In [ ]:

    

import findspark
findspark.init()
import pyspark
sc = pyspark.SparkContext()
from pyspark.mllib.regression import LabeledPoint
from pyspark.ml.classification import LogisticRegression
from pyspark.sql import SparkSession
spark = SparkSession\
    .builder\
    .appName("PythonSQL")\
    .config("spark.some.config.option", "some-value")\
    .getOrCreate()

training = spark.read.format("libsvm").load("/vagrant/notebooks/data/sample_libsvm_data.txt")
lr = LogisticRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8)

# Fit the model
lrModel = lr.fit(training)

# Print the coefficients and intercept for logistic regression
print("Coefficients: " + str(lrModel.coefficients))
print("Intercept: " + str(lrModel.intercept))


    

In [ ]: