OBJECTIVE: Analysis of movie lens dataset to identify the preferences of movies based on the ratings given by different users. Data: The datasets depict ratings with user ID (removed the...

{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "building-recommender.ipynb",
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "BjY0XQCGk_BF",
"colab_type": "text"
},
"source": [
"##Getting and processing the data"
]
},
{
"cell_type": "code",
"metadata": {
"id": "9ZPJJoLdmcSk",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"outputId": "2b72f28b-8c16-4b01-d50f-abbfc415a04c"
},
"source": [
"import pandas\n",
"!apt-get install openjdk-8-jdk-headless -qq > /dev/null\n",
"!wget -q http://www-eu.apache.org/dist/spark/spark-2.4.4/spark-2.4.4-bin-hadoop2.7.tgz\n",
"!tar xvf spark-2.4.4-bin-hadoop2.7.tgz\n",
"!pip install -q findspark"
],
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"text": [
"spark-2.4.4-bin-hadoop2.7/\n",
"spark-2.4.4-bin-hadoop2.7/R/\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/sparkr.zip\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/INDEX\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/html/\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/html/R.css\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/html/00Index.html\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/help/\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/help/aliases.rds\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/help/AnIndex\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/help/SparkR.rdx\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/help/SparkR.rdb\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/help/paths.rds\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/worker/\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/worker/worker.R\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/worker/daemon.R\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/tests/\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/tests/testthat/\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/tests/testthat/test_basic.R\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/profile/\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/profile/shell.R\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/profile/general.R\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/R/\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/R/SparkR.rdx\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/R/SparkR.rdb\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/R/SparkR\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/Meta/\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/Meta/nsInfo.rds\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/Meta/links.rds\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/Meta/hsearch.rds\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/Meta/Rd.rds\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/Meta/features.rds\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/Meta/package.rds\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/DESCRIPTION\n",
"spark-2.4.4-bin-hadoop2.7/R/lib/SparkR/NAMESPACE\n",
"spark-2.4.4-bin-hadoop2.7/sbin/\n",
"spark-2.4.4-bin-hadoop2.7/sbin/stop-shuffle-service.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/start-thriftserver.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/start-slave.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/start-shuffle-service.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/start-mesos-shuffle-service.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/start-master.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/start-history-server.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/spark-config.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/stop-thriftserver.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/stop-slaves.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/stop-slave.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/stop-mesos-shuffle-service.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/stop-mesos-dispatcher.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/stop-master.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/stop-history-server.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/stop-all.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/start-slaves.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/start-mesos-dispatcher.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/start-all.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/spark-daemons.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/spark-daemon.sh\n",
"spark-2.4.4-bin-hadoop2.7/sbin/slaves.sh\n",
"spark-2.4.4-bin-hadoop2.7/python/\n",
"spark-2.4.4-bin-hadoop2.7/python/dist/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark.egg-info/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark.egg-info/SOURCES.txt\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark.egg-info/dependency_links.txt\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark.egg-info/top_level.txt\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark.egg-info/PKG-INFO\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark.egg-info/requires.txt\n",
"spark-2.4.4-bin-hadoop2.7/python/README.md\n",
"spark-2.4.4-bin-hadoop2.7/python/MANIFEST.in\n",
"spark-2.4.4-bin-hadoop2.7/python/setup.py\n",
"spark-2.4.4-bin-hadoop2.7/python/run-tests.py\n",
"spark-2.4.4-bin-hadoop2.7/python/run-tests-with-coverage\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/userlibrary.py\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/userlib-0.1.zip\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/text-test.txt\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/streaming/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/streaming/text-test.txt\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/people_array_utf16le.json\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/people_array.json\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/people1.json\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/people.json\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=9/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=9/day=1/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=9/day=1/part-r-00007.gz.parquet\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=9/day=1/.part-r-00007.gz.parquet.crc\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=10/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=10/day=26/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=10/day=26/part-r-00005.gz.parquet\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=10/day=26/.part-r-00005.gz.parquet.crc\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=10/day=25/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=10/day=25/part-r-00004.gz.parquet\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=10/day=25/part-r-00002.gz.parquet\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=10/day=25/.part-r-00004.gz.parquet.crc\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2015/month=10/day=25/.part-r-00002.gz.parquet.crc\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2014/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2014/month=9/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2014/month=9/day=1/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2014/month=9/day=1/part-r-00008.gz.parquet\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/year=2014/month=9/day=1/.part-r-00008.gz.parquet.crc\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/_metadata\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/_common_metadata\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/parquet_partitioned/_SUCCESS\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/orc_partitioned/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/orc_partitioned/b=1/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/orc_partitioned/b=1/c=1/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/orc_partitioned/b=1/c=1/part-r-00000-829af031-b970-49d6-ad39-30460a0be2c8.orc\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/orc_partitioned/b=1/c=1/.part-r-00000-829af031-b970-49d6-ad39-30460a0be2c8.orc.crc\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/orc_partitioned/b=0/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/orc_partitioned/b=0/c=0/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/orc_partitioned/b=0/c=0/part-r-00000-829af031-b970-49d6-ad39-30460a0be2c8.orc\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/orc_partitioned/b=0/c=0/.part-r-00000-829af031-b970-49d6-ad39-30460a0be2c8.orc.crc\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/orc_partitioned/_SUCCESS\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/ages_newlines.csv\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/sql/ages.csv\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/hello/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/hello/sub_hello/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/hello/sub_hello/sub_hello.txt\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/hello/hello.txt\n",
