SunKyoung Moon Solution for Kickbones1 project

Projects/SunKyoung Moon/SunKyoung Moon_Luis proj.Rmd

@@ -1,46 +1,60 @@
 ---
-title: "kickbones1_from SunKyoung Moon"
-output: md_document
-date: "2024-12-03"
+title: "kickbones1_from SunKyoung Moon(Ver.2.0)"
+output: html_document
+date: "2024-12-17"
 ---
 
+```{r load-libraries, echo=TRUE}
+
+# Load necessary libraries
 library(ggplot2)
 library(dplyr)
 library(tidyr)
 
-#Loading Data
-url <- "https://raw.githubusercontent.com/Dr-Eberle-Zentrum/Data-projects-with-R-and-GitHub/refs/heads/main/Projects/SunKyoung%20Moon/kaggle_dataset.csv"
-
-data <- read.csv(url)
+# Load data
+path <- "C:/R2_data/kaggle_dataset.csv"
+data <- read.csv(path)
 head(data)
 
 # Convert app usage time from minutes/day to hours/day
-data <- data %>%
+mutate_data <- data %>%
   mutate(AppUsageHours = `App.Usage.Time..min.day.` / 60)
 
-# Compute median app usage time and sum users for each device model
-device_summary <- data %>%
-  group_by(`Device.Model`, Gender) %>%
-  summarize(
-    MedianAppUsage = median(AppUsageHours, na.rm = TRUE),
-    UserCount = n()
-  ) %>%
-  ungroup()
+# Calculate user count per device model and sort in descending order
+device_user_counts <- mutate_data %>%
+  group_by(Device.Model) %>%
+  summarize(UserCount = n()) %>%
+  arrange(desc(UserCount)) # Sort by user count
+
+# Convert Device.Model to a factor with levels ordered by UserCount
+mutate_data$Device.Model <- factor(
+  mutate_data$Device.Model,
+  levels = device_user_counts$Device.Model
+)
+
+# Add user count to device labels for display on the x-axis
+mutate_data <- mutate_data %>%
+  left_join(device_user_counts, by = "Device.Model") %>%
+  mutate(DeviceLabel = paste0(Device.Model, "\n", UserCount, " Users"))
 
-# Summarize age groups for scatter plot
-data <- data %>%
+# Add age group column for grouping points in the scatter plot
+age_data <- mutate_data %>%
   mutate(AgeGroup = case_when(
     Age >= 20 & Age <= 29 ~ "20-29",
     Age >= 30 & Age <= 39 ~ "30-39",
     Age >= 40 & Age <= 49 ~ "40-49",
     Age >= 50 & Age <= 59 ~ "50-59",
-    TRUE ~ "Others"
+    TRUE ~ "Others" # Default for ages outside defined ranges
   ))
 
-#Visualization part!
-ggplot(data, aes(x = Device.Model, y = AppUsageHours, fill = Gender)) +
-  geom_violin(alpha = 0.7, scale = "width") +
-  geom_point(aes(color = AgeGroup), position = position_jitter(width = 0.2, height = 0), alpha = 0.5) +
+# Visualization: Violin plot with scatter plot overlay
+ggplot(age_data, aes(x = DeviceLabel, y = AppUsageHours, fill = Gender)) +
+  geom_violin(alpha = 0.7, scale = "width", position = position_dodge(width = 0.8)) +
+  geom_point(
+    aes(color = AgeGroup),
+    position = position_jitterdodge(jitter.width = 0.2, dodge.width = 0.8),
+    alpha = 0.5
+  ) +
   scale_fill_manual(values = c("Male" = "blue", "Female" = "red")) +
   scale_color_manual(values = c(
     "20-29" = "gray",
@@ -50,26 +64,13 @@ ggplot(data, aes(x = Device.Model, y = AppUsageHours, fill = Gender)) +
   )) +
   labs(
     title = "Mobile Device Usage for Different Models",
-    subtitle = "Median app usage time differentiated by gender and age groups",
+    subtitle = "Median app usage time differentiated by gender and age groups\nUser count displayed on x-axis",
     x = "Device Model",
     y = "Median App Usage Time (hours/day)",
     fill = "Gender",
     color = "Age Group"
   ) +
-  theme_minimal()
-
-device_user_counts <- data %>%
-  group_by(Device.Model) %>%
-  summarize(UserCount = n())
-
-ggplot(device_user_counts, aes(x = Device.Model, y = UserCount)) +
-  geom_col(fill = "lightblue") +
-  geom_text(aes(label = UserCount), vjust = -0.5) +
-  labs(
-    title = "User Count per Device Model",
-    x = "Device Model",
-    y = "User Count"
-  ) +
-  theme_minimal()
+  theme_minimal() +
+  theme(axis.text.x = element_text(angle = 30, hjust = 1))
 
