britekit 0.0.4__tar.gz → 0.0.6__tar.gz

{britekit-0.0.4 → britekit-0.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: britekit
-Version: 0.0.4
+Version: 0.0.6
 Summary: Core functions for bioacoustic recognizers.
 Project-URL: Documentation, https://github.com/jhuus/BriteKit#readme
 Project-URL: Issues, https://github.com/jhuus/BriteKit/issues
@@ -32,8 +32,8 @@ Requires-Dist: scipy<2.0,>=1.15
 Requires-Dist: soundfile<1.0,>=0.13
 Requires-Dist: tensorboard<3.0,>=2.19
 Requires-Dist: timm<2.0,>=1.0.17
-Requires-Dist: torch<2.7,>=2.5
-Requires-Dist: torchaudio<2.7,>=2.5
+Requires-Dist: torch<2.9,>=2.5
+Requires-Dist: torchaudio<2.9,>=2.5
 Requires-Dist: yt-dlp>=2025.6.25
 Description-Content-Type: text/markdown
 
@@ -65,10 +65,10 @@ Description-Content-Type: text/markdown
 
 ## Reference Guides
 
-- [Command Reference](command-reference.md)
-- [Command API Reference](command-api-reference.md)
-- [General API Reference](api-reference.md)
-- [Configuration Reference](config-reference.md)
+- [Command Reference](https://github.com/jhuus/BriteKit/blob/master/command-reference.md)
+- [Command API Reference](https://github.com/jhuus/BriteKit/blob/master/command-api-reference.md)
+- [General API Reference](https://github.com/jhuus/BriteKit/blob/master/api-reference.md)
+- [Configuration Reference](https://github.com/jhuus/BriteKit/blob/master/config-reference.md)
 
 # Getting Started
 
@@ -77,7 +77,7 @@ Description-Content-Type: text/markdown
 ## Introduction
 BriteKit (Bioacoustic Recognizer Technology Kit) is a Python package that facilitates the development of bioacoustic recognizers using deep learning.
 It provides a command-line interface (CLI) as well as a Python API, to support functions such as:
-- downloading recordings from Xeno-Canto, iNaturalist, and Youtube (optionally using Google Audioset metadata)
+- downloading recordings from Xeno-Canto, iNaturalist, and YouTube (optionally using Google Audioset metadata)
 - managing training data in a SQLite database
 - training models
 - testing, tuning and calibrating models
@@ -90,10 +90,16 @@ The classes used by the commands can also be accessed, and are documented [here]
 ## License
 BriteKit is distributed under the terms of the [MIT](https://spdx.org/licenses/MIT.html) license.
 ## Installation
-Install the BriteKit package using pip:
+It is best to install BriteKit in a virtual environment, such as a [Python venv](https://docs.python.org/3/library/venv.html). Once you have that set up, install the BriteKit package using pip:
 ```console
 pip install britekit
 ```
+In Windows environments, you then need to uninstall and reinstall PyTorch:
+```
+pip uninstall -y torch torchvision torchaudio
+pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
+```
+Note that cu126 refers to CUDA 12.6.\
 Once BriteKit is installed, initialize a working environment using the `init` command:
 ```console
 britekit init --dest=<directory path>
@@ -118,13 +124,13 @@ cfg, _ = bk.get_config()
 cfg.train.model_type = "effnet.4"
 ```
 ## Downloading Recordings
-The `inat`, `xeno` and `youtube` commands make it easy to download recordings from Xeno_Canto, iNaturalist and Youtube. For iNaturalist it is important to provide the scientific name. For example, to download recordings of the American Green Frog (lithobates clamitans), type:
+The `inat`, `xeno` and `youtube` commands make it easy to download recordings from Xeno-Canto, iNaturalist and YouTube. For iNaturalist it is important to provide the scientific name. For example, to download recordings of the American Green Frog (lithobates clamitans), type:
 ```
 britekit inat --name "lithobates clamitans" --output <output-path>
 ```
-For Xeno-Canto, use `--name` for the common name or `--sci` for the scientific name. For Youtube, specify the ID of the corresponding video. For example, specify `--id K_EsxukdNXM` to download the audio from https://www.youtube.com/watch?v=K_EsxukdNXM.
+For Xeno-Canto, use `--name` for the common name or `--sci` for the scientific name. For YouTube, specify the ID of the corresponding video. For example, specify `--id K_EsxukdNXM` to download the audio from https://www.youtube.com/watch?v=K_EsxukdNXM.
 