"spark-2.4.4-bin-hadoop2.7/python/test_support/SimpleHTTPServer.py\n",
"spark-2.4.4-bin-hadoop2.7/python/test_coverage/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_coverage/sitecustomize.py\n",
"spark-2.4.4-bin-hadoop2.7/python/test_coverage/coverage_daemon.py\n",
"spark-2.4.4-bin-hadoop2.7/python/test_coverage/conf/\n",
"spark-2.4.4-bin-hadoop2.7/python/test_coverage/conf/spark-defaults.conf\n",
"spark-2.4.4-bin-hadoop2.7/python/setup.cfg\n",
"spark-2.4.4-bin-hadoop2.7/python/run-tests\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/python/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/python/pyspark/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/python/pyspark/shell.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/shuffle.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/serializers.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/rdd.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/profiler.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/java_gateway.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/files.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/daemon.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/context.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/conf.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/cloudpickle.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/broadcast.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/accumulators.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/__init__.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/worker.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/version.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/util.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/tests.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/test_serializers.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/test_broadcast.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/taskcontext.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/storagelevel.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/traceback_utils.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/streaming/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/streaming/tests.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/streaming/kinesis.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/streaming/kafka.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/streaming/flume.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/streaming/dstream.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/streaming/context.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/streaming/util.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/streaming/listener.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/streaming/__init__.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/status.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/statcounter.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/tests.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/streaming.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/session.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/readwriter.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/functions.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/dataframe.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/context.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/window.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/utils.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/udf.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/types.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/group.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/conf.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/column.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/catalog.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/sql/__init__.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/shell.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/resultiterable.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/rddsampler.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/util.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/tree.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/tests.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/regression.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/recommendation.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/random.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/fpm.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/feature.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/evaluation.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/clustering.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/classification.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/stat/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/stat/_statistics.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/stat/test.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/stat/distribution.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/stat/__init__.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/stat/KernelDensity.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/linalg/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/linalg/distributed.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/linalg/__init__.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/common.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/mllib/__init__.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/wrapper.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/util.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/tuning.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/tests.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/regression.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/recommendation.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/image.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/fpm.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/feature.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/evaluation.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/clustering.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/classification.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/stat.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/pipeline.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/param/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/param/shared.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/param/_shared_params_code_gen.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/param/__init__.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/linalg/\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/linalg/__init__.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/common.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/base.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/ml/__init__.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/join.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/heapq3.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/find_spark_home.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pyspark/_globals.py\n",
"spark-2.4.4-bin-hadoop2.7/python/pylintrc\n",
"spark-2.4.4-bin-hadoop2.7/python/lib/\n",
"spark-2.4.4-bin-hadoop2.7/python/lib/pyspark.zip\n",
"spark-2.4.4-bin-hadoop2.7/python/lib/py4j-0.10.7-src.zip\n",
