3f67382e7c
Added experimental Python API for Decision Trees. API: * class DecisionTreeModel ** predict() for single examples and RDDs, taking both feature vectors and LabeledPoints ** numNodes() ** depth() ** __str__() * class DecisionTree ** trainClassifier() ** trainRegressor() ** train() Examples and testing: * Added example testing classification and regression with batch prediction: examples/src/main/python/mllib/tree.py * Have also tested example usage in doc of python/pyspark/mllib/tree.py which tests single-example prediction with dense and sparse vectors Also: Small bug fix in python/pyspark/mllib/_common.py: In _linear_predictor_typecheck, changed check for RDD to use isinstance() instead of type() in order to catch RDD subclasses. CC mengxr manishamde Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com> Closes #1727 from jkbradley/decisiontree-python-new and squashes the following commits: 3744488 [Joseph K. Bradley] Renamed test tree.py to decision_tree_runner.py Small updates based on github review. 6b86a9d [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new affceb9 [Joseph K. Bradley] * Fixed bug in doc tests in pyspark/mllib/util.py caused by change in loadLibSVMFile behavior. (It used to threshold labels at 0 to make them 0/1, but it now leaves them as they are.) * Fixed small bug in loadLibSVMFile: If a data file had no features, then loadLibSVMFile would create a single all-zero feature. 67a29bc [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new cf46ad7 [Joseph K. Bradley] Python DecisionTreeModel * predict(empty RDD) returns an empty RDD instead of an error. * Removed support for calling predict() on LabeledPoint and RDD[LabeledPoint] * predict() does not cache serialized RDD any more. aa29873 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new bf21be4 [Joseph K. Bradley] removed old run() func from DecisionTree fa10ea7 [Joseph K. Bradley] Small style update 7968692 [Joseph K. Bradley] small braces typo fix e34c263 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 4801b40 [Joseph K. Bradley] Small style update to DecisionTreeSuite db0eab2 [Joseph K. Bradley] Merge branch 'decisiontree-bugfix2' into decisiontree-python-new 6873fa9 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 225822f [Joseph K. Bradley] Bug: In DecisionTree, the method sequentialBinSearchForOrderedCategoricalFeatureInClassification() indexed bins from 0 to (math.pow(2, featureCategories.toInt - 1) - 1). This upper bound is the bound for unordered categorical features, not ordered ones. The upper bound should be the arity (i.e., max value) of the feature. 93953f1 [Joseph K. Bradley] Likely done with Python API. 6df89a9 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 4562c08 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 665ba78 [Joseph K. Bradley] Small updates towards Python DecisionTree API 188cb0d [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new 6622247 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new b8fac57 [Joseph K. Bradley] Finished Python DecisionTree API and example but need to test a bit more. 2b20c61 [Joseph K. Bradley] Small doc and style updates 1b29c13 [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new 584449a [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new dab0b67 [Joseph K. Bradley] Added documentation for DecisionTree internals 8bb8aa0 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-bugfix 978cfcf [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-bugfix 6eed482 [Joseph K. Bradley] In DecisionTree: Changed from using procedural syntax for functions returning Unit to explicitly writing Unit return type. 376dca2 [Joseph K. Bradley] Updated meaning of maxDepth by 1 to fit scikit-learn and rpart. * In code, replaced usages of maxDepth <-- maxDepth + 1 * In params, replace settings of maxDepth <-- maxDepth - 1 e06e423 [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new bab3f19 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 59750f8 [Joseph K. Bradley] * Updated Strategy to check numClassesForClassification only if algo=Classification. * Updates based on comments: ** DecisionTreeRunner *** Made dataFormat arg default to libsvm ** Small cleanups ** tree.Node: Made recursive helper methods private, and renamed them. 52e17c5 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-bugfix f5a036c [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new da50db7 [Joseph K. Bradley] Added one more test to DecisionTreeSuite: stump with 2 continuous variables for binary classification. Caused problems in past, but fixed now. 8e227ea [Joseph K. Bradley] Changed Strategy so it only requires numClassesForClassification >= 2 for classification cd1d933 [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new 8ea8750 [Joseph K. Bradley] Bug fix: Off-by-1 when finding thresholds for splits for continuous features. 8a758db [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new 5fe44ed [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 2283df8 [Joseph K. Bradley] 2 bug fixes. 73fbea2 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-bugfix 5f920a1 [Joseph K. Bradley] Demonstration of bug before submitting fix: Updated DecisionTreeSuite so that 3 tests fail. Will describe bug in next commit. f825352 [Joseph K. Bradley] Wrote Python API and example for DecisionTree. Also added toString, depth, and numNodes methods to DecisionTreeModel.
