legis_Taiwan(0329)

install.packages("remotes", repos = "https://cran.r-project.org/")

## 
## The downloaded binary packages are in
##  /var/folders/rz/qgdl4bg53r3__zyx803f25mc0000gn/T//RtmpOoYlli/downloaded_packages

remotes::install_github("davidycliao/legisTaiwan@0.2.1", force = TRUE)

## 
## ── R CMD build ─────────────────────────────────────────────────────────────────
##      checking for file ‘/private/var/folders/rz/qgdl4bg53r3__zyx803f25mc0000gn/T/RtmpOoYlli/remotes1273747c55c78/davidycliao-legisTaiwan-989ef0e/DESCRIPTION’ ...  ✔  checking for file ‘/private/var/folders/rz/qgdl4bg53r3__zyx803f25mc0000gn/T/RtmpOoYlli/remotes1273747c55c78/davidycliao-legisTaiwan-989ef0e/DESCRIPTION’
##   ─  preparing ‘legisTaiwan’:
##        checking DESCRIPTION meta-information ...  ✔  checking DESCRIPTION meta-information
##   ─  checking for LF line-endings in source and make files and shell scripts
##   ─  checking for empty or unneeded directories
##   ─  building ‘legisTaiwan_0.2.1.tar.gz’
##      
## 

library("legisTaiwan")
library("ggplot2")
library(dplyr)
library(tidyr)
library(stringr)
library(tidytext)

我做的function: get_ly_bills(), get_ly_legislators_by_term(), get_ly_legislator_cosign_bills(), get_ly_committee_meets(), get_ly_interpellations()

get_ly_bills()

Distribution of 議案狀態 by 會期

Distribution of 議案狀態 by 提案來源 （可以講解就好不用實作）

## Obtain the data by 議案狀態 and 提案來源
bill_origin_count <- final_bills_df %>% 
  group_by(議案狀態, 提案來源) %>% 
  summarise(count = n(), .groups = 'drop') %>% 
  arrange(desc(count))

# Bar plot for 議案狀態 by 提案來源
ggplot(bill_origin_count, aes(x = 議案狀態, y = count, fill = 提案來源)) +
  geom_bar(stat = "identity", position = "stack") +
  labs(
    title = "不同提案來源之議案狀態分佈",
    x = "議案狀態",
    y = "提案數量",
    fill = "提案來源",
  )+
  theme_minimal()+
  theme(axis.text.x = element_text(angle = 45, hjust = 1))+
  theme(text = element_text(family = "Heiti TC Light"))

## Obtain the data from page 1 to page 100 in term 10 （講解就好）

民眾黨在第10屆之提案數量by會期 （可實作）

#Calculate data by 會期 and 提案單位
bills_origin_term10 <- bills_origin_term10_normalized %>% 
  group_by(會期, 提案單位) %>% 
  summarise(count = n(), .groups = 'drop') %>% 
  arrange(會期, desc(count))

#Filter keyword with 黨團
bills_origin_term10_with_party <- bills_origin_term10 %>%
  filter(str_detect(提案單位, "黨團"))

#Filter keyword with 本院台灣民眾黨黨團
minzhongdang_term10 <- bills_origin_term10_with_party %>% 
  filter(str_detect(提案單位, "本院台灣民眾黨黨團"))

#Create plots
ggplot(minzhongdang_term10, aes(x = 會期, y = count)) +
  geom_line(color = "blue", size = 1) +  
  geom_point(color = "red", size = 2) +   
  labs(
    title = "台灣民眾黨在不同會期的提案數量變化(第十屆)",
    x = "會期",
    y = "提案數量"
  ) +
  theme_minimal() + 
  theme(text = element_text(family = "Heiti TC Light")) +
  scale_x_continuous(breaks = seq(min(minzhongdang_term10$會期),
                                  max(minzhongdang_term10$會期),
                                  by = 1))

## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

議案類別 by 會期（可實作）

# Calculate bill categories by different session and drop NA
bills_cat_term10 <- bills_origin_term10_normalized %>% 
  group_by(會期, 議案類別) %>% 
  summarise(count = n(), .groups = 'drop') %>% 
  filter(議案類別 != "--") %>%
  arrange(會期, desc(count))

