Analysis and Modeling

section I 分离文件(不降低重复)

获取重复值的索引->which(duplicated(Data.condition))

删除重复值-> Data[!duplicated(Data.condition),]

手动运行年份2021-2015

data <- read.csv("/Users/kunle/Documents/pythonProject/小论文/PythonScripts/2021-2015.csv")
data_2021 <- data %>%
  filter(Date == 2021)
write.csv(data_2021, "/Users/kunle/Documents/pythonProject/小论文/TXTData/2021_TXT.csv")

手动运行年份2012,2013

data <- read.csv("/Users/kunle/Documents/pythonProject/小论文/TXTData/2012-2013.csv")
data_2013 <- data %>%
  filter(Date == 2013)
write.csv(data_2013, "/Users/kunle/Documents/pythonProject/小论文/TXTData/2013_TXT.csv")

Section II 词频柱状图

制作数据混合表

date = c(2012,2013,2014,2015,2016,2017,2018,2019,2020,2021)
Power_list <- c()
Solution_list <- c()
Spirit_list <- c()
Result_list <- c()
for (i in 1:length(date)){
  str = paste("/Users/kunle/Documents/pythonProject/小论文/TXTData/",date[i],"_TXT.csv", sep = "")
  data <- read.csv(str)
  Power_list[i] <- sum(data$Power)
  Solution_list[i] <- sum(data$Solution)
  Spirit_list[i] <- sum(data$Spirit)
  Result_list[i] <- sum(data$Result)
}
all_data <- data.frame(date = date,
                       Power = Power_list,
                       Solution = Solution_list,
                       Spirit = Spirit_list,
                       Result = Result_list)
all_data <- melt(all_data, id = "date")
head(all_data)

绘图

ggplot(all_data, aes(x = date, y = value, fill = variable)) + 
  geom_bar(stat='identity', position = 'dodge') + 
  labs(x = "年份", y = "频数") +
  scale_x_discrete(limits = date) +
  theme(text = element_text(family='Kai'), legend.position = c(0.02, 0.98), legend.justification = c(0,1))

Warning: Continuous limits supplied to discrete scale.
Did you mean `limits = factor(...)` or `scale_*_continuous()`?

保存本地

setwd("/Users/kunle/Documents/pythonProject/小论文/Results For Paper")
ggsave(filename = "1.png", width = 13, height = 8, units = "in", dpi = 400)