1. Dataset Selection and Analysis Introduction

This project utilizes the Google Play Store Apps dataset, which comprises web-scraped data from 10,000 Play Store apps, offering insights into the Android market. The dataset encompasses information on 10,841 apps, each with 13 attributes such as category, rating, size, and more.

Analyzing this dataset facilitates a deeper understanding of potential patterns within the vast commercial landscape of the Google App Store, providing valuable insights for developers and business operators. Especially noteworthy are the factors influencing rating and price.

df <- read.csv('googleplaystore.csv')
head(df)
##                                                  App       Category Rating
## 1     Photo Editor & Candy Camera & Grid & ScrapBook ART_AND_DESIGN    4.1
## 2                                Coloring book moana ART_AND_DESIGN    3.9
## 3 U Launcher Lite – FREE Live Cool Themes, Hide Apps ART_AND_DESIGN    4.7
## 4                              Sketch - Draw & Paint ART_AND_DESIGN    4.5
## 5              Pixel Draw - Number Art Coloring Book ART_AND_DESIGN    4.3
## 6                         Paper flowers instructions ART_AND_DESIGN    4.4
##   Reviews Size    Installs Type Price Content.Rating                    Genres
## 1     159  19M     10,000+ Free     0       Everyone              Art & Design
## 2     967  14M    500,000+ Free     0       Everyone Art & Design;Pretend Play
## 3   87510 8.7M  5,000,000+ Free     0       Everyone              Art & Design
## 4  215644  25M 50,000,000+ Free     0           Teen              Art & Design
## 5     967 2.8M    100,000+ Free     0       Everyone   Art & Design;Creativity
## 6     167 5.6M     50,000+ Free     0       Everyone              Art & Design
##       Last.Updated        Current.Ver  Android.Ver
## 1  January 7, 2018              1.0.0 4.0.3 and up
## 2 January 15, 2018              2.0.0 4.0.3 and up
## 3   August 1, 2018              1.2.4 4.0.3 and up
## 4     June 8, 2018 Varies with device   4.2 and up
## 5    June 20, 2018                1.1   4.4 and up
## 6   March 26, 2017                1.0   2.3 and up

2. Data Cleaning

Remove the rows with null values.

df$Size[df$Size == "Varies with device"] <- NA
df[df== ""] <- NA
colSums(is.na(df))
##            App       Category         Rating        Reviews           Size 
##              0              0           1474              0           1695 
##       Installs           Type          Price Content.Rating         Genres 
##              0              0              0              1              0 
##   Last.Updated    Current.Ver    Android.Ver 
##              0              1              1
df <- na.omit(df)

Convert the app size from string to float.

head(df$Size, 3)
## [1] "19M"  "14M"  "8.7M"
df$Size <- as.numeric(gsub("[,MKmk]", "", df$Size))
head(df$Size, 3)
## [1] 19.0 14.0  8.7

Convert the count of installs from string to numeric

head(df$Installs, 3)
## [1] "10,000+"    "500,000+"   "5,000,000+"
df$Installs <- as.numeric(gsub("[,+]", "", df$Installs))
head(df$Installs, 3)
## [1] 1e+04 5e+05 5e+06

Convert Reviews and Price to numeric

df$Reviews <- as.numeric(df$Reviews)
df$Price <- as.numeric(gsub("[,+$freeEveryone]", "", df$Price))

Check outliers

library(ggplot2)
## Warning: 程辑包'ggplot2'是用R版本4.2.3 来建造的
ggplot(df, aes(x = "", y = Size)) + geom_boxplot() + labs(title = "Size")

ggplot(df, aes(x = "", y = Installs)) + geom_boxplot() + labs(title = "Installs")

ggplot(df, aes(x = "", y = Reviews)) + geom_boxplot() + labs(title = "Reviews")

The distributions of these variables are normal and there are no outliers.

