def test_int_to_float(self):
from pyspark.mllib.linalg import Vectors
df = self.sc.parallelize([
Row(label=1.0, weight=2.0, features=Vectors.dense(1.0))]).toDF()
lr = LogisticRegression(elasticNetParam=0)
lr.fit(df)
lr.setElasticNetParam(0)
lr.fit(df)
def test_int_to_float(self):
from pyspark.mllib.linalg import Vectors
df = self.sc.parallelize(
[Row(label=1.0, weight=2.0, features=Vectors.dense(1.0))]).toDF()
lr = LogisticRegression(elasticNetParam=0)
lr.fit(df)
lr.setElasticNetParam(0)
lr.fit(df)
def test_invalid_to_float(self):
from pyspark.mllib.linalg import Vectors
self.assertRaises(Exception,
lambda: LogisticRegression(elasticNetParam="happy"))
lr = LogisticRegression(elasticNetParam=0)
self.assertRaises(Exception, lambda: lr.setElasticNetParam("panda"))
# COMMAND ----------
partialPipeline = Pipeline().setStages([tokenizer, remover, counts, binarizer])
preppedData = partialPipeline.fit(train).transform(train)
lrModel = LogisticRegression().fit(preppedData)
display(lrModel, preppedData, "ROC")
# COMMAND ----------
print(lr.explainParams())
# COMMAND ----------
lr.setRegParam(0.01)
lr.setElasticNetParam(0.1)
counts.setVocabSize(1000)
model = p.fit(train)
result = model.transform(test)
print("AUC %(result)s" %
{"result": BinaryClassificationEvaluator().evaluate(result)})
# COMMAND ----------
# DBTITLE 1,Serialize model
model.write().overwrite().save("/mnt/mikem/models/amazon-model")
# COMMAND ----------
# MAGIC %fs ls /mnt/mikem/models/amazon-model/
def test_invalid_to_float(self):
from pyspark.mllib.linalg import Vectors
self.assertRaises(Exception, lambda: LogisticRegression(elasticNetParam="happy"))
lr = LogisticRegression(elasticNetParam=0)
self.assertRaises(Exception, lambda: lr.setElasticNetParam("panda"))
exit(-1)
sc = SparkContext(appName="PythonLogisticRegressionExample")
sqlContext = SQLContext(sc)
# Load and parse the data file into a dataframe.
df = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt").toDF()
# Map labels into an indexed column of labels in [0, numLabels)
stringIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel")
si_model = stringIndexer.fit(df)
td = si_model.transform(df)
[training, test] = td.randomSplit([0.7, 0.3])
lr = LogisticRegression(maxIter=100,
regParam=0.3).setLabelCol("indexedLabel")
lr.setElasticNetParam(0.8)
# Fit the model
lrModel = lr.fit(training)
predictionAndLabels = lrModel.transform(test).select("prediction", "indexedLabel") \
.map(lambda x: (x.prediction, x.indexedLabel))
metrics = MulticlassMetrics(predictionAndLabels)
print("weighted f-measure %.3f" % metrics.weightedFMeasure())
print("precision %s" % metrics.precision())
print("recall %s" % metrics.recall())
sc.stop()
print("Usage: logistic_regression", file=sys.stderr)
exit(-1)
sc = SparkContext(appName="PythonLogisticRegressionExample")
sqlContext = SQLContext(sc)
# Load the data stored in LIBSVM format as a DataFrame.
df = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
# Map labels into an indexed column of labels in [0, numLabels)
stringIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel")
si_model = stringIndexer.fit(df)
td = si_model.transform(df)
[training, test] = td.randomSplit([0.7, 0.3])
lr = LogisticRegression(maxIter=100, regParam=0.3).setLabelCol("indexedLabel")
lr.setElasticNetParam(0.8)
# Fit the model
lrModel = lr.fit(training)
predictionAndLabels = lrModel.transform(test).select("prediction", "indexedLabel") \
.map(lambda x: (x.prediction, x.indexedLabel))
metrics = MulticlassMetrics(predictionAndLabels)
print("weighted f-measure %.3f" % metrics.weightedFMeasure())
print("precision %s" % metrics.precision())
print("recall %s" % metrics.recall())
sc.stop()
