(stringList)
| 77 | |
| 78 | #extracts tokens from the cell value or value list |
| 79 | def expandQuery(stringList): |
| 80 | stringList = [item for item in stringList if type(item) == str] |
| 81 | stringList = preprocessListValues(stringList) |
| 82 | nounList = extractNouns(stringList) |
| 83 | expandedQueryList = [words for segments in nounList for words in segments.split()] |
| 84 | # handle phrase queries |
| 85 | removeNouns = [] |
| 86 | for entity in puncCleanedList: |
| 87 | entityList = entity.split(" ") |
| 88 | if entityList.count('') > 0 and entityList.count('') <= 2: |
| 89 | entityList.remove('') |
| 90 | index = 0 |
| 91 | while index <= len(entityList) - 1: |
| 92 | word = entityList[index] |
| 93 | if word in nounList: |
| 94 | if index + 1 < len(entityList): |
| 95 | nextWord = entityList[index + 1] |
| 96 | if entityList[index + 1] in nounList: |
| 97 | removeNouns.append(word) |
| 98 | removeNouns.append(entityList[index + 1]) |
| 99 | expandedQueryList.append(word + " " + entityList[index + 1]) |
| 100 | index += 1 |
| 101 | index += 1 |
| 102 | |
| 103 | finalNouns = [noun for noun in expandedQueryList if noun not in removeNouns] |
| 104 | stopWordsRemovedList= [word for word in finalNouns if word.lower() not in stopwords.words('english')] |
| 105 | return (list(set(stopWordsRemovedList))) |
| 106 | |
| 107 | #This function saves dictionaries as pickle files in the storage. |
| 108 | def saveDictionaryAsPickleFile(dictionary, dictionaryPath): |
nothing calls this directly
no test coverage detected