lingualabpy 0.0.6__py3-none-any.whl → 0.1.1__py3-none-any.whl

lingualabpy/__init__.py

@@ -1,20 +1,25 @@
-#   -------------------------------------------------------------
-#   Licensed under the MIT License. See LICENSE in project root for information.
-#   -------------------------------------------------------------
-"""lingualabpy"""
-from __future__ import annotations
-
-__version__ = "0.0.6"
-
-default_config = {
-    "participant_col": "participant_id",
-    "participant_label": "IE",
-    "clinician_label": "IV",
-    "f0_bounds": {
-        "female": [100.0, 600.0],
-        "male": [75.0, 300.0],
-    },
-    "unit_frequency": "Hertz",
-}
-
-from lingualabpy.io import read_audio, read_docx, read_json, write_json, read_textgrid
+#   -------------------------------------------------------------
+#   Licensed under the MIT License. See LICENSE in project root for information.
+#   -------------------------------------------------------------
+"""lingualabpy"""
+
+from __future__ import annotations
+
+try:
+    from lingualabpy._version import __version__
+except ImportError:
+    pass
+
+
+default_config = {
+    "participant_col": "participant_id",
+    "participant_label": "IE",
+    "clinician_label": "IV",
+    "f0_bounds": {
+        "female": [100.0, 600.0],
+        "male": [75.0, 300.0],
+    },
+    "unit_frequency": "Hertz",
+}
+
+from lingualabpy.io import read_audio, read_docx, read_json, write_json, read_textgrid

lingualabpy/_version.py

@@ -0,0 +1,34 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+    COMMIT_ID = Union[str, None]
+else:
+    VERSION_TUPLE = object
+    COMMIT_ID = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+commit_id: COMMIT_ID
+__commit_id__: COMMIT_ID
+
+__version__ = version = '0.1.1'
+__version_tuple__ = version_tuple = (0, 1, 1)
+
+__commit_id__ = commit_id = None

