601_blogpost5

Blog post 5 performing more analysis on the dataset as a part of the course “Data Science Fundamentals”

library(tidyverse)

id <- data.frame(read.csv("C:/Users/gunde/Downloads/Indian_Startup_Funding.csv",stringsAsFactors = TRUE))

glimpse(id)

Rows: 3,044
Columns: 8
$ Date             <fct> 09/01/2020, 13/01/2020, 09/01/2020, 02/01/2~
$ StartupName      <fct> BYJUS, Shuttl, Mamaearth, WealthBucket, Fas~
$ IndustryVertical <fct> "E-Tech", "Transportation", "E-commerce", "~
$ SubVertical      <fct> "E-learning", "App based shuttle service", ~
$ CityLocation     <fct> "Bangalore", "Gurgaon", "Bangalore", "New D~
$ Investors        <fct> "Tiger Global Management", "Susquehanna Gro~
$ InvestmentType   <fct> Private Equity Round, Series C, Series B, P~
$ AmountUSD        <fct> "20,00,00,000", "80,48,394", "1,83,58,860",~

## Convert Date variable to Date format
id$Date <- as.Date(id$Date,format("%d/%m/%Y"))
## Confirm
str(id)

'data.frame':   3044 obs. of  8 variables:
 $ Date            : Date, format: "2020-01-09" ...
 $ StartupName     : Factor w/ 2453 levels "#Fame","121Policy",..: 276 1911 1308 2307 656 1579 2441 568 295 495 ...
 $ IndustryVertical: Factor w/ 878 levels "360-degree view creating platform",..: 200 827 190 275 254 440 358 822 191 7 ...
 $ SubVertical     : Factor w/ 1943 levels "\"Women\\\\'s Fashion Clothing Online Platform\"",..: 461 75 1647 1279 515 1487 1216 28 112 1681 ...
 $ CityLocation    : Factor w/ 100 levels "Agra","Ahemadabad",..: 5 29 5 62 55 19 29 74 29 5 ...
 $ Investors       : Factor w/ 2405 levels " Sandeep Aggarwal, Teruhide Sato",..: 2114 2061 1857 2316 1997 468 218 1827 1523 1365 ...
 $ InvestmentType  : Factor w/ 55 levels "Angel","Angel / Seed Funding",..: 26 43 41 21 36 40 26 40 44 30 ...
 $ AmountUSD       : Factor w/ 476 levels "1,00,00,00,000",..: 184 451 75 263 129 469 115 386 406 336 ...

## Make a new column for year
id$year <- as.numeric(format(id$Date,"%Y"))
## Year frequency table
yeartable <- table(id$year)

Cleanstartup <- id[complete.cases(id), ]
dim(Cleanstartup)

[1] 3038    9

Cleanstartup1 <- Cleanstartup
str(Cleanstartup1)

'data.frame':   3038 obs. of  9 variables:
 $ Date            : Date, format: "2020-01-09" ...
 $ StartupName     : Factor w/ 2453 levels "#Fame","121Policy",..: 276 1911 1308 2307 656 1579 2441 568 295 495 ...
 $ IndustryVertical: Factor w/ 878 levels "360-degree view creating platform",..: 200 827 190 275 254 440 358 822 191 7 ...
 $ SubVertical     : Factor w/ 1943 levels "\"Women\\\\'s Fashion Clothing Online Platform\"",..: 461 75 1647 1279 515 1487 1216 28 112 1681 ...
 $ CityLocation    : Factor w/ 100 levels "Agra","Ahemadabad",..: 5 29 5 62 55 19 29 74 29 5 ...
 $ Investors       : Factor w/ 2405 levels " Sandeep Aggarwal, Teruhide Sato",..: 2114 2061 1857 2316 1997 468 218 1827 1523 1365 ...
 $ InvestmentType  : Factor w/ 55 levels "Angel","Angel / Seed Funding",..: 26 43 41 21 36 40 26 40 44 30 ...
 $ AmountUSD       : Factor w/ 476 levels "1,00,00,00,000",..: 184 451 75 263 129 469 115 386 406 336 ...
 $ year            : num  2020 2020 2020 2020 2020 ...

Cleanstartup1$CityLocation <- as.character(Cleanstartup1$CityLocation)
Cleanstartup1$CityLocation[Cleanstartup1$CityLocation != "Bangalore" & Cleanstartup1$CityLocation != "Mumbai" & Cleanstartup1$CityLocation != "New Delhi" & Cleanstartup1$CityLocation != "Gurgaon" & Cleanstartup1$CityLocation != "Pune" & Cleanstartup1$CityLocation != "Hyderabad"] <- "Others"

startup2 <- Cleanstartup1
startup2$IndustryVertical <- as.character(startup2$IndustryVertical)
#clean code
startup2$IndustryVertical[startup2$IndustryVertical != "Consumer Internet" & startup2$IndustryVertical != "Technology" & startup2$IndustryVertical != "E-Commerce" & startup2$IndustryVertical != "Finance" & startup2$IndustryVertical != "Transportation" ] <- "OtherSectors"

table(startup2$IndustryVertical)

Consumer Internet        E-Commerce           Finance 
              941               287                63 
     OtherSectors        Technology    Transportation 
             1265               478                 4 

TopIT <- table(startup2$InvestmentType)
TopIT.df <- as.data.frame(TopIT)
top10IT <- top_n(TopIT.df,10)
top10IT

                   Var1 Freq
1          Debt Funding   25
2        Private Equity 1355
3  Seed / Angel Funding   47
4          Seed Funding 1350
5   Seed/ Angel Funding   60
6    Seed/Angel Funding   23
7      Seed\\\\nFunding   30
8              Series A   25
9              Series B   21
10             Series C   14

boxplot(startup2$AmountUSD, horizontal = TRUE, xlab = "Amount in USD", main = "Startup Investment plot")

boxplot(startup2$AmountUSD ~ Cleanstartup$InvestmentType, horizontal = FALSE, xlab= "Amount of Investment in USD", ylab = "Amount", main = "Investment Type")

boxplot(startup2$InvestmentType ~ Cleanstartup$Investors,horizontal = TRUE, ylab= "Investors", xlab = "Industry Sector", main = "Amount of Investment", boxwex = 0.25)

mytable <- xtabs(startup2$year ~ Cleanstartup$AmountUSD)
boxplot.default(mytable, ylab = "Amount in USD", xlab = "Industry Sector", main = "Year to Amount")

x <- xtabs(startup2$year ~ startup2$IndustryVertical)
plot(x, ylab = "AMount of Investment", xlab = "IndustryVertical")