1/13/2022
1.Load the library
library(tidyverse)
── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──
✓ ggplot2 3.3.5 ✓ purrr 0.3.4 ✓ tibble 3.1.3 ✓ dplyr 1.0.7 ✓ tidyr 1.1.3 ✓ stringr 1.4.0 ✓ readr 2.0.0 ✓ forcats 0.5.1
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ── x dplyr::filter() masks stats::filter() x dplyr::lag() masks stats::lag()
2.Load the dataset
file <- '5G Smartphone Available in India.csv' smartphone5g <- read_csv(file,show_col_types = FALSE) smartphone5g %>% glimpse
Rows: 183 Columns: 15 $ `product name` <chr> "Vivo V23 5G", "Vivo V23 Pro 5G", "OnePl… $ `processor price` <chr> "MediaTek Dimensity 920 MT6877T Processo… $ `camera specs rear` <chr> "64 + 8 + 2 MP Triple Rear Camera", "108… $ `camera specs front` <chr> "50+8 MP Dual Front Camera", "50+8 MP Du… $ `display size` <chr> "6.44 inches AMOLED Display", "6.56 inch… $ `ram of phone` <chr> "8 GB RAM", "8 GB RAM", "6 GB RAM", "6 G… $ storage <chr> "128 GB Storage", "128 GB Storage", "128… $ battery <chr> "4200 mAh Battery", "4300 mAh Battery", … $ `android version` <chr> "Android v12 OS", "Android v12 OS", "And… $ `score by smartprice` <dbl> NA, NA, 8.0, 7.8, NA, 7.5, 8.0, 7.3, 8.3… $ `first site` <chr> NA, NA, NA, "Amazon", NA, "Amazon", "Ama… $ `price in first site` <dbl> NA, NA, NA, 16999, NA, 29390, 24999, 179… $ `second site` <chr> NA, NA, NA, "Flipkart", NA, "Flipkart", … $ `price in second site` <dbl> NA, NA, NA, 18885, NA, 29990, 25999, NA,… $ `Price of product(available)` <dbl> 29990, 38990, 27999, 16999, 26999, 29390…
3.Check the null values in the dataset
sapply(smartphone5g,function(x) sum(is.na(x)))
product name processor price
0 0
camera specs rear camera specs front
0 0
display size ram of phone
0 0
storage battery
0 0
android version score by smartprice
0 29
first site price in first site
56 56
second site price in second site
92 92
Price of product(available)
0
4.Summary score column to check average score
summary(smartphone5g$`score by smartprice`)
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
7.000 7.800 8.000 7.973 8.200 8.800 29
Data source from the websites below
table(smartphone5g$`first site`) %>% names
[1] "Amazon" "Flipkart" "Tatacliq"
5.Replace null in score column with average score
smartphone5g$`score by smartprice`[is.na(smartphone5g$`score by smartprice`)] <- 7.973
6.Convert columns with character to factors
smartphone5g <- smartphone5g %>% mutate_if(is.character,as.factor)
7.Cut price at interval 10,000INR
smartphone5g$price_range <-
cut(smartphone5g$`Price of product(available)`,
breaks=seq(1e+04,2e+05,1e+04))
8.Plot01_Does the higher price mean the better smartphone?
9.Plot02_5G Smartphone Price Overview by Storage and RAM in India
10.Plot03_5G Smartphone Average Price by OS/RAM/Storage in India
smartphone5g %>% select(c(`product name`)) %>% head
# A tibble: 6 × 1
`product name`
<fct>
1 Vivo V23 5G
2 Vivo V23 Pro 5G
3 OnePlus Nord 2
4 Xiaomi Redmi Note 11T 5G
5 Xiaomi 11i HyperCharge
6 OPPO Reno 6
smartphone5g$brand<-
sapply(strsplit(as.character(smartphone5g$`product name`),' '),'[[',1)
smartphone5g$brand <- tolower(smartphone5g$brand) smartphone5g$brand[1:5]
[1] "vivo" "vivo" "oneplus" "xiaomi" "xiaomi"
11.Plot04_5G Smartphone Brand Overview in India
12.Extract brand information from processor column
smartphone5g$`processor price` %>% head
[1] MediaTek Dimensity 920 MT6877T Processor [2] MediaTek Dimensity 1200 MT6893 Processor [3] MediaTek Dimensity 1200 MT6893 Processor [4] MediaTek Dimensity 810 MT6833 Processor [5] MediaTek Dimensity 920 MT6877T Processor [6] MediaTek Dimensity 900 MT6877 Processor 30 Levels: Apple A14 Bionic Processor ... Samsung Exynos 9 Octa 990 Processor
smartphone5g$processor_brand<-
sapply(strsplit(as.character(smartphone5g$`processor price`),' '),'[[',1)
smartphone5g$processor_brand %>% head
[1] "MediaTek" "MediaTek" "MediaTek" "MediaTek" "MediaTek" "MediaTek"
13.Plot05_5G Smartphone Processor Brand Overview in India