84 lines
2.7 KiB
Bash
Executable file
84 lines
2.7 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
|
|
#
|
|
# 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.
|
|
#
|
|
|
|
|
|
# Figure out where the Spark framework is installed
|
|
FWDIR="$(cd `dirname $0`; cd ../; pwd)"
|
|
|
|
# CD into the python directory to find things on the right path
|
|
cd "$FWDIR/python"
|
|
|
|
FAILED=0
|
|
|
|
rm -f unit-tests.log
|
|
|
|
# Remove the metastore and warehouse directory created by the HiveContext tests in SparkSQL
|
|
rm -rf metastore warehouse
|
|
|
|
function run_test() {
|
|
echo "Running test: $1"
|
|
SPARK_TESTING=1 $FWDIR/bin/pyspark $1 2>&1 | tee -a > unit-tests.log
|
|
FAILED=$((PIPESTATUS[0]||$FAILED))
|
|
|
|
# Fail and exit on the first test failure.
|
|
if [[ $FAILED != 0 ]]; then
|
|
cat unit-tests.log | grep -v "^[0-9][0-9]*" # filter all lines starting with a number.
|
|
echo -en "\033[31m" # Red
|
|
echo "Had test failures; see logs."
|
|
echo -en "\033[0m" # No color
|
|
exit -1
|
|
fi
|
|
}
|
|
|
|
echo "Running PySpark tests. Output is in python/unit-tests.log."
|
|
|
|
run_test "pyspark/rdd.py"
|
|
run_test "pyspark/context.py"
|
|
run_test "pyspark/conf.py"
|
|
if [ -n "$_RUN_SQL_TESTS" ]; then
|
|
run_test "pyspark/sql.py"
|
|
fi
|
|
# These tests are included in the module-level docs, and so must
|
|
# be handled on a higher level rather than within the python file.
|
|
export PYSPARK_DOC_TEST=1
|
|
run_test "pyspark/broadcast.py"
|
|
run_test "pyspark/accumulators.py"
|
|
run_test "pyspark/serializers.py"
|
|
unset PYSPARK_DOC_TEST
|
|
run_test "pyspark/shuffle.py"
|
|
run_test "pyspark/tests.py"
|
|
run_test "pyspark/mllib/_common.py"
|
|
run_test "pyspark/mllib/classification.py"
|
|
run_test "pyspark/mllib/clustering.py"
|
|
run_test "pyspark/mllib/linalg.py"
|
|
run_test "pyspark/mllib/random.py"
|
|
run_test "pyspark/mllib/recommendation.py"
|
|
run_test "pyspark/mllib/regression.py"
|
|
run_test "pyspark/mllib/tests.py"
|
|
run_test "pyspark/mllib/util.py"
|
|
|
|
if [[ $FAILED == 0 ]]; then
|
|
echo -en "\033[32m" # Green
|
|
echo "Tests passed."
|
|
echo -en "\033[0m" # No color
|
|
fi
|
|
|
|
# TODO: in the long-run, it would be nice to use a test runner like `nose`.
|
|
# The doctest fixtures are the current barrier to doing this.
|