lingualabpy 0.0.5__tar.gz → 0.0.6__tar.gz

{lingualabpy-0.0.5 → lingualabpy-0.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lingualabpy
-Version: 0.0.5
+Version: 0.0.6
 Summary: Tools and utilities from the LINGUA laboratory
 Author-email: Christophe Bedetti <christophe.bedetti@umontreal.ca>
 Requires-Python: >=3.8.1
@@ -19,6 +19,8 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Requires-Dist: click
+Requires-Dist: matplotlib
+Requires-Dist: opencv-python
 Requires-Dist: pandas
 Requires-Dist: praat-parselmouth
 Requires-Dist: praat-textgrids

{lingualabpy-0.0.5 → lingualabpy-0.0.6}/pyproject.toml

@@ -28,7 +28,7 @@ classifiers = [
 requires-python = ">=3.8.1"
 dynamic = ["version"]
 
-dependencies = ["click", "pandas", "praat-parselmouth", "praat-textgrids", "pydub", "python-docx"]
+dependencies = ["click", "matplotlib", "opencv-python", "pandas", "praat-parselmouth", "praat-textgrids", "pydub", "python-docx"]
 
 [project.optional-dependencies]
 test = ["pytest", "pytest-cov"]
@@ -42,6 +42,7 @@ lingualabpy_audio_metrics = "lingualabpy.cli.audio_metrics:main"
 lingualabpy_audio_triming = "lingualabpy.cli.audio_triming:main"
 lingualabpy_docx2json = "lingualabpy.cli.docx2json:main"
 lingualabpy_jsons2csv = "lingualabpy.cli.jsons2csv:main"
+lingualabpy_plot_sound = "lingualabpy.cli.plot_sound:main"
 
 [project.urls]
 Documentation = "https://github.com/lingualab/lingualabpy"

{lingualabpy-0.0.5 → lingualabpy-0.0.6}/src/lingualabpy/__init__.py

@@ -4,7 +4,7 @@
 """lingualabpy"""
 from __future__ import annotations
 
-__version__ = "0.0.5"
+__version__ = "0.0.6"
 
 default_config = {
     "participant_col": "participant_id",

lingualabpy-0.0.6/src/lingualabpy/cli/plot_sound.py

@@ -0,0 +1,55 @@
+import cv2
+import os
+import click
+from parselmouth import Sound
+import matplotlib.pyplot as plt
+from pathlib import Path
+
+from lingualabpy.plot import draw_pitch, draw_spectrogram
+
+
+@click.command()
+@click.option("--output", default=None, help="")
+@click.argument("audiofile", nargs=1, type=click.Path(exists=True))
+def main(audiofile, output):
+    if not output:
+        output = Path(audiofile).stem + ".png"
+
+    sound = Sound(audiofile)
+
+    pitch = sound.to_pitch()
+
+    # If desired, pre-emphasize the sound fragment before calculating the spectrogram
+    pre_emphasized_snd = sound.copy()
+    pre_emphasized_snd.pre_emphasize()
+    spectrogram = pre_emphasized_snd.to_spectrogram(
+        window_length=0.03, maximum_frequency=8000
+    )
+
+    # amplitude figure
+    tmp_amplitude_png = "tmp_amplitude.png"
+    amplitude = plt.figure()
+    plt.plot(sound.xs(), sound.values.T)
+    plt.xlim([sound.xmin, sound.xmax])
+    plt.xlabel("time [s]")
+    plt.ylabel("amplitude")
+    amplitude.set_figwidth(sound.xmax / 4)
+    plt.savefig(tmp_amplitude_png)
+
+    # spectro pitch figure
+    tmp_spectro_pitch_png = "tmp_spectro_pitch.png"
+    spectro_pitch = plt.figure()
+    draw_spectrogram(spectrogram)
+    plt.twinx()
+    draw_pitch(pitch)
+    plt.xlim([sound.xmin, sound.xmax])
+    spectro_pitch.set_figwidth(sound.xmax / 4)
+    plt.savefig(tmp_spectro_pitch_png)
+
+    # concatenation
+    fig_concat = cv2.vconcat(
+        [cv2.imread(tmp_amplitude_png), cv2.imread(tmp_spectro_pitch_png)]
+    )
+    cv2.imwrite(output, fig_concat)
+    os.remove(tmp_amplitude_png)
+    os.remove(tmp_spectro_pitch_png)

lingualabpy-0.0.6/src/lingualabpy/plot.py

@@ -0,0 +1,23 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+
+def draw_spectrogram(spectrogram, dynamic_range=70):
+    X, Y = spectrogram.x_grid(), spectrogram.y_grid()
+    sg_db = 10 * np.log10(spectrogram.values)
+    plt.pcolormesh(X, Y, sg_db, vmin=sg_db.max() - dynamic_range, cmap="afmhot")
+    plt.ylim([spectrogram.ymin, spectrogram.ymax])
+    plt.xlabel("time [s]")
+    plt.ylabel("frequency [Hz]")
+
+
+def draw_pitch(pitch):
+    # Extract selected pitch contour, and
+    # replace unvoiced samples by NaN to not plot
+    pitch_values = pitch.selected_array["frequency"]
+    pitch_values[pitch_values == 0] = np.nan
+    plt.plot(pitch.xs(), pitch_values, "o", markersize=5, color="w")
+    plt.plot(pitch.xs(), pitch_values, "o", markersize=2)
+    plt.grid(False)
+    plt.ylim(0, pitch.ceiling)
+    plt.ylabel("fundamental frequency [Hz]")