sonusai 0.20.2__py3-none-any.whl → 1.0.1__py3-none-any.whl

sonusai/lsdb.py

@@ -1,12 +1,12 @@
 """sonusai lsdb
 
-usage: lsdb [-hta] [-i MIXID] [-c CID] LOC
+usage: lsdb [-hsa] [-i MIXID] [-c CID] LOC
 
 Options:
     -h, --help
     -i MIXID, --mixid MIXID         Mixture ID(s) to analyze. [default: *].
     -c CID, --class_index CID       Analyze mixtures that contain this class index.
-    -t, --targets                   List all target files.
+    -s, --sources                   List all source files.
     -a, --all_class_counts          List all class counts.
 
 List mixture data information from a SonusAI mixture database.
@@ -16,25 +16,10 @@ Inputs:
 
 """
 
-import signal
-
-from sonusai import logger
-from sonusai.mixture import GeneralizedIDs
+from sonusai.datatypes import GeneralizedIDs
 from sonusai.mixture import MixtureDatabase
 
 
-def signal_handler(_sig, _frame):
-    import sys
-
-    from sonusai import logger
-
-    logger.info("Canceled due to keyboard interrupt")
-    sys.exit(1)
-
-
-signal.signal(signal.SIGINT, signal_handler)
-
-
 def lsdb(
     mixdb: MixtureDatabase,
     mixids: GeneralizedIDs = "*",
@@ -42,7 +27,8 @@ def lsdb(
     list_targets: bool = False,
     all_class_counts: bool = False,
 ) -> None:
-    from sonusai.mixture import SAMPLE_RATE
+    from sonusai import logger
+    from sonusai.constants import SAMPLE_RATE
     from sonusai.queries import get_mixids_from_class_indices
     from sonusai.utils import consolidate_range
     from sonusai.utils import max_text_width
@@ -54,38 +40,36 @@ def lsdb(
     total_samples = mixdb.total_samples()
     total_duration = total_samples / SAMPLE_RATE
 
-    logger.info(f'{"Mixtures":{desc_len}} {mixdb.num_mixtures}')
-    logger.info(f'{"Duration":{desc_len}} {seconds_to_hms(seconds=total_duration)}')
-    logger.info(f'{"Targets":{desc_len}} {mixdb.num_target_files}')
-    logger.info(f'{"Noises":{desc_len}} {mixdb.num_noise_files}')
-    logger.info(f'{"Feature":{desc_len}} {mixdb.feature}')
+    logger.info(f"{'Mixtures':{desc_len}} {mixdb.num_mixtures}")
+    logger.info(f"{'Duration':{desc_len}} {seconds_to_hms(seconds=total_duration)}")
+    logger.info(f"{'Sources':{desc_len}} {mixdb.num_source_files}")
+    logger.info(f"{'Feature':{desc_len}} {mixdb.feature}")
     logger.info(
-        f'{"Feature shape":{desc_len}} {mixdb.fg_stride} x {mixdb.feature_parameters} '
-        f'({mixdb.fg_stride * mixdb.feature_parameters} total params)'
+        f"{'Feature shape':{desc_len}} {mixdb.fg_stride} x {mixdb.feature_parameters} "
+        f"({mixdb.fg_stride * mixdb.feature_parameters} total params)"
     )
-    logger.info(f'{"Feature samples":{desc_len}} {mixdb.feature_samples} samples ({mixdb.feature_ms} ms)')
+    logger.info(f"{'Feature samples':{desc_len}} {mixdb.feature_samples} samples ({mixdb.feature_ms} ms)")
     logger.info(
-        f'{"Feature step samples":{desc_len}} {mixdb.feature_step_samples} samples ' f'({mixdb.feature_step_ms} ms)'
+        f"{'Feature step samples':{desc_len}} {mixdb.feature_step_samples} samples ({mixdb.feature_step_ms} ms)"
     )
-    logger.info(f'{"Feature overlap":{desc_len}} {mixdb.fg_step / mixdb.fg_stride} ({mixdb.feature_step_ms} ms)')
-    logger.info(f'{"SNRs":{desc_len}} {mixdb.snrs}')
-    logger.info(f'{"Random SNRs":{desc_len}} {mixdb.random_snrs}')
-    logger.info(f'{"Classes":{desc_len}} {mixdb.num_classes}')
+    logger.info(f"{'Feature overlap':{desc_len}} {mixdb.fg_step / mixdb.fg_stride} ({mixdb.feature_step_ms} ms)")
+    logger.info(f"{'SNRs':{desc_len}} {mixdb.snrs}")
+    logger.info(f"{'Random SNRs':{desc_len}} {mixdb.random_snrs}")
+    logger.info(f"{'Classes':{desc_len}} {mixdb.num_classes}")
     # TODO: fix class count
-    logger.info(f'{"Class count":{desc_len}} not supported')
+    logger.info(f"{'Class count':{desc_len}} not supported")
     # print_class_count(class_count=class_count, length=desc_len, print_fn=logger.info)
     # TODO: add class weight calculations here
     logger.info("")
 
