pyspark線性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：用於二分類的閾值 # aggregationDepth：這個參數在很多地方見過，treeAggregate相比Aggregate更高效， # 它避免一次性將所有分區的結果傳到彙總端（可能內存不足，可能分區太多），所以它先對分區做些整理、合併等操作，再傳遞結果。 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))