Overview#

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

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("peri_euridice", 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("Jacopo Peri – Euridice (1600) version v2.4")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

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

Jacopo Peri – Euridice (1600) version v2.4
Datapackage 'peri_euridice' @ v2.4
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'peri_euridice': ["'peri_euridice.measures' (MuseScoreFacetName.MuseScoreMeasures)",
                                           "'peri_euridice.notes' (MuseScoreFacetName.MuseScoreNotes)",
                                           "'peri_euridice.expanded' (MuseScoreFacetName.MuseScoreHarmonies)",
                                           "'peri_euridice.chords' (MuseScoreFacetName.MuseScoreChords)",
                                           "'peri_euridice.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 ... staff_17_ambitus staff_17_instrument staff_18_ambitus staff_18_instrument staff_19_ambitus staff_19_instrument staff_20_ambitus staff_20_instrument staff_21_ambitus staff_21_instrument
corpus piece
peri_euridice peri_euridice_scene_0 {1: '4/2'} {1: -1} 15 14 120.0 15 14 120.0 220.50 103 ... <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
peri_euridice_scene_1 {1: '4/4', 2: '4/2', 33: '3/4', 36: '6/4', 47:... {1: 0, 19: -1, 39: 0, 59: -2, 65: -1} 121 119 939.0 121 119 939.0 2092.50 1328 ... <NA> Voice <NA> Voice 65-74 (F4-D5) Voice <NA> Voice 41-58 (F2-Bb3) Piano
peri_euridice_scene_2 {1: '2/2', 2: '4/2', 61: '2/2', 62: '6/2', 69:... {1: 0, 34: -1, 43: 0, 92: -1, 112: 0, 128: -1,... 288 288 2332.0 288 288 2332.0 4807.00 2759 ... 61-74 (C#4-D5) Voice 50-62 (D3-D4) Voice 66-75 (F#4-Eb5) Voice <NA> Voice 38-58 (D2-Bb3) Piano
peri_euridice_scene_3 {1: '4/2'} {1: -1, 8: 0, 65: -1, 104: 0, 125: -1} 136 135 1076.0 136 135 1076.0 2461.50 1475 ... <NA> Voice 64-74 (E4-D5) Voice <NA> Voice 41-57 (F2-A3) Piano <NA> <NA>
peri_euridice_scene_4 {1: '4/2'} {1: 0, 14: -1, 56: 0, 102: -1, 194: 0, 225: -1... 306 304 2440.0 306 304 2440.0 4972.75 2657 ... <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
peri_euridice_scene_5 {1: '4/2', 257: '6/2'} {1: 0, 24: -1, 33: 0, 46: -1, 50: 0, 176: -1, ... 261 260 2108.0 261 260 2108.0 4438.00 2687 ... 41-58 (F2-Bb3) Piano <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>

6 rows × 97 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
peri_euridice    1600.0
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 1600 ('peri_euridice', 'peri_euridice_scene_0') to 1600 ('peri_euridice', 'peri_euridice_scene_0').

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()
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 ... staff_17_ambitus staff_17_instrument staff_18_ambitus staff_18_instrument staff_19_ambitus staff_19_instrument staff_20_ambitus staff_20_instrument staff_21_ambitus staff_21_instrument
corpus piece
peri_euridice peri_euridice_scene_0 {1: '4/2'} {1: -1} 15 14 120.0 15 14 120.0 220.50 103 ... <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
peri_euridice_scene_1 {1: '4/4', 2: '4/2', 33: '3/4', 36: '6/4', 47:... {1: 0, 19: -1, 39: 0, 59: -2, 65: -1} 121 119 939.0 121 119 939.0 2092.50 1328 ... <NA> Voice <NA> Voice 65-74 (F4-D5) Voice <NA> Voice 41-58 (F2-Bb3) Piano
peri_euridice_scene_2 {1: '2/2', 2: '4/2', 61: '2/2', 62: '6/2', 69:... {1: 0, 34: -1, 43: 0, 92: -1, 112: 0, 128: -1,... 288 288 2332.0 288 288 2332.0 4807.00 2759 ... 61-74 (C#4-D5) Voice 50-62 (D3-D4) Voice 66-75 (F#4-Eb5) Voice <NA> Voice 38-58 (D2-Bb3) Piano
peri_euridice_scene_3 {1: '4/2'} {1: -1, 8: 0, 65: -1, 104: 0, 125: -1} 136 135 1076.0 136 135 1076.0 2461.50 1475 ... <NA> Voice 64-74 (E4-D5) Voice <NA> Voice 41-57 (F2-A3) Piano <NA> <NA>
peri_euridice_scene_4 {1: '4/2'} {1: 0, 14: -1, 56: 0, 102: -1, 194: 0, 225: -1... 306 304 2440.0 306 304 2440.0 4972.75 2657 ... <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
peri_euridice_scene_5 {1: '4/2', 257: '6/2'} {1: 0, 24: -1, 33: 0, 46: -1, 50: 0, 176: -1, ... 261 260 2108.0 261 260 2108.0 4438.00 2687 ... 41-58 (F2-Bb3) Piano <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>

6 rows × 97 columns

Composition years histogram#

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
Euridice 6 1120 9015 11009 2884
sum 6 1120 9015 11009 2884 
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 |
|:--------------|---------:|-----------:|---------:|--------:|---------:|
| peri_euridice |        6 |       1120 |     9015 |   11009 |     2884 |
| sum           |        6 |       1120 |     9015 |   11009 |     2884 |

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()

1127 measures over 6 files.
mc mn quarterbeats duration_qb keysig timesig act_dur mc_offset numbering_offset dont_count barline breaks repeats next
corpus piece i
peri_euridice peri_euridice_scene_0 0 1 0 0 8.0 -1 4/2 2 0 <NA> 1 <NA> <NA> firstMeasure (2,)
1 2 1 8 8.0 -1 4/2 2 0 <NA> <NA> <NA> <NA> <NA> (3,)
2 3 2 16 8.0 -1 4/2 2 0 <NA> <NA> <NA> <NA> <NA> (4,)
3 4 3 24 8.0 -1 4/2 2 0 <NA> <NA> <NA> <NA> <NA> (5,)
4 5 4 32 8.0 -1 4/2 2 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
peri_euridice peri_euridice_scene_0 0 2 1 8 8 12.0 0 0 4/2 2 1 ... I (M3, P5) (M3, P5) (1, 3, 5) (1, 3, 5), major (1, 3, 5) (1, #3, 5) F I I
1 3 2 20 20 2.0 1 1 4/2 2 1 ... IV (M3, P5) (M3, P5) (4, 6, 1) (4, 6, 1), major (4, 6, 1) (4, #6, 1) F I IV
2 3 2 22 22 2.0 3/2 3/2 4/2 2 1 ... IV (m3, m6) (M3, P5) (6, 1, 4) (6, 1, 4), major (6, 1, 4) (#6, 1, 4) F I IV6
3 4 3 24 24 2.0 0 0 4/2 2 1 ... V (P4, P5) (P4, P5) (5, 1, 2) (5, 1, 2), major (5, 1, 2) (5, 1, 2) F I V(4)
4 4 3 26 26 1.0 1/2 1/2 4/2 2 1 ... V (M3, P5) (M3, P5) (5, 7, 2) (5, 7, 2), major (5, 7, 2) (5, #7, 2) F I V

5 rows × 51 columns

Concatenated annotation tables contains 2683 rows.
Dataset contains 2683 tokens and 316 types over 6 documents.