def get_scores_for_category(self):
cat_counts, not_cat_counts = self._get_counts()
scores = ScaledFScore.get_scores_for_category(cat_counts, not_cat_counts)
np.testing.assert_almost_equal(scores,
[0.23991183969723384, 0.24969810634506373, 0.23991183969723384,
0.27646711056272855, 0.92885244834997516, 0.42010144843632563,
0.49166017105966719, 0.0, 0.0, 0.50262304057984664])
def get_scores_for_category(self):
cat_counts, not_cat_counts = self._get_counts()
scores = ScaledFScore.get_scores_for_category(cat_counts,
not_cat_counts)
np.testing.assert_almost_equal(scores, [
0.23991183969723384, 0.24969810634506373, 0.23991183969723384,
0.27646711056272855, 0.92885244834997516, 0.42010144843632563,
0.49166017105966719, 0.0, 0.0, 0.50262304057984664
])
def get_scaled_f_scores_vs_background(self, scaler_algo='none', beta=1.):
'''
Parameters
----------
scaler_algo : str
see get_scaled_f_scores, default 'none'
beta : float
default 1.
Returns
-------
pd.DataFrame of scaled_f_score scores compared to background corpus
'''
df = self.get_term_and_background_counts()
df['Scaled f-score'] = ScaledFScore.get_scores_for_category(
df['corpus'], df['background'], scaler_algo, beta)
return df.sort_values(by='Scaled f-score', ascending=False)