本文整理汇总了Python中document.Document.getNumDifferentWords方法的典型用法代码示例。如果您正苦于以下问题：Python Document.getNumDifferentWords方法的具体用法？Python Document.getNumDifferentWords怎么用？Python Document.getNumDifferentWords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.getNumDifferentWords方法的2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: main
# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import getNumDifferentWords [as 别名]
def main():
# Initial input checking
if len(sys.argv) < 2:
print("Insufficient arguments. Usage: parse.py <fileName>")
sys.exit(22)
if os.path.isfile(sys.argv[1]) == False:
print("File does not exist.")
sys.exit(22)
if sys.argv[1][-3:] == "txt":
doc = Document()
with open(sys.argv[1]) as file:
parser = document.Parser(file, doc)
parser.parseDocument()
# for w in doc:
# print("%s: %s" % (w, doc.getWordCount(w)))
if len(sys.argv) >= 3:
if "-stats" in sys.argv:
print("Document Statistics:")
print("Total Words : %d" % (doc.getNumTotalWords()))
print("Different Words : %d" % (doc.getNumDifferentWords()))
print("Number of Sentences : %d" % (doc.getNumSentences()))
print("Number of Paragraphs: %d" % (doc.getNumParagraphs()))
print("------------")
if "-lw" in sys.argv:
print("Words in Document:")
for w in doc:
print("%s" % (w))
print("------------")
if "-lwf" in sys.argv:
print("Word Frequency in Document:")
for w in doc:
print("%s: %s" % (w, doc.getWordCount(w)))
print("------------")
if "-mfw" in sys.argv:
print("Most Frequent Word(s) in Document:")
maxFreq = 0
mostFreqWords = []
for w in doc:
if doc.getWordCount(w) > maxFreq:
maxFreq = doc.getWordCount(w)
mostFreqWords = []
mostFreqWords.append(w)
elif doc.getWordCount(w) == maxFreq:
mostFreqWords.append(w)
for w in mostFreqWords:
print("%s: %s" % (w, maxFreq))
print("------------")
for args in sys.argv:
if "-find=" in args:
searchWord = args[6:]
if len(searchWord) > 0:
print("Searching for Word \"%s\" in Document:" % searchWord)
print("%s: %s" % (searchWord, doc.getWordCount(searchWord)))
print("------------")
elif sys.argv[1][-3:] == "csv":
csv = Custom_CSV()
with open(sys.argv[1]) as file:
parser = custom_csv.CSV_Parser(file, csv)
parser.parseCSV()
else:
print("Bad file extenstion.")
sys.exit(22)示例2: main
# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import getNumDifferentWords [as 别名]
#.........这里部分代码省略.........
print("---");
for e in c:
print("%f" % e)
print("mean: %f" % vector_math.meanRow(c))
else:
print("Column %d had no entries" % col)
print("------------")
elif filename[-3:] == 'txt':
doc = Document()
# Read Document
print('Opening document...')
try:
with open(args.file) as file:
print('Parsing document...')
parser = document.Parser(file, doc)
parser.parseDocument()
print('Done!')
print("------------")
except FileNotFoundError as e:
print('Could not find file %s' % (args.file))
return e.errno
# Display Document
if args.display_all:
print('Displaying all words and their occurrences...')
print('%-16s %-13s' % ('Word', 'Occurrences'))
for w in doc:
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.most_frequent:
print('Finding most frequent...')
mostFreq = doc.getMostFrequentWord()
print('%-16s %-13s' % ('Most Frequent', 'Occurrences'))
print('%-16s %-13d' % (mostFreq, doc.getWordCount(mostFreq)))
print("------------")
if args.most_frequent_percent:
percent = int(args.most_frequent_percent)
if percent > 100 or percent < 0:
print('%d is an invalid percentage -- must be between 0 and 100' % percent)
return 22
print('Finding words within %d percent of the most frequent...' % percent)
mostFreqWords = doc.getMostFrequentWords(percent)
print('%-16s %-13s' % ('Most Frequent', 'Occurrences'))
for w in mostFreqWords:
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.top:
topNum = int(args.top)
if topNum < 0:
print('Please do not give the program negative numbers')
return 22
print('Finding top %d words...' % topNum)
topWords = doc.getTopWords(topNum)
print('%-16s %-13s' % ('Top %d Frequent' % topNum, 'Occurrences'))
for w in topWords:
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.equal_to:
freq = int(args.equal_to)
print('Finding words with %d ocurrences...' % freq)
wordsEqual = doc.getWordsEqualToFrequency(freq)
print('%-16s %-13s' % ('Word', 'Occurrences'))
wordsEqual = sorted(wordsEqual)
for w in wordsEqual:
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.above:
freq = int(args.above)
print('Finding words above %d occurrences...' % freq)
wordsAbove = doc.getWordsAboveFrequency(freq)
print('%-16s %-13s' % ('Word', 'Occurrences'))
wordsAbove = sorted(wordsAbove)
for w in wordsAbove:
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.word:
print('Finding occurrences for %s...' % args.word)
print('%-16s %-13s' % ('Word', 'Occurrences'))
for w in args.word.split(','):
print('%-16s %-13d' % (w, doc.getWordCount(w)))
print("------------")
if args.is_in:
print('Checking if %s is in the document...' % args.is_in)
if doc.getWordCount(args.is_in) > 0:
print('"%s" IS in the document!' % args.is_in)
else:
print('"%s" IS NOT in the document!' % args.is_in)
print("------------")
if args.stats:
print("Document Statistics:")
print("Number Total Words : %d" % (doc.getNumTotalWords()))
print("Number Different Words: %d" % (doc.getNumDifferentWords()))
print("Number of Sentences : %d" % (doc.getNumSentences()))
print("Number of Paragraphs : %d" % (doc.getNumParagraphs()))
print("------------")
else:
print('Please provide either a .csv or a .txt file to be parsed')
return 22
return 0