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("frescobaldi_fiori_musicali", 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("Girolamo Frescobaldi (1583-1643) – Fiori Musicali, op. 12 (1635) version v2.4")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

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

Girolamo Frescobaldi (1583-1643) – Fiori Musicali, op. 12 (1635) version v2.4
Datapackage 'frescobaldi_fiori_musicali' @ v2.4
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'frescobaldi_fiori_musicali': ["'frescobaldi_fiori_musicali.measures' "
                                                        '(MuseScoreFacetName.MuseScoreMeasures)',
                                                        "'frescobaldi_fiori_musicali.notes' "
                                                        '(MuseScoreFacetName.MuseScoreNotes)',
                                                        "'frescobaldi_fiori_musicali.expanded' "
                                                        '(MuseScoreFacetName.MuseScoreHarmonies)',
                                                        "'frescobaldi_fiori_musicali.chords' "
                                                        '(MuseScoreFacetName.MuseScoreChords)',
                                                        "'frescobaldi_fiori_musicali.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	all_notes_qb	n_onsets	n_onset_positions	guitar_chord_count	form_label_count	label_count	annotated_key	composed_start	composed_end	composed_source	composer
corpus
frescobaldi_fiori_musicali	12.01_Toccata_avanti_la_Messa_della_Domenica	{1: '4/2'}	{1: 0}	8	8	64.0	8	8	64.0	244.0	200	121	0	0	57	d	1635	1635	Bärenreiter Verlag (https://imslp.org/wiki/Spe...	Girolamo Frescobaldi

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()

19370 notes over 47 files.

			mc	mn	quarterbeats	quarterbeats_all_endings	duration_qb	duration	mc_onset	mn_onset	timesig	staff	voice	chord_id	midi	name	nominal_duration	octave	scalar	tied	tpc_name	tpc
corpus	piece	i
frescobaldi_fiori_musicali	12.01_Toccata_avanti_la_Messa_della_Domenica	0	1	1	0	0	6.0	3/2	0	0	4/2	2	2	17	50	D3	1	3	3/2	<NA>	D	2
		1	1	1	0	0	2.0	1/2	0	0	4/2	2	1	11	65	F4	1/2	4	1	<NA>	F	-1
		2	1	1	0	0	2.0	1/2	0	0	4/2	1	2	6	69	A4	1/2	4	1	<NA>	A	3
		3	1	1	0	0	2.0	1/2	0	0	4/2	1	1	0	74	D5	1/2	5	1	<NA>	D	2
		4	1	1	2	2	1.0	1/4	1/2	1/2	4/2	2	1	12	62	D4	1/4	4	1	<NA>	D	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	Frescobaldi Fiori Musicali	33
1	Frescobaldi Fiori Musicali	33
2	Frescobaldi Fiori Musicali	33
3	Frescobaldi Fiori Musicali	33
4	Frescobaldi Fiori Musicali	33
...	...	...
63951	Frescobaldi Fiori Musicali	78
63952	Frescobaldi Fiori Musicali	78
63953	Frescobaldi Fiori Musicali	78
63954	Frescobaldi Fiori Musicali	78
63955	Frescobaldi Fiori Musicali	79

63956 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	Frescobaldi Fiori Musicali	-4
1	Frescobaldi Fiori Musicali	-4
2	Frescobaldi Fiori Musicali	-3
3	Frescobaldi Fiori Musicali	-3
4	Frescobaldi Fiori Musicali	-3
...	...	...
5809	Frescobaldi Fiori Musicali	8
5810	Frescobaldi Fiori Musicali	8
5811	Frescobaldi Fiori Musicali	8
5812	Frescobaldi Fiori Musicali	8
5813	Frescobaldi Fiori Musicali	9

5814 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	midi	name	nominal_duration	octave	scalar	tied	tpc_name	tpc	corpus_name
corpus	piece	i
frescobaldi_fiori_musicali	12.01_Toccata_avanti_la_Messa_della_Domenica	0	1	1	0	0	6.0	3/2	0	0	4/2	2	2	17	50	D3	1	3	3/2	<NA>	D	2	Frescobaldi Fiori Musicali
		1	1	1	0	0	2.0	1/2	0	0	4/2	2	1	11	65	F4	1/2	4	1	<NA>	F	-1	Frescobaldi Fiori Musicali
		2	1	1	0	0	2.0	1/2	0	0	4/2	1	2	6	69	A4	1/2	4	1	<NA>	A	3	Frescobaldi Fiori Musicali
		3	1	1	0	0	2.0	1/2	0	0	4/2	1	1	0	74	D5	1/2	5	1	<NA>	D	2	Frescobaldi Fiori Musicali
		4	1	1	2	2	1.0	1/4	1/2	1/2	4/2	2	1	12	62	D4	1/4	4	1	<NA>	D	2	Frescobaldi Fiori Musicali
	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
	12.47_Capriccio_sopra_la_Girolmeta	1322	101	101	587	587	1.0	1/4	5/4	5/4	6/4	1	1	1317	66	F#4	1/4	4	1	<NA>	F#	6	Frescobaldi Fiori Musicali
		1323	102	102	588	588	6.0	3/2	0	0	6/4	2	2	1326	43	G2	1	2	3/2	<NA>	G	1	Frescobaldi Fiori Musicali
		1324	102	102	588	588	6.0	3/2	0	0	6/4	2	1	1325	59	B3	1	3	3/2	<NA>	B	5	Frescobaldi Fiori Musicali
		1325	102	102	588	588	6.0	3/2	0	0	6/4	1	2	1324	62	D4	1	4	3/2	<NA>	D	2	Frescobaldi Fiori Musicali
		1326	102	102	588	588	6.0	3/2	0	0	6/4	1	1	1323	67	G4	1	4	3/2	<NA>	G	1	Frescobaldi Fiori Musicali

19370 rows × 21 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: 28580.416666666668 / 31975.583333333336 = 0.8938200241329973'

Notes and staves

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

Distribution of notes over staves:

	counts	%
staff
1	10442	53.91
2	8928	46.09