celldetective 1.3.9.post4__py3-none-any.whl → 1.4.0__py3-none-any.whl

celldetective/measure.py

@@ -20,13 +20,21 @@ from skimage.feature import blob_dog, blob_log
 from celldetective.utils import rename_intensity_column, create_patch_mask, remove_redundant_features, \
 	remove_trajectory_measurements, contour_of_instance_segmentation, extract_cols_from_query, step_function, interpolate_nan, _remove_invalid_cols
 from celldetective.preprocessing import field_correction
-from celldetective.extra_properties import *
+
+# try:
+# 	from celldetective.extra_properties import *
+# 	extra_props = True
+# except Exception as e:
+# 	print(f"The module extra_properties seems corrupted: {e}... Skip...")
+# 	extra_props = False
+
 from inspect import getmembers, isfunction
 from skimage.morphology import disk
 from scipy.signal import find_peaks, peak_widths
 
 from celldetective.segmentation import filter_image
 from celldetective.regionprops import regionprops_table
+from celldetective.utils import pretty_table
 
 abs_path = os.sep.join([os.path.split(os.path.dirname(os.path.realpath(__file__)))[0], 'celldetective'])
 
@@ -211,7 +219,7 @@ def measure(stack=None, labels=None, trajectories=None, channel_names=None,
 		measurements = measurements.sort_values(by=[column_labels['track'],column_labels['time']])
 		measurements = measurements.dropna(subset=[column_labels['track']])
 	else:
-		measurements['ID'] = np.arange(len(df))
+		measurements['ID'] = np.arange(len(measurements))
 
 	measurements = measurements.reset_index(drop=True)
 	measurements = _remove_invalid_cols(measurements)
@@ -365,26 +373,35 @@ def measure_features(img, label, features=['area', 'intensity_mean'], channels=N
 					corrected_image = field_correction(img[:,:,ind].copy(), threshold_on_std=norm['threshold_on_std'], operation=norm['operation'], model=norm['model'], clip=norm['clip'])
 					img[:, :, ind] = corrected_image
 	
-	import celldetective.extra_properties as extra_props
-
-	extra = getmembers(extra_props, isfunction)
-	extra = [extra[i][0] for i in range(len(extra))]
-
-	extra_props_list = []
-	feats = features.copy()
-	for f in features:
-		if f in extra:
-			feats.remove(f)
-			extra_props_list.append(getattr(extra_props, f))
-
-	# Add intensity nan mean if need to measure mean intensities
-	if measure_mean_intensities:
-		extra_props_list.append(getattr(extra_props, 'intensity_nanmean'))
-
-	if len(extra_props_list) == 0:
-		extra_props_list = None
+	try:
+		import celldetective.extra_properties as extra_props
+		extraprops = True
+	except Exception as e:
+		print(f"The module extra_properties seems corrupted: {e}... Skip...")
+		extraprops = False
+
+	if extraprops:
+		extra = getmembers(extra_props, isfunction)
+		extra = [extra[i][0] for i in range(len(extra))]
+
+		extra_props_list = []
+		feats = features.copy()
+		for f in features:
+			if f in extra:
+				feats.remove(f)
+				extra_props_list.append(getattr(extra_props, f))
+
+		# Add intensity nan mean if need to measure mean intensities
+		if measure_mean_intensities:
+			extra_props_list.append(getattr(extra_props, 'intensity_nanmean'))
+
+		if len(extra_props_list) == 0:
+			extra_props_list = None
+		else:
+			extra_props_list = tuple(extra_props_list)
 	else:
-		extra_props_list = tuple(extra_props_list)
+		extra_props_list = []
+		feats = features.copy()
 
 	props = regionprops_table(label, intensity_image=img, properties=feats, extra_properties=extra_props_list, channel_names=channels)
 	df_props = pd.DataFrame(props)
@@ -837,17 +854,32 @@ def local_normalisation(image, labels, background_intensity, measurement='intens
 
 def normalise_by_cell(image, labels, distance=5, model='median', operation='subtract', clip=False):
 
-	import celldetective.extra_properties as extra_props
+	try:
+		import celldetective.extra_properties as extra_props
+		extraprops = True
+	except Exception as e:
+		print(f"The module extra_properties seems corrupted: {e}... Skip...")
+		extraprops = False
 
 	border = contour_of_instance_segmentation(label=labels, distance=distance * (-1))
 	if model == 'mean':
+		
 		measurement = 'intensity_nanmean'
-		extra_props = [getattr(extra_props, measurement)]
+		if extraprops:
+			extra_props = [getattr(extra_props, measurement)]
+		else:
+			extra_props = []
+
 		background_intensity = regionprops_table(intensity_image=image, label_image=border,
 												 extra_properties=extra_props)
 	elif model == 'median':
+		
 		measurement = 'intensity_median'
-		extra_props = [getattr(extra_props, measurement)]
+		if extraprops:
+			extra_props = [getattr(extra_props, measurement)]
+		else:
+			extra_props = []
+
 		background_intensity = regionprops_table(intensity_image=image, label_image=border,
 												 extra_properties=extra_props)
 
@@ -1250,16 +1282,20 @@ def classify_irreversible_events(data, class_attr, r2_threshold=0.5, percentile_
 			# ambiguity, possible transition, use `unique_state` technique after
 			df.loc[indices, class_attr] = 2
 
-	print("Classes after initial pass: ",df.loc[df['FRAME']==0,class_attr].value_counts())
+	print("Number of cells per class after the initial pass: ")
+	pretty_table(df.loc[df['FRAME']==0,class_attr].value_counts().to_dict())
 
 	df.loc[df[class_attr]!=2, class_attr.replace('class', 't')] = -1
 	# Try to fit time on class 2 cells (ambiguous)
 	df = estimate_time(df, class_attr, model='step_function', class_of_interest=[2], r2_threshold=r2_threshold)
-	print("Classes after fit: ", df.loc[df['FRAME']==0,class_attr].value_counts())
+	
+	print("Number of cells per class after conditional signal fit: ")
+	pretty_table(df.loc[df['FRAME']==0,class_attr].value_counts().to_dict())
 
 	# Revisit class 2 cells to classify as neg/pos with percentile tolerance
 	df.loc[df[class_attr]==2,:] = classify_unique_states(df.loc[df[class_attr]==2,:].copy(), class_attr, percentile_recovery)
-	print("Classes after unique state recovery: ",df.loc[df['FRAME']==0,class_attr].value_counts())
+	print("Number of cells per class after recovery pass (median state): ")
+	pretty_table(df.loc[df['FRAME']==0,class_attr].value_counts().to_dict())
 	
 	return df