AzharuddinKazi

rm(list=ls(all=TRUE))
fnBirthDay <- function(simulations){
  set.seed(1234)
  yes = 0
  #no =0
  
  
  x=sample(1:7, simulations,replace = TRUE)
  y=sample(1:7, simulations,replace = TRUE)

AzharuddinKazi

rm(list=ls(all=TRUE))

dataset <- data.frame(item = c("pocketknife", "beans", "potatoes", "onions","phone", "lemons",
                               "sleeping bag", "rope", "compass","umbrella","sweater","medicines","others"), 
                      survivalpoints = c(15, 16, 13, 14, 20,12,17,18,17,19,10,12,11), 
                      weight = c( 5, 6, 3, 4,11,2,7,8, 10,9,1,12,11))
sum(dataset$survivalpoints) 
sum(dataset$weight)
      

AzharuddinKazi

# Rows are  users (5 users) and # columns are songs (6 songs)
N=matrix(c(5,0,3,4,3,2,
           2,1,4,0,0,5,
           1,1,1,0,2,1,
           1,0,0,0,5,5,
           4,3,2,3,4,1),byrow=T,ncol=6)
rownames(N)= c("User1","User2","User3","User4","User5")
colnames(N) = c("Song1","Song2","Song3","Song4","Song5","Song6")

# UserId = c("User1","User2","User3","User4","User5")

AzharuddinKazi

import os                        
import pandas as pd              
import re                        
import numpy as np                
from sklearn.metrics import confusion_matrix
import random
import nltk
from sklearn.metrics import recall_score, precision_score, accuracy_score
from sklearn.naive_bayes import MultinomialNB

AzharuddinKazi

#Loading Data into R: 
bankdata=read.csv("E:\\UniversalBank.csv", header=TRUE, sep=",")  

#Data preparation
#(a) to remove the columns ID & ZIP  
bankdata_1 = subset(bankdata, select=-c(ID, ZIP.Code)) 

#(b) To create dummy variables for the categorical variable “Education” and add those dummy variables to the original data.  
library("dummies") 
Educations = dummy(bankdata_1$Education) 

AzharuddinKazi

rm(list=ls(all=TRUE))

#Consider mtacrs data of R-datasets
data(mtcars)
mydata <- data.frame(mtcars)
mydata <- na.omit(mydata) # listwise deletion of missing
summary(mydata)
str(mydata)

mydata <- scale(mydata) # standardize variables 

AzharuddinKazi

#### problem statement: given data about different customers, we have to classify prospective loan takes, i.e, classify loan takes and non-loan takers

### reading from a dataset named Universal Bank

data<-read.csv("E:\\UniversalBank.csv",header=T)
data1=subset(data, select=-c(ID,ZIP.Code))
str(data1)

## segregating the categorical and numeric variables

AzharuddinKazi

#Predict flower species(classify)
iris
head(iris)
dim(iris)
names(iris) 
str(iris)
table(iris$Species)

#split train and test
set.seed(1234)