Overview

This notebook gives a general overview of the features included in the dataset.

Show imports Hide imports

%load_ext autoreload
%autoreload 2
import os

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

import utils

RESULTS_PATH = os.path.abspath(os.path.join(utils.OUTPUT_FOLDER, "overview"))
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

D = utils.get_dataset("corelli", corpus_release="v2.7")
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("Arcangelo Corelli – Trio Sonatas version v2.7")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

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

Arcangelo Corelli – Trio Sonatas version v2.7
Datapackage 'corelli' @ v2.7
dimcat version 3.4.0

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

filtered_D = filters.HasHarmonyLabelsFilter(keep_values=[True]).process(D)
all_metadata = filtered_D.get_metadata()
assert len(all_metadata) > 0, "No pieces selected for analysis."
all_metadata

		TimeSig	KeySig	last_mc	last_mn	length_qb	last_mc_unfolded	last_mn_unfolded	length_qb_unfolded	volta_mcs	all_notes_qb	...	electronic encoder	originalFormat	staff_1_ambitus	staff_1_instrument	staff_2_ambitus	staff_2_instrument	staff_3_ambitus	staff_3_instrument	staff_4_ambitus	staff_4_instrument
corpus	piece
corelli	op01n01a	{1: '4/4'}	{1: -1}	14	14	56.0	14	14	56.0	()	224.00	...	Frances Bennion & Steven Rasmussen	xml	74-84 (D5-C6)	StringInstrument	67-81 (G4-A5)	StringInstrument	36-60 (C2-C4)	StringInstrument	36-60 (C2-C4)	Keyboard
	op01n01b	{1: '4/4'}	{1: -1}	38	38	152.0	38	38	152.0	()	559.75	...	Frances Bennion & Steven Rasmussen	xml	60-82 (C4-Bb5)	StringInstrument	62-86 (D4-D6)	StringInstrument	41-65 (F2-F4)	StringInstrument	38-62 (D2-D4)	Keyboard
	op01n01c	{1: '3/4'}	{1: -1}	37	37	111.0	37	37	111.0	()	430.00	...	Frances Bennion & Steven Rasmussen	xml	64-86 (E4-D6)	StringInstrument	62-84 (D4-C6)	StringInstrument	36-60 (C2-C4)	StringInstrument	36-60 (C2-C4)	Keyboard
	op01n01d	{1: '3/4'}	{1: -1}	98	98	294.0	196	196	588.0	()	963.00	...	Frances Bennion & Steven Rasmussen	xml	64-86 (E4-D6)	StringInstrument	65-86 (F4-D6)	StringInstrument	36-64 (C2-E4)	StringInstrument	36-81 (C2-A5)	Keyboard
	op01n02a	{1: '4/4'}	{1: 1}	19	19	76.0	19	19	76.0	()	288.00	...	Frances Bennion & Steven Rasmussen	xml	67-83 (G4-B5)	StringInstrument	59-83 (B3-B5)	StringInstrument	38-64 (D2-E4)	StringInstrument	38-64 (D2-E4)	Keyboard
	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
	op04n11b	{1: '3/4'}	{1: -2}	74	73	219.0	148	146	438.0	()	754.00	...	<NA>	xml	62-84 (D4-C6)	<NA>	62-80 (D4-Ab5)	<NA>	39-63 (Eb2-Eb4)	<NA>	39-63 (Eb2-Eb4)	<NA>
	op04n11c	{1: '4/4'}	{1: -2}	36	36	144.0	72	72	288.0	()	559.50	...	<NA>	xml	60-84 (C4-C6)	<NA>	59-84 (B3-C6)	<NA>	38-63 (D2-Eb4)	<NA>	38-63 (D2-Eb4)	<NA>
	op04n12a	{1: '3/4'}	{1: 2}	36	35	105.0	36	35	105.0	()	397.00	...	<NA>	xml	66-83 (F#4-B5)	<NA>	64-79 (E4-G5)	<NA>	42-66 (F#2-F#4)	<NA>	42-66 (F#2-F#4)	<NA>
	op04n12b	{1: '2/2'}	{1: 2}	40	39	156.0	40	39	156.0	()	562.50	...	<NA>	xml	57-83 (A3-B5)	<NA>	61-81 (C#4-A5)	<NA>	42-64 (F#2-E4)	<NA>	42-64 (F#2-E4)	<NA>
	op04n12c	{1: '12/8'}	{1: 2}	19	19	114.0	38	38	228.0	()	332.50	...	<NA>	xml	64-83 (E4-B5)	<NA>	62-79 (D4-G5)	<NA>	46-64 (A#2-E4)	<NA>	46-64 (A#2-E4)	<NA>