 

Projects/SunKyoung Moon/SunKyoung-Moon_Luis-proj.md

@@ -1,44 +1,102 @@
-library(ggplot2) library(dplyr) library(tidyr)
+    # Load necessary libraries
+    library(ggplot2)
+    library(dplyr)
 
-\#Loading Data url <-
-“<https://raw.githubusercontent.com/Dr-Eberle-Zentrum/Data-projects-with-R-and-GitHub/refs/heads/main/Projects/SunKyoung%20Moon/kaggle_dataset.csv>”
+    ## 
+    ## 다음의 패키지를 부착합니다: 'dplyr'
 
-data &lt;- read.csv(url) head(data)
+    ## The following objects are masked from 'package:stats':
+    ## 
+    ##     filter, lag
 
-# Convert app usage time from minutes/day to hours/day
+    ## The following objects are masked from 'package:base':
+    ## 
+    ##     intersect, setdiff, setequal, union
 
-data &lt;- data %&gt;% mutate(AppUsageHours = `App.Usage.Time..min.day.`
-/ 60)
+    library(tidyr)
 
-# Compute median app usage time and sum users for each device model
+    # Load data
+    path <- "C:/R2_data/kaggle_dataset.csv"
+    data <- read.csv(path)
+    head(data)
 
-device\_summary &lt;- data %&gt;% group\_by(`Device.Model`, Gender)
-%&gt;% summarize( MedianAppUsage = median(AppUsageHours, na.rm = TRUE),
-UserCount = n() ) %&gt;% ungroup()
+    ##   User.ID   Device.Model Operating.System App.Usage.Time..min.day.
+    ## 1       1 Google Pixel 5          Android                      393
+    ## 2       2      OnePlus 9          Android                      268
+    ## 3       3   Xiaomi Mi 11          Android                      154
+    ## 4       4 Google Pixel 5          Android                      239
+    ## 5       5      iPhone 12              iOS                      187
+    ## 6       6 Google Pixel 5          Android                       99
+    ##   Screen.On.Time..hours.day. Battery.Drain..mAh.day. Number.of.Apps.Installed
+    ## 1                        6.4                    1872                       67
+    ## 2                        4.7                    1331                       42
+    ## 3                        4.0                     761                       32
+    ## 4                        4.8                    1676                       56
+    ## 5                        4.3                    1367                       58
+    ## 6                        2.0                     940                       35
+    ##   Data.Usage..MB.day. Age Gender User.Behavior.Class
+    ## 1                1122  40   Male                   4
+    ## 2                 944  47 Female                   3
+    ## 3                 322  42   Male                   2
+    ## 4                 871  20   Male                   3
+    ## 5                 988  31 Female                   3
+    ## 6                 564  31   Male                   2
 
-# Summarize age groups for scatter plot
+    # Convert app usage time from minutes/day to hours/day
+    mutate_data <- data %>%
+      mutate(AppUsageHours = `App.Usage.Time..min.day.` / 60)
 
-data &lt;- data %&gt;% mutate(AgeGroup = case\_when( Age &gt;= 20 & Age
-&lt;= 29 ~ “20-29”, Age &gt;= 30 & Age &lt;= 39 ~ “30-39”, Age &gt;= 40
-& Age &lt;= 49 ~ “40-49”, Age &gt;= 50 & Age &lt;= 59 ~ “50-59”, TRUE ~
-“Others” ))
+    # Calculate user count per device model and sort in descending order
+    device_user_counts <- mutate_data %>%
+      group_by(Device.Model) %>%
+      summarize(UserCount = n()) %>%
+      arrange(desc(UserCount)) # Sort by user count
 
-\#Visualization part! ggplot(data, aes(x = Device.Model, y =
-AppUsageHours, fill = Gender)) + geom\_violin(alpha = 0.7, scale =
-“width”) + geom\_point(aes(color = AgeGroup), position =
-position\_jitter(width = 0.2, height = 0), alpha = 0.5) +
-scale\_fill\_manual(values = c(“Male” = “blue”, “Female” = “red”)) +
-scale\_color\_manual(values = c( “20-29” = “gray”, “30-39” = “green”,
-“40-49” = “pink”, “50-59” = “purple” )) + labs( title = “Mobile Device
-Usage for Different Models”, subtitle = “Median app usage time
-differentiated by gender and age groups”, x = “Device Model”, y =
-“Median App Usage Time (hours/day)”, fill = “Gender”, color = “Age
-Group” ) + theme\_minimal()
+    # Convert Device.Model to a factor with levels ordered by UserCount
+    mutate_data$Device.Model <- factor(
+      mutate_data$Device.Model,
+      levels = device_user_counts$Device.Model
+    )
 
