Notes

Show imports Hide imports

import os

import dimcat as dc
import ms3
import pandas as pd
import plotly.express as px
from dimcat import filters, plotting

import utils

pd.set_option("display.max_rows", 1000)
pd.set_option("display.max_columns", 500)

Show source Hide source

RESULTS_PATH = os.path.abspath(os.path.join(utils.OUTPUT_FOLDER, "notes_stats"))
os.makedirs(RESULTS_PATH, exist_ok=True)


def make_output_path(
    filename: str,
    extension=None,
    path=RESULTS_PATH,
) -> str:
    return utils.make_output_path(filename=filename, extension=extension, path=path)


def save_figure_as(
    fig, filename, formats=("png", "pdf"), directory=RESULTS_PATH, **kwargs
):
    if formats is not None:
        for fmt in formats:
            plotting.write_image(fig, filename, directory, format=fmt, **kwargs)
    else:
        plotting.write_image(fig, filename, directory, **kwargs)

Loading data

Show source Hide source

D = utils.get_dataset("jc_bach_sonatas", corpus_release="v2.4")
package = D.inputs.get_package()
package_info = package._package.custom
git_tag = package_info.get("git_tag")
utils.print_heading("Data and software versions")
print("Johann Christian Bach – Keyboard Sonatas version v2.4")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

Data and software versions
--------------------------

Johann Christian Bach – Keyboard Sonatas version v2.4
Datapackage 'jc_bach_sonatas' @ v2.4
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'jc_bach_sonatas': ["'jc_bach_sonatas.measures' (MuseScoreFacetName.MuseScoreMeasures)",
                                             "'jc_bach_sonatas.notes' (MuseScoreFacetName.MuseScoreNotes)",
                                             "'jc_bach_sonatas.expanded' (MuseScoreFacetName.MuseScoreHarmonies)",
                                             "'jc_bach_sonatas.chords' (MuseScoreFacetName.MuseScoreChords)",
                                             "'jc_bach_sonatas.metadata' (FeatureName.Metadata)"]}},
 'outputs': {'basepath': None, 'packages': {}},
 'pipeline': []}

Metadata

filtered_D = filters.HasHarmonyLabelsFilter(keep_values=[True]).process(D)

all_metadata = filtered_D.get_metadata()
all_metadata.reset_index(level=1).groupby(level=0).nth(0).iloc[:, :20]

	piece	TimeSig	KeySig	last_mc	last_mn	length_qb	last_mc_unfolded	last_mn_unfolded	length_qb_unfolded	volta_mcs	all_notes_qb	n_onsets	n_onset_positions	guitar_chord_count	form_label_count	label_count	annotated_key	harmony_version	annotators	reviewers
corpus
jc_bach_sonatas	wa01op05no1a_Allegretto	{1: '2/4'}	{1: -2}	84	82	164.0	168	164	328.0	()	313.0	896	638	0	0	120	Bb	2.3.0	Adrian Nagel (2.1.1.), Ehsan Mohagheghi Fard (...	AN, EF

chronological_order = utils.chronological_corpus_order(all_metadata)
corpus_colors = dict(zip(chronological_order, utils.CORPUS_COLOR_SCALE))

notes_feature = filtered_D.get_feature("notes")
all_notes = notes_feature.df
print(f"{len(all_notes.index)} notes over {len(all_notes.groupby(level=[0,1]))} files.")
all_notes.head()

38003 notes over 29 files.

			mc	mn	quarterbeats	quarterbeats_all_endings	duration_qb	duration	mc_onset	mn_onset	timesig	staff	voice	chord_id	gracenote	midi	name	nominal_duration	octave	scalar	tied	tremolo	tpc_name	tpc
corpus	piece	i
jc_bach_sonatas	wa01op05no1a_Allegretto	0	1	0	0	0	0.375	3/32	0	3/8	2/4	1	1	0	<NA>	74	D5	1/16	5	3/2	<NA>	<NA>	D	2
		1	1	0	3/8	3/8	0.125	1/32	3/32	15/32	2/4	1	1	1	<NA>	75	Eb5	1/32	5	1	<NA>	<NA>	Eb	-3
		2	2	1	1/2	1/2	1.000	1/4	0	0	2/4	1	2	7	<NA>	74	D5	1/4	5	1	<NA>	<NA>	D	2
		3	2	1	1/2	1/2	1.000	1/4	0	0	2/4	1	1	2	<NA>	77	F5	1/4	5	1	<NA>	<NA>	F	-1
		4	2	1	3/4	3/4	0.250	1/16	1/16	1/16	2/4	2	1	8	<NA>	58	Bb3	1/16	3	1	<NA>	<NA>	Bb	-2

