小编Dav*_* Li的帖子

我尝试在我的 win10 笔记本电脑上运行 PySpark 脚本，该脚本正在使用 PySpark 和 Spark MLlib 构建线性回归模型，

我的代码如下：

from pyspark import SparkConf, SparkContext
from pyspark.sql import SQLContext
from pyspark.ml.feature import VectorAssembler
from pyspark.ml.regression import LinearRegression
import pandas as pd

sc = SparkContext()
sqlContext = SQLContext(sc)

    house_df = sqlContext.read.format('com.databricks.spark.csv').options(header='true', inferschema='true').load(
        'data/boston.csv')
house_df1 = house_df.drop('ID')

import six

for i in house_df1.columns:
    if not (isinstance(house_df1.select(i).take(1)[0][0], six.string_types)):
        print("Correlation to MEDV for ", i, house_df1.stat.corr('medv', i))

vectorAssembler = VectorAssembler(inputCols=['crim', 'zn', 'indus',
                                             'chas', 'nox', 'rm', 'age', 'dis', 'rad', 'tax',
                                             'ptratio', 'black', 'lstat'], outputCol='features') …