pyspark-ml学习笔记：LogisticRegression

 

具体查看下面代码及其注释：

数据可以查看github：https://github.com/MachineLP/Spark-/tree/master/pyspark-ml

import os
import sys

#下面这些目录都是你自己机器的Spark安装目录和Java安装目录
os.environ['SPARK_HOME'] = "/Users/***/spark-2.4.3-bin-hadoop2.7/"

sys.path.append("/Users/***/spark-2.4.3-bin-hadoop2.7/bin")
sys.path.append("/Users/***/spark-2.4.3-bin-hadoop2.7/python")
sys.path.append("/Users/***/spark-2.4.3-bin-hadoop2.7/python/pyspark")
sys.path.append("/Users/***/spark-2.4.3-bin-hadoop2.7/python/lib")
sys.path.append("/Users/***/spark-2.4.3-bin-hadoop2.7/python/lib/pyspark.zip")
sys.path.append("/Users/***/spark-2.4.3-bin-hadoop2.7/lib/py4j-0.9-src.zip")
# sys.path.append("/Library/Java/JavaVirtualMachines/jdk1.8.0_144.jdk/Contents/Home")
os.environ['JAVA_HOME'] = "/Library