qq=vat.transform(dat).head()
qq
qq = poly.transform(df).head()
>>> px = PolynomialExpansion(degree=2, inputCol="dense", outputCol="expanded")
>>> px.transform(df).head().expanded
DenseVector([0.5, 0.25, 2.0, 1.0, 4.0])
>>> px.setParams(outputCol="test").transform(df).head().test
DenseVector([0.5, 0.25, 2.0, 1.0, 4.0])
>>> polyExpansionPath = temp_path + "/poly-expansion"
>>> px.save(polyExpansionPath)
>>> loadedPx = PolynomialExpansion.load(polyExpansionPath)
>>> loadedPx.getDegree() == px.getDegree()
True
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.feature import HashingTF, Tokenizer
# Prepare training documents from a list of (id, text, label) tuples.
training = spark.createDataFrame([
(0, "a b c d e spark", 1.0),
(1, "b d", 0.0),
(2, "spark f g h", 1.0),