def weight_notes(nl, group_col="midi", precise=True):
    summed_durations = nl.groupby(group_col).duration_qb.sum()
    shortest_duration = summed_durations[summed_durations > 0].min()
    summed_durations /= shortest_duration  # normalize such that the shortest duration results in 1 occurrence
    if not precise:
        # This simple trick reduces compute time but also precision:
        # The rationale is to have the smallest value be slightly larger than 0.5 because
        # if it was exactly 0.5 it would be rounded down by repeat_notes_according_to_weights()
        summed_durations /= 1.9999999
    return repeat_notes_according_to_weights(summed_durations)


def repeat_notes_according_to_weights(weights):
    try:
        counts = weights.round().astype(int)
    except Exception:
        return pd.Series(dtype=int)
    counts_reflecting_weights = []
    for pitch, count in counts.items():
        counts_reflecting_weights.extend([pitch] * count)
    return pd.Series(counts_reflecting_weights)

Ambitus

corpus_names = {
    corp: utils.get_corpus_display_name(corp) for corp in chronological_order
}
chronological_corpus_names = list(corpus_names.values())
corpus_name_colors = {
    corpus_names[corp]: color for corp, color in corpus_colors.items()
}
all_notes["corpus_name"] = all_notes.index.get_level_values(0).map(corpus_names)

grouped_notes = all_notes.groupby("corpus_name")
weighted_midi = pd.concat(
    [weight_notes(nl, "midi", precise=False) for _, nl in grouped_notes],
    keys=grouped_notes.groups.keys(),
).reset_index(level=0)
weighted_midi.columns = ["dataset", "midi"]
weighted_midi

	dataset	midi
0	JC Bach Sonatas	29
1	JC Bach Sonatas	31
2	JC Bach Sonatas	32
3	JC Bach Sonatas	32
4	JC Bach Sonatas	32
...	...	...
6081	JC Bach Sonatas	87
6082	JC Bach Sonatas	88
6083	JC Bach Sonatas	88
6084	JC Bach Sonatas	89
6085	JC Bach Sonatas	89

6086 rows × 2 columns

# fig = px.violin(weighted_midi,
#                 x='dataset',
#                 y='midi',
#                 color='dataset',
#                 title="Corpus-wise distribution over registers (ambitus)",
#                 box=True,
#                 labels=dict(
#                     dataset='',
#                     midi='distribution of pitches by duration'
#                 ),
#                 category_orders=dict(dataset=chronological_corpus_names),
#                 color_discrete_map=corpus_name_colors,
#                 width=1000, height=600,
#                )
# fig.update_traces(spanmode='hard') # do not extend beyond outliers
# fig.update_layout(**utils.STD_LAYOUT,
#                  showlegend=False)
# fig.update_yaxes(
#     tickmode= 'array',
#     tickvals= [12, 24, 36, 48, 60, 72, 84, 96],
#     ticktext = ["C0", "C1", "C2", "C3", "C4", "C5", "C6", "C7"],
# )
# fig.update_xaxes(tickangle=45)
# save_figure_as(fig, "ambitus_corpuswise_violins")
# fig.show()

Tonal Pitch Classes (TPC)

weighted_tpc = pd.concat(
    [weight_notes(nl, "tpc") for _, nl in grouped_notes],
    keys=grouped_notes.groups.keys(),
).reset_index(level=0)
weighted_tpc.columns = ["dataset", "tpc"]
weighted_tpc

	dataset	tpc
0	JC Bach Sonatas	-8
1	JC Bach Sonatas	-7
2	JC Bach Sonatas	-7
3	JC Bach Sonatas	-7
4	JC Bach Sonatas	-7
...	...	...
73023	JC Bach Sonatas	13
73024	JC Bach Sonatas	13
73025	JC Bach Sonatas	13
73026	JC Bach Sonatas	13
73027	JC Bach Sonatas	13

73028 rows × 2 columns

As violin plot

# fig = px.violin(weighted_tpc,
#                 x='dataset',
#                 y='tpc',
#                 color='dataset',
#                 title="Corpus-wise distribution over line of fifths (tonal pitch classes)",
#                 box=True,
#                 labels=dict(
#                     dataset='',
#                     tpc='distribution of tonal pitch classes by duration'
#                 ),
#                 category_orders=dict(dataset=chronological_corpus_names),
#                 color_discrete_map=corpus_name_colors,
#                 width=1000,
#                 height=600,
#                )
# fig.update_traces(spanmode='hard') # do not extend beyond outliers
# fig.update_layout(**utils.STD_LAYOUT,
#                  showlegend=False)
# fig.update_yaxes(
#     tickmode= 'array',
#     tickvals= [-12, -9, -6, -3, 0, 3, 6, 9, 12, 15, 18],
#     ticktext = ["Dbb", "Bbb", "Gb", "Eb", "C", "A", "F#", "D#", "B#", "G##", "E##"],
#     zerolinecolor='grey',
#     zeroline=True
# )
# fig.update_xaxes(tickangle=45)
# save_figure_as(fig, "pitch_class_distributions_corpuswise_violins")
# fig.show()