3. Data Handling

Show the data types of all variables.

str(df)
## 'data.frame':    7728 obs. of  13 variables:
##  $ App           : chr  "Photo Editor & Candy Camera & Grid & ScrapBook" "Coloring book moana" "U Launcher Lite – FREE Live Cool Themes, Hide Apps" "Sketch - Draw & Paint" ...
##  $ Category      : chr  "ART_AND_DESIGN" "ART_AND_DESIGN" "ART_AND_DESIGN" "ART_AND_DESIGN" ...
##  $ Rating        : num  4.1 3.9 4.7 4.5 4.3 4.4 3.8 4.1 4.4 4.7 ...
##  $ Reviews       : num  159 967 87510 215644 967 ...
##  $ Size          : num  19 14 8.7 25 2.8 5.6 19 29 33 3.1 ...
##  $ Installs      : num  1e+04 5e+05 5e+06 5e+07 1e+05 5e+04 5e+04 1e+06 1e+06 1e+04 ...
##  $ Type          : chr  "Free" "Free" "Free" "Free" ...
##  $ Price         : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ Content.Rating: chr  "Everyone" "Everyone" "Everyone" "Teen" ...
##  $ Genres        : chr  "Art & Design" "Art & Design;Pretend Play" "Art & Design" "Art & Design" ...
##  $ Last.Updated  : chr  "January 7, 2018" "January 15, 2018" "August 1, 2018" "June 8, 2018" ...
##  $ Current.Ver   : chr  "1.0.0" "2.0.0" "1.2.4" "Varies with device" ...
##  $ Android.Ver   : chr  "4.0.3 and up" "4.0.3 and up" "4.0.3 and up" "4.2 and up" ...
##  - attr(*, "na.action")= 'omit' Named int [1:3113] 24 38 43 53 68 69 74 86 89 90 ...
##   ..- attr(*, "names")= chr [1:3113] "24" "38" "43" "53" ...

Only 5 variables are numeric, and the rest are characters.

summary(df)
##      App              Category             Rating         Reviews        
##  Length:7728        Length:7728        Min.   :1.000   Min.   :       1  
##  Class :character   Class :character   1st Qu.:4.000   1st Qu.:     108  
##  Mode  :character   Mode  :character   Median :4.300   Median :    2324  
##                                        Mean   :4.174   Mean   :  294708  
##                                        3rd Qu.:4.500   3rd Qu.:   38980  
##                                        Max.   :5.000   Max.   :44893888  
##       Size           Installs             Type               Price        
##  Min.   :  1.00   Min.   :1.000e+00   Length:7728        Min.   :  0.000  
##  1st Qu.:  6.10   1st Qu.:1.000e+04   Class :character   1st Qu.:  0.000  
##  Median : 16.00   Median :1.000e+05   Mode  :character   Median :  0.000  
##  Mean   : 37.29   Mean   :8.419e+06                      Mean   :  1.128  
##  3rd Qu.: 37.00   3rd Qu.:1.000e+06                      3rd Qu.:  0.000  
##  Max.   :994.00   Max.   :1.000e+09                      Max.   :400.000  
##  Content.Rating        Genres          Last.Updated       Current.Ver       
##  Length:7728        Length:7728        Length:7728        Length:7728       
##  Class :character   Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character  
##                                                                             
##                                                                             
##                                                                             
##  Android.Ver       
##  Length:7728       
##  Class :character  
##  Mode  :character  
##                    
##                    
## 

Show the count of unique values of each non-numeric variable.

chr_unique_counts <- sapply(df, function(x) {
  if (is.character(x)) {
    length(unique(x))
  } else {
    NA
  }
})

chr_unique_counts <- chr_unique_counts[!is.na(chr_unique_counts)]
print(chr_unique_counts)
##            App       Category           Type Content.Rating         Genres 
##           7028             33              2              6            112 
##   Last.Updated    Current.Ver    Android.Ver 
##           1278           2520             32

The number of unique values for each variable varies significantly, ranging from 2 to 7028.

