NA 
##     H2O Internal Security:      FALSE 
##     H2O API Extensions:         Amazon S3, Algos, AutoML, Core V3, TargetEncoder, Core V4 
##     R Version:                  R version 4.0.2 (2020-06-22)

library(h2o)
model <- h2o.deeplearning(y='Exited',training_frame = as.h2o(train_data),activation = 'Rectifier',hidden = c(6,6),epochs = 100,train_samples_per_iteration = -2)

## 
  |                                                                            
  |                                                                      |   0%
  |                                                                            
  |======================================================================| 100%
## 
  |                                                                            
  |                                                                      |   0%
  |                                                                            
  |============================                                          |  40%
  |                                                                            
  |======================================================================| 100%

pro_pre <- h2o.predict(model,as.h2o(test_data[-11]))

## 
  |                                                                            
  |                                                                      |   0%
  |                                                                            
  |======================================================================| 100%
## 
  |                                                                            
  |                                                                      |   0%
  |                                                                            
  |======================================================================| 100%

y_pred <- (pro_pre > 0.5)
y_pred <- as.vector(y_pred)

cm <-table(test_data[,11],y_pred) 

cm

##    y_pred
##        0    1
##   0 1504   89
##   1  195  212

#Acurracy score
(1508+189)/2000

## [1] 0.8485