阅读量:0
小小练习。见代码+注释
# 加载必要的包 library(rvest) library(dplyr) library(tidyr) # 指定网页URL url <- "https://research.un.org/en/unmembers/scmembers" # 读取网页内容 webpage <- read_html(url) # 提取所有表格节点 table_nodes <- html_nodes(webpage, "table") # 将第一个表格转换为数据框 sc_members_table1 <- html_table(table_nodes[1], fill = TRUE) # 将第二个表格转换为数据框 sc_members_table2 <- html_table(table_nodes[2], fill = TRUE) # 合并两个数据框 sc_members_combined <- bind_rows(sc_members_table1, sc_members_table2) # 显示合并后的数据框 print(sc_members_combined) # 保存合并后的数据框为CSV文件 write.csv(sc_members_combined, "web_data.csv", row.names = FALSE) # ------------------------------ 处理数据。 ------------------------------ # 读取CSV文件 data <- read.csv("web_data.csv", stringsAsFactors = FALSE) data # 删掉最后一列 data <- data[, -ncol(data)] head(data, 2) # 拆分Members of Security Council列 print(colnames(data)) # Members.of.Security.Council # 分割国家为单独的行 Members of Security Council data_split <- data %>% separate_rows(`Members.of.Security.Council`, sep = ", ") %>% select(Year, `Members.of.Security.Council`) # 重命名列 colnames(data_split) <- c("Year", "Country") # 列出联合国常任理事国的英文名字 permanent_members <- c("China", "France", "Russian Federation", "United Kingdom", "United States") # 新建一列 votes,所有值为 1 data_split <- data_split %>% mutate(votes = 1) # 新建一列 veto,对于常任理事国,veto 值为 1,否则为 0 data_split <- data_split %>% mutate(veto = ifelse(Country %in% permanent_members, 1, 0)) # 新建一列 vote_share,根据 Year 列的值进行计算 data_split <- data_split %>% mutate(vote_share = ifelse(Year >= 1996, 1/15, 1/11)) # 保存结果到新的CSV文件 write.csv(data_split, "clean_data.csv", row.names = FALSE) # 查看结果 print(data_split)