megadetector 10.0.4__py3-none-any.whl → 10.0.5__py3-none-any.whl

megadetector/data_management/cct_json_utils.py

@@ -298,6 +298,7 @@ class SequenceOptions:
     """
 
     def __init__(self):
+
         #: Images separated by <= this duration will be grouped into the same sequence.
         self.episode_interval_seconds = 60.0
 

megadetector/data_management/speciesnet_to_md.py

@@ -3,7 +3,7 @@
 speciesnet_to_md.py
 
 Converts the WI (SpeciesNet) predictions.json format to MD .json format.  This is just a
-command-line wrapper around utils.wi_utils.generate_md_results_from_predictions_json.
+command-line wrapper around utils.wi_taxonomy_utils.generate_md_results_from_predictions_json.
 
 """
 
@@ -11,7 +11,7 @@ command-line wrapper around utils.wi_utils.generate_md_results_from_predictions_
 
 import sys
 import argparse
-from megadetector.utils.wi_utils import generate_md_results_from_predictions_json
+from megadetector.utils.wi_taxonomy_utils import generate_md_results_from_predictions_json
 
 
 #%% Command-line driver

megadetector/postprocessing/classification_postprocessing.py

@@ -25,14 +25,14 @@ from megadetector.utils.ct_utils import sort_dictionary_by_value
 from megadetector.utils.ct_utils import sort_dictionary_by_key
 from megadetector.utils.ct_utils import invert_dictionary
 
-from megadetector.utils.wi_utils import clean_taxonomy_string
-from megadetector.utils.wi_utils import taxonomy_level_index
-from megadetector.utils.wi_utils import taxonomy_level_string_to_index
+from megadetector.utils.wi_taxonomy_utils import clean_taxonomy_string
+from megadetector.utils.wi_taxonomy_utils import taxonomy_level_index
+from megadetector.utils.wi_taxonomy_utils import taxonomy_level_string_to_index
 
-from megadetector.utils.wi_utils import non_taxonomic_prediction_strings
-from megadetector.utils.wi_utils import human_prediction_string
-from megadetector.utils.wi_utils import animal_prediction_string
-from megadetector.utils.wi_utils import blank_prediction_string # noqa
+from megadetector.utils.wi_taxonomy_utils import non_taxonomic_prediction_strings
+from megadetector.utils.wi_taxonomy_utils import human_prediction_string
+from megadetector.utils.wi_taxonomy_utils import animal_prediction_string
+from megadetector.utils.wi_taxonomy_utils import blank_prediction_string # noqa
 
 
 #%% Options classes
@@ -1100,7 +1100,8 @@ def restrict_to_taxa_list(taxa_list,
                           input_file,
                           output_file,
                           allow_walk_down=False,
-                          add_pre_filtering_description=True):
+                          add_pre_filtering_description=True,
+                          allow_redundant_latin_names=False):
     """
     Given a prediction file in MD .json format, likely without having had
     a geofence applied, apply a custom taxa list.
@@ -1123,6 +1124,10 @@ def restrict_to_taxa_list(taxa_list,
         add_pre_filtering_description (bool, optional): should we add a new metadata
             field that summarizes each image's classifications prior to taxonomic
             restriction?
+        allow_redundant_latin_names (bool, optional): if False, we'll raise an Exception
+            if the same latin name appears twice in the taxonomy list; if True, we'll
+            just print a warning and ignore all entries other than the first for this
+            latin name
     """
 