     if list_targets:
-        logger.info("Target details:")
-        idx_len = max_text_width(mixdb.num_target_files)
-        for idx, target in enumerate(mixdb.target_files):
-            desc = f"  {idx:{idx_len}} Name"
-            logger.info(f"{desc:{desc_len}} {target.name}")
-            desc = f"  {idx:{idx_len}} Truth index"
-            logger.info(f"{desc:{desc_len}} {target.class_indices}")
-        logger.info("")
+        logger.info("Source details:")
+        for category, sources in mixdb.source_files.items():
+            print(f"  {category}:")
+            for source in sources:
+                logger.info(f"{'    Name':{desc_len}} {source.name}")
+                logger.info(f"{'    Truth index':{desc_len}} {source.class_indices}")
+            logger.info("")
 
     if class_index is not None:
         if 0 <= class_index > mixdb.num_classes:
@@ -104,7 +88,7 @@ def lsdb(
             # print_class_count(class_count=class_count, length=desc_len, print_fn=logger.info, all_class_counts=True)
     else:
         logger.info(
-            f"Calculating statistics from truth_f files for {len(mixids):,} mixtures" f" ({consolidate_range(mixids)})"
+            f"Calculating statistics from truth_f files for {len(mixids):,} mixtures ({consolidate_range(mixids)})"
         )
         logger.info("Not supported")
 
@@ -112,13 +96,10 @@ def lsdb(
 def main() -> None:
     from docopt import docopt
 
-    import sonusai
-    from sonusai import create_file_handler
-    from sonusai import initial_log_messages
-    from sonusai import update_console_handler
+    from sonusai import __version__ as sai_version
     from sonusai.utils import trim_docstring
 
-    args = docopt(trim_docstring(__doc__), version=sonusai.__version__, options_first=True)
+    args = docopt(trim_docstring(__doc__), version=sai_version, options_first=True)
 
     mixid = args["--mixid"]
     class_index = args["--class_index"]
@@ -126,6 +107,11 @@ def main() -> None:
     all_class_counts = args["--all_class_counts"]
     location = args["LOC"]
 
+    from sonusai import create_file_handler
+    from sonusai import initial_log_messages
+    from sonusai import logger
+    from sonusai import update_console_handler
+
     if class_index is not None:
         class_index = int(class_index)
 
@@ -146,4 +132,11 @@ def main() -> None:
 
 
 if __name__ == "__main__":
-    main()
+    from sonusai import exception_handler
+    from sonusai.utils import register_keyboard_interrupt
+
+    register_keyboard_interrupt()
+    try:
+        main()
+    except Exception as e:
+        exception_handler(e)

sonusai/main.py

@@ -10,21 +10,6 @@ for more information on a specific command.
 
