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("pergolesi_stabat_mater", corpus_release="v3.2")
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("Giovanni Battista Pergolesi – Stabat Mater (1736) version v3.2")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

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

Giovanni Battista Pergolesi – Stabat Mater (1736) version v3.2
Datapackage 'pergolesi_stabat_mater' @ v3.2
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'pergolesi_stabat_mater': ["'pergolesi_stabat_mater.measures' "
                                                    '(MuseScoreFacetName.MuseScoreMeasures)',
                                                    "'pergolesi_stabat_mater.notes' "
                                                    '(MuseScoreFacetName.MuseScoreNotes)',
                                                    "'pergolesi_stabat_mater.expanded' "
                                                    '(MuseScoreFacetName.MuseScoreHarmonies)',
                                                    "'pergolesi_stabat_mater.chords' "
                                                    '(MuseScoreFacetName.MuseScoreChords)',
                                                    "'pergolesi_stabat_mater.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	all_notes_qb	n_onsets	...	pdf	wdt:P86	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
pergolesi_stabat_mater	01. Stabat Mater dolorosa	{1: '4/4'}	{1: -4}	47	47	188.0	47	47	188.0	882.50	1068	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	64-79 (E4-G5)	Soprano	60-73 (C4-Db5)	Alto	56-85 (Ab3-Db6)	Piano	32-70 (Ab1-Bb4)	Piano
	02. Cujus animam gementem	{1: '3/8'}	{1: -3}	108	108	162.0	108	108	162.0	762.00	1036	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	65-80 (F4-Ab5)	Soprano	55-84 (G3-C6)	Piano	36-65 (C2-F4)	Piano	<NA>	<NA>
	03. O quam tristis et afflicta	{1: '4/4'}	{1: -2}	26	26	104.0	26	26	104.0	533.00	588	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	67-82 (G4-Bb5)	Soprano	58-75 (Bb3-Eb5)	Alto	55-86 (G3-D6)	Piano	37-64 (C#2-E4)	Piano
	04. Quae moerebat et dolebat	{1: '2/4'}	{1: -3}	103	103	206.0	103	103	206.0	737.25	1133	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	62-77 (D4-F5)	Alto	53-84 (F3-C6)	Piano	34-65 (Bb1-F4)	Piano	<NA>	<NA>
	05. Quis est homo qui non fleret	{1: '4/4', 20: '6/8'}	{1: -3}	49	49	166.0	49	49	166.0	851.00	1027	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	63-80 (Eb4-Ab5)	Soprano	60-75 (C4-Eb5)	Alto	55-82 (G3-Bb5)	Piano	31-79 (G1-G5)	Piano
	06. Vidit suum dulcem natum	{1: '4/4'}	{1: -4}	43	43	172.0	43	43	172.0	704.50	926	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	65-80 (F4-Ab5)	Soprano	56-82 (Ab3-Bb5)	Piano	29-62 (F1-D4)	Piano	<NA>	<NA>
	07. Eja, Mater fons amois	{1: '3/8'}	{1: -3}	94	94	141.0	94	94	141.0	597.00	994	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	59-75 (B3-Eb5)	Alto	55-84 (G3-C6)	Piano	42-68 (F#2-Ab4)	Piano	<NA>	<NA>

7 rows × 59 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
pergolesi_stabat_mater    1736.0
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 1736 ('pergolesi_stabat_mater', '01. Stabat Mater dolorosa') to 1736 ('pergolesi_stabat_mater', '01. Stabat Mater dolorosa').

