python/ml/aft_survival_regression.py

0001 #
0002 # Licensed to the Apache Software Foundation (ASF) under one or more
0003 # contributor license agreements.  See the NOTICE file distributed with
0004 # this work for additional information regarding copyright ownership.
0005 # The ASF licenses this file to You under the Apache License, Version 2.0
0006 # (the "License"); you may not use this file except in compliance with
0007 # the License.  You may obtain a copy of the License at
0008 #
0009 #    http://www.apache.org/licenses/LICENSE-2.0
0010 #
0011 # Unless required by applicable law or agreed to in writing, software
0012 # distributed under the License is distributed on an "AS IS" BASIS,
0013 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014 # See the License for the specific language governing permissions and
0015 # limitations under the License.
0016 #
0017
0018 """
0019 An example demonstrating aft survival regression.
0020 Run with:
0021   bin/spark-submit examples/src/main/python/ml/aft_survival_regression.py
0022 """
0023 from __future__ import print_function
0024
0025 # $example on$
0026 from pyspark.ml.regression import AFTSurvivalRegression
0027 from pyspark.ml.linalg import Vectors
0028 # $example off$
0029 from pyspark.sql import SparkSession
0030
0031 if __name__ == "__main__":
0032     spark = SparkSession \
0033         .builder \
0034         .appName("AFTSurvivalRegressionExample") \
0035         .getOrCreate()
0036
0037     # $example on$
0038     training = spark.createDataFrame([
0039         (1.218, 1.0, Vectors.dense(1.560, -0.605)),
0040         (2.949, 0.0, Vectors.dense(0.346, 2.158)),
0041         (3.627, 0.0, Vectors.dense(1.380, 0.231)),
0042         (0.273, 1.0, Vectors.dense(0.520, 1.151)),
0043         (4.199, 0.0, Vectors.dense(0.795, -0.226))], ["label", "censor", "features"])
0044     quantileProbabilities = [0.3, 0.6]
0045     aft = AFTSurvivalRegression(quantileProbabilities=quantileProbabilities,
0046                                 quantilesCol="quantiles")
0047
0048     model = aft.fit(training)
0049
0050     # Print the coefficients, intercept and scale parameter for AFT survival regression
0051     print("Coefficients: " + str(model.coefficients))
0052     print("Intercept: " + str(model.intercept))
0053     print("Scale: " + str(model.scale))
0054     model.transform(training).show(truncate=False)
0055     # $example off$
0056
0057     spark.stop()