Github user davies commented on a diff in the pull request: https://github.com/apache/spark/pull/4151#discussion_r23656969 --- Diff: python/pyspark/ml/feature.py --- @@ -0,0 +1,88 @@ +# +# 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. +# + +from pyspark.sql import inherit_doc +from pyspark.ml import JavaTransformer +from pyspark.ml.param.shared import HasInputCol, HasOutputCol, HasNumFeatures + + +@inherit_doc +class Tokenizer(JavaTransformer, HasInputCol, HasOutputCol): + """ + A tokenizer that converts the input string to lowercase and then splits it by white spaces. + + >>> from pyspark.sql import Row + >>> dataset = sqlCtx.inferSchema(sc.parallelize([Row(text="a b c")])) + >>> tokenizer = Tokenizer() \ + .setInputCol("text") \ + .setOutputCol("words") + >>> print tokenizer.transform(dataset).first() + Row(text=u'a b c', words=[u'a', u'b', u'c']) + >>> print tokenizer.transform(dataset, {tokenizer.outputCol: "tokens"}).first() + Row(text=u'a b c', tokens=[u'a', u'b', u'c']) + """ + + def __init__(self): + super(Tokenizer, self).__init__() + + @property + def _java_class(self): + return "org.apache.spark.ml.feature.Tokenizer" + + +@inherit_doc +class HashingTF(JavaTransformer, HasInputCol, HasOutputCol, HasNumFeatures): + """ + Maps a sequence of terms to their term frequencies using the hashing trick. + + >>> from pyspark.sql import Row + >>> dataset = sqlCtx.inferSchema(sc.parallelize([Row(words=["a", "b", "c"])])) + >>> hashingTF = HashingTF() \ + .setNumFeatures(10) \ + .setInputCol("words") \ + .setOutputCol("features") + >>> print hashingTF.transform(dataset).first().features + (10,[7,8,9],[1.0,1.0,1.0]) + >>> params = {hashingTF.numFeatures: 5, hashingTF.outputCol: "vector"} + >>> print hashingTF.transform(dataset, params).first().vector + (5,[2,3,4],[1.0,1.0,1.0]) + """ + + def __init__(self): + super(HashingTF, self).__init__() + + @property + def _java_class(self): + return "org.apache.spark.ml.feature.HashingTF" --- End diff -- We could put this as an class attribute.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org