-BriteKit also supports downloads using [Google Audioset](https://research.google.com/audioset/), which is metadata that classifies sounds in Youtube videos. Audioset was released in March 2017, so any videos uploaded later than that are not included. Also, some videos that are tagged in Audioset are no longer available. Type `britekit audioset --help` for more information.
+BriteKit also supports downloads using [Google Audioset](https://research.google.com/audioset/), which is metadata that classifies sounds in YouTube videos. Audioset was released in March 2017, so any videos uploaded later than that are not included. Also, some videos that are tagged in Audioset are no longer available. Type `britekit audioset --help` for more information.
 ## Managing Training Data
 Once you have a collection of recordings, the steps to prepare it for training are:
 1. Extract spectrograms from recordings and insert them into the training database.
@@ -200,7 +206,7 @@ To run a test, you need to annotate a set of test recordings, analyze them with
 | Column | Description |
 |---|---|
 | recording | Just the stem of the recording name, e.g. XC12345, not XC12345.mp3. |
-| classes | Defined classes found in the recording, separated by commas. For example "AMCR,BCCH,COYE", but without the quotes.
+| classes | Defined classes found in the recording, separated by commas. For example: AMCR,BCCH,COYE.
 
 Per-minute annotations are defined in a CSV file with these columns:
 | Column | Description |
@@ -232,7 +238,7 @@ Here is a practical approach:
 2. Do an initial tuning pass of the main training hyperparameters, especially model_type, head_type and num_epochs.
 3. Based on the above, carefully tune the audio/spectrogram parameters.
 
-This usually leads to a substantial improvement in scores (see [Metrics (PR-AUC and ROC-AUC)](#metrics-pr-auc-and-roc-auc), and then you can proceed to fine-tuning the training and inference. For inference, it is usually worth tuning the `audio_power` parameter. If you are using a SED classifier head, it is also worth tuning `segment_len` and `overlap`. For traininf, it may be worth tuning the data augmentation hyperparameters, which are described in detail in the [Data Augmentation](#data-augmentation) section below.
+This usually leads to a substantial improvement in scores (see [Metrics (PR-AUC and ROC-AUC)](#metrics-pr-auc-and-roc-auc), and then you can proceed to fine-tuning the training and inference. For inference, it is usually worth tuning the `audio_power` parameter. If you are using a SED classifier head, it is also worth tuning `segment_len` and `overlap`. For training, it may be worth tuning the data augmentation hyperparameters, which are described in detail in the [Data Augmentation](#data-augmentation) section below.
 
