在Seaborn中绘制具有与“hue”类似的多个属性的图表

Question

我有以下示例数据集，名为df ，其中舞台时间是到达df天数：

id stage1_time stage_1_to_2_time stage_2_time stage_2_to_3_time stage3_time
a  10          30                40           30                70
b  30               
c  15          30                45     
d       

我编写了以下脚本来获取stage1_time对CDF的散点图：

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import scipy.stats as stats

dict = {'id': id, 'stage_1_time': [10, 30, 15, None], 'stage_1_to_2_time': [30, None, 30, None], 'stage_2_time' : [40, None, 45, None],'stage_2_to_3_time' : [30, None, None, None],'stage_3_time' : [70, None, None, None]}
df = pd.DataFrame(dict)

#create eCDF function
def ecdf(df):
    n = len(df)
    x = np.sort(df)
    y = np.arange(1.0, n+1) / n
    return x, y

def generate_scatter_plot(df):

    x, y = ecdf(df)

    plt.plot(x, y, marker='.', linestyle='none') 
    plt.axvline(x.mean(), color='gray', linestyle='dashed', linewidth=2) #Add mean

    x_m = int(x.mean())
    y_m = stats.percentileofscore(df.as_matrix(), x.mean())/100.0

    plt.annotate('(%s,%s)' % (x_m,int(y_m*100)) , xy=(x_m,y_m), xytext=(10,-5), textcoords='offset points')

    percentiles= np.array([0,25,50,75,100])
    x_p = np.percentile(df, percentiles)
    y_p = percentiles/100.0

    plt.plot(x_p, y_p, marker='D', color='red', linestyle='none') # Overlay quartiles

    for x,y in zip(x_p, y_p):                                        
        plt.annotate('%s' % int(x), xy=(x,y), xytext=(10,-5), textcoords='offset points')

#Data to plot
stage1_time = df['stage_1_time'].dropna().sort_values()

#Scatter Plot
stage1_time_scatter = generate_scatter_plot(pd.DataFrame({"df" : stage1_time.as_matrix()}))
plt.title('Scatter Plot of Days to Stage1')
plt.xlabel('Days to Stage1')
plt.ylabel('Cumulative Probability')
plt.legend(('Days to Stage1', "Mean", 'Quartiles'), loc='lower right')
plt.margins(0.02)

plt.show()

输出：

目前，所有达到stage1根据其累积概率绘制的天数，但是我想要实现的是当我绘制时散布有三种颜色：那些到达stage1并留在那里的人，那些进入stage2和那些谁转移到stage3 。 我也想在图表中的数据计数：＃在stage1中，＃ stage2中和＃ stage3 。

有人可以帮忙到那里吗？

仅供参考，意图是使用它作为基础，这样我也可以为stage2_time创建一个图形，其中到达stage_3的图形突出显示不同的颜色。

Answer 1

您可以创建一个新列并使用它来存储最终阶段，然后使用此新列为您的绘图着色。

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import scipy.stats as stats
import math

dict = {'id': id, 'Progressive_time': [10, 30, 15, None],'stage_1_to_2_time': [30, None, 30, None], 'Active_time' : [40,None, 45, None],'stage_2_to_3_time' : [30, None, None,None],'Engaged_time' : [70, None, None, None]}
df = pd.DataFrame(dict)

    #create eCDF function
def ecdf(df, serie):
    n = len(df)
    df['x'] = np.sort(df[serie])
    df['y'] = np.arange(1.0, n+1) / n
    return df

def generate_scatter_plot(df,serie,nb_stage):
    df=df.dropna(subset=[serie]).sort_values(by=[serie])
    st=1
    for i in range(1,nb_stage*2,2):
        df.loc[df.iloc[:,i].notnull(),'stage']=st
        st=st+1

    df= ecdf(df, serie)
    plt.plot(df.loc[df['stage'] == 1, 'x'], df.loc[df['stage'] == 1, 'y'], marker='.', linestyle='none',c='blue') 
    plt.plot(df.loc[df['stage'] == 2, 'x'], df.loc[df['stage'] == 2, 'y'], marker='.', linestyle='none',c='red') 
    plt.plot(df.loc[df['stage'] == 3, 'x'], df.loc[df['stage'] == 3, 'y'], marker='.', linestyle='none',c='green') 
    plt.axvline(df['x'].mean(), color='gray', linestyle='dashed', linewidth=2) #Add mean


    x_m = int(df['x'].mean())
    y_m = stats.percentileofscore(df[serie], df['x'].mean())/100.0

    plt.annotate('(%s,%s)' % (x_m,int(y_m*100)) , xy=(x_m,y_m), xytext=(10,-5), textcoords='offset points')

    percentiles= np.array([0,25,50,75,100])
    x_p = np.percentile(df[serie], percentiles)
    y_p = percentiles/100.0

    plt.plot(x_p, y_p, marker='D', color='red', linestyle='none') # Overlay quartiles

    for x,y in zip(x_p, y_p):                                        
        plt.annotate('%s' % int(x), xy=(x,y), xytext=(10,-5), textcoords='offset points')

#Scatter Plot
stage1_time_scatter = generate_scatter_plot(df,'stage_1_time',3)
plt.title('Scatter Plot of Days to Stage1')
plt.xlabel('Days to Stage1')
plt.ylabel('Cumulative Probability')
plt.legend(('Progressive','Active','Engaged','Days to Stage1', "Mean", 'Quartiles'), loc='lower right')
plt.margins(0.02)

plt.show()