1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
|
/*
* 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 org.apache.spark.annotation.{Experimental, Since}
import org.apache.spark.ml.Transformer
import org.apache.spark.ml.param.{BooleanParam, ParamMap, StringArrayParam}
import org.apache.spark.ml.param.shared.{HasInputCol, HasOutputCol}
import org.apache.spark.ml.util._
import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.functions.{col, udf}
import org.apache.spark.sql.types.{ArrayType, StringType, StructType}
/**
* stop words list
*/
private[spark] object StopWords {
/**
* Use the same default stopwords list as scikit-learn.
* The original list can be found from "Glasgow Information Retrieval Group"
* [[http://ir.dcs.gla.ac.uk/resources/linguistic_utils/stop_words]]
*/
val English = Array( "a", "about", "above", "across", "after", "afterwards", "again",
"against", "all", "almost", "alone", "along", "already", "also", "although", "always",
"am", "among", "amongst", "amoungst", "amount", "an", "and", "another",
"any", "anyhow", "anyone", "anything", "anyway", "anywhere", "are",
"around", "as", "at", "back", "be", "became", "because", "become",
"becomes", "becoming", "been", "before", "beforehand", "behind", "being",
"below", "beside", "besides", "between", "beyond", "bill", "both",
"bottom", "but", "by", "call", "can", "cannot", "cant", "co", "con",
"could", "couldnt", "cry", "de", "describe", "detail", "do", "done",
"down", "due", "during", "each", "eg", "eight", "either", "eleven", "else",
"elsewhere", "empty", "enough", "etc", "even", "ever", "every", "everyone",
"everything", "everywhere", "except", "few", "fifteen", "fify", "fill",
"find", "fire", "first", "five", "for", "former", "formerly", "forty",
"found", "four", "from", "front", "full", "further", "get", "give", "go",
"had", "has", "hasnt", "have", "he", "hence", "her", "here", "hereafter",
"hereby", "herein", "hereupon", "hers", "herself", "him", "himself", "his",
"how", "however", "hundred", "i", "ie", "if", "in", "inc", "indeed",
"interest", "into", "is", "it", "its", "itself", "keep", "last", "latter",
"latterly", "least", "less", "ltd", "made", "many", "may", "me",
"meanwhile", "might", "mill", "mine", "more", "moreover", "most", "mostly",
"move", "much", "must", "my", "myself", "name", "namely", "neither",
"never", "nevertheless", "next", "nine", "no", "nobody", "none", "noone",
"nor", "not", "nothing", "now", "nowhere", "of", "off", "often", "on",
"once", "one", "only", "onto", "or", "other", "others", "otherwise", "our",
"ours", "ourselves", "out", "over", "own", "part", "per", "perhaps",
"please", "put", "rather", "re", "same", "see", "seem", "seemed",
"seeming", "seems", "serious", "several", "she", "should", "show", "side",
"since", "sincere", "six", "sixty", "so", "some", "somehow", "someone",
"something", "sometime", "sometimes", "somewhere", "still", "such",
"system", "take", "ten", "than", "that", "the", "their", "them",
"themselves", "then", "thence", "there", "thereafter", "thereby",
"therefore", "therein", "thereupon", "these", "they", "thick", "thin",
"third", "this", "those", "though", "three", "through", "throughout",
"thru", "thus", "to", "together", "too", "top", "toward", "towards",
"twelve", "twenty", "two", "un", "under", "until", "up", "upon", "us",
"very", "via", "was", "we", "well", "were", "what", "whatever", "when",
"whence", "whenever", "where", "whereafter", "whereas", "whereby",
"wherein", "whereupon", "wherever", "whether", "which", "while", "whither",
"who", "whoever", "whole", "whom", "whose", "why", "will", "with",
"within", "without", "would", "yet", "you", "your", "yours", "yourself", "yourselves")
}
/**
* :: Experimental ::
* A feature transformer that filters out stop words from input.
* Note: null values from input array are preserved unless adding null to stopWords explicitly.
* @see [[http://en.wikipedia.org/wiki/Stop_words]]
*/
@Experimental
class StopWordsRemover(override val uid: String)
extends Transformer with HasInputCol with HasOutputCol with DefaultParamsWritable {
def this() = this(Identifiable.randomUID("stopWords"))
/** @group setParam */
def setInputCol(value: String): this.type = set(inputCol, value)
/** @group setParam */
def setOutputCol(value: String): this.type = set(outputCol, value)
/**
* the stop words set to be filtered out
* Default: [[StopWords.English]]
* @group param
*/
val stopWords: StringArrayParam = new StringArrayParam(this, "stopWords", "stop words")
/** @group setParam */
def setStopWords(value: Array[String]): this.type = set(stopWords, value)
/** @group getParam */
def getStopWords: Array[String] = $(stopWords)
/**
* whether to do a case sensitive comparison over the stop words
* Default: false
* @group param
*/
val caseSensitive: BooleanParam = new BooleanParam(this, "caseSensitive",
"whether to do case-sensitive comparison during filtering")
/** @group setParam */
def setCaseSensitive(value: Boolean): this.type = set(caseSensitive, value)
/** @group getParam */
def getCaseSensitive: Boolean = $(caseSensitive)
setDefault(stopWords -> StopWords.English, caseSensitive -> false)
override def transform(dataset: DataFrame): DataFrame = {
val outputSchema = transformSchema(dataset.schema)
val t = if ($(caseSensitive)) {
val stopWordsSet = $(stopWords).toSet
udf { terms: Seq[String] =>
terms.filter(s => !stopWordsSet.contains(s))
}
} else {
val toLower = (s: String) => if (s != null) s.toLowerCase else s
val lowerStopWords = $(stopWords).map(toLower(_)).toSet
udf { terms: Seq[String] =>
terms.filter(s => !lowerStopWords.contains(toLower(s)))
}
}
val metadata = outputSchema($(outputCol)).metadata
dataset.select(col("*"), t(col($(inputCol))).as($(outputCol), metadata))
}
override def transformSchema(schema: StructType): StructType = {
val inputType = schema($(inputCol)).dataType
require(inputType.sameType(ArrayType(StringType)),
s"Input type must be ArrayType(StringType) but got $inputType.")
SchemaUtils.appendColumn(schema, $(outputCol), inputType, schema($(inputCol)).nullable)
}
override def copy(extra: ParamMap): StopWordsRemover = defaultCopy(extra)
}
@Since("1.6.0")
object StopWordsRemover extends DefaultParamsReadable[StopWordsRemover] {
@Since("1.6.0")
override def load(path: String): StopWordsRemover = super.load(path)
}
|