lingualabpy/audio/metrics.py

@@ -1,85 +1,85 @@
-from collections import defaultdict
-import numpy as np
-from parselmouth import Sound
-from parselmouth.praat import call
-
-from lingualabpy.tools.data import UnchangeableDict
-
-
-def measure_pitch(sound: Sound, f0min: str, f0max: str, unit: str) -> UnchangeableDict:
-    """
-    This function measures duration, pitch, HNR, jitter, and shimmer
-    This is the function to measure source acoustics using default male parameters.
-    """
-    # compute usefull praat object
-    pitch = call(sound, "To Pitch", 0.0, f0min, f0max)
-    harmonicity = call(sound, "To Harmonicity (cc)", 0.01, f0min, 0.1, 1.0)
-    point_process = call(sound, "To PointProcess (periodic, cc)", f0min, f0max)
-
-    # metrics container
-    metrics = UnchangeableDict()
-
-    # Metrics computation
-    metrics["duration"] = call(sound, "Get total duration")
-    metrics["f0_mean"] = call(pitch, "Get mean", 0, 0, unit)
-    metrics["F0_std"] = call(pitch, "Get standard deviation", 0, 0, unit)
-    metrics["hnr"] = call(harmonicity, "Get mean", 0, 0)
-
-    # jitter
-    jitter_types = ["local", ["local", "absolute"], "rap", "ppq5", "ddp"]
-    for jitter_type in jitter_types:
-        if isinstance(jitter_type, list):
-            metric_name = f"jitter_{'_'.join(jitter_type)}"
-            praat_function = f"Get jitter ({', '.join(jitter_type)})"
-        else:
-            metric_name = f"jitter_{jitter_type}"
-            praat_function = f"Get jitter ({jitter_type})"
-        metrics[metric_name] = call(
-            point_process, praat_function, 0, 0, 0.0001, 0.02, 1.3
-        )
-
-    # shimmer
-    shimmer_types = ["local", "local_dB", "apq3", "apq5", "apq11", "dda"]
-    for shimmer_type in shimmer_types:
-        metric_name = f"shimmer_{shimmer_type}"
-        praat_function = f"Get shimmer ({shimmer_type})"
-        metrics[metric_name] = call(
-            [sound, point_process], praat_function, 0, 0, 0.0001, 0.02, 1.3, 1.6
-        )
-
-    return metrics
-
-
-def measure_formants(
-    sound: Sound, f0min: str, f0max: str, unit: str
-) -> UnchangeableDict:
-    """
-    This function measures formants at each glottal pulse
-
-    Puts, D. A., Apicella, C. L., & Cárdenas, R. A. (2012). Masculine voices signal men's threat potential in forager and industrial societies. Proceedings of the Royal Society of London B: Biological Sciences, 279(1728), 601-609.
-
-    Adapted from: DOI 10.17605/OSF.IO/K2BHS
-    """
-    # compute usefull praat object
-    point_process = call(sound, "To PointProcess (periodic, cc)", f0min, f0max)
-    formants = call(sound, "To Formant (burg)", 0.0025, 5, 5000, 0.025, 50)
-    number_of_points = call(point_process, "Get number of points")
-
-    # metrics container
-    metrics = UnchangeableDict()
-
-    # Measure formants only at glottal pulses
-    formants_list = defaultdict(list)
-    for index in range(1, number_of_points + 1):
-        time = call(point_process, "Get time from index", index)
-        for pulse in [1, 2, 3, 4]:
-            value = call(formants, "Get value at time", pulse, time, unit, "Linear")
-            if str(value) != "nan":
-                formants_list[pulse].append(value)
-
-    # calculate mean and median formants across pulses, median is what is used in all subsequent calculations
-    for pulse in [1, 2, 3, 4]:
-        metrics[f"formants_{pulse}_mean"] = np.mean(formants_list[pulse])
-        metrics[f"formants_{pulse}_median"] = np.median(formants_list[pulse])
-
-    return metrics
+from collections import defaultdict
+import numpy as np
+from parselmouth import Sound
+from parselmouth.praat import call
+
+from lingualabpy.tools.data import UnchangeableDict
+
+
+def measure_pitch(sound: Sound, f0min: str, f0max: str, unit: str) -> UnchangeableDict:
+    """
+    This function measures duration, pitch, HNR, jitter, and shimmer
+    This is the function to measure source acoustics using default male parameters.
+    """
+    # compute usefull praat object
+    pitch = call(sound, "To Pitch", 0.0, f0min, f0max)
+    harmonicity = call(sound, "To Harmonicity (cc)", 0.01, f0min, 0.1, 1.0)
+    point_process = call(sound, "To PointProcess (periodic, cc)", f0min, f0max)
+
+    # metrics container
+    metrics = UnchangeableDict()
+
+    # Metrics computation
+    metrics["duration"] = call(sound, "Get total duration")
+    metrics["f0_mean"] = call(pitch, "Get mean", 0, 0, unit)
+    metrics["F0_std"] = call(pitch, "Get standard deviation", 0, 0, unit)
+    metrics["hnr"] = call(harmonicity, "Get mean", 0, 0)
+
+    # jitter
+    jitter_types = ["local", ["local", "absolute"], "rap", "ppq5", "ddp"]
+    for jitter_type in jitter_types:
+        if isinstance(jitter_type, list):
+            metric_name = f"jitter_{'_'.join(jitter_type)}"
+            praat_function = f"Get jitter ({', '.join(jitter_type)})"
+        else:
+            metric_name = f"jitter_{jitter_type}"
+            praat_function = f"Get jitter ({jitter_type})"
+        metrics[metric_name] = call(
+            point_process, praat_function, 0, 0, 0.0001, 0.02, 1.3
+        )
+
+    # shimmer
+    shimmer_types = ["local", "local_dB", "apq3", "apq5", "apq11", "dda"]
+    for shimmer_type in shimmer_types:
+        metric_name = f"shimmer_{shimmer_type}"
+        praat_function = f"Get shimmer ({shimmer_type})"
+        metrics[metric_name] = call(
+            [sound, point_process], praat_function, 0, 0, 0.0001, 0.02, 1.3, 1.6
+        )
+
+    return metrics
+
+
+def measure_formants(
+    sound: Sound, f0min: str, f0max: str, unit: str
+) -> UnchangeableDict:
+    """
+    This function measures formants at each glottal pulse
+
+    Puts, D. A., Apicella, C. L., & Cárdenas, R. A. (2012). Masculine voices signal men's threat potential in forager and industrial societies. Proceedings of the Royal Society of London B: Biological Sciences, 279(1728), 601-609.
+
+    Adapted from: DOI 10.17605/OSF.IO/K2BHS
+    """
+    # compute usefull praat object
+    point_process = call(sound, "To PointProcess (periodic, cc)", f0min, f0max)
+    formants = call(sound, "To Formant (burg)", 0.0025, 5, 5000, 0.025, 50)
+    number_of_points = call(point_process, "Get number of points")
+
+    # metrics container
+    metrics = UnchangeableDict()
+
+    # Measure formants only at glottal pulses
+    formants_list = defaultdict(list)
+    for index in range(1, number_of_points + 1):
+        time = call(point_process, "Get time from index", index)
+        for pulse in [1, 2, 3, 4]:
+            value = call(formants, "Get value at time", pulse, time, unit, "Linear")
+            if str(value) != "nan":
+                formants_list[pulse].append(value)
+
+    # calculate mean and median formants across pulses, median is what is used in all subsequent calculations
+    for pulse in [1, 2, 3, 4]:
+        metrics[f"formants_{pulse}_mean"] = np.mean(formants_list[pulse])
+        metrics[f"formants_{pulse}_median"] = np.median(formants_list[pulse])
+
+    return metrics

