Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/11871#discussion_r57397665
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala ---
@@ -31,51 +31,16 @@ import org.apache.spark.sql.types.{ArrayType,
StringType, StructType}
*/
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")
+ /** Read stop words list from resources */
+ def readStopWords(language: String): Array[String] = {
--- End diff --
`loadStopWords` might be a better name here.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