 """
 
-import signal
-
-
-def signal_handler(_sig, _frame):
-    import sys
-
-    from sonusai import logger
-
-    logger.info("Canceled due to keyboard interrupt")
-    sys.exit(1)
-
-
-signal.signal(signal.SIGINT, signal_handler)
-
-
 def main() -> None:
     from importlib import import_module
     from pkgutil import iter_modules
@@ -44,13 +29,13 @@ def main() -> None:
 
     from docopt import docopt
 
-    from sonusai import __version__
+    from sonusai import __version__ as sai_version
     from sonusai.utils import add_commands_to_docstring
     from sonusai.utils import trim_docstring
 
     args = docopt(
         trim_docstring(add_commands_to_docstring(__doc__, plugin_docstrings)),
-        version=__version__,
+        version=sai_version,
         options_first=True,
     )
 
@@ -61,15 +46,16 @@ def main() -> None:
     from os.path import join
     from subprocess import call
 
-    import sonusai
+    from sonusai import BASEDIR
+    from sonusai import commands_list
     from sonusai import logger
 
-    base_commands = sonusai.commands_list()
+    base_commands = commands_list()
     if command == "help":
         if not argv:
             exit(call(["sonusai", "-h"]))  # noqa: S603, S607
         elif argv[0] in base_commands:
-            exit(call(["python", f"{join(sonusai.BASEDIR, argv[0])}.py", "-h"]))  # noqa: S603, S607
+            exit(call(["python", f"{join(BASEDIR, argv[0])}.py", "-h"]))  # noqa: S603, S607
 
         for data in plugins.values():
             if argv[0] in data["commands"]:
@@ -79,7 +65,7 @@ def main() -> None:
         sys.exit(1)
 
     if command in base_commands:
-        exit(call(["python", f"{join(sonusai.BASEDIR, command)}.py", *argv]))  # noqa: S603, S607
+        exit(call(["python", f"{join(BASEDIR, command)}.py", *argv]))  # noqa: S603, S607
 
     for data in plugins.values():
         if command in data["commands"]:
@@ -90,4 +76,11 @@ def main() -> None:
 
 
 if __name__ == "__main__":
-    main()
+    from sonusai import exception_handler
+    from sonusai.utils import register_keyboard_interrupt
+
+    register_keyboard_interrupt()
+    try:
+        main()
+    except Exception as e:
+        exception_handler(e)

sonusai/metrics/calc_audio_stats.py

@@ -1,5 +1,5 @@
-from sonusai.mixture.datatypes import AudioStatsMetrics
-from sonusai.mixture.datatypes import AudioT
+from ..datatypes import AudioStatsMetrics
+from ..datatypes import AudioT
 
 
 def _convert_str_with_factors_to_int(x: str) -> int:
@@ -11,22 +11,9 @@ def _convert_str_with_factors_to_int(x: str) -> int:
 
 
 def calc_audio_stats(audio: AudioT, win_len: float | None = None) -> AudioStatsMetrics:
-    from sonusai.mixture import SAMPLE_RATE
-    from sonusai.mixture import Transformer
+    from ..mixture.sox_effects import sox_stats
 
-    args = ["stats"]
-    if win_len is not None:
-        args.extend(["-w", str(win_len)])
-
-    tfm = Transformer()
-
-    _, _, out = tfm.build(
-        input_array=audio,
-        sample_rate_in=SAMPLE_RATE,
-        output_filepath="-n",
-        extra_args=args,
-        return_output=True,
-    )
+    out = sox_stats(audio, win_len)
 
     if out is None:
         raise SystemError("Call to sox failed")

sonusai/metrics/calc_class_weights.py

@@ -1,8 +1,8 @@
 import numpy as np
 
-from sonusai.mixture.datatypes import GeneralizedIDs
-from sonusai.mixture.datatypes import Truth
-from sonusai.mixture.mixdb import MixtureDatabase
+from ..datatypes import GeneralizedIDs
+from ..datatypes import Truth
+from ..mixture.mixdb import MixtureDatabase
 
