本文整理汇总了Python中document.Document.setTotalTfIdf方法的典型用法代码示例。如果您正苦于以下问题：Python Document.setTotalTfIdf方法的具体用法？Python Document.setTotalTfIdf怎么用？Python Document.setTotalTfIdf使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类document.Document的用法示例。
在下文中一共展示了Document.setTotalTfIdf方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: handleQuery
# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import setTotalTfIdf [as 别名]
def handleQuery(queryStr):
queryTerms = queryStr.split()
stopwordsInQuery = []
for term in queryTerms:
if isInvalidTerm(term):
print("Warning: Invalid query, \"" + term + "\" is not a valid query term")
queryTerms.remove(term)
elif term in stopwords:
stopwordsInQuery.append(term)
if len(queryTerms) == 0:
print("Error: Invalid query, no valid query terms")
return
elif len(stopwordsInQuery) == len(queryTerms):
print("Error: Invalid query, all terms are stopwords")
return
elif len(stopwordsInQuery) > 0:
print("Warning: The following terms were ignored because they are stopwords:")
printList(stopwordsInQuery)
print()
queryTerms = diff(queryTerms, stopwordsInQuery)
# Calculate IDFs
idfs = {}
numDocuments = float(len(documents))
# print("numDocuments: " + str(numDocuments))
for word in allWords:
# print("DocFreq: " + str(getDocumentFreq(word)))
idf = math.log10(numDocuments / getDocumentFreq(word))
idfs.update({word: idf})
# print("IDF's:")
# printDict(idfs)
# Calculate tf-idfs
for document in documents:
# print("Doc #" + str(document.id))
for term in document.terms:
term.setTfIdf(idfs.get(term.text))
# Create query as document
queryDocument = Document(-1, "Query", queryStr, queryTerms, "query")
for term in queryDocument.terms:
# print("Query term")
idfForQueryTerm = idfs.get(term.text)
if idfForQueryTerm:
term.setTfIdf(idfForQueryTerm)
else:
term.setTfIdf(0)
for document in documents:
# print("Doc #" + str(document.id))
document.setTotalTfIdf()
# print("Query Doc")
queryDocument.setTotalTfIdf()
for document in documents:
# print("Doc #" + str(document.id))
for term in document.terms:
term.setSimilarity(document.totalTfIdf)
for term in queryDocument.terms:
# print("Query term")
term.setSimilarity(queryDocument.totalTfIdf)
for document in documents:
# print("Doc #" + str(document.id))
document.setTotalSimilarity(queryDocument.terms)
document.addTitleBonus(queryDocument.terms)
# print(document)
printTopDocuments()