 To run the `tune` command, you would typically use a config YAML file as described earlier, plus a special tuning YAML file, as in this example:
 ```
@@ -243,7 +249,7 @@ To run the `tune` command, you would typically use a config YAML file as describ
   - 512
   step: 64
 ```
-This gives the name of the parameter to tune, its datatype, and the bounds and step sizes to try. In this case, we want to try spec_width values of 256, 320, 384, 448 and 512. You can also tune multiple parameters at the same time, by simply appending more definitions similar to this one. Parameters that have a choice of defined values rather than a range are specified like this:
+This gives the name of the parameter to tune, its data type, and the bounds and step sizes to try. In this case, we want to try spec_width values of 256, 320, 384, 448 and 512. You can also tune multiple parameters at the same time, by simply appending more definitions similar to this one. Parameters that have a choice of defined values rather than a range are specified like this:
 ```
 - name: head_type
   type: categorical

{britekit-0.0.4 → britekit-0.0.6}/README.md

@@ -26,10 +26,10 @@
 
 ## Reference Guides
 
-- [Command Reference](command-reference.md)
-- [Command API Reference](command-api-reference.md)
-- [General API Reference](api-reference.md)
-- [Configuration Reference](config-reference.md)
+- [Command Reference](https://github.com/jhuus/BriteKit/blob/master/command-reference.md)
+- [Command API Reference](https://github.com/jhuus/BriteKit/blob/master/command-api-reference.md)
+- [General API Reference](https://github.com/jhuus/BriteKit/blob/master/api-reference.md)
+- [Configuration Reference](https://github.com/jhuus/BriteKit/blob/master/config-reference.md)
 
 # Getting Started
 
@@ -38,7 +38,7 @@
 ## Introduction
 BriteKit (Bioacoustic Recognizer Technology Kit) is a Python package that facilitates the development of bioacoustic recognizers using deep learning.
 It provides a command-line interface (CLI) as well as a Python API, to support functions such as:
-- downloading recordings from Xeno-Canto, iNaturalist, and Youtube (optionally using Google Audioset metadata)
+- downloading recordings from Xeno-Canto, iNaturalist, and YouTube (optionally using Google Audioset metadata)
 - managing training data in a SQLite database
 - training models
 - testing, tuning and calibrating models
@@ -51,10 +51,16 @@ The classes used by the commands can also be accessed, and are documented [here]
 ## License
 BriteKit is distributed under the terms of the [MIT](https://spdx.org/licenses/MIT.html) license.
 ## Installation
-Install the BriteKit package using pip:
+It is best to install BriteKit in a virtual environment, such as a [Python venv](https://docs.python.org/3/library/venv.html). Once you have that set up, install the BriteKit package using pip:
 ```console
 pip install britekit
 ```
+In Windows environments, you then need to uninstall and reinstall PyTorch:
+```
+pip uninstall -y torch torchvision torchaudio
+pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
+```
+Note that cu126 refers to CUDA 12.6.\
 Once BriteKit is installed, initialize a working environment using the `init` command:
 ```console
 britekit init --dest=<directory path>
@@ -79,13 +85,13 @@ cfg, _ = bk.get_config()
 cfg.train.model_type = "effnet.4"
 ```
 ## Downloading Recordings
-The `inat`, `xeno` and `youtube` commands make it easy to download recordings from Xeno_Canto, iNaturalist and Youtube. For iNaturalist it is important to provide the scientific name. For example, to download recordings of the American Green Frog (lithobates clamitans), type:
+The `inat`, `xeno` and `youtube` commands make it easy to download recordings from Xeno-Canto, iNaturalist and YouTube. For iNaturalist it is important to provide the scientific name. For example, to download recordings of the American Green Frog (lithobates clamitans), type:
 ```
 britekit inat --name "lithobates clamitans" --output <output-path>
 ```
-For Xeno-Canto, use `--name` for the common name or `--sci` for the scientific name. For Youtube, specify the ID of the corresponding video. For example, specify `--id K_EsxukdNXM` to download the audio from https://www.youtube.com/watch?v=K_EsxukdNXM.
+For Xeno-Canto, use `--name` for the common name or `--sci` for the scientific name. For YouTube, specify the ID of the corresponding video. For example, specify `--id K_EsxukdNXM` to download the audio from https://www.youtube.com/watch?v=K_EsxukdNXM.
 
-BriteKit also supports downloads using [Google Audioset](https://research.google.com/audioset/), which is metadata that classifies sounds in Youtube videos. Audioset was released in March 2017, so any videos uploaded later than that are not included. Also, some videos that are tagged in Audioset are no longer available. Type `britekit audioset --help` for more information.
+BriteKit also supports downloads using [Google Audioset](https://research.google.com/audioset/), which is metadata that classifies sounds in YouTube videos. Audioset was released in March 2017, so any videos uploaded later than that are not included. Also, some videos that are tagged in Audioset are no longer available. Type `britekit audioset --help` for more information.
 ## Managing Training Data
 Once you have a collection of recordings, the steps to prepare it for training are:
 1. Extract spectrograms from recordings and insert them into the training database.
@@ -161,7 +167,7 @@ To run a test, you need to annotate a set of test recordings, analyze them with
 | Column | Description |
 |---|---|
 | recording | Just the stem of the recording name, e.g. XC12345, not XC12345.mp3. |
-| classes | Defined classes found in the recording, separated by commas. For example "AMCR,BCCH,COYE", but without the quotes.
+| classes | Defined classes found in the recording, separated by commas. For example: AMCR,BCCH,COYE.
 
 Per-minute annotations are defined in a CSV file with these columns:
 | Column | Description |
@@ -193,7 +199,7 @@ Here is a practical approach:
 2. Do an initial tuning pass of the main training hyperparameters, especially model_type, head_type and num_epochs.
 3. Based on the above, carefully tune the audio/spectrogram parameters.
 
-This usually leads to a substantial improvement in scores (see [Metrics (PR-AUC and ROC-AUC)](#metrics-pr-auc-and-roc-auc), and then you can proceed to fine-tuning the training and inference. For inference, it is usually worth tuning the `audio_power` parameter. If you are using a SED classifier head, it is also worth tuning `segment_len` and `overlap`. For traininf, it may be worth tuning the data augmentation hyperparameters, which are described in detail in the [Data Augmentation](#data-augmentation) section below.
+This usually leads to a substantial improvement in scores (see [Metrics (PR-AUC and ROC-AUC)](#metrics-pr-auc-and-roc-auc), and then you can proceed to fine-tuning the training and inference. For inference, it is usually worth tuning the `audio_power` parameter. If you are using a SED classifier head, it is also worth tuning `segment_len` and `overlap`. For training, it may be worth tuning the data augmentation hyperparameters, which are described in detail in the [Data Augmentation](#data-augmentation) section below.
 
 To run the `tune` command, you would typically use a config YAML file as described earlier, plus a special tuning YAML file, as in this example:
 ```
@@ -204,7 +210,7 @@ To run the `tune` command, you would typically use a config YAML file as describ
   - 512
   step: 64
 ```
-This gives the name of the parameter to tune, its datatype, and the bounds and step sizes to try. In this case, we want to try spec_width values of 256, 320, 384, 448 and 512. You can also tune multiple parameters at the same time, by simply appending more definitions similar to this one. Parameters that have a choice of defined values rather than a range are specified like this:
+This gives the name of the parameter to tune, its data type, and the bounds and step sizes to try. In this case, we want to try spec_width values of 256, 320, 384, 448 and 512. You can also tune multiple parameters at the same time, by simply appending more definitions similar to this one. Parameters that have a choice of defined values rather than a range are specified like this:
 ```
 - name: head_type
   type: categorical