Create a new columns ‘Paid’, which is the label encoding of the ordinal variable Type.

df$Paid <- as.numeric(as.factor(df$Type)) - 1
unique(df$Paid)
## [1] 0 1

Convert some variables to factors

head(df)
##                                                  App       Category Rating
## 1     Photo Editor & Candy Camera & Grid & ScrapBook ART_AND_DESIGN    4.1
## 2                                Coloring book moana ART_AND_DESIGN    3.9
## 3 U Launcher Lite – FREE Live Cool Themes, Hide Apps ART_AND_DESIGN    4.7
## 4                              Sketch - Draw & Paint ART_AND_DESIGN    4.5
## 5              Pixel Draw - Number Art Coloring Book ART_AND_DESIGN    4.3
## 6                         Paper flowers instructions ART_AND_DESIGN    4.4
##   Reviews Size Installs Type Price Content.Rating                    Genres
## 1     159 19.0    1e+04 Free     0       Everyone              Art & Design
## 2     967 14.0    5e+05 Free     0       Everyone Art & Design;Pretend Play
## 3   87510  8.7    5e+06 Free     0       Everyone              Art & Design
## 4  215644 25.0    5e+07 Free     0           Teen              Art & Design
## 5     967  2.8    1e+05 Free     0       Everyone   Art & Design;Creativity
## 6     167  5.6    5e+04 Free     0       Everyone              Art & Design
##       Last.Updated        Current.Ver  Android.Ver Paid
## 1  January 7, 2018              1.0.0 4.0.3 and up    0
## 2 January 15, 2018              2.0.0 4.0.3 and up    0
## 3   August 1, 2018              1.2.4 4.0.3 and up    0
## 4     June 8, 2018 Varies with device   4.2 and up    0
## 5    June 20, 2018                1.1   4.4 and up    0
## 6   March 26, 2017                1.0   2.3 and up    0
df$Content.Rating = as.factor(df$Content.Rating)
df$Genres = as.factor(df$Genres)
df$Category = as.factor(df$Category)

Perform log transformations

head(df)
##                                                  App       Category Rating
## 1     Photo Editor & Candy Camera & Grid & ScrapBook ART_AND_DESIGN    4.1
## 2                                Coloring book moana ART_AND_DESIGN    3.9
## 3 U Launcher Lite – FREE Live Cool Themes, Hide Apps ART_AND_DESIGN    4.7
## 4                              Sketch - Draw & Paint ART_AND_DESIGN    4.5
## 5              Pixel Draw - Number Art Coloring Book ART_AND_DESIGN    4.3
## 6                         Paper flowers instructions ART_AND_DESIGN    4.4
##   Reviews Size Installs Type Price Content.Rating                    Genres
## 1     159 19.0    1e+04 Free     0       Everyone              Art & Design
## 2     967 14.0    5e+05 Free     0       Everyone Art & Design;Pretend Play
## 3   87510  8.7    5e+06 Free     0       Everyone              Art & Design
## 4  215644 25.0    5e+07 Free     0           Teen              Art & Design
## 5     967  2.8    1e+05 Free     0       Everyone   Art & Design;Creativity
## 6     167  5.6    5e+04 Free     0       Everyone              Art & Design
##       Last.Updated        Current.Ver  Android.Ver Paid
## 1  January 7, 2018              1.0.0 4.0.3 and up    0
## 2 January 15, 2018              2.0.0 4.0.3 and up    0
## 3   August 1, 2018              1.2.4 4.0.3 and up    0
## 4     June 8, 2018 Varies with device   4.2 and up    0
## 5    June 20, 2018                1.1   4.4 and up    0
## 6   March 26, 2017                1.0   2.3 and up    0
df$log_Reviews <- log(df$Reviews + 1)
df$log_Installs <- log(df$Installs + 1)