"spark-2.4.4-bin-hadoop2.7/python/lib/PY4J_LICENSE.txt\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/pyspark.streaming.rst\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/pyspark.sql.rst\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/epytext.py\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/conf.py\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/Makefile\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/pyspark.rst\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/pyspark.mllib.rst\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/pyspark.ml.rst\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/make2.bat\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/make.bat\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/index.rst\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/_templates/\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/_templates/layout.html\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/_static/\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/_static/pyspark.js\n",
"spark-2.4.4-bin-hadoop2.7/python/docs/_static/pyspark.css\n",
"spark-2.4.4-bin-hadoop2.7/python/.gitignore\n",
"spark-2.4.4-bin-hadoop2.7/python/.coveragerc\n",
"spark-2.4.4-bin-hadoop2.7/bin/\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-class\n",
"spark-2.4.4-bin-hadoop2.7/bin/pyspark2.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/pyspark\n",
"spark-2.4.4-bin-hadoop2.7/bin/load-spark-env.sh\n",
"spark-2.4.4-bin-hadoop2.7/bin/load-spark-env.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/docker-image-tool.sh\n",
"spark-2.4.4-bin-hadoop2.7/bin/sparkR2.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/sparkR.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/sparkR\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-submit2.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-submit.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-submit\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-sql2.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-sql.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-sql\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-shell2.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-shell.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-shell\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-class2.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/spark-class.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/run-example.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/run-example\n",
"spark-2.4.4-bin-hadoop2.7/bin/pyspark.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/find-spark-home.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/find-spark-home\n",
"spark-2.4.4-bin-hadoop2.7/bin/beeline.cmd\n",
"spark-2.4.4-bin-hadoop2.7/bin/beeline\n",
"spark-2.4.4-bin-hadoop2.7/README.md\n",
"spark-2.4.4-bin-hadoop2.7/conf/\n",
"spark-2.4.4-bin-hadoop2.7/conf/spark-env.sh.template\n",
"spark-2.4.4-bin-hadoop2.7/conf/spark-defaults.conf.template\n",
"spark-2.4.4-bin-hadoop2.7/conf/slaves.template\n",
"spark-2.4.4-bin-hadoop2.7/conf/metrics.properties.template\n",
"spark-2.4.4-bin-hadoop2.7/conf/log4j.properties.template\n",
"spark-2.4.4-bin-hadoop2.7/conf/fairscheduler.xml.template\n",
"spark-2.4.4-bin-hadoop2.7/conf/docker.properties.template\n",
"spark-2.4.4-bin-hadoop2.7/data/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/gmm_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/als/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/als/test.data\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/als/sample_movielens_ratings.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/streaming_kmeans_data_test.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/sample_svm_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/sample_multiclass_classification_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/sample_movielens_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/sample_linear_regression_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/sample_libsvm_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/sample_lda_libsvm_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/sample_lda_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/sample_kmeans_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/sample_isotonic_regression_libsvm_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/sample_fpgrowth.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/sample_binary_classification_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/ridge-data/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/ridge-data/lpsa.data\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/pic_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/pagerank_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/kmeans_data.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/iris_libsvm.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=multichannel/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=multichannel/date=2018-02/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=multichannel/date=2018-02/grayscale.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=multichannel/date=2018-02/chr30.4.184.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=multichannel/date=2018-01/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=multichannel/date=2018-01/BGRA_alpha_60.png\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=multichannel/date=2018-01/BGRA.png\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=kittens/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=kittens/date=2018-02/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=kittens/date=2018-02/DP802813.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=kittens/date=2018-02/DP153539.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=kittens/date=2018-02/54893.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=kittens/date=2018-01/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=kittens/date=2018-01/not-image.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/partitioned/cls=kittens/date=2018-01/29.5.a_b_EGDP022204.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/multi-channel/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/multi-channel/grayscale.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/multi-channel/chr30.4.184.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/multi-channel/BGRA_alpha_60.png\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/multi-channel/BGRA.png\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/license.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/kittens/\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/kittens/not-image.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/kittens/DP802813.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/kittens/DP153539.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/kittens/54893.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/origin/kittens/29.5.a_b_EGDP022204.jpg\n",
"spark-2.4.4-bin-hadoop2.7/data/mllib/images/license.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/graphx/\n",
"spark-2.4.4-bin-hadoop2.7/data/graphx/users.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/graphx/followers.txt\n",
"spark-2.4.4-bin-hadoop2.7/data/streaming/\n",
"spark-2.4.4-bin-hadoop2.7/data/streaming/AFINN-111.txt\n",
"spark-2.4.4-bin-hadoop2.7/NOTICE\n",
"spark-2.4.4-bin-hadoop2.7/licenses/\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-jtransforms.html\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-json-formatter.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-jquery.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-join.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-jodd.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-jline.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-javolution.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-javassist.html\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-janino.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-heapq.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-graphlib-dot.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-f2j.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-datatables.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-dagre-d3.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-d3.min.js.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-cloudpickle.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-bootstrap.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-automaton.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-arpack.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-antlr.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-CC0.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-AnchorJS.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-zstd.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-zstd-jni.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-xmlenc.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-vis.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-spire.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-sorttable.js.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-slf4j.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-scopt.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-scala.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-sbt-launch-lib.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-respond.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-reflectasm.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-pyrolite.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-py4j.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-protobuf.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-pmml-model.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-paranamer.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-netlib.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-mustache.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-modernizr.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-minlog.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-matchMedia-polyfill.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-machinist.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-leveldbjni.txt\n",