{britekit-0.0.4 → britekit-0.0.6}/britekit/__about__.py

@@ -1,4 +1,4 @@
 # SPDX-FileCopyrightText: 2025-present Jan Huus <jhuus1@gmail.com>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.4"
+__version__ = "0.0.6"

{britekit-0.0.4 → britekit-0.0.6}/britekit/commands/_audioset.py

@@ -255,6 +255,7 @@ def audioset(
     help="Path to CSV with curated list of clips.",
 )
 @click.option(
+    "-o",
     "--output",
     "output_dir",
     required=True,

{britekit-0.0.4 → britekit-0.0.6}/britekit/commands/_inat.py

@@ -103,6 +103,7 @@ def inat(
 )
 @click.option("--name", required=True, type=str, help="Species name.")
 @click.option(
+    "-o",
     "--output",
     "output_dir",
     required=True,

{britekit-0.0.4 → britekit-0.0.6}/britekit/commands/_reports.py

@@ -244,12 +244,14 @@ def rpt_epochs(
     max_roc_score, max_roc_epoch = 0, 0
     pr_scores = []
     roc_scores = []
-    util.set_logging(level=logging.ERROR) # suppress output from Analyzer and PerSegmentTester
     with tempfile.TemporaryDirectory() as temp_dir:
         cfg.misc.ckpt_folder = temp_dir
 
         for epoch_num in epoch_nums:
+            util.set_logging() # restore console output
             logging.info(f"Processing epoch {epoch_num}")
+            # suppress output from Analyzer and PerSegmentTester
+            util.set_logging(level=logging.ERROR)
 
             # copy checkpoint to temp dir
             from_path = epoch_to_ckpt[epoch_num]
@@ -270,6 +272,7 @@ def rpt_epochs(
                 temp_dir,
                 threshold=0.8,
             )
+
             tester.initialize()
 
             pr_stats = tester.get_pr_auc_stats()
@@ -288,8 +291,6 @@ def rpt_epochs(
 
             os.remove(to_path)
 
-    util.set_logging() # restore console output
-
     # Save CSV
     df = pd.DataFrame()
     df["epoch"] = epoch_nums

{britekit-0.0.4 → britekit-0.0.6}/britekit/commands/_train.py

@@ -56,6 +56,16 @@ def _train_cmd(
     cfg_path: str,
 ):
     util.set_logging()
+
+    import platform, torch
+    if platform.system() == "Windows" and not torch.cuda.is_available():
+        logging.warning(
+            "CUDA is not available. On Windows, reinstall a CUDA-enabled PyTorch build like this:\n"
+            "  pip uninstall -y torch torchvision torchaudio\n"
+            "  pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cuxxx"
+            "For example, use cu126 for CUDA 12.6."
+        )
+
     train(cfg_path)
 
 

{britekit-0.0.4 → britekit-0.0.6}/britekit/commands/_xeno.py

@@ -154,6 +154,7 @@ def xeno(
 @click.option("--key", type=str, help="Xeno-Canto API key.")
 @click.option("--name", required=True, type=str, help="Species name.")
 @click.option(
+    "-o",
     "--output",
     "output_dir",
     required=True,