 
 def calc_class_weights_from_truth(truth: Truth, other_weight: float | None = None, other_index: int = -1) -> np.ndarray:
@@ -74,7 +74,7 @@ def calc_class_weights_from_mixdb(
         weights: Class weights. [num_classes, 1]
             Note: for Keras use dict(enumerate(weights))
     """
-    from sonusai.mixture import get_class_count_from_mixids
+    from ..mixture.class_count import get_class_count_from_mixids
 
     count = np.ceil(np.array(get_class_count_from_mixids(mixdb=mixdb, mixids=mixids)) / mixdb.feature_step_samples)
     total_features = sum(count)

sonusai/metrics/calc_optimal_thresholds.py

@@ -1,11 +1,14 @@
 import numpy as np
 
-from sonusai.mixture.datatypes import Predict
-from sonusai.mixture.datatypes import Truth
+from ..datatypes import Predict
+from ..datatypes import Truth
 
 
 def calc_optimal_thresholds(
-    truth: Truth, predict: Predict, timesteps: int = 0, truth_thr: float = 0.5
+    truth: Truth,
+    predict: Predict,
+    timesteps: int = 0,
+    truth_thr: float = 0.5,
 ) -> tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]:
     """Calculates optimal thresholds for each class from one-hot prediction and truth data where both are
     one-hot probabilities (or quantized decisions) with size [frames, num_classes] or [frames, timesteps, num_classes].
@@ -24,8 +27,8 @@ def calc_optimal_thresholds(
     from sklearn.metrics import roc_auc_score
     from sklearn.metrics import roc_curve
 
-    from sonusai.utils import get_num_classes_from_predict
-    from sonusai.utils import reshape_outputs
+    from ..utils.reshape import get_num_classes_from_predict
+    from ..utils.reshape import reshape_outputs
 
     if truth.shape != predict.shape:
         raise ValueError("truth and predict are not the same shape")

sonusai/metrics/calc_pesq.py

@@ -1,6 +1,6 @@
 import numpy as np
 
-from sonusai.mixture.constants import SAMPLE_RATE
+from ..constants import SAMPLE_RATE
 
 
 def calc_pesq(
@@ -23,7 +23,7 @@ def calc_pesq(
 
     from pesq import pesq
 
-    from sonusai import logger
+    from .. import logger
 
     try:
         with warnings.catch_warnings():

sonusai/metrics/calc_segsnr_f.py

@@ -1,9 +1,9 @@
 import numpy as np
 
-from sonusai.mixture.datatypes import AudioF
-from sonusai.mixture.datatypes import Segsnr
-from sonusai.mixture.datatypes import SnrFBinMetrics
-from sonusai.mixture.datatypes import SnrFMetrics
+from ..datatypes import AudioF
+from ..datatypes import Segsnr
+from ..datatypes import SnrFBinMetrics
+from ..datatypes import SnrFMetrics
 
 
 def calc_segsnr_f(segsnr_f: Segsnr) -> SnrFMetrics:

sonusai/metrics/calc_speech.py

@@ -1,18 +1,23 @@
 import numpy as np
 
-from sonusai.mixture.constants import SAMPLE_RATE
-from sonusai.mixture.datatypes import SpeechMetrics
-
+from ..constants import SAMPLE_RATE
+from ..datatypes import SpeechMetrics
 from .calc_pesq import calc_pesq
 
 
-def calc_speech(hypothesis: np.ndarray, reference: np.ndarray, sample_rate: int = SAMPLE_RATE) -> SpeechMetrics:
-    """Calculate speech metrics pesq, c_sig, c_bak, and c_ovl.
+def calc_speech(
+    hypothesis: np.ndarray,
+    reference: np.ndarray,
+    pesq: float | None = None,
+    sample_rate: int = SAMPLE_RATE,
+) -> SpeechMetrics:
+    """Calculate speech metrics c_sig, c_bak, and c_ovl.
 
