def test_default_read_write(self):
temp_path = tempfile.mkdtemp()
lr = LogisticRegression()
lr.setMaxIter(50)
lr.setThreshold(0.75)
writer = DefaultParamsWriter(lr)
savePath = temp_path + "/lr"
writer.save(savePath)
reader = DefaultParamsReadable.read()
lr2 = reader.load(savePath)
self.assertEqual(lr.uid, lr2.uid)
self.assertEqual(lr.extractParamMap(), lr2.extractParamMap())
# test overwrite
lr.setThreshold(0.8)
writer.overwrite().save(savePath)
reader = DefaultParamsReadable.read()
lr3 = reader.load(savePath)
self.assertEqual(lr.uid, lr3.uid)
self.assertEqual(lr.extractParamMap(), lr3.extractParamMap())
def test_default_read_write(self):
temp_path = tempfile.mkdtemp()
lr = LogisticRegression()
lr.setMaxIter(50)
lr.setThreshold(.75)
writer = DefaultParamsWriter(lr)
savePath = temp_path + "/lr"
writer.save(savePath)
reader = DefaultParamsReadable.read()
lr2 = reader.load(savePath)
self.assertEqual(lr.uid, lr2.uid)
self.assertEqual(lr.extractParamMap(), lr2.extractParamMap())
# test overwrite
lr.setThreshold(.8)
writer.overwrite().save(savePath)
reader = DefaultParamsReadable.read()
lr3 = reader.load(savePath)
self.assertEqual(lr.uid, lr3.uid)
self.assertEqual(lr.extractParamMap(), lr3.extractParamMap())
def test_default_read_write_default_params(self):
lr = LogisticRegression()
self.assertFalse(lr.isSet(lr.getParam("threshold")))
lr.setMaxIter(50)
lr.setThreshold(0.75)
# `threshold` is set by user, default param `predictionCol` is not set by user.
self.assertTrue(lr.isSet(lr.getParam("threshold")))
self.assertFalse(lr.isSet(lr.getParam("predictionCol")))
self.assertTrue(lr.hasDefault(lr.getParam("predictionCol")))
writer = DefaultParamsWriter(lr)
metadata = json.loads(writer._get_metadata_to_save(lr, self.sc))
self.assertTrue("defaultParamMap" in metadata)
reader = DefaultParamsReadable.read()
metadataStr = json.dumps(metadata, separators=[",", ":"])
loadedMetadata = reader._parseMetaData(
metadataStr,
)
reader.getAndSetParams(lr, loadedMetadata)
self.assertTrue(lr.isSet(lr.getParam("threshold")))
self.assertFalse(lr.isSet(lr.getParam("predictionCol")))
self.assertTrue(lr.hasDefault(lr.getParam("predictionCol")))
# manually create metadata without `defaultParamMap` section.
del metadata["defaultParamMap"]
metadataStr = json.dumps(metadata, separators=[",", ":"])
loadedMetadata = reader._parseMetaData(
metadataStr,
)
with self.assertRaisesRegex(AssertionError, "`defaultParamMap` section not found"):
reader.getAndSetParams(lr, loadedMetadata)
# Prior to 2.4.0, metadata doesn't have `defaultParamMap`.
metadata["sparkVersion"] = "2.3.0"
metadataStr = json.dumps(metadata, separators=[",", ":"])
loadedMetadata = reader._parseMetaData(
metadataStr,
)
reader.getAndSetParams(lr, loadedMetadata)
def test_default_read_write_default_params(self):
lr = LogisticRegression()
self.assertFalse(lr.isSet(lr.getParam("threshold")))
lr.setMaxIter(50)
lr.setThreshold(.75)