{britekit-0.0.4 → britekit-0.0.6}/britekit/commands/_youtube.py

@@ -60,6 +60,7 @@ def youtube(
     help="Youtube ID.",
 )
 @click.option(
+    "-o",
     "--output",
     "output_dir",
     required=True,

{britekit-0.0.4/britekit/install/yaml/samples → britekit-0.0.6/britekit/install/yaml}/base_config.yaml

@@ -11,7 +11,7 @@ audio: !!python/object:britekit.core.base_config.Audio
   sampling_rate: 18000
   spec_duration: 5.0
   spec_height: 128
-  spec_width: 500
+  spec_width: 480
   top_db: 80
   win_length: 0.055
 infer: !!python/object:britekit.core.base_config.Inference
@@ -25,12 +25,12 @@ infer: !!python/object:britekit.core.base_config.Inference
   min_score: 0.8
   num_threads: 3
   openvino_block_size: 100
+  overlap: 0.0
   raise_min_to_confirm: 0.5
   scaling_coefficient: 1.0
   scaling_intercept: 0.0
   seed: 99
   segment_len: null
-  spec_overlap_seconds: 0.0
 misc: !!python/object:britekit.core.base_config.Miscellaneous
   ckpt_folder: data/ckpt
   classes_file: data/classes.txt
@@ -41,13 +41,16 @@ misc: !!python/object:britekit.core.base_config.Miscellaneous
   search_ckpt_path: null
   source_regexes:
   - !!python/tuple
-    - XC\d+
+    - ^[A-Za-z0-9_-]{11}-\d+$
+    - Audioset
+  - !!python/tuple
+    - ^XC\d+$
     - Xeno-Canto
   - !!python/tuple
-    - N\d+
+    - ^N\d+$
     - iNaturalist
   - !!python/tuple
-    - \d+
+    - ^\d+$
     - Macaulay Library
   - !!python/tuple
     - .*
@@ -108,7 +111,7 @@ train: !!python/object:britekit.core.base_config.Training
   noise_class_name: Noise
   num_epochs: 10
   num_folds: 1
-  num_workers: 2
+  num_workers: 3
   offpeak_weight: 0.002
   opt_beta1: 0.9
   opt_beta2: 0.999
@@ -124,6 +127,6 @@ train: !!python/object:britekit.core.base_config.Training
   shuffle: true
   test_pickle: null
   train_db: data/training.db
-  train_pickle: null
+  train_pickle: data/training.pkl
   val_portion: 0
   warmup_fraction: 0.0

{britekit-0.0.4/install/yaml/samples → britekit-0.0.6/install/yaml}/base_config.yaml

@@ -11,7 +11,7 @@ audio: !!python/object:britekit.core.base_config.Audio
   sampling_rate: 18000
   spec_duration: 5.0
   spec_height: 128
-  spec_width: 500
+  spec_width: 480
   top_db: 80
   win_length: 0.055
 infer: !!python/object:britekit.core.base_config.Inference
@@ -25,12 +25,12 @@ infer: !!python/object:britekit.core.base_config.Inference
   min_score: 0.8
   num_threads: 3
   openvino_block_size: 100
+  overlap: 0.0
   raise_min_to_confirm: 0.5
   scaling_coefficient: 1.0
   scaling_intercept: 0.0
   seed: 99
   segment_len: null
-  spec_overlap_seconds: 0.0
 misc: !!python/object:britekit.core.base_config.Miscellaneous
   ckpt_folder: data/ckpt
   classes_file: data/classes.txt
@@ -41,13 +41,16 @@ misc: !!python/object:britekit.core.base_config.Miscellaneous
   search_ckpt_path: null
   source_regexes:
   - !!python/tuple
-    - XC\d+
+    - ^[A-Za-z0-9_-]{11}-\d+$
+    - Audioset
+  - !!python/tuple
+    - ^XC\d+$
     - Xeno-Canto
   - !!python/tuple
-    - N\d+
+    - ^N\d+$
     - iNaturalist
   - !!python/tuple
-    - \d+
+    - ^\d+$
     - Macaulay Library
   - !!python/tuple
     - .*
@@ -108,7 +111,7 @@ train: !!python/object:britekit.core.base_config.Training
   noise_class_name: Noise
   num_epochs: 10
   num_folds: 1
-  num_workers: 2
+  num_workers: 3
   offpeak_weight: 0.002
   opt_beta1: 0.9
   opt_beta2: 0.999
@@ -124,6 +127,6 @@ train: !!python/object:britekit.core.base_config.Training
   shuffle: true
   test_pickle: null
   train_db: data/training.db
-  train_pickle: null
+  train_pickle: data/training.pkl
   val_portion: 0
   warmup_fraction: 0.0