-device\_user\_counts &lt;- data %&gt;% group\_by(Device.Model) %&gt;%
-summarize(UserCount = n())
+    # Add user count to device labels for display on the x-axis
+    mutate_data <- mutate_data %>%
+      left_join(device_user_counts, by = "Device.Model") %>%
+      mutate(DeviceLabel = paste0(Device.Model, "\n", UserCount, " Users"))
 
-ggplot(device\_user\_counts, aes(x = Device.Model, y = UserCount)) +
-geom\_col(fill = “lightblue”) + geom\_text(aes(label = UserCount), vjust
-= -0.5) + labs( title = “User Count per Device Model”, x = “Device
-Model”, y = “User Count” ) + theme\_minimal()
+    # Add age group column for grouping points in the scatter plot
+    age_data <- mutate_data %>%
+      mutate(AgeGroup = case_when(
+        Age >= 20 & Age <= 29 ~ "20-29",
+        Age >= 30 & Age <= 39 ~ "30-39",
+        Age >= 40 & Age <= 49 ~ "40-49",
+        Age >= 50 & Age <= 59 ~ "50-59",
+        TRUE ~ "Others" # Default for ages outside defined ranges
+      ))
+
+    # Visualization: Violin plot with scatter plot overlay
+    ggplot(age_data, aes(x = DeviceLabel, y = AppUsageHours, fill = Gender)) +
+      geom_violin(alpha = 0.7, scale = "width", position = position_dodge(width = 0.8)) +
+      geom_point(
+        aes(color = AgeGroup),
+        position = position_jitterdodge(jitter.width = 0.2, dodge.width = 0.8),
+        alpha = 0.5
+      ) +
+      scale_fill_manual(values = c("Male" = "blue", "Female" = "red")) +
+      scale_color_manual(values = c(
+        "20-29" = "gray",
+        "30-39" = "green",
+        "40-49" = "pink",
+        "50-59" = "purple"
+      )) +
+      labs(
+        title = "Mobile Device Usage for Different Models",
+        subtitle = "Median app usage time differentiated by gender and age groups\nUser count displayed on x-axis",
+        x = "Device Model",
+        y = "Median App Usage Time (hours/day)",
+        fill = "Gender",
+        color = "Age Group"
+      ) +
+      theme_minimal() +
+      theme(axis.text.x = element_text(angle = 30, hjust = 1))
+
+![](SunKyoung-Moon_Luis-proj_files/figure-markdown_strict/load-libraries-1.png)

Projects/kickbones1/Result Image.Rmd

@@ -0,0 +1,13 @@
+---
+title: "kickbones1_from SunKyoung Moon(fist trial)"
+author: "Luis"
+output: md_document
+date: "2024-12-03"
+---
+
+#Result Image
+![Result](solution for kickbones1(first trial).png)
+
+```r
+```{r, echo=FALSE, out.width="50%"}
+knitr::include_graphics("solution for kickbones1(first trial).png")

Projects/kickbones1/Result-Image.md

@@ -0,0 +1,4 @@
+\#Result Image ![Result](solution%20for%20kickbones1(first%20trial).png)
+
+\`\`\`r
+<img src="solution for kickbones1(first trial).png" width="50%" />

