Fixed bug in file name recognition in data.py

deepof/data.py

@@ -21,6 +21,7 @@ from sklearn import random_projection
 from sklearn.decomposition import KernelPCA
 from sklearn.manifold import TSNE
 from sklearn.preprocessing import MinMaxScaler, StandardScaler
+from tqdm import tqdm
 import deepof.pose_utils
 import deepof.utils
 import deepof.visuals
@@ -95,11 +96,11 @@ class project:
 
     def __str__(self):
         if self.exp_conditions:
-            return "DLC analysis of {} videos across {} conditions".format(
+            return "deepof analysis of {} videos across {} conditions".format(
                 len(self.videos), len(self.exp_conditions)
             )
         else:
-            return "DLC analysis of {} videos".format(len(self.videos))
+            return "deepof analysis of {} videos".format(len(self.videos))
 
     @property
     def subset_condition(self):
@@ -167,7 +168,7 @@ class project:
         if self.table_format == ".h5":
 
             tab_dict = {
-                deepof.utils.re.findall("(.*?)_", tab)[0]: pd.read_hdf(
+                deepof.utils.re.findall("(.*)DLC", tab)[0]: pd.read_hdf(
                     deepof.utils.os.path.join(self.table_path, tab), dtype=float
                 )
                 for tab in self.tables
@@ -192,7 +193,7 @@ class project:
                     ],
                     names=["scorer", "bodyparts", "coords"],
                 )
-                tab_dict[deepof.utils.re.findall("(.*?)_", tab)[0]] = data
+                tab_dict[deepof.utils.re.findall("(.*)DLC", tab)[0]] = data
 
         lik_dict = defaultdict()
 
@@ -409,7 +410,7 @@ class coordinates:
                 len(self._videos), len(self._exp_conditions)
             )
         else:
-            return "DLC analysis of {} videos".format(len(self._videos))
+            return "deepof analysis of {} videos".format(len(self._videos))
 
     def get_coords(
         self,
@@ -643,12 +644,13 @@ class coordinates:
         """Annotates coordinates using a simple rule-based pipeline"""
 
         tag_dict = {}
-        for idx, key in enumerate(self._tables.keys()):
+        for idx, key in tqdm(enumerate(self._tables.keys()), total=len(self._videos)):
             tag_dict[key] = deepof.pose_utils.rule_based_tagging(
                 list(self._tables.keys()),
                 self._videos,
                 self,
                 idx,
+                arena_type=self._arena,
                 recog_limit=1,
                 path=os.path.join(self._path, "Videos"),
                 hparams=hparams,
@@ -972,7 +974,6 @@ def merge_tables(*args):
 # TODO:
 #   - Generate ragged training array using a metric (acceleration, maybe?)
 #   - Use something like Dynamic Time Warping to put all instances in the same length
-#   - add rule_based_annotation method to coordinates class!!
 #   - with the current implementation, preprocess can't fully work on merged table_dict instances.
 #   While some operations (mainly alignment) should be carried out before merging, others require
 #   the whole dataset to function properly.

deepof/pose_utils.py

@@ -17,7 +17,6 @@ import pandas as pd
 import regex as re
 import seaborn as sns
 from itertools import combinations
-from scipy import spatial
 from scipy import stats
 from tqdm import tqdm
 from typing import Any, List, NewType
@@ -110,7 +109,12 @@ def close_double_contact(
 
 
 def climb_wall(
-    arena_type: str, arena: np.array, pos_dict: pd.DataFrame, tol: float, nose: str
+    arena_type: str,
+    arena: np.array,
+    pos_dict: pd.DataFrame,
+    tol: float,
+    nose: str,
+    centered_data: bool = True,
 ) -> np.array:
     """Returns True if the specified mouse is climbing the wall
 
@@ -129,7 +133,7 @@ def climb_wall(
     nose = pos_dict[nose]
 
     if arena_type == "circular":
-        center = np.array(arena[:2])
+        center = np.zeros(2) if centered_data else np.array(arena[:2])
         climbing = np.linalg.norm(nose - center, axis=1) > (arena[2] + tol)
 
     else:
@@ -420,6 +424,7 @@ def rule_based_tagging(
     videos: List,
     coordinates: Coordinates,
     vid_index: int,
+    arena_type: str,
     recog_limit: int = 1,
     path: str = os.path.join("."),
     hparams: dict = {},
@@ -455,7 +460,7 @@ def rule_based_tagging(
     undercond = "_" if len(animal_ids) > 1 else ""
 
     try:
-        vid_name = re.findall("(.*?)_", tracks[vid_index])[0]
+        vid_name = re.findall("(.*)DLC", tracks[vid_index])[0]
     except IndexError:
         vid_name = tracks[vid_index]
 
@@ -527,15 +532,7 @@ def rule_based_tagging(
 
     for _id in animal_ids:
         tag_dict[_id + undercond + "climbing"] = deepof.utils.smooth_boolean_array(
-            pd.Series(
-                (
-                    spatial.distance.cdist(
-                        np.array(coords[_id + undercond + "Nose"]), np.zeros([1, 2])
-                    )
-                    > (w / 200 + arena[2])
-                ).reshape(coords.shape[0]),
-                index=coords.index,
-            ).astype(bool)
+            climb_wall(arena_type, arena, coords, w / 200, _id + undercond + "Nose")
         )
         tag_dict[_id + undercond + "speed"] = speeds[_id + undercond + "Center"]
         tag_dict[_id + undercond + "huddle"] = deepof.utils.smooth_boolean_array(
@@ -695,7 +692,7 @@ def rule_based_video(
     undercond = "_" if len(animal_ids) > 1 else ""
 
     try:
-        vid_name = re.findall("(.*?)_", tracks[vid_index])[0]
+        vid_name = re.findall("(.*)DLC", tracks[vid_index])[0]
     except IndexError:
         vid_name = tracks[vid_index]
 

tests/test_pose_utils.py

@@ -366,6 +366,7 @@ def test_rule_based_tagging():
         list([i + "_" for i in prun.get_coords().keys()]),
         ["test_video_circular_arena.mp4"],
         prun,
+        arena_type="circular",
         vid_index=0,
         path=os.path.join(".", "tests", "test_examples", "Videos"),
     )
@@ -389,6 +390,7 @@ def test_rule_based_video():
         list([i + "_" for i in prun.get_coords().keys()]),
         ["test_video_circular_arena.mp4"],
         prun,
+        arena_type="circular",
         vid_index=0,
         path=os.path.join(".", "tests", "test_examples", "Videos"),
     )