4. Descriptive Analysis

  1. Statistics
library(dplyr)
## Warning: 程辑包'dplyr'是用R版本4.2.3 来建造的
## 
## 载入程辑包:'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
numerical_vars <- df %>%
  select_if(is.numeric)
summary(numerical_vars)
##      Rating         Reviews              Size           Installs        
##  Min.   :1.000   Min.   :       1   Min.   :  1.00   Min.   :1.000e+00  
##  1st Qu.:4.000   1st Qu.:     108   1st Qu.:  6.10   1st Qu.:1.000e+04  
##  Median :4.300   Median :    2324   Median : 16.00   Median :1.000e+05  
##  Mean   :4.174   Mean   :  294708   Mean   : 37.29   Mean   :8.419e+06  
##  3rd Qu.:4.500   3rd Qu.:   38980   3rd Qu.: 37.00   3rd Qu.:1.000e+06  
##  Max.   :5.000   Max.   :44893888   Max.   :994.00   Max.   :1.000e+09  
##      Price              Paid          log_Reviews       log_Installs    
##  Min.   :  0.000   Min.   :0.00000   Min.   : 0.6931   Min.   : 0.6931  
##  1st Qu.:  0.000   1st Qu.:0.00000   1st Qu.: 4.6890   1st Qu.: 9.2104  
##  Median :  0.000   Median :0.00000   Median : 7.7513   Median :11.5129  
##  Mean   :  1.128   Mean   :0.07492   Mean   : 7.7157   Mean   :11.6514  
##  3rd Qu.:  0.000   3rd Qu.:0.00000   3rd Qu.:10.5708   3rd Qu.:13.8155  
##  Max.   :400.000   Max.   :1.00000   Max.   :17.6198   Max.   :20.7233
  1. A rough inspection of patterns between pairs of variables in the data.
library(GGally)
## Warning: 程辑包'GGally'是用R版本4.2.3 来建造的
## Registered S3 method overwritten by 'GGally':
##   method from   
##   +.gg   ggplot2
numerical_vars <- df[, sapply(df, is.numeric)]
pairs(numerical_vars)

numerical_vars <- df %>%
  select_if(is.numeric)
correlations <- cor(numerical_vars)

library(corrplot)
## Warning: 程辑包'corrplot'是用R版本4.2.3 来建造的
## corrplot 0.92 loaded
corrplot(correlations, method="color", tl.srt=45)

From the pair plot and the correlation matrix, it appears that there may be certain patterns among certain variables. For instance, there is a relatively high correlation between ‘Installs’ and ‘Reviews,’ which aligns with our common understanding. Additionally, concerning the ‘Rating’ variable, the highest correlation is observed with the logarithm of ’Reviews.

  1. Which category commands the largest market share among the apps?
category_counts <- sort(table(df$Category), decreasing = TRUE)
category_counts <- as.data.frame(category_counts)
colnames(category_counts)[1] <- "Category"

ggplot(data = category_counts, aes(x = "", y = Freq, fill = Category)) +
  geom_bar(stat = "identity", width = 1, color = "white") +
  coord_polar("y", start = 0) +
  theme_void() +
  labs(title = "Category Distribution")

Among all categories, FAMILY and GAME collectively dominate the market, accounting for the highest share. The combined proportion of the top six categories exceeds 50%.

  1. How does the performance of the apps fare in terms of ratings?
ggplot(df, aes(x = Rating)) + geom_density(fill = "green", alpha = 0.6) +
  labs(title = "Density Plot of Rating", x = "Rating", y = "Density")

ggplot(df, aes(x = Category, y = Rating)) +
  geom_boxplot() +
  theme_void() +
  labs(title = "App Ratings Distribution") + 
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

library(dplyr)
avg_rating <- df %>%
  group_by(Category) %>%
  summarize(Avg_Rating = mean(Rating, na.rm = TRUE)) %>%
  arrange(desc(Avg_Rating))
print(avg_rating)
## # A tibble: 33 × 2
##    Category            Avg_Rating
##    <fct>                    <dbl>
##  1 EVENTS                    4.48
##  2 EDUCATION                 4.39
##  3 ART_AND_DESIGN            4.36
##  4 PARENTING                 4.35
##  5 PERSONALIZATION           4.32
##  6 BOOKS_AND_REFERENCE       4.32
##  7 BEAUTY                    4.29
##  8 GAME                      4.27
##  9 SOCIAL                    4.26
## 10 WEATHER                   4.24
## # ℹ 23 more rows