# Create plot
ggplot(bills_cat_term10, aes(x = 會期, y = count, fill = 議案類別)) +
  geom_bar(stat = "identity", position = "stack") +
  labs(
    title = "不同會期之立委提出議案類別數量",
    x = "會期",
    y = "議案數量",
    fill = "議案類別"
  ) +
  theme(text = element_text(family = "Heiti TC Light"))+
  scale_x_continuous(breaks = seq(min(bills_origin_term10_with_party$會期, na.rm = TRUE), 
                                  max(bills_origin_term10_with_party$會期, na.rm = TRUE), 
                                  by = 1)) 

## Warning: Removed 1 row containing missing values or values outside the scale range
## (`geom_bar()`).

分析第10屆立委提案中帶有兩岸、中國、大陸等字眼之法案（可實作）

get_ly_legislators_by_term （可實作）

Distribution of legislators by party

KMT legislators by different terms (可實作)

DPP legislators by different terms (可實作)

get_ly_legislator_cosign_bills() 可實作

Get 魯明哲co-signed bills and their status in term 8

Get鍾佳濱co-signed bills and their status in term 8 （可解釋不用實作）

get_ly_committee_meets() 可實作

於國防外交委員會（code= 35）中抓取第一頁資料（100筆）並分析會議種類與數量

meet <- get_ly_committee_meets(35)

## 
## Fetching meetings data for committee ID 35...
##   |                                                                              |                                                                      |   0%  |                                                                              |==============                                                        |  20%  |                                                                              |============================                                          |  40%  |                                                                              |==========================================                            |  60%  |                                                                              |========================================================              |  80%  |                                                                              |======================================================================| 100%
## 
## 
## ====== Retrieved Information ======
## -----------------------------------
## Total Meetings: 743
## Page: 1 of 8
## Records per page: 100
## 
## Meeting Type Distribution:
##  公聽會: 1
##  委員會: 86
##  聯席會議: 8
##  黨團協商: 5
## 
## Session Distribution:
##  Session 1: 40
##  Session 2: 29
##  Session 3: 11
##  Session 7: 5
##  Session 8: 15
## 
## Location Distribution:
##  紅樓301會議室: 97
##  紅樓302會議室: 1
##  群賢樓801會議室: 1
##  群賢樓9樓大禮堂: 1
## ===================================

meet_data <- meet$meetings
meet_data$會議種類 <- as.factor(meet_data$會議種類)

# Create plots: 會議種類與數量
ggplot(meet_data, aes(x = 會議種類)) + 
  geom_bar(fill = "skyblue", color = "black") +  # 填充顏色並加上邊框
  theme_minimal() +  # 使用乾淨的主題
  labs(
    title = "會議種類分佈",  # 圖標題
    x = "會議種類",  # x軸標籤
    y = "頻次"  # y軸標籤
  ) + 
  theme(axis.text.x = element_text(angle = 45, hjust = 1))+
  theme(text = element_text(family = "Heiti TC Light"))

於國防外交委員會當中，出席次數前十名的委員並繪製條狀圖（可實作）

#Clean data
attendees <- meet_data %>%
  separate_rows(出席委員, sep = ",") %>%  
  filter(!is.na(出席委員) & 出席委員 != "")

#Obtain data by 出席委員
attendees_count <- attendees %>% 
  group_by(出席委員) %>% 
  summarise(count = n(), .groups = "drop") %>% 
  arrange(desc(count))

# Grab top 10
top_10_attendees <- attendees_count %>% 
  head(10)

# Create plots: 國防外交委員會中前十名的出席委員
ggplot(top_10_attendees, aes(x = reorder(出席委員, count), y = count)) + 
  geom_bar(stat = "identity", fill = "steelblue", color = "black") + 
  coord_flip() +  
  theme_minimal() +
  labs(
    title = "Top 10 出席委員（國防外交委員會）",
    x = "委員名稱",
    y = "出席次數"
  ) + 
  theme(axis.text.x = element_text(angle = 45, hjust = 1))+
  theme(text = element_text(family = "Heiti TC Light"))