Projects/kickbones1/Solution for kickbones1 (first trial).Rmd

@@ -0,0 +1,80 @@
+---
+title: "kickbones1_from SunKyoung Moon(fist trial)"
+author: "Luis"
+output: md_document
+date: "2024-12-03"
+---
+
+library(ggplot2)
+library(dplyr)
+library(tidyr)
+
+#Loading Data
+url <- "https://raw.githubusercontent.com/Dr-Eberle-Zentrum/Data-projects-with-R-and-GitHub/refs/heads/main/Projects/SunKyoung%20Moon/kaggle_dataset.csv"
+
+data <- read.csv(url)
+head(data)
+
+# Convert app usage time from minutes/day to hours/day
+data <- data %>%
+  mutate(AppUsageHours = `App.Usage.Time..min.day.` / 60)
+
+# Compute median app usage time and sum users for each device model
+device_summary <- data %>%
+  group_by(`Device.Model`, Gender) %>%
+  summarize(
+    MedianAppUsage = median(AppUsageHours, na.rm = TRUE),
+    UserCount = n()
+  ) %>%
+  ungroup()
+
+# Summarize age groups for scatter plot
+data <- data %>%
+  mutate(AgeGroup = case_when(
+    Age >= 20 & Age <= 29 ~ "20-29",
+    Age >= 30 & Age <= 39 ~ "30-39",
+    Age >= 40 & Age <= 49 ~ "40-49",
+    Age >= 50 & Age <= 59 ~ "50-59",
+    TRUE ~ "Others"
+  ))
+
+#Visualization part!
+ggplot(data, aes(x = Device.Model, y = AppUsageHours, fill = Gender)) +
+  geom_violin(alpha = 0.7, scale = "width") +
+  geom_point(aes(color = AgeGroup), position = position_jitter(width = 0.2, height = 0), alpha = 0.5) +
+  scale_fill_manual(values = c("Male" = "blue", "Female" = "red")) +
+  scale_color_manual(values = c(
+    "20-29" = "gray",
+    "30-39" = "green",
+    "40-49" = "pink",
+    "50-59" = "purple"
+  )) +
+  labs(
+    title = "Mobile Device Usage for Different Models",
+    subtitle = "Median app usage time differentiated by gender and age groups",
+    x = "Device Model",
+    y = "Median App Usage Time (hours/day)",
+    fill = "Gender",
+    color = "Age Group"
+  ) +
+  theme_minimal()
+
+device_user_counts <- data %>%
+  group_by(Device.Model) %>%
+  summarize(UserCount = n())
+
+ggplot(device_user_counts, aes(x = Device.Model, y = UserCount)) +
+  geom_col(fill = "lightblue") +
+  geom_text(aes(label = UserCount), vjust = -0.5) +
+  labs(
+    title = "User Count per Device Model",
+    x = "Device Model",
+    y = "User Count"
+  ) +
+  theme_minimal()
+
+#Result
+
+![visualization_Result](https://imgur.com/jni0RwO)
+![Visualization_Result2](https://imgur.com/DOEtSmH)
+

Projects/kickbones1/Solution-for-kickbones1--first-trial-.md

@@ -0,0 +1,47 @@
+library(ggplot2) library(dplyr) library(tidyr)
+
+\#Loading Data url <-
+“<https://raw.githubusercontent.com/Dr-Eberle-Zentrum/Data-projects-with-R-and-GitHub/refs/heads/main/Projects/SunKyoung%20Moon/kaggle_dataset.csv>”
+
+data &lt;- read.csv(url) head(data)
+
+# Convert app usage time from minutes/day to hours/day
+
+data &lt;- data %&gt;% mutate(AppUsageHours = `App.Usage.Time..min.day.`
+/ 60)
+
+# Compute median app usage time and sum users for each device model
+
+device\_summary &lt;- data %&gt;% group\_by(`Device.Model`, Gender)
+%&gt;% summarize( MedianAppUsage = median(AppUsageHours, na.rm = TRUE),
+UserCount = n() ) %&gt;% ungroup()
+
+# Summarize age groups for scatter plot
+
+data &lt;- data %&gt;% mutate(AgeGroup = case\_when( Age &gt;= 20 & Age
+&lt;= 29 ~ “20-29”, Age &gt;= 30 & Age &lt;= 39 ~ “30-39”, Age &gt;= 40
+& Age &lt;= 49 ~ “40-49”, Age &gt;= 50 & Age &lt;= 59 ~ “50-59”, TRUE ~
+“Others” ))
+
+\#Visualization part! ggplot(data, aes(x = Device.Model, y =
+AppUsageHours, fill = Gender)) + geom\_violin(alpha = 0.7, scale =
+“width”) + geom\_point(aes(color = AgeGroup), position =
+position\_jitter(width = 0.2, height = 0), alpha = 0.5) +
+scale\_fill\_manual(values = c(“Male” = “blue”, “Female” = “red”)) +
+scale\_color\_manual(values = c( “20-29” = “gray”, “30-39” = “green”,
+“40-49” = “pink”, “50-59” = “purple” )) + labs( title = “Mobile Device
+Usage for Different Models”, subtitle = “Median app usage time
+differentiated by gender and age groups”, x = “Device Model”, y =
+“Median App Usage Time (hours/day)”, fill = “Gender”, color = “Age
+Group” ) + theme\_minimal()
+
+device\_user\_counts &lt;- data %&gt;% group\_by(Device.Model) %&gt;%
+summarize(UserCount = n())
+
+ggplot(device\_user\_counts, aes(x = Device.Model, y = UserCount)) +
+geom\_col(fill = “lightblue”) + geom\_text(aes(label = UserCount), vjust
+= -0.5) + labs( title = “User Count per Device Model”, x = “Device
+Model”, y = “User Count” ) + theme\_minimal()
+
+\#Result ![visualization\_Result](https://imgur.com/jni0RwO)
+![Visualization\_Result2](https://imgur.com/DOEtSmH)