149 rows × 56 columns

mean_composition_years = utils.corpus_mean_composition_years(all_metadata)
chronological_order = mean_composition_years.index.to_list()
corpus_colors = dict(zip(chronological_order, utils.CORPUS_COLOR_SCALE))
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()
}

mean_composition_years

corpus
corelli    1688.100671
Name: mean_composition_year, dtype: float64

Composition dates

This section relies on the dataset’s metadata.

valid_composed_start = pd.to_numeric(all_metadata.composed_start, errors="coerce")
valid_composed_end = pd.to_numeric(all_metadata.composed_end, errors="coerce")
print(
    f"Composition dates range from {int(valid_composed_start.min())} {valid_composed_start.idxmin()} "
    f"to {int(valid_composed_end.max())} {valid_composed_end.idxmax()}."
)

Composition dates range from 1681 ('corelli', 'op01n01a') to 1694 ('corelli', 'op04n01a').

Mean composition years per corpus

def make_summary(metadata_df):
    piece_is_annotated = metadata_df.label_count > 0
    return metadata_df[piece_is_annotated].copy()

Show source Hide source

summary = make_summary(all_metadata)
bar_data = pd.concat(
    [
        mean_composition_years.rename("year"),
        summary.groupby(level="corpus").size().rename("pieces"),
    ],
    axis=1,
).reset_index()

N = len(summary)
fig = px.bar(
    bar_data,
    x="year",
    y="pieces",
    color="corpus",
    color_discrete_map=corpus_colors,
    title=f"Temporal coverage of the {N} annotated pieces in the Distant Listening Corpus",
)
fig.update_traces(width=5)
fig.update_layout(**utils.STD_LAYOUT)
fig.update_traces(width=5)
save_figure_as(fig, "pieces_timeline_bars")
fig.show()

