def _extract_phenotype(data_phenotype, nuclei, wildcards, features):
from lasagna.pipelines._20170914_endo import feature_table_stack
from lasagna.process import feature_table, default_object_features
df = feature_table_stack(data_phenotype, nuclei, features)
features = default_object_features.copy()
features['cell'] = features.pop('label')
df2 = feature_table(nuclei, nuclei, features)
df = df.join(df2.set_index('cell'), on='cell')
for k, v in wildcards.items():
df[k] = v
return df
def get_features(data, peaks):
""" Uses peaks from DO only
"""
DO_masks = peaks_to_DO_masks(peaks)
arr = []
# loop over peak sources
for source, mask in DO_masks.items():
# peak object features
objects = feature_table(mask, mask, object_features)
# DO/sequencing features
table = build_feature_table(data, mask, peak_features, all_index)
table = objects.join(table)
table['source'] = source
arr += [table]
return pd.concat(arr)
def test_feature_table():
features = {
'area':
lambda region: region.area,
'bounds':
lambda region: region.bbox,
'label':
lambda region: np.median(region.intensity_image[region.intensity_image
> 0]),
}
data = read_stack(stack)
mask = read_stack(nuclei)
df = feature_table(data[0][0], mask, features)
df_ = pd.read_pickle(home('feature_table.pkl'))
assert (df == df_).all().all()
def get_nuclear_features(dapi, nuclei):
features = dict(object_features)
features.update(peak_features)
return feature_table(dapi, nuclei, features)