於國防外交委員會當中，出席次數大於40次的委員並繪製散點圖(可實作 蠻酷)

#Clean data
attendees <- meet_data %>%
  separate_rows(出席委員, sep = ",") %>%  # 根據 "、" 進行分割
  filter(!is.na(出席委員) & 出席委員 != "")

#Obtain data by 出席次數大於40次的立委
attendees_count_40 <- attendees %>% 
  group_by(出席委員) %>% 
  summarise(count = n(), .groups = "drop") %>% 
  filter(count > 40) %>% 
  arrange(count) 

#Create plots: 立委與出席次數
ggplot(attendees_count_40, aes(x = 出席委員, y = count)) +
  geom_point(aes(color = 出席委員)) +
  geom_text(aes(label = 出席委員), vjust = -0.5, size = 3, check_overlap = TRUE, 
             family = "Heiti TC Light") +  # 確保這裡也設置了字體
  theme_minimal() +
  labs(
    title = "立法委員與出席次數",
    x = "立法委員",
    y = "出席次數"
  ) +
  theme(axis.text.x = element_blank(),
        legend.title = element_text(family = "Heiti TC Light"),  # 確保圖例標題也使用中文字體
        legend.text = element_text(family = "Heiti TC Light"),
        plot.title = element_text(family = "Heiti TC Light"),
        axis.title.x = element_text(family = "Heiti TC Light"),
        axis.title.y = element_text(family = "Heiti TC Light")) 

get_ly_interpellations()、有網址(可實作)

第八屆立委中，前十位質詢次數的有哪些立委？（抓取前100頁資料）

第八屆立委當中，質詢當中最常出現的關鍵字前十名（可實作，簡單的text analysis）

#Filter key words in interpellations
duty_words <- final_interpellations_df %>% 
  unnest_tokens(word, description) %>%
  count(word, sort = TRUE) %>%
  filter(nchar(word) > 1)

#View the data
top_duty_words <- head(duty_words, 10)

#Creating plots with keywords frequency in interperllation
ggplot(top_duty_words, aes(x = reorder(word, n), y = n)) +
  geom_bar(stat = "identity", fill = "steelblue3") +
  labs(title = "Frequency of Keywords in Interpellation Descriptions", 
       x = "Keyword", y = "Frequency") +
  theme_minimal() +
  coord_flip()+
  theme(text = element_text(family = "Heiti TC Light"))

按會期和立法者來分質詢次數: （可實作）

Top ten interperlation by legislators from session 1 to 8 in term 8

# Step 1: 整理資料 + 抓前五名立委
top_5_legislators <- final_interpellations_df %>%
  separate_rows(legislators, sep = ",") %>%
  filter(!is.na(sessionTimes)) %>%
  mutate(sessionTimes = as.numeric(sessionTimes)) %>%
  group_by(legislators) %>%
  summarise(total_count = n(), .groups = "drop") %>%
  slice_max(order_by = total_count, n = 5)

# Step 2: 篩選資料並重新統計
filtered_data <- final_interpellations_df %>%
  separate_rows(legislators, sep = ",") %>%
  filter(legislators %in% top_5_legislators$legislators,
         !is.na(sessionTimes)) %>%
  mutate(sessionTimes = as.numeric(sessionTimes)) %>%
  group_by(legislators, sessionTimes) %>%
  summarise(count = n(), .groups = "drop")

# Step 3: 畫圖
ggplot(filtered_data, aes(x = sessionTimes, y = count, 
                          group = legislators, color = legislators)) +
  geom_line() + 
  labs(title = "各會期中前五名立法者的質詢次數趨勢（第八屆）",
       x = "會期",
       y = "質詢次數") +
  theme_minimal() +
  scale_x_continuous(
    breaks = sort(unique(filtered_data$sessionTimes)),
    labels = paste0("第", sort(unique(filtered_data$sessionTimes)), "會期")
  ) +
  theme(
    axis.text.x = element_text(angle = 45, hjust = 1, family = "Heiti TC Light"),
    text = element_text(family = "Heiti TC Light")
  )