Course project: 9995 Introduction to Market Analytics
Oskar Hiekkanen
# scientific notation -> decimal numbers
options(scipen=999)Task 1
From Module 2, read the car.data.csv file, and provide a summary of the “doors,” “persons,” and “safety” variables. Provide a brief description of the variables.
Variable descriptions
The dataset describes different characteristics of cars. The dataset contians 1728 observations.
- Doors : The number of doors on a car (Factor w/ 4 levels “2”,“3”,“4”,“5more”)
- Persons : The number of people the car is rated for. (Factor w/ 3 levels “2”,“4”,“more”)
- Safety : The safety rating of the car. (Factor w/ 3 levels “high”,“low”,“med”)
require(readr)## Loading required package: readrlibrary(readr)
car_data <- read_csv("car.data.csv")## Parsed with column specification:
## cols(
## buying = col_character(),
## maint = col_character(),
## doors = col_character(),
## persons = col_character(),
## lug_boot = col_character(),
## safety = col_character(),
## rating = col_character()
## )#Type transformations
car_data$safety = factor(car_data$safety)
car_data$maint = factor(car_data$maint)
car_data$buying = factor(car_data$buying)
car_data$lug_boot = factor(car_data$lug_boot)
car_data$rating = factor(car_data$rating)
car_data$doors = factor(car_data$doors)
car_data$persons = factor(car_data$persons)
attach(car_data)Summary of the “doors,” “persons,” and “safety” variables
car_summary <- data.frame(doors, persons, safety)
summary(car_summary)## doors persons safety
## 2 :432 2 :576 high:576
## 3 :432 4 :576 low :576
## 4 :432 more:576 med :576
## 5more:432#Garbage collection
detach(car_data, car_summary)
remove(car_data, car_summary)Task 2
From Module 3, read the german data set, and provide a “table” analysis of the “status of existing checking account” variable. Briefly describe the output.
library(tibble)
# From: http://archive.ics.uci.edu/ml/datasets/Statlog+(German+Credit+Data)
d <- read.table('http://archive.ics.uci.edu/ml/machine-learning-databases/statlog/german/german.data',
stringsAsFactors=F,header=F)
colnames(d) <- c('Status.of.existing.checking.account', 'Duration.in.month',
'Credit.history', 'Purpose', 'Credit.amount', 'Savings.account.bonds',
'Present.employment.since',
'Installment.rate.in.percentage.of.disposable.income',
'Personal.status.and.sex', 'Other.debtors.guarantors',
'Present.residence.since', 'Property', 'Age.in.years',
'Other.installment.plans', 'Housing',
'Number.of.existing.credits.at.this.bank', 'Job',
'Number.of.people.being.liable.to.provide.maintenance.for',
'Telephone', 'foreign.worker', 'Good.Loan')
mapping <- list('A11'='... < 0 DM',
'A12'='0 <= ... < 200 DM',
'A13'='... >= 200 DM / salary assignments for at least 1 year',
'A14'='no checking account',
'A30'='no credits taken/all credits paid back duly',
'A31'='all credits at this bank paid back duly',
'A32'='existing credits paid back duly till now',
'A33'='delay in paying off in the past',
'A34'='critical account/other credits existing (not at this bank)',
'A40'='car (new)',
'A41'='car (used)',
'A42'='furniture/equipment',
'A43'='radio/television',
'A44'='domestic appliances',
'A45'='repairs',
'A46'='education',
'A47'='(vacation - does not exist?)',
'A48'='retraining',
'A49'='business',
'A410'='others',
'A61'='... < 100 DM',
'A62'='100 <= ... < 500 DM',
'A63'='500 <= ... < 1000 DM',
'A64'='.. >= 1000 DM',
'A65'='unknown/ no savings account',
'A71'='unemployed',
'A72'='... < 1 year',
'A73'='1 <= ... < 4 years',
'A74'='4 <= ... < 7 years',
'A75'='.. >= 7 years',
'A91'='male : divorced/separated',
'A92'='female : divorced/separated/married',
'A93'='male : single',
'A94'='male : married/widowed',
'A95'='female : single',
'A101'='none',
'A102'='co-applicant',
'A103'='guarantor',
'A121'='real estate',
'A122'='if not A121 : building society savings agreement/life insurance',
'A123'='if not A121/A122 : car or other, not in attribute 6',
'A124'='unknown / no property',
'A141'='bank',
'A142'='stores',
'A143'='none',
'A151'='rent',
'A152'='own',
'A153'='for free',
'A171'='unemployed/ unskilled - non-resident',
'A172'='unskilled - resident',
'A173'='skilled employee / official',
'A174'='management/ self-employed/highly qualified employee/ officer',
'A191'='none',
'A192'='yes, registered under the customers name',
'A201'='yes',
'A202'='no')
for(i in 1:(dim(d))[2]) {
if(class(d[,i])=='character') {
d[,i] <- as.factor(as.character(mapping[d[,i]]))
}
}
d$Good.Loan <- as.factor(ifelse(d$Good.Loan==1,'GoodLoan','BadLoan'))
vars <- setdiff(colnames(d),'Good.Loan')
creditdata <- d
# not part of GCD data- notional example for listing 1.3
tab1 <- as.table(matrix(data=c(50,6,0,44),nrow=2,ncol=2))
dimnames(tab1) <- list('loan.as.pct.disposable.income'=c('LT.15pct','GT.15pct'),'loan.quality.pop1'=c('goodloan','badloan'))
tab2 <- as.table(matrix(data=c(34,18,16,32),nrow=2,ncol=2))
dimnames(tab2) <- list('loan.as.pct.disposable.income'=c('LT.15pct','GT.15pct'),'loan.quality.pop2'=c('goodloan','badloan'))
# Garbage collection
rm(mapping, d, tab1, tab2, vars, i)From Module 3, read the german data set, and provide a “table” analysis of the “status of existing checking account” variable. Briefly describe the output.
summary(as_tibble(creditdata$Status.of.existing.checking.account))## Warning: Calling `as_tibble()` on a vector is discouraged, because the behavior is likely to change in the future. Use `tibble::enframe(name = NULL)` instead.