(all_notes)

			mc	mn	quarterbeats	quarterbeats_all_endings	duration_qb	duration	mc_onset	mn_onset	timesig	staff	voice	chord_id	gracenote	midi	name	nominal_duration	octave	scalar	tied	tremolo	tpc_name	tpc	corpus_name
corpus	piece	i
jc_bach_sonatas	wa01op05no1a_Allegretto	0	1	0	0	0	0.375	3/32	0	3/8	2/4	1	1	0	<NA>	74	D5	1/16	5	3/2	<NA>	<NA>	D	2	JC Bach Sonatas
		1	1	0	3/8	3/8	0.125	1/32	3/32	15/32	2/4	1	1	1	<NA>	75	Eb5	1/32	5	1	<NA>	<NA>	Eb	-3	JC Bach Sonatas
		2	2	1	1/2	1/2	1.000	1/4	0	0	2/4	1	2	7	<NA>	74	D5	1/4	5	1	<NA>	<NA>	D	2	JC Bach Sonatas
		3	2	1	1/2	1/2	1.000	1/4	0	0	2/4	1	1	2	<NA>	77	F5	1/4	5	1	<NA>	<NA>	F	-1	JC Bach Sonatas
		4	2	1	3/4	3/4	0.250	1/16	1/16	1/16	2/4	2	1	8	<NA>	58	Bb3	1/16	3	1	<NA>	<NA>	Bb	-2	JC Bach Sonatas
	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
	wa12op17no6c_Prestissimo	1769	107	105	1251/2	1251/2	0.500	1/8	1/4	1/4	12/8	2	1	1707	<NA>	41	F2	1/8	2	1	<NA>	<NA>	F	-1	JC Bach Sonatas
		1770	107	105	626	626	0.500	1/8	3/8	3/8	12/8	2	1	1708	<NA>	46	Bb2	1/8	2	1	<NA>	<NA>	Bb	-2	JC Bach Sonatas
		1771	107	105	1253/2	1253/2	0.500	1/8	1/2	1/2	12/8	2	1	1709	<NA>	41	F2	1/8	2	1	<NA>	<NA>	F	-1	JC Bach Sonatas
		1772	107	105	627	627	0.500	1/8	5/8	5/8	12/8	2	1	1710	<NA>	38	D2	1/8	2	1	<NA>	<NA>	D	2	JC Bach Sonatas
		1773	107	105	1255/2	1255/2	0.500	1/8	3/4	3/4	12/8	2	1	1711	<NA>	34	Bb1	1/8	1	1	<NA>	<NA>	Bb	-2	JC Bach Sonatas

38003 rows × 23 columns

width = 1400
height = 800

weighted_pitch_values = pd.concat(
    [
        weighted_midi.rename(columns={"midi": "value"}),
        weighted_tpc.rename(columns={"tpc": "value"}),
    ],
    keys=["MIDI pitch", "Tonal pitch class"],
    names=["distribution"],
).reset_index(level=[0, 1])

fig = plotting.make_violin_plot(
    weighted_pitch_values,
    x_col="dataset",
    y_col="value",
    color="dataset",
    facet_row="distribution",
    box=True,
    labels=dict(dataset="", tpc="distribution of tonal pitch classes by duration"),
    category_orders=dict(dataset=chronological_corpus_names),
    # color_discrete_map=corpus_name_colors,
    color_discrete_sequence=px.colors.qualitative.Dark24,
    traces_settings=dict(
        spanmode="hard",
        width=1,
        # scalemode='width'
    ),
    layout=dict(
        showlegend=False,
        margin=dict(
            t=0,
            b=0,
            l=0,
            r=0,
        ),
    ),
    x_axis=dict(
        # tickangle=45,
        tickfont_size=15
    ),
    y_axis=dict(
        tickmode="array",
        tickvals=[-12, -9, -6, -3, 0, 3, 6, 9, 12, 15, 24, 36, 48, 60, 72, 84, 96],
        ticktext=[
            "Dbb",
            "Bbb",
            "Gb",
            "Eb",
            "C",
            "A",
            "F#",
            "D#",
            "B#",
            "G##",
            "C1",
            "C2",
            "C3",
            "C4",
            "C5",
            "C6",
            "C7",
        ],
        zerolinecolor="grey",
        zeroline=True,
    ),
    width=width,
    height=height,
)
utils.realign_subplot_axes(fig, y_axes=dict(title_text=""))
save_figure_as(fig, "notes_violin", width=width, height=height)
fig

