python_采样_多个散点图在一起

参考：
https://www.jianshu.com/p/14e635662fff

#sampleBy根据指定字段分层抽样，抽取0.02%
sample_data = df.sampleBy('gender',{1:0.0002,2:0.0002}).select("balance","numTrans","numIntlTrans")
sample_data.take(5)
To put multiple 2D charts in one go you can use

data_multi = dict([
    (elem, data_sample.select(elem).rdd.flatMap(lambda row: row).collect()) 
    for elem in numerical
])
​
sctr = chrt.Scatter(data_multi, x='balance', y='numTrans')
​
chrt.show(sctr)
​
​
# 或者这样
​
#按字段将值分开
data_multi ={elem:sample_data.select(elem).rdd.flatMap(lambda x:x).collect()\
             for elem in ["balance","numTrans","numIntlTrans"]}
#画散点图，plt.scatter(x,y)
plt.scatter(data_multi["numTrans"],data_multi["balance"],c ='r',marker='o',label="numTrans-balance")
plt.scatter(data_multi["numIntlTrans"],data_multi["balance"],c ='b',marker="x",label="numInt-balance")
plt.grid(True)#网格
plt.xlabel("x value")
plt.ylabel("y value")
plt.legend(loc='upper right')#图例的位置
plt.title("scatter view")