## This warning is displayed once per session.## value
## ... < 0 DM :274
## ... >= 200 DM / salary assignments for at least 1 year: 63
## 0 <= ... < 200 DM :269
## no checking account :394rm(creditdata)Task 3
From Module 4, read the custdata.tsv data, and generate a bar chart of customers by state of residence in descending order. Provide a brief description of the chart
Prepare data:
library(dplyr, tibble)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unioncustomerData.df <- read.table("./custdata.tsv", header = T, sep='\t')
custCountByState.tbl <- as_tibble(customerData.df) %>%
# here's a cool verb, "count()
# use ?count() to get a sense of what count can do
# essentially count() does a counting by group of the variable of interest
# so, count how many observations by state, and then sort by descending order
count(state.of.res, sort = TRUE) %>%
# since the count variable is 'n' you may wish to provide some better name
mutate(numberOfObservationsInState = n) %>%
# and then delete 'n' from the data
select(-n)
# Garbage collection
rm(customerData.df)require(ggplot2)## Loading required package: ggplot2library(ggplot2)
ggplot(custCountByState.tbl) +
geom_col(aes(x=reorder(state.of.res,numberOfObservationsInState),
y=numberOfObservationsInState), fill="blue") +
coord_flip()
# Garbage collection
rm(custCountByState.tbl)Task 4
From Module 5, read the psub.Rdata and perform an ordinary least squares (OLS) regression on the ENTIRE data. Personal income is your variable of interest, which will be a function of the explanatory variables age, sex, working class, and education level. Be sure to briefly explain the regression output
# Load data
load("psub.RData")
# Create datafile
varsForOLS <- psub %>%
mutate(personalIncome = PINCP, groupingID = ORIGRANDGROUP, age = AGEP, sex = SEX,
workingClass = COW, educationLevel = SCHL) %>%
select(personalIncome, groupingID, age, sex, workingClass, educationLevel)
attach(varsForOLS)
#Get regression output
summary(lm(personalIncome ~ age + sex + workingClass + educationLevel + groupingID))##
## Call:
## lm(formula = personalIncome ~ age + sex + workingClass + educationLevel +
## groupingID)
##
## Residuals:
## Min 1Q Median 3Q Max
## -91692 -17398 -4120 11897 195790
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) -7434.0865 4744.8406 -1.567
## age 1066.7433 99.6603 10.704
## sexF -11375.8825 1721.2481 -6.609
## workingClassFederal government employee 7034.8539 4523.4830 1.555
## workingClassLocal government employee -7461.3689 3315.4484 -2.250
## workingClassPrivate not-for-profit employee -8867.9873 2809.7547 -3.156
## workingClassSelf-employed incorporated 5512.2580 4883.9231 1.129
## workingClassSelf-employed not incorporated -10866.7183 4610.8969 -2.357
## workingClassState government employee -11493.7408 4246.4707 -2.707
## educationLevelAssociate's degree 21475.9598 3996.8974 5.373
## educationLevelBachelor's degree 37293.9782 3391.2106 10.997
## educationLevelDoctorate degree 47488.8295 10544.9251 4.503
## educationLevelGED or alternative credential 9461.4068 5275.3554 1.794
## educationLevelMaster's degree 51238.1550 3985.9499 12.855
## educationLevelProfessional degree 84405.9363 7255.1298 11.634
## educationLevelRegular high school diploma 7923.2703 3309.3434 2.394
## educationLevelsome college credit, no degree 14543.8061 3343.7947 4.349
## groupingID 0.7427 2.8546 0.260
## Pr(>|t|)
## (Intercept) 0.11743
## age < 0.0000000000000002 ***
## sexF 0.0000000000579 ***
## workingClassFederal government employee 0.12016
## workingClassLocal government employee 0.02460 *
## workingClassPrivate not-for-profit employee 0.00164 **
## workingClassSelf-employed incorporated 0.25927
## workingClassSelf-employed not incorporated 0.01859 *
## workingClassState government employee 0.00689 **
## educationLevelAssociate's degree 0.0000000927900 ***
## educationLevelBachelor's degree < 0.0000000000000002 ***
## educationLevelDoctorate degree 0.0000073330317 ***
## educationLevelGED or alternative credential 0.07314 .
## educationLevelMaster's degree < 0.0000000000000002 ***
## educationLevelProfessional degree < 0.0000000000000002 ***
## educationLevelRegular high school diploma 0.01681 *
## educationLevelsome college credit, no degree 0.0000147975404 ***
## groupingID 0.79477
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 28670 on 1206 degrees of freedom
## Multiple R-squared: 0.3227, Adjusted R-squared: 0.3132
## F-statistic: 33.8 on 17 and 1206 DF, p-value: < 0.00000000000000022# Garbage collection
rm(varsForOLS, psub)