solution by Yue for Jun Gi

Projects/JungiHong/Yue_Z9.Rmd

@@ -0,0 +1,106 @@
+---
+title: "Yue_Z9"
+output: md_document
+date: "2024-12-04"
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+```{r pressure,echo=FALSE}
+
+library(ggplot2)
+library(tidyverse)
+library(readxl)
+
+#the first one
+#read xlsx file
+file<-"Volleyball Passing- USA and TU.xlsx"
+data <- read_excel(file,sheet = "TU sort by pass score")
+new_data <- data[2:5, 6:9]
+
+#Formation of new data
+colnames(new_data) <- c("Pass Score", "Attempts", "Points_Won", "Points_Lost")
+
+clean_data <- new_data %>%
+  mutate(
+    Pass_Score = as.factor("Pass Score"),
+    Attempts = as.numeric(Attempts),
+    Points_Won = as.numeric(Points_Won),
+    Points_Lost = as.numeric(Points_Lost)
+  ) %>%
+  pivot_longer(
+    cols = c(Points_Won, Points_Lost), 
+    names_to = "Outcome", 
+    values_to = "Count"
+  ) %>%
+  group_by(`Pass Score`) %>%
+  mutate(`Pass Score` = factor(`Pass Score`, levels = c("zeros", "ones", "twos", "threes")))
+
+# visualization
+ggplot(clean_data, aes(x = `Pass Score`, y= Count ,fill = Outcome)) +
+  geom_bar(stat = "identity", position = "stack") +
+  labs(
+    title = "Stacked Bar Chart: Breakdown of Points Won and Lost by Pass Score",
+    x = "Pass Score Categories",
+    y = "Total Attempts"
+  ) +
+  theme_minimal() +
+  scale_fill_manual(values = c("Points_Won" = "skyblue", "Points_Lost" = "tomato"))
+
+#THE second
+#get data
+folder_path <- "passing stats"
+file_list <- list.files(path = folder_path, pattern = "\\.xlsx$", full.names = TRUE)
+#read every data
+extract_totals_data <- function(file_path) {
+  data <- read_excel(file_path, sheet = "totals")
+#last 3
+  last_three_rows <- tail(data, 3)
+  colnames(last_three_rows) <- as.character(last_three_rows[1, ])
+#delate first row
+  last_three_rows <- last_three_rows[-1, ]
+#filter
+  filtered_data <- last_three_rows[, c("side-outs", "points", "average")]
+  return(filtered_data)
+}
+#new data
+results_list <- lapply(file_list, extract_totals_data)
+final_results <- do.call(rbind, results_list)
+final_results <- final_results %>%
+  mutate(average = round(as.numeric(average), 2))
+print(final_results)
+
+final_results$points <- as.numeric(as.character(final_results$points))
+final_results$average <- as.numeric(as.character(final_results$average))
+
+#won and lost
+won_data <- final_results[final_results$`side-outs` == "won", ]
+lost_data <- final_results[final_results$`side-outs` == "lost", ]
+
+
+# cor
+won_cor <- cor(won_data$average, won_data$points, use = "complete.obs")
+lost_cor <- cor(lost_data$average,lost_data$points, use = "complete.obs")
+
+# plot
+ggplot(final_results, aes(x = average, y = points, color = `side-outs`, shape = `side-outs`)) +
+  geom_point(size = 3) +
+  geom_smooth(method = "lm", se = FALSE) + 
+  scale_color_manual(values = c("won" = "blue", "lost" = "red")) +
+  scale_shape_manual(values = c("won" = 16, "lost" = 17)) + 
+  labs(title = "Correlation Between Passing Scores and Points Won/Lost",
+       x = "Passing Score (Average)", 
+       y = "Points (Won or Lost)",
+       color = "Side-outs", shape = "Side-outs") + 
+  annotate("text", x = 2.0, y = 180, 
+           label = paste("Won Trend (r =", round(won_cor, 2), ")", sep = ""),
+           color = "blue", hjust = 0, vjust = 1) +
+  annotate("text", x = 2.0, y = 170, 
+           label = paste("Lost Trend (r =", round(lost_cor, 2), ")", sep = ""),
+           color = "red", hjust = 0, vjust = 1) +
+  theme_minimal() +
+  theme(legend.position = "topleft")
+
+
+```

Projects/JungiHong/Yue_Z9.md

@@ -0,0 +1,39 @@
+    ## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
+    ## ✔ dplyr     1.1.4     ✔ readr     2.1.5
+    ## ✔ forcats   1.0.0     ✔ stringr   1.5.1
+    ## ✔ lubridate 1.9.3     ✔ tibble    3.2.1
+    ## ✔ purrr     1.0.2     ✔ tidyr     1.3.1
+    ## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
+    ## ✖ dplyr::filter() masks stats::filter()
+    ## ✖ dplyr::lag()    masks stats::lag()
+    ## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
+    ## New names:
+
+![](Yue_Z9_files/figure-markdown_strict/pressure-1.png)
+
+    ## New names:
+    ## New names:
+    ## New names:
+    ## New names:
+    ## New names:
+    ## • `` -> `...5`
+    ## • `` -> `...6`
+    ## • `` -> `...7`
+
+    ## # A tibble: 10 × 3
+    ##    `side-outs` points average
+    ##    <chr>       <chr>    <dbl>
+    ##  1 won         150       2.83
+    ##  2 lost        53        2.04
+    ##  3 won         117       2.66
+    ##  4 lost        30        2.14
+    ##  5 won         140       2.69
+    ##  6 lost        81        2.08
+    ##  7 won         161       2.52
+    ##  8 lost        58        2.52
+    ##  9 won         93        2.38
+    ## 10 lost        67        2.09
+
+    ## `geom_smooth()` using formula = 'y ~ x'
+
+![](Yue_Z9_files/figure-markdown_strict/pressure-2.png)