summary

		TimeSig	KeySig	last_mc	last_mn	length_qb	last_mc_unfolded	last_mn_unfolded	length_qb_unfolded	volta_mcs	all_notes_qb	...	electronic encoder	originalFormat	staff_1_ambitus	staff_1_instrument	staff_2_ambitus	staff_2_instrument	staff_3_ambitus	staff_3_instrument	staff_4_ambitus	staff_4_instrument
corpus	piece
corelli	op01n01a	{1: '4/4'}	{1: -1}	14	14	56.0	14	14	56.0	()	224.00	...	Frances Bennion & Steven Rasmussen	xml	74-84 (D5-C6)	StringInstrument	67-81 (G4-A5)	StringInstrument	36-60 (C2-C4)	StringInstrument	36-60 (C2-C4)	Keyboard
	op01n01b	{1: '4/4'}	{1: -1}	38	38	152.0	38	38	152.0	()	559.75	...	Frances Bennion & Steven Rasmussen	xml	60-82 (C4-Bb5)	StringInstrument	62-86 (D4-D6)	StringInstrument	41-65 (F2-F4)	StringInstrument	38-62 (D2-D4)	Keyboard
	op01n01c	{1: '3/4'}	{1: -1}	37	37	111.0	37	37	111.0	()	430.00	...	Frances Bennion & Steven Rasmussen	xml	64-86 (E4-D6)	StringInstrument	62-84 (D4-C6)	StringInstrument	36-60 (C2-C4)	StringInstrument	36-60 (C2-C4)	Keyboard
	op01n01d	{1: '3/4'}	{1: -1}	98	98	294.0	196	196	588.0	()	963.00	...	Frances Bennion & Steven Rasmussen	xml	64-86 (E4-D6)	StringInstrument	65-86 (F4-D6)	StringInstrument	36-64 (C2-E4)	StringInstrument	36-81 (C2-A5)	Keyboard
	op01n02a	{1: '4/4'}	{1: 1}	19	19	76.0	19	19	76.0	()	288.00	...	Frances Bennion & Steven Rasmussen	xml	67-83 (G4-B5)	StringInstrument	59-83 (B3-B5)	StringInstrument	38-64 (D2-E4)	StringInstrument	38-64 (D2-E4)	Keyboard
	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
	op04n11b	{1: '3/4'}	{1: -2}	74	73	219.0	148	146	438.0	()	754.00	...	<NA>	xml	62-84 (D4-C6)	<NA>	62-80 (D4-Ab5)	<NA>	39-63 (Eb2-Eb4)	<NA>	39-63 (Eb2-Eb4)	<NA>
	op04n11c	{1: '4/4'}	{1: -2}	36	36	144.0	72	72	288.0	()	559.50	...	<NA>	xml	60-84 (C4-C6)	<NA>	59-84 (B3-C6)	<NA>	38-63 (D2-Eb4)	<NA>	38-63 (D2-Eb4)	<NA>
	op04n12a	{1: '3/4'}	{1: 2}	36	35	105.0	36	35	105.0	()	397.00	...	<NA>	xml	66-83 (F#4-B5)	<NA>	64-79 (E4-G5)	<NA>	42-66 (F#2-F#4)	<NA>	42-66 (F#2-F#4)	<NA>
	op04n12b	{1: '2/2'}	{1: 2}	40	39	156.0	40	39	156.0	()	562.50	...	<NA>	xml	57-83 (A3-B5)	<NA>	61-81 (C#4-A5)	<NA>	42-64 (F#2-E4)	<NA>	42-64 (F#2-E4)	<NA>
	op04n12c	{1: '12/8'}	{1: 2}	19	19	114.0	38	38	228.0	()	332.50	...	<NA>	xml	64-83 (E4-B5)	<NA>	62-79 (D4-G5)	<NA>	46-64 (A#2-E4)	<NA>	46-64 (A#2-E4)	<NA>

149 rows × 56 columns

Composition years histogram

Show source Hide source

hist_data = summary.reset_index()
hist_data.corpus = hist_data.corpus.map(corpus_names)
fig = px.histogram(
    hist_data,
    x="composed_end",
    color="corpus",
    labels=dict(
        composed_end="decade",
        count="pieces",
    ),
    color_discrete_map=corpus_name_colors,
    title=f"Temporal coverage of the {N} annotated pieces in the Distant Listening Corpus",
)
fig.update_traces(xbins=dict(size=10))
fig.update_layout(**utils.STD_LAYOUT)
fig.update_legends(font=dict(size=16))
save_figure_as(fig, "pieces_timeline_histogram", height=1250)
fig.show()

Dimensions

Overview

def make_overview_table(groupby, group_name="pieces"):
    n_groups = groupby.size().rename(group_name)
    absolute_numbers = dict(
        measures=groupby.last_mn.sum(),
        length=groupby.length_qb.sum(),
        notes=groupby.n_onsets.sum(),
        labels=groupby.label_count.sum(),
    )
    absolute = pd.DataFrame.from_dict(absolute_numbers)
    absolute = pd.concat([n_groups, absolute], axis=1)
    sum_row = pd.DataFrame(absolute.sum(), columns=["sum"]).T
    absolute = pd.concat([absolute, sum_row])
    return absolute


absolute = make_overview_table(summary.groupby("workTitle"))
# print(absolute.astype(int).to_markdown())
absolute.astype(int)

	pieces	measures	length	notes	labels
Sonata da camera	50	1330	5155	19017	3967
Sonata da chiesa	99	3447	12990	49126	10347
sum	149	4777	18145	68143	14314

def summarize_dataset(D):
    all_metadata = D.get_metadata()
    summary = make_summary(all_metadata)
    return make_overview_table(summary.groupby(level=0))


corpus_summary = summarize_dataset(D)
print(corpus_summary.astype(int).to_markdown())

|         |   pieces |   measures |   length |   notes |   labels |
|:--------|---------:|-----------:|---------:|--------:|---------:|
| corelli |      149 |       4777 |    18145 |   68143 |    14314 |
| sum     |      149 |       4777 |    18145 |   68143 |    14314 |