     These are all related and thus included in one function. Reference: matlab script "compute_metrics.m".
 
     :param hypothesis: estimated audio
     :param reference: reference audio
+    :param pesq: pesq
     :param sample_rate: sample rate of audio
     :return: SpeechMetrics named tuple
     """
@@ -36,18 +41,21 @@ def calc_speech(hypothesis: np.ndarray, reference: np.ndarray, sample_rate: int
     seg_snr = np.mean(segsnr_dist)
 
     # PESQ
-    _pesq = calc_pesq(hypothesis=hypothesis, reference=reference, sample_rate=sample_rate)
+    if pesq is None:
+        pesq = calc_pesq(hypothesis=hypothesis, reference=reference, sample_rate=sample_rate)
 
     # Now compute the composite measures
-    csig = float(np.clip(3.093 - 1.029 * llr_mean + 0.603 * _pesq - 0.009 * wss_dist, 1, 5))
-    cbak = float(np.clip(1.634 + 0.478 * _pesq - 0.007 * wss_dist + 0.063 * seg_snr, 1, 5))
-    covl = float(np.clip(1.594 + 0.805 * _pesq - 0.512 * llr_mean - 0.007 * wss_dist, 1, 5))
+    csig = float(np.clip(3.093 - 1.029 * llr_mean + 0.603 * pesq - 0.009 * wss_dist, 1, 5))
+    cbak = float(np.clip(1.634 + 0.478 * pesq - 0.007 * wss_dist + 0.063 * seg_snr, 1, 5))
+    covl = float(np.clip(1.594 + 0.805 * pesq - 0.512 * llr_mean - 0.007 * wss_dist, 1, 5))
 
-    return SpeechMetrics(_pesq, csig, cbak, covl)
+    return SpeechMetrics(csig, cbak, covl)
 
 
 def _calc_weighted_spectral_slope_measure(
-    hypothesis: np.ndarray, reference: np.ndarray, sample_rate: int = SAMPLE_RATE
+    hypothesis: np.ndarray,
+    reference: np.ndarray,
+    sample_rate: int = SAMPLE_RATE,
 ) -> np.ndarray:
     from scipy.fftpack import fft
 
@@ -250,7 +258,9 @@ def _calc_weighted_spectral_slope_measure(
 
 
 def _calc_log_likelihood_ratio_measure(
-    hypothesis: np.ndarray, reference: np.ndarray, sample_rate: int = SAMPLE_RATE
+    hypothesis: np.ndarray,
+    reference: np.ndarray,
+    sample_rate: int = SAMPLE_RATE,
 ) -> np.ndarray:
     from scipy.linalg import toeplitz
 
@@ -296,7 +306,9 @@ def _calc_log_likelihood_ratio_measure(
 
 
 def _calc_snr(
-    hypothesis: np.ndarray, reference: np.ndarray, sample_rate: int = SAMPLE_RATE
+    hypothesis: np.ndarray,
+    reference: np.ndarray,
+    sample_rate: int = SAMPLE_RATE,
 ) -> tuple[float, np.ndarray]:
     # The lengths of the reference and hypothesis must be the same.
     reference_length = len(reference)

sonusai/metrics/class_summary.py

@@ -2,10 +2,10 @@
 import numpy as np
 import pandas as pd
 
-from sonusai.mixture import GeneralizedIDs
-from sonusai.mixture import MixtureDatabase
-from sonusai.mixture import Predict
-from sonusai.mixture import Truth
+from ..datatypes import GeneralizedIDs
+from ..datatypes import Predict
+from ..datatypes import Truth
+from ..mixture.mixdb import MixtureDatabase
 
 
 def class_summary(
@@ -31,7 +31,7 @@ def class_summary(
       macro avg     0.85    0.83    0.84    0.05    0.96            3768
       micro-avgwo
     """
-    from sonusai.metrics import one_hot
+    from ..metrics.one_hot import one_hot
 
     num_classes = truth_f.shape[1]
 