The distribution of ratings is skewed, with the highest probability density around 4.3. There are variations in ratings across different categories, and the ‘EVENTS’ category stands out with the highest average rating at 4.47.
5) Can the size of an app be managed, and does the app’s size have an influence on its rating

ggplot(df, aes(x = Size, y = Rating)) +
  geom_point(alpha = 0.5) +
  geom_smooth(method = "lm", se = TRUE, color = "blue") +
  labs(title = "Scatter Plot of Rating and Size", x = "Size", y = "Rating")
## `geom_smooth()` using formula = 'y ~ x'

From the graph, it can be observed that size has a slight impact on rating. Smaller-sized apps tend to have slightly higher ratings. However, it’s worth noting that many larger-sized apps also achieve high ratings.

  1. How to set pricing for an app?
ggplot(df, aes(x = log(Price))) + geom_density(fill = "green", alpha = 0.6) +
  labs(title = "Density Plot of Price", x = "Price(log)", y = "Density")
## Warning: Removed 7149 rows containing non-finite values (`stat_density()`).

The majority of apps are free, but there are also a few highly-priced apps.

top_categories <- df %>%
  group_by(Category) %>%
  summarize(Avg_Price = mean(Price), na.rm = TRUE) %>%
  top_n(7, Avg_Price) %>%
  arrange(desc(Avg_Price))

filtered_data <- df %>%
  filter(Category %in% top_categories$Category)

ggplot(filtered_data, aes(x = Category, y = log(Price))) +
  geom_violin() +
  labs(title = "Violin Plot of Top 7 Categories by Avg Price (log)", x = "Category", y = "Price (log)") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1, vjust = 1))
## Warning: Removed 2711 rows containing non-finite values (`stat_ydensity()`).

As depicted in the above graph, categories such as ‘Family’ and ‘Finance’ exhibit the highest average prices, suggesting that apps in these categories may adopt a premium pricing strategy.

  1. what is the difference between the paid and free APP
ggplot(df, aes(x = Type, y = log_Installs)) +
  geom_boxplot() +
  labs(title = "Boxplot of Downloads and Reviews for Paid Apps", x = "Type", y = "Downloads")

ggplot(df, aes(x = Type, y = Rating)) +
  geom_boxplot() +
  labs(title = "Boxplot of Downloads and Reviews for Paid Apps", x = "Type", y = "Downloads")

The download count for free apps significantly surpasses that of paid apps, yet paid apps tend to receive higher ratings.

5. Analysis Conclusion

1). There may be certain patterns among certain variables. For instance, there is a relatively high correlation between ‘Installs’ and ‘Reviews,’ which aligns with our common understanding. Additionally, concerning the ‘Rating’ variable, the highest correlation is observed with the logarithm of ’Reviews.

2). Among all categories, FAMILY and GAME collectively dominate the market, accounting for the highest share. The combined proportion of the top six categories exceeds 50%.

3). The distribution of ratings is skewed, with the highest probability density around 4.3. There are variations in ratings across different categories, and the ‘EVENTS’ category stands out with the highest average rating at 4.47.

4). Size has a slight impact on rating. Smaller-sized apps tend to have slightly higher ratings. However, it’s worth noting that many larger-sized apps also achieve high ratings.

5). The majority of apps are free, but categories such as ‘Family’ and ‘Finance’ exhibit the highest average prices, suggesting that apps in these categories may adopt a premium pricing strategy.

6). The download count for free apps significantly surpasses that of paid apps, yet paid apps tend to receive higher ratings.