def standardScaler(self): from pyspark.ml.feature import StandardScaler dataFrame = self.session.read.format("libsvm").load( self.dataDir + "/data/mllib/sample_libsvm_data.txt") scaler = StandardScaler(inputCol="features", outputCol="scaledFeatures", withStd=True, withMean=False) scalerModel = scaler.fit(dataFrame) scaledData = scalerModel.transform(dataFrame) scaledData.show() scaler = MinMaxScaler(inputCol="features", outputCol="scaledFeatures") # Compute summary statistics and generate MinMaxScalerModel scalerModel = scaler.fit(dataFrame) # rescale each feature to range [min, max]. scaledData = scalerModel.transform(dataFrame) print("Features scaled to range: [%f, %f]" % (scaler.getMin(), scaler.getMax())) scaledData.select("features", "scaledFeatures").show() scaler = MaxAbsScaler(inputCol="features", outputCol="scaledFeatures") # Compute summary statistics and generate MaxAbsScalerModel scalerModel = scaler.fit(dataFrame) # rescale each feature to range [-1, 1]. scaledData = scalerModel.transform(dataFrame) scaledData.select("features", "scaledFeatures").show()