通過scatter_matrix繪制散點圖矩陣圖，話不多說室叉，直接上碼
#讀入數(shù)據(jù)
data=spark.read.csv("path\\xxx.csv",header=True,inferSchema='true')
#查看數(shù)據(jù)類型
data.printSchema()
#過濾數(shù)據(jù)
data=data[data['coupon_consume_ratio']!='NULL']
#更改數(shù)據(jù)類型
data=data.withColumn('coupon_consume_ratio',data['coupon_consume_ratio'].cast('double'))
#查看數(shù)據(jù)
import pandas as pd
pd.DataFrame(data.take(5),columns=data.columns).transpose()
#查看數(shù)據(jù)的統(tǒng)計信息
data.describe().toPandas().transpose()
#找出所有列中的數(shù)值列
numberic_features=[ t[0] for t in data.dtypes if (t[1]=='int' or t[1]=='double') and t[0]!='xxxx']
#選取數(shù)值列數(shù)據(jù)
data_pd=data.select(numberic_features).toPandas()
#繪制散點圖矩陣
axs=pd.plotting.scatter_matrix(data_pd,figsize=(12,12))
n=len(data_pd.columns)
for i in range(n):
v=axs[i,0]
v.yaxis.label.set_rotation(0)
v.yaxis.label.set_ha('right')
v.set_yticks(())
h=axs[n-1,i]
h.xaxis.label.set_rotation(90)
h.set_xticks(())