     ##%% Read target taxa list
@@ -1137,11 +1142,14 @@ def restrict_to_taxa_list(taxa_list,
     taxa_list = [s for s in taxa_list if len(s) > 0]
 
     target_latin_to_common = {}
+
     for s in taxa_list:
+
         if s.strip().startswith('#'):
             continue
         tokens = s.split(',')
-        assert len(tokens) <= 2
+        # We allow additional columns now
+        # assert len(tokens) <= 2
         binomial_name = tokens[0]
         assert len(binomial_name.split(' ')) in (1,2,3), \
             'Illegal binomial name in species list: {}'.format(binomial_name)
@@ -1149,9 +1157,17 @@ def restrict_to_taxa_list(taxa_list,
             common_name = tokens[1].strip().lower()
         else:
             common_name = None
-        assert binomial_name not in target_latin_to_common
+        if binomial_name in target_latin_to_common:
+            error_string = 'scientific name {} appears multiple times in the taxonomy list'.format(
+                    binomial_name)
+            if allow_redundant_latin_names:
+                print('Warning: {}'.format(error_string))
+            else:
+                raise ValueError(error_string)
         target_latin_to_common[binomial_name] = common_name
 
+    # ...for each line in the taxonomy file
+
 
     ##%% Read taxonomy file
 

megadetector/postprocessing/generate_csv_report.py

@@ -42,7 +42,7 @@ import pandas as pd
 
 from copy import deepcopy
 
-from megadetector.utils.wi_utils import load_md_or_speciesnet_file
+from megadetector.utils.wi_taxonomy_utils import load_md_or_speciesnet_file
 from megadetector.utils.ct_utils import get_max_conf
 from megadetector.utils.ct_utils import is_list_sorted
 from megadetector.detection.run_detector import \

megadetector/postprocessing/load_api_results.py

@@ -24,7 +24,7 @@ from collections.abc import Mapping
 import pandas as pd
 
 from megadetector.utils import ct_utils
-from megadetector.utils.wi_utils import load_md_or_speciesnet_file
+from megadetector.utils.wi_taxonomy_utils import load_md_or_speciesnet_file
 
 
 #%% Functions for loading .json results into a Pandas DataFrame, and writing back to .json

megadetector/postprocessing/md_to_wi.py

@@ -10,7 +10,7 @@ Converts the MD .json format to the WI predictions.json format.
 
 import sys
 import argparse
-from megadetector.utils.wi_utils import generate_predictions_json_from_md_results
+from megadetector.utils.wi_taxonomy_utils import generate_predictions_json_from_md_results
 
 
 #%% Command-line driver

megadetector/postprocessing/postprocess_batch_results.py

@@ -47,7 +47,7 @@ from tqdm import tqdm
 from megadetector.visualization import visualization_utils as vis_utils
 from megadetector.visualization import plot_utils
 from megadetector.utils.write_html_image_list import write_html_image_list
-from megadetector.utils.wi_utils import load_md_or_speciesnet_file
+from megadetector.utils.wi_taxonomy_utils import load_md_or_speciesnet_file
 from megadetector.utils import path_utils
 from megadetector.utils.ct_utils import args_to_object
 from megadetector.utils.ct_utils import sets_overlap

megadetector/postprocessing/repeat_detection_elimination/repeat_detections_core.py

@@ -637,7 +637,7 @@ def _find_matches_in_directory(dir_name_and_rows, options):
 
         if 'max_detection_conf' not in row or 'detections' not in row or \
             row['detections'] is None:
-            print('Skipping row {}'.format(i_directory_row))
+            # print('Skipping row {}'.format(i_directory_row))
             continue
 
         # Don't bother checking images with no detections above threshold

megadetector/utils/ct_utils.py

@@ -850,6 +850,24 @@ def isnan(v):
         return False
 
 
+def compare_values_nan_equal(v0,v1):
+    """
+    Utility function for comparing two values when we want to return True if both
+    values are NaN.
+
+    Args:
+        v0 (object): the first value to compare
+        v1 (object): the second value to compare
+
+    Returns:
+        bool: True if v0 == v1, or if both v0 and v1 are NaN
+    """
+
+    if isinstance(v0,float) and isinstance(v1,float) and np.isnan(v0) and np.isnan(v1):
+        return True
+    return v0 == v1
+
+
 def sets_overlap(set1, set2):
     """
     Determines whether two sets overlap.