diff options
Diffstat (limited to 'python/pyspark/ml/feature.py')
-rw-r--r-- | python/pyspark/ml/feature.py | 71 |
1 files changed, 70 insertions, 1 deletions
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py index ddb33f427a..8804dace84 100644 --- a/python/pyspark/ml/feature.py +++ b/python/pyspark/ml/feature.py @@ -21,7 +21,7 @@ from pyspark.ml.util import keyword_only from pyspark.ml.wrapper import JavaEstimator, JavaModel, JavaTransformer from pyspark.mllib.common import inherit_doc -__all__ = ['Binarizer', 'HashingTF', 'IDF', 'IDFModel', 'Normalizer', 'OneHotEncoder', +__all__ = ['Binarizer', 'HashingTF', 'IDF', 'IDFModel', 'NGram', 'Normalizer', 'OneHotEncoder', 'PolynomialExpansion', 'RegexTokenizer', 'StandardScaler', 'StandardScalerModel', 'StringIndexer', 'StringIndexerModel', 'Tokenizer', 'VectorAssembler', 'VectorIndexer', 'Word2Vec', 'Word2VecModel'] @@ -266,6 +266,75 @@ class IDFModel(JavaModel): @inherit_doc +@ignore_unicode_prefix +class NGram(JavaTransformer, HasInputCol, HasOutputCol): + """ + A feature transformer that converts the input array of strings into an array of n-grams. Null + values in the input array are ignored. + It returns an array of n-grams where each n-gram is represented by a space-separated string of + words. + When the input is empty, an empty array is returned. + When the input array length is less than n (number of elements per n-gram), no n-grams are + returned. + + >>> df = sqlContext.createDataFrame([Row(inputTokens=["a", "b", "c", "d", "e"])]) + >>> ngram = NGram(n=2, inputCol="inputTokens", outputCol="nGrams") + >>> ngram.transform(df).head() + Row(inputTokens=[u'a', u'b', u'c', u'd', u'e'], nGrams=[u'a b', u'b c', u'c d', u'd e']) + >>> # Change n-gram length + >>> ngram.setParams(n=4).transform(df).head() + Row(inputTokens=[u'a', u'b', u'c', u'd', u'e'], nGrams=[u'a b c d', u'b c d e']) + >>> # Temporarily modify output column. + >>> ngram.transform(df, {ngram.outputCol: "output"}).head() + Row(inputTokens=[u'a', u'b', u'c', u'd', u'e'], output=[u'a b c d', u'b c d e']) + >>> ngram.transform(df).head() + Row(inputTokens=[u'a', u'b', u'c', u'd', u'e'], nGrams=[u'a b c d', u'b c d e']) + >>> # Must use keyword arguments to specify params. + >>> ngram.setParams("text") + Traceback (most recent call last): + ... + TypeError: Method setParams forces keyword arguments. + """ + + # a placeholder to make it appear in the generated doc + n = Param(Params._dummy(), "n", "number of elements per n-gram (>=1)") + + @keyword_only + def __init__(self, n=2, inputCol=None, outputCol=None): + """ + __init__(self, n=2, inputCol=None, outputCol=None) + """ + super(NGram, self).__init__() + self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.NGram", self.uid) + self.n = Param(self, "n", "number of elements per n-gram (>=1)") + self._setDefault(n=2) + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, n=2, inputCol=None, outputCol=None): + """ + setParams(self, n=2, inputCol=None, outputCol=None) + Sets params for this NGram. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + def setN(self, value): + """ + Sets the value of :py:attr:`n`. + """ + self._paramMap[self.n] = value + return self + + def getN(self): + """ + Gets the value of n or its default value. + """ + return self.getOrDefault(self.n) + + +@inherit_doc class Normalizer(JavaTransformer, HasInputCol, HasOutputCol): """ Normalize a vector to have unit norm using the given p-norm. |