return word_frequency
def get_part_of_speech_tags(self):
"""
Returns the part of speech tags as a list of tuples. The first part of each tuple is the
term, the second one the part of speech tag.
Note: the same word can have a different part of speech tag. In the example below,
see "refuse" and "permit"
>>> from gender_novels.novel import Novel
>>> summary = "They refuse to permit us to obtain the refuse permit."
>>> novel_metadata = {'author': 'Hawthorne, Nathaniel', 'title': 'Scarlet Letter',
... 'corpus_name': 'sample_novels', 'date': '1900',
... 'filename': None, 'text': summary}
>>> novel = Novel(novel_metadata)
>>> novel.get_part_of_speech_tags()[:4]
[('They', 'PRP'), ('refuse', 'VBP'), ('to', 'TO'), ('permit', 'VB')]
>>> novel.get_part_of_speech_tags()[-4:]
[('the', 'DT'), ('refuse', 'NN'), ('permit', 'NN'), ('.', '.')]
:rtype: list
"""
text = nltk.word_tokenize(self.text)
pos_tags = nltk.pos_tag(text)
return pos_tags
if __name__ == '__main__':
from dh_testers.testRunner import main_test
main_test()
encoding=target_encoding) as target_file:
target_file.write(text)
def load_graph_settings(show_grid_lines=True):
'''
This function sets the seaborn graph settings to the defaults for our project.
Defaults to displaying gridlines. To remove gridlines, call with False.
:return:
'''
show_grid_lines_string = str(show_grid_lines)
palette = "colorblind"
style_name = "white"
background_color = (252 / 255, 245 / 255, 233 / 255, 0.4)
style_list = {
'axes.edgecolor': '.6',
'grid.color': '.9',
'axes.grid': show_grid_lines_string,
'font.family': 'serif',
'axes.facecolor': background_color,
'figure.facecolor': background_color
}
sns.set_color_codes(palette)
sns.set_style(style_name, style_list)
if __name__ == '__main__':
from dh_testers.testRunner import main_test
main_test(import_plus_relative=True
) # this allows for relative calls in the import.
