megadetector 10.0.3__py3-none-any.whl → 10.0.5__py3-none-any.whl

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/postprocessing/separate_detections_into_folders.py

@@ -587,7 +587,7 @@ def separate_detections_into_folders(options):
             # token = tokens[0]
             for token in tokens:
                 subtokens = token.split('=')
-                assert len(subtokens) == 2 and is_float(subtokens[1]), \
+                assert (len(subtokens) == 2) and (is_float(subtokens[1])), \
                     'Illegal classification threshold {}'.format(token)
                 classification_thresholds[subtokens[0]] = float(subtokens[1])
 

megadetector/postprocessing/subset_json_detector_output.py

@@ -221,7 +221,7 @@ def remove_classification_categories_below_count(data, options):
     classification_category_ids_to_keep = set()
 
     for classification_category_id in classification_category_id_to_count:
-        if classification_category_id_to_count[classification_category_id] > \
+        if classification_category_id_to_count[classification_category_id] >= \
             options.remove_classification_categories_below_count:
                 classification_category_ids_to_keep.add(classification_category_id)
 
@@ -235,7 +235,6 @@ def remove_classification_categories_below_count(data, options):
     if n_categories_removed == 0:
         return data
 
-
     # Filter the category list
     output_classification_categories = {}
     for category_id in data['classification_categories']:
@@ -245,7 +244,6 @@ def remove_classification_categories_below_count(data, options):
     data['classification_categories'] = output_classification_categories
     assert len(data['classification_categories']) == len(classification_category_ids_to_keep)
 
-
     # If necessary, filter the category descriptions
     if 'classification_category_descriptions' in data:
         output_classification_category_descriptions = {}

megadetector/utils/ct_utils.py

@@ -16,6 +16,8 @@ import builtins
 import datetime
 import tempfile
 import shutil
+import platform
+import sys
 import uuid
 
 import jsonpickle
@@ -848,6 +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.
@@ -1053,6 +1073,57 @@ def make_test_folder(subfolder=None):
                             append_guid=True)
 
 
+#%% Environment utilities
+
+def is_sphinx_build():
+    """
+    Determine whether we are running in the context of our Sphinx build.
+
+    Returns:
+        bool: True if we're running a Sphinx build
+    """
+
+    is_sphinx = hasattr(builtins, '__sphinx_build__')
+    return is_sphinx
+
+
+def is_running_in_gha():
+    """
+    Determine whether we are running on a GitHub Actions runner.
+
+    Returns:
+        bool: True if we're running in a GHA runner
+    """
+
+    running_in_gha = False
+
+    if ('GITHUB_ACTIONS' in os.environ):
+        # Documentation is inconsistent on how this variable presents itself
+        if isinstance(os.environ['GITHUB_ACTIONS'],bool) and \
+            os.environ['GITHUB_ACTIONS']:
+            running_in_gha = True
+        elif isinstance(os.environ['GITHUB_ACTIONS'],str) and \
+            os.environ['GITHUB_ACTIONS'].lower() == ('true'):
+            running_in_gha = True
+
+    return running_in_gha
+
+
+def environment_is_wsl():
+    """
+    Determines whether we're running in WSL.
+
+    Returns:
+        True if we're running in WSL
+    """
+
+    if sys.platform not in ('linux','posix'):
+        return False
+    platform_string = ' '.join(platform.uname()).lower()
+    return 'microsoft' in platform_string and 'wsl' in platform_string
+
+
+
 #%% Tests
 
 def test_write_json():

megadetector/utils/md_tests.py

@@ -21,6 +21,7 @@ since much of what it tries to test is, e.g., imports.
 import os
 import json
 import glob
+import sys
 import tempfile
 import urllib
 import urllib.request
@@ -141,9 +142,6 @@ class MDTestOptions:
         #: Number of cores to use for multi-CPU inference tests
         self.n_cores_for_multiprocessing_tests = 2
 