"spark-2.4.4-bin-hadoop2.7/licenses/LICENSE-kryo.txt\n",
"spark-2.4.4-bin-hadoop2.7/LICENSE\n",
"spark-2.4.4-bin-hadoop2.7/examples/\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/ElementwiseProductExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/DenseKMeans.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRegressionExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeClassificationExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/CosineSimilarity.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/CorrelationsExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/Correlations.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/ChiSqSelectorExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/BisectingKMeansExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassificationMetricsExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/AssociationRulesExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/AbstractParams.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/Word2VecExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnySVD.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnyPCA.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/TFIDFExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/SummaryStatisticsExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/StreamingTestExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/StreamingLogisticRegression.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/StreamingLinearRegressionExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/StreamingKMeansExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/StratifiedSamplingExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/StandardScalerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/SparseNaiveBayes.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/SimpleFPGrowth.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/SampledRDDs.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/SVMWithSGDExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/SVDExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/RegressionMetricsExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/RecommendationExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/RandomRDDGeneration.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestRegressionExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/RandomForestClassificationExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/PrefixSpanExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/PowerIterationClusteringExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/PMMLModelExportExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/PCAOnSourceVectorExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/PCAOnRowMatrixExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/PCAExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/NormalizerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/NaiveBayesExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/MultivariateSummarizer.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/MulticlassMetricsExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/MultiLabelMetricsExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/LogisticRegressionWithLBFGSExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegressionWithSGDExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/LatentDirichletAllocationExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/LDAExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/LBFGSExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/KernelDensityEstimationExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/KMeansExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/IsotonicRegressionExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/HypothesisTestingKolmogorovSmirnovTestExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/HypothesisTestingExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingRegressionExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostingClassificationExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/GaussianMixtureExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/FPGrowthExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/RankingMetricsExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegression.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/Word2VecExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/VectorSlicerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/VectorSizeHintExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/VectorIndexerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/VectorAssemblerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/UnaryTransformerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/TokenizerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/TfIdfExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/SummarizerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/StringIndexerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/StopWordsRemoverExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/StandardScalerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/SQLTransformerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/RandomForestRegressorExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/RandomForestExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/RFormulaExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/QuantileDiscretizerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/PowerIterationClusteringExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/PolynomialExpansionExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/PipelineExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/PCAExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/OneVsRestExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/NormalizerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/NGramExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/MultilayerPerceptronClassifierExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/MulticlassLogisticRegressionWithElasticNetExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/ModelSelectionViaTrainValidationSplitExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/ModelSelectionViaCrossValidationExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/MinMaxScalerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/MinHashLSHExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/MaxAbsScalerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionWithElasticNetExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionSummaryExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/LinearSVCExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionWithElasticNetExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/LDAExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/KMeansExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/IsotonicRegressionExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/InteractionExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/IndexToStringExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/ImputerExample.scala\n",
"spark-2.4.4-bin-hadoop2.7/examples/src/main/scala/org/apache/spark/examples/ml/GradientBoostedTreeRegressorExample.scala\n",
...