lingualabpy/audio/triming.py

@@ -1,11 +1,11 @@
-from pydub import AudioSegment
-
-
-def extract_audio(audio: AudioSegment, intervals: list[list[float]]) -> AudioSegment:
-    """"""
-    new_audio = AudioSegment.empty()
-
-    for start, end in intervals:
-        new_audio += audio[start * 1000 : end * 1000]
-
-    return new_audio
+from pydub import AudioSegment
+
+
+def extract_audio(audio: AudioSegment, intervals: list[list[float]]) -> AudioSegment:
+    """"""
+    new_audio = AudioSegment.empty()
+
+    for start, end in intervals:
+        new_audio += audio[start * 1000 : end * 1000]
+
+    return new_audio

lingualabpy/cli/audio_metrics.py

@@ -1,59 +1,59 @@
-import click
-from parselmouth import Sound
-from pathlib import Path
-
-from lingualabpy import default_config, write_json
-from lingualabpy.audio.metrics import measure_pitch, measure_formants
-
-
-@click.command()
-@click.option(
-    "--sex",
-    type=click.Choice(["female", "male"]),
-    help=f"Set f0min and f0max for praat analysis. {default_config['f0_bounds']}",
-)
-@click.option(
-    "--f0min",
-    type=float,
-    help="Define f0min for praat analysis. Not required if sex is specify",
-)
-@click.option(
-    "--f0max",
-    type=float,
-    help="Define f0max for praat analysis. Not required if sex is specify",
-)
-@click.option(
-    "--unit_frequency",
-    default=default_config["unit_frequency"],
-    show_default=True,
-)
-@click.option("--participant_id", "-p", default=None, help="")
-@click.option("--output_json", default=None, help="")
-@click.argument("audiofile", nargs=1, type=click.Path(exists=True))
-def main(sex, f0min, f0max, unit_frequency, participant_id, output_json, audiofile):
-    """Doc"""
-    if sex:
-        f0min, f0max = default_config["f0_bounds"][sex]
-    else:
-        if not f0min or not f0max:
-            raise click.UsageError(
-                "'--f0min' and '--f0max' are required if '--sex' is not specified"
-            )
-
-    sound = Sound(audiofile)
-    metrics = measure_pitch(sound, f0min, f0max, unit_frequency)
-    metrics.update(measure_formants(sound, f0min, f0max, unit_frequency))
-
-    audiofile_stem = Path(audiofile).stem
-
-    if participant_id:
-        metrics["participant_id"] = participant_id
-
-    audiofile = Path(audiofile)
-
-    metrics["filename"] = audiofile.name
-
-    if not output_json:
-        output_json = audiofile.stem + "_metric-audio.json"
-
-    write_json(dict(metrics), output_json)
+import click
+from parselmouth import Sound
+from pathlib import Path
+
+from lingualabpy import default_config, write_json
+from lingualabpy.audio.metrics import measure_pitch, measure_formants
+
+
+@click.command()
+@click.option(
+    "--sex",
+    type=click.Choice(["female", "male"]),
+    help=f"Set f0min and f0max for praat analysis. {default_config['f0_bounds']}",
+)
+@click.option(
+    "--f0min",
+    type=float,
+    help="Define f0min for praat analysis. Not required if sex is specify",
+)
+@click.option(
+    "--f0max",
+    type=float,
+    help="Define f0max for praat analysis. Not required if sex is specify",
+)
+@click.option(
+    "--unit_frequency",
+    default=default_config["unit_frequency"],
+    show_default=True,
+)
+@click.option("--participant_id", "-p", default=None, help="")
+@click.option("--output_json", default=None, help="")
+@click.argument("audiofile", nargs=1, type=click.Path(exists=True))
+def main(sex, f0min, f0max, unit_frequency, participant_id, output_json, audiofile):
+    """Doc"""
+    if sex:
+        f0min, f0max = default_config["f0_bounds"][sex]
+    else:
+        if not f0min or not f0max:
+            raise click.UsageError(
+                "'--f0min' and '--f0max' are required if '--sex' is not specified"