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	all_notes_qb	n_onsets	...	pdf	wdt:P86	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
pergolesi_stabat_mater	01. Stabat Mater dolorosa	{1: '4/4'}	{1: -4}	47	47	188.0	47	47	188.0	882.50	1068	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	64-79 (E4-G5)	Soprano	60-73 (C4-Db5)	Alto	56-85 (Ab3-Db6)	Piano	32-70 (Ab1-Bb4)	Piano
	02. Cujus animam gementem	{1: '3/8'}	{1: -3}	108	108	162.0	108	108	162.0	762.00	1036	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	65-80 (F4-Ab5)	Soprano	55-84 (G3-C6)	Piano	36-65 (C2-F4)	Piano	<NA>	<NA>
	03. O quam tristis et afflicta	{1: '4/4'}	{1: -2}	26	26	104.0	26	26	104.0	533.00	588	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	67-82 (G4-Bb5)	Soprano	58-75 (Bb3-Eb5)	Alto	55-86 (G3-D6)	Piano	37-64 (C#2-E4)	Piano
	04. Quae moerebat et dolebat	{1: '2/4'}	{1: -3}	103	103	206.0	103	103	206.0	737.25	1133	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	62-77 (D4-F5)	Alto	53-84 (F3-C6)	Piano	34-65 (Bb1-F4)	Piano	<NA>	<NA>
	05. Quis est homo qui non fleret	{1: '4/4', 20: '6/8'}	{1: -3}	49	49	166.0	49	49	166.0	851.00	1027	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	63-80 (Eb4-Ab5)	Soprano	60-75 (C4-Eb5)	Alto	55-82 (G3-Bb5)	Piano	31-79 (G1-G5)	Piano
	06. Vidit suum dulcem natum	{1: '4/4'}	{1: -4}	43	43	172.0	43	43	172.0	704.50	926	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	65-80 (F4-Ab5)	Soprano	56-82 (Ab3-Bb5)	Piano	29-62 (F1-D4)	Piano	<NA>	<NA>
	07. Eja, Mater fons amois	{1: '3/8'}	{1: -3}	94	94	141.0	94	94	141.0	597.00	994	...	https://imslp.org/wiki/Special:ReverseLookup/1...	https://www.wikidata.org/wiki/Q185312	59-75 (B3-Eb5)	Alto	55-84 (G3-C6)	Piano	42-68 (F#2-Ab4)	Piano	<NA>	<NA>

7 rows × 59 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
Stabat Mater	7	470	1139	6772	1189
sum	7	470	1139	6772	1189

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 |
|:-----------------------|---------:|-----------:|---------:|--------:|---------:|
| pergolesi_stabat_mater |        7 |        470 |     1139 |    6772 |     1189 |
| sum                    |        7 |        470 |     1139 |    6772 |     1189 |

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()

798 measures over 12 files.

			mc	mn	quarterbeats	duration_qb	keysig	timesig	act_dur	mc_offset	numbering_offset	dont_count	barline	breaks	repeats	next
corpus	piece	i
pergolesi_stabat_mater	01. Stabat Mater dolorosa	0	1	1	0	4.0	-4	4/4	1	0	<NA>	<NA>	<NA>	<NA>	firstMeasure	(2,)
		1	2	2	4	4.0	-4	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(3,)
		2	3	3	8	4.0	-4	4/4	1	0	<NA>	<NA>	<NA>	<NA>	<NA>	(4,)
		3	4	4	12	4.0	-4	4/4	1	0	<NA>	<NA>	<NA>	line	<NA>	(5,)
		4	5	5	16	4.0	-4	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
pergolesi_stabat_mater	01. Stabat Mater dolorosa	0	1	1	0	0	1.0	0	0	4/4	4	1	...	i	(m3, P5)	(m3, P5)	(1, 3, 5)	(1, 3, 5), minor	(1, b3, 5)	(1, 3, 5)	f	i	i
		1	1	1	1	1	1.0	1/4	1/4	4/4	4	1	...	i	(M3, M6)	(m3, P5)	(3, 5, 1)	(3, 5, 1), minor	(b3, 5, 1)	(3, 5, 1)	f	i	i6
		2	1	1	2	2	1.0	1/2	1/2	4/4	4	1	...	V	(P4, P5)	(P4, P5)	(5, 1, 2)	(5, 1, 2), minor	(5, 1, 2)	(5, 1, 2)	f	i	V(4)
		3	1	1	3	3	1.0	3/4	3/4	4/4	4	1	...	V	(m3, m6)	(M3, P5)	(#7, 2, 5)	(#7, 2, 5), minor	(7, 2, 5)	(#7, 2, 5)	f	i	V6
		4	2	2	4	4	1.0	0	0	4/4	4	1	...	i	(m3, P5)	(m3, P5)	(1, 3, 5)	(1, 3, 5), minor	(1, b3, 5)	(1, 3, 5)	f	i	i(9)

5 rows × 51 columns

Concatenated annotation tables contains 1175 rows.
Dataset contains 1175 tokens and 141 types over 7 documents.