diff options
author | Zheng RuiFeng <ruifengz@foxmail.com> | 2016-05-11 12:49:41 +0200 |
---|---|---|
committer | Nick Pentreath <nickp@za.ibm.com> | 2016-05-11 12:49:41 +0200 |
commit | d88afabdfa83be47f36d833105aadd6b818ceeee (patch) | |
tree | 224f8a6fc5268e30bf200ab30f4e20f5c0164b34 /examples/src/main/python/ml | |
parent | fafc95af79fa34f82964a86407c2ee046eda3814 (diff) | |
download | spark-d88afabdfa83be47f36d833105aadd6b818ceeee.tar.gz spark-d88afabdfa83be47f36d833105aadd6b818ceeee.tar.bz2 spark-d88afabdfa83be47f36d833105aadd6b818ceeee.zip |
[SPARK-15150][EXAMPLE][DOC] Update LDA examples
## What changes were proposed in this pull request?
1,create a libsvm-type dataset for lda: `data/mllib/sample_lda_libsvm_data.txt`
2,add python example
3,directly read the datafile in examples
4,BTW, change to `SparkSession` in `aft_survival_regression.py`
## How was this patch tested?
manual tests
`./bin/spark-submit examples/src/main/python/ml/lda_example.py`
Author: Zheng RuiFeng <ruifengz@foxmail.com>
Closes #12927 from zhengruifeng/lda_pe.
Diffstat (limited to 'examples/src/main/python/ml')
-rw-r--r-- | examples/src/main/python/ml/aft_survival_regression.py | 19 | ||||
-rw-r--r-- | examples/src/main/python/ml/lda_example.py | 64 |
2 files changed, 77 insertions, 6 deletions
diff --git a/examples/src/main/python/ml/aft_survival_regression.py b/examples/src/main/python/ml/aft_survival_regression.py index 0ee01fd825..9879679829 100644 --- a/examples/src/main/python/ml/aft_survival_regression.py +++ b/examples/src/main/python/ml/aft_survival_regression.py @@ -17,19 +17,26 @@ from __future__ import print_function -from pyspark import SparkContext -from pyspark.sql import SQLContext # $example on$ from pyspark.ml.regression import AFTSurvivalRegression from pyspark.mllib.linalg import Vectors # $example off$ +from pyspark.sql import SparkSession + +""" +An example demonstrating aft survival regression. +Run with: + bin/spark-submit examples/src/main/python/ml/aft_survival_regression.py +""" if __name__ == "__main__": - sc = SparkContext(appName="AFTSurvivalRegressionExample") - sqlContext = SQLContext(sc) + spark = SparkSession \ + .builder \ + .appName("PythonAFTSurvivalRegressionExample") \ + .getOrCreate() # $example on$ - training = sqlContext.createDataFrame([ + training = spark.createDataFrame([ (1.218, 1.0, Vectors.dense(1.560, -0.605)), (2.949, 0.0, Vectors.dense(0.346, 2.158)), (3.627, 0.0, Vectors.dense(1.380, 0.231)), @@ -48,4 +55,4 @@ if __name__ == "__main__": model.transform(training).show(truncate=False) # $example off$ - sc.stop() + spark.stop() diff --git a/examples/src/main/python/ml/lda_example.py b/examples/src/main/python/ml/lda_example.py new file mode 100644 index 0000000000..6ca56adf3c --- /dev/null +++ b/examples/src/main/python/ml/lda_example.py @@ -0,0 +1,64 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + + +from __future__ import print_function + +# $example on$ +from pyspark.ml.clustering import LDA +# $example off$ +from pyspark.sql import SparkSession + + +""" +An example demonstrating LDA. +Run with: + bin/spark-submit examples/src/main/python/ml/lda_example.py +""" + + +if __name__ == "__main__": + # Creates a SparkSession + spark = SparkSession \ + .builder \ + .appName("PythonKMeansExample") \ + .getOrCreate() + + # $example on$ + # Loads data. + dataset = spark.read.format("libsvm").load("data/mllib/sample_lda_libsvm_data.txt") + + # Trains a LDA model. + lda = LDA(k=10, maxIter=10) + model = lda.fit(dataset) + + ll = model.logLikelihood(dataset) + lp = model.logPerplexity(dataset) + print("The lower bound on the log likelihood of the entire corpus: " + str(ll)) + print("The upper bound bound on perplexity: " + str(lp)) + + # Describe topics. + topics = model.describeTopics(3) + print("The topics described by their top-weighted terms:") + topics.show(truncate=False) + + # Shows the result + transformed = model.transform(dataset) + transformed.show(truncate=False) + # $example off$ + + spark.stop() |