{britekit-0.0.4 → britekit-0.0.6}/pyproject.toml

@@ -31,8 +31,8 @@ dependencies = [
   "pandas>=2.2,<2.3",
   "pyinaturalist>=0.20,<1.0",
   "soundfile>=0.13,<1.0",
-  "torch>=2.5,<2.7",
-  "torchaudio>=2.5,<2.7",
+  "torch>=2.5,<2.9",
+  "torchaudio>=2.5,<2.9",
   "librosa>=0.10,<2.0",
   "lightning>=2.5,<2.6",
   "matplotlib>=3.9,<3.11",

{britekit-0.0.4 → britekit-0.0.6}/src/britekit/models/base_model.py

@@ -178,15 +178,10 @@ class BaseModel(pl.LightningModule):
         else:
             preds = torch.softmax(seg_logits, dim=1)
 
-        acc = accuracy(preds, y, task="multilabel", num_labels=self.num_classes)
         self.log("val_loss", loss, on_step=False, on_epoch=True, prog_bar=True)
-        self.log("val_acc", acc, on_step=False, on_epoch=True, prog_bar=True)
 
-        pr_auc = metrics.average_precision_score(y.cpu(), preds.cpu(), average="micro")
         roc_auc = metrics.roc_auc_score(y.cpu(), preds.cpu(), average="micro")
-
-        self.log("val_pr_auc", pr_auc, on_step=False, on_epoch=True, prog_bar=True)
-        self.log("val_roc_auc", roc_auc, on_step=False, on_epoch=True, prog_bar=True)
+        self.log("val_roc", roc_auc, on_step=False, on_epoch=True, prog_bar=True)
 
         return loss
 
@@ -199,18 +194,8 @@ class BaseModel(pl.LightningModule):
 
         if self.multi_label:
             preds = torch.sigmoid(seg_logits)
-            micro_aps = metrics.average_precision_score(
-                y.cpu(), preds.cpu(), average="micro"
-            )
-            self.log(
-                "test_micro_aps", micro_aps, on_step=False, on_epoch=True, prog_bar=True
-            )
-            macro_aps = metrics.average_precision_score(
-                y.cpu(), preds.cpu(), average="macro"
-            )
-            self.log(
-                "test_macro_aps", macro_aps, on_step=False, on_epoch=True, prog_bar=True
-            )
+            roc_auc = metrics.roc_auc_score(y.cpu(), preds.cpu(), average="micro")
+            self.log("test_roc_auc", roc_auc, on_step=False, on_epoch=True, prog_bar=True)
 
         return loss
 

{britekit-0.0.4 → britekit-0.0.6}/src/britekit/testing/per_minute_tester.py

@@ -237,7 +237,7 @@ class PerMinuteTester(BaseTester):
                 f"\rPercent complete: {int(threshold * 100)}%", end="", flush=True
             )
 
-        logging.info()
+        logging.info("")
         pr_table_dict = {}
         pr_table_dict["annotated_thresholds"] = thresholds
         pr_table_dict["annotated_precisions_minutes"] = precision_annotated_minutes
@@ -425,7 +425,7 @@ class PerMinuteTester(BaseTester):
         rpt.append(
             f"      Recall (minutes) = {100 * self.details_dict['recall_trained']:.2f}%\n"
         )
-        logging.info()
+        logging.info("")
         with open(os.path.join(self.output_dir, "summary_report.txt"), "w") as summary:
             for rpt_line in rpt:
                 logging.info(rpt_line[:-1])

{britekit-0.0.4 → britekit-0.0.6}/src/britekit/testing/per_segment_tester.py

@@ -543,7 +543,7 @@ class PerSegmentTester(BaseTester):
             f"Average of macro-ROC-annotated and micro-ROC-trained = {self.roc_auc_dict['combined_roc_auc_trained']:.4f}\n"
         )
 
-        logging.info()
+        logging.info("")
         with open(os.path.join(self.output_dir, "summary_report.txt"), "w") as summary:
             for rpt_line in rpt:
                 logging.info(rpt_line[:-1])