# `threshold` is set by user, default param `predictionCol` is not set by user.
self.assertTrue(lr.isSet(lr.getParam("threshold")))
self.assertFalse(lr.isSet(lr.getParam("predictionCol")))
self.assertTrue(lr.hasDefault(lr.getParam("predictionCol")))
writer = DefaultParamsWriter(lr)
metadata = json.loads(writer._get_metadata_to_save(lr, self.sc))
self.assertTrue("defaultParamMap" in metadata)
reader = DefaultParamsReadable.read()
metadataStr = json.dumps(metadata, separators=[',', ':'])
loadedMetadata = reader._parseMetaData(metadataStr, )
reader.getAndSetParams(lr, loadedMetadata)
self.assertTrue(lr.isSet(lr.getParam("threshold")))
self.assertFalse(lr.isSet(lr.getParam("predictionCol")))
self.assertTrue(lr.hasDefault(lr.getParam("predictionCol")))
# manually create metadata without `defaultParamMap` section.
del metadata['defaultParamMap']
metadataStr = json.dumps(metadata, separators=[',', ':'])
loadedMetadata = reader._parseMetaData(metadataStr, )
with self.assertRaisesRegexp(AssertionError, "`defaultParamMap` section not found"):
reader.getAndSetParams(lr, loadedMetadata)
# Prior to 2.4.0, metadata doesn't have `defaultParamMap`.
metadata['sparkVersion'] = '2.3.0'
metadataStr = json.dumps(metadata, separators=[',', ':'])
loadedMetadata = reader._parseMetaData(metadataStr, )
reader.getAndSetParams(lr, loadedMetadata)
def estimator_transformer():
spark = SparkSession \
.builder \
.appName("Python Spark SQL basic example") \
.config("spark.some.config.option", "some-value") \
.getOrCreate()
# Prepare training data from a list of (label, features) tuples.
training = spark.createDataFrame([(1.0, Vectors.dense([0.0, 1.1, 0.1])),
(0.0, Vectors.dense([2.0, 1.0, -1.0])),
(0.0, Vectors.dense([2.0, 1.3, 1.0])),
(1.0, Vectors.dense([0.0, 1.2, -0.5]))],
["label", "features"])
# Create a LogisticRegression instance. This instance is an Estimator.
lr = LogisticRegression(maxIter=10, regParam=0.01)
# Print out the parameters, documentation, and any default values.
print("\nLogisticRegression parameters:\n" + lr.explainParams() + "\n")
lr.setMaxIter(10).setRegParam(0.01).setAggregationDepth(5)
# Learn a LogisticRegression model. This uses the parameters stored in lr.
model1 = lr.fit(training)
# Since model1 is a Model (i.e., a transformer produced by an Estimator),
# we can view the parameters it used during fit().
# This prints the parameter (name: value) pairs, where names are unique IDs for this
# LogisticRegression instance.
print("\nModel 1 was fit using parameters: ")
print(model1.extractParamMap())
# We may alternatively specify parameters using a Python dictionary as a paramMap
paramMap = {lr.maxIter: 20}
paramMap[
lr.maxIter] = 30 # Specify 1 Param, overwriting the original maxIter.
paramMap.update({
lr.regParam: 0.1,
lr.threshold: 0.55
}) # Specify multiple Params.
# You can combine paramMaps, which are python dictionaries.
paramMap2 = {
lr.probabilityCol: "myProbability"
} # Change output column name
paramMapCombined = paramMap.copy()
paramMapCombined.update(paramMap2)
# Now learn a new model using the paramMapCombined parameters.
# paramMapCombined overrides all parameters set earlier via lr.set* methods.
model2 = lr.fit(training, paramMapCombined)
print("\nModel 2 was fit using parameters: ")
print(model2.extractParamMap())
# Prepare test data
test = spark.createDataFrame([(1.0, Vectors.dense([-1.0, 1.5, 1.3])),
(0.0, Vectors.dense([3.0, 2.0, -0.1])),
(1.0, Vectors.dense([0.0, 2.2, -1.5]))],
["label", "features"])
# Make predictions on test data using the Transformer.transform() method.
# LogisticRegression.transform will only use the 'features' column.
# Note that model2.transform() outputs a "myProbability" column instead of the usual
# 'probability' column since we renamed the lr.probabilityCol parameter previously.
prediction = model2.transform(test)
result = prediction.select("features", "label", "myProbability", "prediction") \
.collect()
for row in result:
print("features=%s, label=%s -> prob=%s, prediction=%s" %
(row.features, row.label, row.myProbability, row.prediction))
spark.stop()
