R中几个类别变量除以一个类别变量的条形图

问题描述

我想想一想分类变量对于其他几个分类变量的变化。

我的数据看起来像这样

ax.xaxis.labelpad = -10 # Adjust x-axis label position

在我的真实################################# ### Modules imported used ### ################################# import pandas as pd import numpy as np from datetime import datetime from datetime import date import time import matplotlib.pyplot as plt import matplotlib import matplotlib.dates as mdates # file_path_setup = 'G:/Stocks/PowerPivotApps/Price download/' # Performance_History = pd.read_csv(file_path_setup + 'Performance.txt',dtype=str,sep=',') # Portfolio = Performance_History.loc[Performance_History['ExecutionType'] == 'All Portfolios'] # Portfolio = Performance_History.loc[Performance_History['ExecutionType'] == 'Selected Portfolios'] # remove "# set minimum level for performance time" #Portfolios_Nr_of_Stocks = Portfolio['NrOfStocks'] #Portfolio_Performance_Time = Portfolio['PerformanceTime'] #Portfolio_Date = Portfolio['Date'] Portfolio_Date = ['2020-08-31','2020-09-01','2020-09-02','2020-09-03','2020-09-04','2020-09-07','2020-09-08','2020-09-09','2020-09-10','2020-09-11','2020-09-14','2020-09-15','2020-09-16','2020-09-17','2020-09-18','2020-09-21','2020-09-22','2020-09-23','2020-09-24','2020-09-25','2020-09-28','2020-09-29','2020-09-30','2020-10-01','2020-10-02','2020-10-05','2020-10-06','2020-10-07','2020-10-08','2020-10-09','2020-10-12','2020-10-13','2020-10-14','2020-10-15','2020-10-16'] Portfolio_Performance_Time =['00:11:11','00:11:07','00:11:16','00:10:42','00:10:54','00:10:46','00:10:27','00:11:23','00:11:35','00:10:23','00:10:51','00:41:22','00:11:05','00:11:15','00:10:50','00:10:41','00:19:47','00:10:43','00:10:48','00:11:12','00:10:45','00:11:02','00:10:57','00:11:01','00:15:17','00:14:33','00:18:49','00:14:28','00:20:45','00:14:29','00:14:45','00:17:52','00:14:37','00:14:08','00:15:05','00:14:46','00:14:39','00:14:40'] Portfolios_Nr_of_Stocks = ['621','619','617','622','621','613','607','620','680','679','681','488','678','676','676'] # Convert To integer numberofstocks = [int(stock) for stock in Portfolios_Nr_of_Stocks] # Convert to time def get_sec(time_str): """Get Seconds from time.""" h,m,s = time_str.split(':') return int(h) * 3600 + int(m) * 60 + int(s) PerformanceTime = [get_sec(t) for t in Portfolio_Performance_Time] # print(type(numberofstocks)) # print type # convert to date series date_portfolio = [datetime.strptime(d,'%Y-%m-%d') for d in Portfolio_Date] # https://matplotlib.org/gallery/api/two_scales.html # https://cmdlinetips.com/2019/10/how-to-make-a-plot-with-two-different-y-axis-in-python-with-matplotlib/ # create figure and axis objects with subplots() fig,ax = plt.subplots(figsize=(12,8)) # figsize -> size of the plot window # make a plot ax.plot(date_portfolio,PerformanceTime,color="red",marker="x") # set x-axis label ax.set_xlabel("Date",fontsize=14) # set y-axis label ax.set_ylabel("Performance Time",fontsize=14) # set title ax.set_title("Execution History",fontsize=20,loc="center",pad=10) # format y-axis label to hh:mm:ss formatter_yx1 = matplotlib.ticker.FuncFormatter(lambda s,x: time.strftime('%H:%M:%S',time.gmtime(s))) ax.yaxis.set_major_formatter(formatter_yx1) # rotate x-axis lables and adjust size plt.xticks(rotation=90,ha='right') # plt.xticks(rotation=90,ha='right',fontsize='x-small') # Small font text # set minimum level for performance time,y-axis 1 ax.set_ylim([min(PerformanceTime)-100,25*60]) # -100 -> set minimum. 25*60 -> Set maximum # twin object for two different y-axis on the sample plot ax2=ax.twinx() # make a plot with different y-axis using second axis object ax2.plot(date_portfolio,numberofstocks,color="blue",marker="o") # ax2.set_ylim([620,680]) ax2.set_ylabel("Nr Of Stocks",fontsize=14) # set minimum level for performance time,y-axis 2 ax2.set_ylim([600,max(numberofstocks)+10]) # -100 -> set minimum. 25*60 -> Set maximum # set date interval ax.xaxis.set_major_locator(mdates.DayLocator(interval=7)) # max interval ax.xaxis.set_minor_locator(mdates.DayLocator(interval=1)) # minimum interval ax.xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m-%d')) # set date format ax.xaxis.labelpad = -10 # Adjust x-axis label position # Plot graph plt.show() 中，我有13个类别变量，我想按类别对它们进行如下划分。

有没有更简单的方法可以对 Species Class species2 1 setosa 1 0 2 setosa 1 1 3 setosa 1 0 4 setosa 1 1 5 setosa 1 0 6 setosa 1 1 7 setosa 0 0 8 setosa 0 1 9 setosa 1 1 10 setosa 1 1 中的点阵或其他软件包执行此操作？理想情况下，我想要一个带有每个变量面板的图，显示每个级别的计数或百分率，并用变量“类”进行着色。

在此示例中，我使用了以下代码。

dataset

解决方法

也许您正在寻找这个。我建议您使用ggplot2。接下来描述的代码可以根据需要为每个变量构建图。它被称为一个墓地。获得它的关键是将数据重塑得很长。根据您的代码，您必须根据每个变量进行拆分，然后使用lattice创建每个单独的图。优点是tidyverse（pivot_longer()）中的函数使您可以轻松调整绘图函数的方式转换数据。这里的代码为每个变量生成一个图。就您而言，如果您有更多类别变量，则可以使用ncol和nrow选项调整构面。接下来的解决方案：

library(tidyverse)
#Data
data <- iris
data <- as.data.frame(data)
data <- data[-c(1,2,3,4)]
data$Class <- as.factor(c(rbinom(50,1,0.7),rbinom(100,0.1)))
data$species2 <- as.factor(rbinom(150,0.85))
#Code
data %>% pivot_longer(-Class) %>%
  group_by(name,Class,value) %>%
  summarise(N=n()) %>%
  ggplot(aes(y=value,x=N,fill=Class))+
  geom_bar(stat = 'identity',color='black',alpha=0.2)+
  facet_wrap(.~name,scales='free')+
  theme_bw()+
  theme(legend.position = 'top')

输出：

对于百分比，您可以尝试以下操作：

#Code 2
data %>% pivot_longer(-Class) %>%
  group_by(name,alpha=0.2,position = 'fill')+
  scale_x_continuous(labels = scales::percent)+
  facet_wrap(.~name,scales='free')+
  theme_bw()+
  theme(legend.position = 'top')

输出：