def test_missingness_threshold(thre):
clf = InsilicoClassifier()
# Create a dataframe which looks like a checker board of 1s and 0s
# and set the first n percent of the observations in the column to missing.
# The percent missing is the column header
df = pd.DataFrame(np.tile([1, 0], 550).reshape((100, 11)),
index=['I{}'.format(i) for i in range(100)],
columns=['{}0%'.format(i) for i in range(11)])
for x in range(11):
df.iloc[np.arange(0, x * 10), x] = -1
# The pattern of five letters repeat over and over. This ensures that the
# for each y value some are missing others are not.
y = pd.Series(np.tile(['a', 'b', 'c', 'd', 'e'], 20), index=df.index)
clf.extract_prob(df, y, missingness_threshold=thre)
df.iloc[:, np.arange(int((thre + 0.05) * 10))].columns
def extracted_data(request):
clf = InsilicoClassifier()
key, value = request.param
df_data = {
'data': np.concatenate([np.eye(5) for i in range(4)]),
'index': ['row{}'.format(i) for i in range(20)],
'columns': ['col{}'.format(i) for i in range(5)],
}
if key == 'gs':
y = pd.Series(value)
else:
y = pd.Series(['gold{}'.format(x) for x in np.repeat(np.arange(5), 4)])
df_data.update({key: value})
df = pd.DataFrame(**df_data)
y.index = df.index
probs = clf.extract_prob(df, y)
return probs, df, y