#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Jun 8 09:27:08 2018
@author: luogan
"""
from pyspark.ml import Pipeline
from pyspark.ml.regression import RandomForestRegressor
from pyspark.ml.feature import VectorIndexer
from pyspark.ml.evaluation import RegressionEvaluator
from pyspark.sql import SparkSession
spark= SparkSession .builder .appName("dataFrame") .getOrCreate()
# Load and parse the data file, converting it to a DataFrame.
data = spark.read.format("libsvm").load("/home/luogan/lg/softinstall/spark-2.2.0-bin-hadoop2.7/data/mllib/sample_libsvm_data.txt")
# Automatically identify categorical features, and index them.
# Set maxCategories so features with > 4 distinct values are treated as continuous.
featureIndexer = V