spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From mengxr <...@git.apache.org>
Subject [GitHub] spark pull request: [Spark-9028] [ML] Add CountVectorizer as an es...
Date Fri, 14 Aug 2015 15:54:52 GMT
Github user mengxr commented on a diff in the pull request:

    https://github.com/apache/spark/pull/7388#discussion_r37090327
  
    --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala ---
    @@ -0,0 +1,196 @@
    +/*
    + * 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.
    + */
    +package org.apache.spark.ml.feature
    +
    +import scala.collection.mutable
    +
    +import org.apache.spark.annotation.Experimental
    +import org.apache.spark.ml.param._
    +import org.apache.spark.ml.param.shared.{HasInputCol, HasOutputCol}
    +import org.apache.spark.ml.util.{Identifiable, SchemaUtils}
    +import org.apache.spark.ml.{Estimator, Model}
    +import org.apache.spark.mllib.linalg.{VectorUDT, Vectors}
    +import org.apache.spark.rdd.RDD
    +import org.apache.spark.sql.functions._
    +import org.apache.spark.sql.types._
    +import org.apache.spark.sql.DataFrame
    +
    +/**
    + * Params for [[CountVectorizer]] and [[CountVectorizerModel]].
    + */
    +private[feature] trait CountVectorizerParams extends Params with HasInputCol with HasOutputCol
{
    +
    +  /**
    +   * Max size of the vocabulary.
    +   * CountVectorizer will build a vocabulary that only considers the top
    +   * vocabSize terms ordered by term frequency across the corpus.
    +   *
    +   * Default: 10000
    +   * @group param
    +   */
    +  val vocabSize: IntParam =
    +    new IntParam(this, "vocabSize", "size of the vocabulary", ParamValidators.gt(0))
    +
    +  /** @group getParam */
    +  def getVocabSize: Int = $(vocabSize)
    +
    +  /**
    +   * The minimum number of times a token must appear in the corpus to be included in
the vocabulary.
    +   * Note that this is not the same as document frequency: [[minTokenCount]] counts tokens
including
    +   * duplicates of terms, whereas document frequency counts unique terms.  Support for
document
    +   * frequency will be added in the future.
    +   *
    +   * Default: 1
    +   * @group param
    +   */
    +  val minTokenCount: IntParam = new IntParam(this, "minTokenCount",
    +    "minimum number of times a token must appear in the corpus to be included in the
vocabulary."
    +    , ParamValidators.gtEq(1))
    +
    +  /** @group getParam */
    +  def getMinTokenCount: Int = $(minTokenCount)
    +
    +  /** Validates and transforms the input schema. */
    +  protected def validateAndTransformSchema(schema: StructType): StructType = {
    +    SchemaUtils.checkColumnType(schema, $(inputCol), new ArrayType(StringType, true))
    +    SchemaUtils.appendColumn(schema, $(outputCol), new VectorUDT)
    +  }
    +
    +  /**
    +   * Filter to ignore scarce words in a document. For each document, terms with
    +   * frequency (count) less than the given threshold are ignored.
    +   * Default: 1
    +   * @group param
    +   */
    +  val minTermFreq: IntParam = new IntParam(this, "minTermFreq",
    --- End diff --
    
    Should mention that this doesn't affect fitting.


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message