fig = plotting.make_box_plot(
    weighted_pitch_values,
    x_col="dataset",
    y_col="value",
    color="dataset",
    facet_row="distribution",
    # box=True,
    labels=dict(dataset="", tpc="distribution of tonal pitch classes by duration"),
    category_orders=dict(dataset=chronological_corpus_names),
    # color_discrete_map=corpus_name_colors,
    color_discrete_sequence=px.colors.qualitative.Light24,
    # traces_settings=dict(spanmode='hard'),
    layout=dict(showlegend=False, margin=dict(t=0)),
    x_axis=dict(tickangle=45, tickfont_size=15),
    y_axis=dict(
        tickmode="array",
        tickvals=[-12, -9, -6, -3, 0, 3, 6, 9, 12, 15, 24, 36, 48, 60, 72, 84, 96],
        ticktext=[
            "Dbb",
            "Bbb",
            "Gb",
            "Eb",
            "C",
            "A",
            "F#",
            "D#",
            "B#",
            "G##",
            "C1",
            "C2",
            "C3",
            "C4",
            "C5",
            "C6",
            "C7",
        ],
        zerolinecolor="grey",
        zeroline=True,
    ),
    width=width,
    height=height,
)
utils.realign_subplot_axes(fig, y_axes=True)
save_figure_as(fig, "notes_box", width=width, height=height)
fig

As bar plots

bar_data = all_notes.groupby("tpc").duration_qb.sum().reset_index()
x_values = list(range(bar_data.tpc.min(), bar_data.tpc.max() + 1))
x_names = ms3.fifths2name(x_values)
fig = px.bar(
    bar_data,
    x="tpc",
    y="duration_qb",
    labels=dict(tpc="Named pitch class", duration_qb="Duration in quarter notes"),
    color_discrete_sequence=utils.CORPUS_COLOR_SCALE,
    width=1000,
    height=300,
)
fig.update_layout(**utils.STD_LAYOUT)
fig.update_xaxes(
    zerolinecolor="grey",
    tickmode="array",
    tickvals=x_values,
    ticktext=x_names,
    dtick=1,
    ticks="outside",
    tickcolor="black",
    minor=dict(dtick=6, gridcolor="grey", showgrid=True),
)
save_figure_as(fig, "pitch_class_distribution_absolute_bars")
fig.show()

scatter_data = all_notes.groupby(["corpus_name", "tpc"]).duration_qb.sum().reset_index()
fig = px.bar(
    scatter_data,
    x="tpc",
    y="duration_qb",
    color="corpus_name",
    labels=dict(
        duration_qb="duration",
        tpc="named pitch class",
    ),
    category_orders=dict(dataset=chronological_corpus_names),
    color_discrete_map=corpus_name_colors,
    width=1000,
    height=500,
)
fig.update_layout(**utils.STD_LAYOUT)
fig.update_xaxes(
    zerolinecolor="grey",
    tickmode="array",
    tickvals=x_values,
    ticktext=x_names,
    dtick=1,
    ticks="outside",
    tickcolor="black",
    minor=dict(dtick=6, gridcolor="grey", showgrid=True),
)
save_figure_as(fig, "pitch_class_distribution_corpuswise_absolute_bars")
fig.show()

As scatter plots

fig = px.scatter(
    scatter_data,
    x="tpc",
    y="duration_qb",
    color="corpus_name",
    labels=dict(
        duration_qb="duration",
        tpc="named pitch class",
    ),
    category_orders=dict(dataset=chronological_corpus_names),
    color_discrete_map=corpus_name_colors,
    facet_col="corpus_name",
    facet_col_wrap=3,
    facet_col_spacing=0.03,
    width=1000,
    height=1000,
)
fig.update_traces(mode="lines+markers")
fig.for_each_annotation(lambda a: a.update(text=a.text.split("=")[-1]))
fig.update_layout(**utils.STD_LAYOUT, showlegend=False)
fig.update_xaxes(
    zerolinecolor="grey",
    tickmode="array",
    tickvals=[-12, -6, 0, 6, 12, 18],
    ticktext=["Dbb", "Gb", "C", "F#", "B#", "E##"],
    visible=True,
)
fig.update_yaxes(zeroline=False, matches=None, showticklabels=True)
save_figure_as(fig, "pitch_class_distribution_corpuswise_scatter")
fig.show()

no_accidental = bar_data[bar_data.tpc.between(-1, 5)].duration_qb.sum()
with_accidental = bar_data[~bar_data.tpc.between(-1, 5)].duration_qb.sum()

entire = no_accidental + with_accidental
(
    f"Fraction of note duration without accidental of the entire durations: {no_accidental} / {entire} = "
    f"{no_accidental / entire}"
)

'Fraction of note duration without accidental of the entire durations: 11968.083333333332 / 18256.625 = 0.655547415435949'

Notes and staves

print("Distribution of notes over staves:")
utils.value_count_df(all_notes.staff)

Distribution of notes over staves:

	counts	%
staff
1	21641	56.95
2	16362	43.05