+            )
+
+    sound = Sound(audiofile)
+    metrics = measure_pitch(sound, f0min, f0max, unit_frequency)
+    metrics.update(measure_formants(sound, f0min, f0max, unit_frequency))
+
+    audiofile_stem = Path(audiofile).stem
+
+    if participant_id:
+        metrics["participant_id"] = participant_id
+
+    audiofile = Path(audiofile)
+
+    metrics["filename"] = audiofile.name
+
+    if not output_json:
+        output_json = audiofile.stem + "_metric-audio.json"
+
+    write_json(dict(metrics), output_json)

lingualabpy/cli/audio_triming.py

@@ -1,48 +1,48 @@
-import click
-
-from lingualabpy import default_config, read_audio, read_textgrid
-from lingualabpy.audio.triming import extract_audio
-from lingualabpy.text.textgrid import extract_intervals
-from lingualabpy.tools.interval import intervals_masking, interval_to_list
-
-
-@click.command()
-@click.option(
-    "--participant_label",
-    default=default_config["participant_label"],
-    show_default=True,
-)
-@click.option(
-    "--clinician_label",
-    default=default_config["clinician_label"],
-    show_default=True,
-)
-@click.option("--remove_overlap", is_flag=True, show_default=True)
-@click.argument("textgrid", nargs=1, type=click.Path(exists=True))
-@click.argument("audiofile", nargs=1, type=click.Path(exists=True))
-@click.argument("output", nargs=1)
-def main(
-    participant_label, clinician_label, remove_overlap, textgrid, audiofile, output
-):
-    """Doc"""
-    grid = read_textgrid(textgrid)
-
-    try:
-        participant_intervals, clinician_intervals = extract_intervals(
-            grid, [participant_label, clinician_label]
-        )
-    except Exception as e:
-        raise Exception(f"Failed to extract intervals for {textgrid}", repr(e))
-
-    if remove_overlap:
-        participant_intervals = intervals_masking(
-            participant_intervals, clinician_intervals
-        )
-    else:
-        participant_intervals = map(interval_to_list, participant_intervals)
-
-    audio = read_audio(audiofile)
-
-    audio_clean = extract_audio(audio, participant_intervals)
-
-    audio_clean.export(output, format="wav")
+import click
+
+from lingualabpy import default_config, read_audio, read_textgrid
+from lingualabpy.audio.triming import extract_audio
+from lingualabpy.text.textgrid import extract_intervals
+from lingualabpy.tools.interval import intervals_masking, interval_to_list
+
+
+@click.command()
+@click.option(
+    "--participant_label",
+    default=default_config["participant_label"],
+    show_default=True,
+)
+@click.option(
+    "--clinician_label",
+    default=default_config["clinician_label"],
+    show_default=True,
+)
+@click.option("--remove_overlap", is_flag=True, show_default=True)
+@click.argument("textgrid", nargs=1, type=click.Path(exists=True))
+@click.argument("audiofile", nargs=1, type=click.Path(exists=True))
+@click.argument("output", nargs=1)
+def main(
+    participant_label, clinician_label, remove_overlap, textgrid, audiofile, output
+):
+    """Doc"""
+    grid = read_textgrid(textgrid)
+
+    try:
+        participant_intervals, clinician_intervals = extract_intervals(
+            grid, [participant_label, clinician_label]
+        )
+    except Exception as e:
+        raise Exception(f"Failed to extract intervals for {textgrid}", repr(e))
+
+    if remove_overlap:
+        participant_intervals = intervals_masking(
+            participant_intervals, clinician_intervals
+        )
+    else:
+        participant_intervals = map(interval_to_list, participant_intervals)
+
+    audio = read_audio(audiofile)
+
+    audio_clean = extract_audio(audio, participant_intervals)
+
+    audio_clean.export(output, format="wav")