@@ -58,11 +58,11 @@ def class_summary(
     else:
         row_n = [f"Class {i}" for i in range(1, num_classes + 1)]
 
-    df = pd.DataFrame(metrics[:, table_idx], columns=col_n, index=row_n) # pyright: ignore [reportArgumentType]
+    df = pd.DataFrame(metrics[:, table_idx], columns=col_n, index=row_n)  # pyright: ignore [reportArgumentType]
 
     # [miPPV, miTPR, miF1, miFPR, miACC, miAP, miAUC, TPSUM]
     avg_row_n = ["Macro-avg", "Micro-avg", "Weighted-avg"]
-    dfavg = pd.DataFrame(metavg, columns=col_n, index=avg_row_n) # pyright: ignore [reportArgumentType]
+    dfavg = pd.DataFrame(metavg, columns=col_n, index=avg_row_n)  # pyright: ignore [reportArgumentType]
 
     # dfblank = pd.DataFrame([''])
     # pd.concat([df, dfblank, dfblank, dfavg])

sonusai/metrics/confusion_matrix_summary.py

@@ -2,10 +2,10 @@
 import numpy as np
 import pandas as pd
 
-from sonusai.mixture import GeneralizedIDs
-from sonusai.mixture import MixtureDatabase
-from sonusai.mixture import Predict
-from sonusai.mixture import Truth
+from ..datatypes import GeneralizedIDs
+from ..datatypes import Predict
+from ..datatypes import Truth
+from ..mixture.mixdb import MixtureDatabase
 
 
 def confusion_matrix_summary(
@@ -30,7 +30,7 @@ def confusion_matrix_summary(
 
     Returns pandas dataframes of confusion matrix cmdf and normalized confusion matrix cmndf.
     """
-    from sonusai.metrics import one_hot
+    from ..metrics.one_hot import one_hot
 
     num_classes = truth_f.shape[1]
     # TODO: re-work for modern mixdb API

sonusai/metrics/one_hot.py

@@ -1,7 +1,7 @@
 import numpy as np
 
-from sonusai.mixture.datatypes import Predict
-from sonusai.mixture.datatypes import Truth
+from ..datatypes import Predict
+from ..datatypes import Truth
 
 
 def one_hot(
@@ -53,8 +53,8 @@ def one_hot(
     from sklearn.metrics import precision_recall_fscore_support
     from sklearn.metrics import roc_auc_score
 
-    from sonusai.utils import get_num_classes_from_predict
-    from sonusai.utils import reshape_outputs
+    from ..utils.reshape import get_num_classes_from_predict
+    from ..utils.reshape import reshape_outputs
 
     if truth.shape != predict.shape:
         raise ValueError("truth and predict are not the same shape")

sonusai/metrics/snr_summary.py

@@ -2,11 +2,11 @@
 import numpy as np
 import pandas as pd
 
-from sonusai.mixture import GeneralizedIDs
-from sonusai.mixture import MixtureDatabase
-from sonusai.mixture import Predict
-from sonusai.mixture import Segsnr
-from sonusai.mixture import Truth
+from ..datatypes import GeneralizedIDs
+from ..datatypes import Predict
+from ..datatypes import Segsnr
+from ..datatypes import Truth
+from ..mixture.mixdb import MixtureDatabase
 
 
 def snr_summary(
@@ -40,8 +40,8 @@ def snr_summary(
     """
     import warnings
 
-    from sonusai.metrics import one_hot
-    from sonusai.queries import get_mixids_from_snr
+    from ..metrics.one_hot import one_hot
+    from ..queries.queries import get_mixids_from_snr
 
     num_classes = truth_f.shape[1]