-        #: Number of cores to use for multi-CPU video tests
-        self.n_cores_for_video_tests = 2
-
         #: Batch size to use when testing batches of size > 1
         self.alternative_batch_size = 3
 
@@ -1062,7 +1060,6 @@ def run_python_tests(options):
         video_options.input_video_file = os.path.join(options.scratch_dir,options.test_videos[0])
         video_options.output_json_file = os.path.join(options.scratch_dir,'single_video_output.json')
         video_options.frame_sample = 10
-        video_options.n_cores = options.n_cores_for_video_tests
         video_options.detector_options = copy(options.detector_options)
 
         _ = process_videos(video_options)
@@ -1086,7 +1083,6 @@ def run_python_tests(options):
         video_options.output_video_file = None
         video_options.recursive = True
         video_options.verbose = True
-        video_options.n_cores = options.n_cores_for_video_tests
         video_options.json_confidence_threshold = 0.05
         video_options.time_sample = 2
         video_options.detector_options = copy(options.detector_options)
@@ -1295,7 +1291,7 @@ def run_cli_tests(options):
 
         batch_string = ' --batch_size {}'.format(options.alternative_batch_size)
 
-        # I reduce the number of loader workers here to force batching to actually appen; with a small
+        # I reduce the number of loader workers here to force batching to actually append; with a small
         # number of images and a few that are intentionally corrupt, with the default number of loader
         # workers we end up with batches that are mostly just one image.
         cmd = base_cmd + ' --use_image_queue --preprocess_on_image_queue --loader_workers 2' + batch_string
@@ -1591,9 +1587,9 @@ def run_cli_tests(options):
 
         cmd += ' "{}" "{}"'.format(options.default_model,options.scratch_dir)
         cmd += ' --output_json_file "{}"'.format(video_inference_output_file)
-        cmd += ' --n_cores {}'.format(options.n_cores_for_video_tests)
         cmd += ' --frame_sample 4'
         cmd += ' --verbose'
+        cmd += ' --recursive'
         cmd += ' --detector_options {}'.format(dict_to_kvp_list(options.detector_options))
 
         cmd_results = execute_and_print(cmd)
@@ -1789,6 +1785,11 @@ def test_suite_entry_point():
     options.skip_localhost_downloads = True
     options.skip_import_tests = False
 
+    if sys.platform == 'darwin':
+        print('Detected a Mac environment, widening tolerance')
+        options.max_coord_error = 0.05
+        options.max_conf_error = 0.05
+
     options = download_test_data(options)
 
     run_tests(options)

megadetector/utils/path_utils.py

@@ -36,6 +36,7 @@ from tqdm import tqdm
 from megadetector.utils.ct_utils import is_iterable
 from megadetector.utils.ct_utils import make_test_folder
 from megadetector.utils.ct_utils import sort_dictionary_by_value
+from megadetector.utils.ct_utils import environment_is_wsl
 
 # Should all be lower-case
 IMG_EXTENSIONS = ('.jpg', '.jpeg', '.gif', '.png', '.tif', '.tiff', '.bmp')
@@ -622,21 +623,7 @@ def is_executable(filename):
     return which(filename) is not None
 
 
-#%% Platform-independent way to open files in their associated application
-
-def environment_is_wsl():
-    """
-    Determines whether we're running in WSL.
-
-    Returns:
-        True if we're running in WSL.
-    """
-
-    if sys.platform not in ('linux','posix'):
-        return False
-    platform_string = ' '.join(platform.uname()).lower()
-    return 'microsoft' in platform_string and 'wsl' in platform_string
-
+#%% WSL utilities
 
 def wsl_path_to_windows_path(filename, failure_behavior='none'):
     r"""
@@ -731,6 +718,8 @@ def windows_path_to_wsl_path(filename, failure_behavior='none'):
 # ...def window_path_to_wsl_path(...)
 
 
+#%% Platform-independent file openers
+
 def open_file_in_chrome(filename):
     """
     Open a file in chrome, regardless of file type.  I typically use this to open