Measures

all_measures = D.get_feature("measures")
print(
    f"{len(all_measures.index)} measures over {len(all_measures.groupby(level=[0,1]))} files."
)
all_measures.head()

4790 measures over 149 files.

			mc	mn	quarterbeats	duration_qb	keysig	timesig	act_dur	mc_offset	numbering_offset	dont_count	barline	breaks	repeats	next
corpus	piece	i
corelli	op01n01a	0	1	1	0	4.0	-1	4/4	1	0	<NA>	<NA>	<NA>	<NA>	firstMeasure	(2,)
		1	2	2	4	4.0	-1	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(3,)
		2	3	3	8	4.0	-1	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(4,)
		3	4	4	12	4.0	-1	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(5,)
		4	5	5	16	4.0	-1	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(6,)

all_measures.get_default_analysis().plot_grouped()

Harmony labels

All symbols, independent of the local key (the mode of which changes their semantics).

try:
    all_annotations = D.get_feature("harmonylabels").df
except Exception:
    all_annotations = pd.DataFrame()
n_annotations = len(all_annotations.index)
includes_annotations = n_annotations > 0
if includes_annotations:
    display(all_annotations.head())
    print(f"Concatenated annotation tables contains {all_annotations.shape[0]} rows.")
    no_chord = all_annotations.root.isna()
    if no_chord.sum() > 0:
        print(
            f"{no_chord.sum()} of them are not chords. Their values are:"
            f" {all_annotations.label[no_chord].value_counts(dropna=False).to_dict()}"
        )
    all_chords = all_annotations[~no_chord].copy()
    print(
        f"Dataset contains {all_chords.shape[0]} tokens and {len(all_chords.chord.unique())} types over "
        f"{len(all_chords.groupby(level=[0,1]))} documents."
    )
    all_annotations["corpus_name"] = all_annotations.index.get_level_values(0).map(
        utils.get_corpus_display_name
    )
    all_chords["corpus_name"] = all_chords.index.get_level_values(0).map(
        utils.get_corpus_display_name
    )
else:
    print("Dataset contains no annotations.")

			mc	mn	quarterbeats	quarterbeats_all_endings	duration_qb	mc_onset	mn_onset	timesig	staff	voice	...	numeral_or_applied_to_numeral	intervals_over_bass	intervals_over_root	scale_degrees	scale_degrees_and_mode	scale_degrees_major	scale_degrees_minor	globalkey	localkey	chord
corpus	piece	i
corelli	op01n01a	0	1	1	0	0	1.0	0	0	4/4	4	1	...	I	(M3, P5)	(M3, P5)	(1, 3, 5)	(1, 3, 5), major	(1, 3, 5)	(1, #3, 5)	F	I	I
		1	1	1	1	1	1.0	1/4	1/4	4/4	4	1	...	vii	(m3, M6)	(m3, d5)	(2, 4, 7)	(2, 4, 7), major	(2, 4, 7)	(2, 4, #7)	F	I	viio6
		2	1	1	2	2	2.0	1/2	1/2	4/4	4	1	...	I	(m3, m6)	(M3, P5)	(3, 5, 1)	(3, 5, 1), major	(3, 5, 1)	(#3, 5, 1)	F	I	I6
		3	2	2	4	4	0.5	0	0	4/4	4	1	...	IV	(M3, P5)	(M3, P5)	(4, 6, 1)	(4, 6, 1), major	(4, 6, 1)	(4, #6, 1)	F	I	IV
		4	2	2	9/2	9/2	0.5	1/8	1/8	4/4	4	1	...	I	(M3, P5)	(M3, P5)	(1, 3, 5)	(1, 3, 5), major	(1, 3, 5)	(1, #3, 5)	F	I	I

5 rows × 52 columns

Concatenated annotation tables contains 14043 rows.
Dataset contains 14043 tokens and 490 types over 149 documents.