本文整理汇总了Python中dataset.Dataset.build_vocabulary方法的典型用法代码示例。如果您正苦于以下问题：Python Dataset.build_vocabulary方法的具体用法？Python Dataset.build_vocabulary怎么用？Python Dataset.build_vocabulary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dataset.Dataset的用法示例。
在下文中一共展示了Dataset.build_vocabulary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: read_data
# 需要导入模块: from dataset import Dataset [as 别名]
# 或者: from dataset.Dataset import build_vocabulary [as 别名]
def read_data(dirname, return_dataset=False):
ds = Dataset(dirname, Reader.get_classes())
emails, classes = [], []
for sentences, email_type in ds.get_text():
ds.build_vocabulary(sentences)
emails.append(sentences)
classes.append(email_type)
# transform word to indices
emails = [list(map(ds.get_word_indices().get, s)) for s in emails]
# count how many times a word appear with the ith class
counts = np.zeros((len(ds.vocabulary), len(set(classes))))
for i, e in enumerate(emails):
for w in e:
counts[w, classes[i]] += 1
# emails = ds.bag_of_words(emails) # using bow we dont need counts
if return_dataset:
return np.array(emails), np.array(classes), counts, ds
return np.array(emails), np.array(classes), counts示例2: read_file_with_dataset
# 需要导入模块: from dataset import Dataset [as 别名]
# 或者: from dataset.Dataset import build_vocabulary [as 别名]
def read_file_with_dataset(dirname, ds_orig, return_dataset=False):
ds = Dataset(dirname, ['spam', 'ham'])
emails = []
for sentences in ds.get_text_file():
ds.build_vocabulary(sentences)
emails.append(sentences)
# transform word to indices
dic = ds_orig.get_word_indices()
for i, s in enumerate(emails):
for j, x in enumerate(s):
if x in dic:
emails[i][j] = dic[x]
else:
emails[i][j] = random.randint(0, len(dic)-1) # if the word was not seen before, we pick a random one
print(emails)
return np.array(emails)