pyspark线性SVC

from pyspark.ml.classification import LinearSVC
from pyspark.sql import SparkSession

spark = SparkSession\
    .builder\
    .appName("linearSVC Example")\
    .getOrCreate()

training = spark.read.format("libsvm").load("sample_libsvm_data.txt")
# threshold：用于二分类的阈值
# aggregationDepth：这个参数在很多地方见过，treeAggregate相比Aggregate更高效，
# 它避免一次性将所有分区的结果传到汇总端（可能内存不足，可能分区太多），所以它先对分区做些整理、合并等操作，再传递结果。

lsvc = LinearSVC(maxIter=10, regParam=0.1)

# Fit the model
lsvcModel = lsvc.fit(training)

# Print the coefficients and intercept for linear SVC
print("Coefficients: " + str(lsvcModel.coefficients))
print("Intercept: " + str(lsvcModel.intercept))