本文整理汇总了Python中utilities.Utilities.iterateTweetsFromFile方法的典型用法代码示例。如果您正苦于以下问题：Python Utilities.iterateTweetsFromFile方法的具体用法？Python Utilities.iterateTweetsFromFile怎么用？Python Utilities.iterateTweetsFromFile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utilities.Utilities的用法示例。
在下文中一共展示了Utilities.iterateTweetsFromFile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: generateDataSetStats125
# 需要导入模块: from utilities import Utilities [as 别名]
# 或者: from utilities.Utilities import iterateTweetsFromFile [as 别名]
def generateDataSetStats125():
currentDay = Settings.startTime
while currentDay<=Settings.endTime:
data = {'day': datetime.strftime(currentDay, Settings.twitter_api_time_format), 'train_classes': defaultdict(int), 'test_classes': defaultdict(int)}
inputTrainingSetFile = Utilities.getTrainingFile(currentDay, DocumentType.typeRuuslUnigram, Settings.numberOfExperts)
inputTestSetFile = Utilities.getTestFile(currentDay, DocumentType.typeRuuslUnigram, Settings.numberOfExperts, bottom=True)
for file, tweetType in [(inputTrainingSetFile, 'training'), (inputTestSetFile, 'test')]:
for tweet in Utilities.iterateTweetsFromFile(file):
if tweetType=='training': data['train_classes'][tweet['class']]+=1
else: data['test_classes'][tweet['class']]+=1
Utilities.writeAsJsonToFile(data, Settings.stats_for_dataset_125)
currentDay+=timedelta(days=1)示例2: generate
# 需要导入模块: from utilities import Utilities [as 别名]
# 或者: from utilities.Utilities import iterateTweetsFromFile [as 别名]
def generate(self):
for inputFile, outputFile in [
(self.inputTrainingSetFile, self.outputTrainingSetFile),
(self.inputTestSetFile, self.outputTestSetFile),
]:
for tweet in Utilities.iterateTweetsFromFile(inputFile):
data = {}
for k in DocumentType.keys:
data[k] = tweet[k]
data["screen_name"] = tweet["user"]["screen_name"]
data["user_id"] = tweet["user"]["id_str"]
data["document"] = self.modifyDocument(data["text"])
Utilities.writeAsJsonToFile(data, outputFile)