lingualabpy/cli/docx2json.py

@@ -1,21 +1,21 @@
-import click
-
-from lingualabpy import read_docx, write_json
-from lingualabpy.text.parser import parse_waywithwords
-
-
-@click.command()
-@click.option("--origin", default="waywithwords", show_default=True)
-@click.argument("docx_path", nargs=1, type=click.Path(exists=True))
-@click.argument("output", nargs=1)
-def main(docx_path, output, origin):
-    """Doc"""
-    document = read_docx(docx_path)
-
-    if origin == "waywithwords":
-        data = parse_waywithwords(document)
-
-    else:
-        raise ValueError(f"{origin} is not implemented")
-
-    write_json(data, output)
+import click
+
+from lingualabpy import read_docx, write_json
+from lingualabpy.text.parser import parse_waywithwords
+
+
+@click.command()
+@click.option("--origin", default="waywithwords", show_default=True)
+@click.argument("docx_path", nargs=1, type=click.Path(exists=True))
+@click.argument("output", nargs=1)
+def main(docx_path, output, origin):
+    """Doc"""
+    document = read_docx(docx_path)
+
+    if origin == "waywithwords":
+        data = parse_waywithwords(document)
+
+    else:
+        raise ValueError(f"{origin} is not implemented")
+
+    write_json(data, output)

lingualabpy/cli/jsons2csv.py

@@ -1,23 +1,23 @@
-import click
-import json
-
-from lingualabpy import default_config, read_json
-from lingualabpy.tools.data import merge_participants_to_df
-
-
-@click.command()
-@click.option(
-    "-c",
-    "--column",
-    default=default_config["participant_col"],
-    show_default=True,
-)
-@click.argument("jsons", nargs=-1, type=click.Path(exists=True))
-@click.argument("output", nargs=1)
-def main(column, jsons, output):
-    """ """
-    data = []
-    for path in jsons:
-        data.append(read_json(path))
-    df = merge_participants_to_df(data, participant_col=column)
-    df.to_csv(output)
+import click
+import json
+
+from lingualabpy import default_config, read_json
+from lingualabpy.tools.data import merge_participants_to_df
+
+
+@click.command()
+@click.option(
+    "-c",
+    "--column",
+    default=default_config["participant_col"],
+    show_default=True,
+)
+@click.argument("jsons", nargs=-1, type=click.Path(exists=True))
+@click.argument("output", nargs=1)
+def main(column, jsons, output):
+    """ """
+    data = []
+    for path in jsons:
+        data.append(read_json(path))
+    df = merge_participants_to_df(data, participant_col=column)
+    df.to_csv(output)