Overview#

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

Hide imports 
import os
from collections import defaultdict, Counter
from fractions import Fraction

from git import Repo
import dimcat as dc
import ms3
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go

from utils import CADENCE_COLORS, CORPUS_COLOR_SCALE, STD_LAYOUT, TYPE_COLORS, color_background, corpus_mean_composition_years, value_count_df, get_corpus_display_name, get_repo_name, print_heading, resolve_dir
Hide source 
CORPUS_PATH = os.path.abspath(os.path.join('..', '..'))
ANNOTATED_ONLY = os.getenv("ANNOTATED_ONLY", "True").lower() in ('true', '1', 't')
print_heading("Notebook settings")
print(f"CORPUS_PATH: {CORPUS_PATH!r}")
print(f"ANNOTATED_ONLY: {ANNOTATED_ONLY}")
CORPUS_PATH = resolve_dir(CORPUS_PATH)

Notebook settings
-----------------

CORPUS_PATH: '/home/runner/work/workflow_deployment/scarlatti_sonatas'
ANNOTATED_ONLY: False
Hide source 
repo = Repo(CORPUS_PATH)
print_heading("Data and software versions")
print(f"Data repo '{get_repo_name(repo)}' @ {repo.commit().hexsha[:7]}")
print(f"dimcat version {dc.__version__}")
print(f"ms3 version {ms3.__version__}")

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

Data repo 'scarlatti_sonatas' @ e09b178
dimcat version 0.3.0
ms3 version 2.5.2

dataset = dc.Dataset()
dataset.load(directory=CORPUS_PATH, parse_tsv=False)

[default|all]
All corpora
-----------
View: This view is called 'default'. It 
	- excludes pieces that are not contained in the metadata,
	- filters out file extensions requiring conversion (such as .xml), and
	- excludes review files and folders.

                       has   active   scores measures           notes        expanded       
                  metadata     view detected detected parsed detected parsed detected parsed
corpus                                                                                      
scarlatti_sonatas      yes  default       69       69     69       69     69       69     69

483/1380 files are excluded from this view.

483 files have been excluded based on their subdir.

N = 69 annotated pieces, 207 parsed dataframes.
Hide data loading 
all_metadata = dataset.data.metadata()
assert len(all_metadata) > 0, "No pieces selected for analysis."
print(f"Metadata covers {len(all_metadata)} of the {dataset.data.count_pieces()} scores.")
all_notes = dataset.get_facet('notes')
all_measures = dataset.get_facet('measures')
mean_composition_years = corpus_mean_composition_years(all_metadata)
chronological_order = mean_composition_years.index.to_list()
corpus_colors = dict(zip(chronological_order, CORPUS_COLOR_SCALE))
corpus_names = {corp: 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()}

Metadata covers 69 of the 69 scores.

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 1738 ('scarlatti_sonatas', 'K001') to 1749 ('scarlatti_sonatas', 'K098').

Mean composition years per corpus#

Hide source 
summary = all_metadata.copy()
summary.length_qb = all_measures.groupby(level=[0,1]).act_dur.sum() * 4.0
summary = pd.concat([summary,
                     all_notes.groupby(level=[0,1]).size().rename('notes'),
                    ], axis=1)
bar_data = pd.concat([mean_composition_years.rename('year'), 
                      summary.groupby(level='corpus').size().rename('pieces')],
                     axis=1
                    ).reset_index()
fig = px.bar(bar_data, x='year', y='pieces', color='corpus',
             color_discrete_map=corpus_colors,
            )
fig.update_traces(width=5)
fig.update_layout(**STD_LAYOUT)
fig.update_yaxes(gridcolor='lightgrey')
fig.update_traces(width=5)

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,
                  )
fig.update_traces(xbins=dict(
    size=10
))
fig.update_layout(**STD_LAYOUT)
fig.update_yaxes(gridcolor='lightgrey')
fig.show()

Dimensions#

Overview#

Hide source 
corpus_metadata = summary.groupby(level=0)
n_pieces = corpus_metadata.size().rename('pieces')
absolute_numbers = dict(
    measures = corpus_metadata.last_mn.sum(),
    length = corpus_metadata.length_qb.sum(),
    notes = corpus_metadata.notes.sum(),
    labels = corpus_metadata.label_count.sum(),
)
absolute = pd.DataFrame.from_dict(absolute_numbers)
absolute = pd.concat([n_pieces, absolute], axis=1)
sum_row = pd.DataFrame(absolute.sum(), columns=['sum']).T
absolute = pd.concat([absolute, sum_row])
relative = absolute.div(n_pieces, axis=0)
complete_summary = pd.concat([absolute, relative, absolute.iloc[:1,2:].div(absolute.measures, axis=0)], axis=1, keys=['absolute', 'per piece', 'per measure'])
complete_summary = complete_summary.apply(pd.to_numeric).round(2)
complete_summary.index = complete_summary.index.map(dict(corpus_names, sum='sum'))
complete_summary
absolute per piece per measure
pieces measures length notes labels pieces measures length notes labels length notes labels
Scarlatti Sonatas 69 5560 13633.0 65253 12480 1.0 80.58 197.58 945.7 180.87 2.45 11.74 2.24
sum 69 5560 13633.0 65253 12480 NaN NaN NaN NaN NaN NaN NaN NaN

Measures#

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

5581 measures over 69 files.
mc mn quarterbeats duration_qb keysig timesig act_dur mc_offset numbering_offset dont_count barline breaks repeats next quarterbeats_all_endings volta
corpus fname interval
scarlatti_sonatas K001 [0.0, 4.0) 1 1 0 4.0 -1 4/4 1 0 <NA> <NA> <NA> <NA> firstMeasure (2,) NaN <NA>
[4.0, 8.0) 2 2 4 4.0 -1 4/4 1 0 <NA> <NA> <NA> <NA> <NA> (3,) NaN <NA>
[8.0, 12.0) 3 3 8 4.0 -1 4/4 1 0 <NA> <NA> <NA> <NA> <NA> (4,) NaN <NA>
[12.0, 16.0) 4 4 12 4.0 -1 4/4 1 0 <NA> <NA> <NA> <NA> <NA> (5,) NaN <NA>
[16.0, 20.0) 5 5 16 4.0 -1 4/4 1 0 <NA> <NA> <NA> <NA> <NA> (6,) NaN <NA> 
print("Distribution of time signatures per XML measure (MC):")
all_measures.timesig.value_counts(dropna=False)

Distribution of time signatures per XML measure (MC):

3/8     2699
2/4      888
4/4      746
3/4      493
2/2      458
12/8     235
6/8       62
Name: timesig, dtype: int64

Harmony labels#

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

try:
    all_annotations = dataset.get_facet('expanded')
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: {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 {len(all_chords.groupby(level=[0,1]))} documents.")
    all_annotations['corpus_name'] = all_annotations.index.get_level_values(0).map(get_corpus_display_name)
    all_chords['corpus_name'] = all_chords.index.get_level_values(0).map(get_corpus_display_name)
else:
    print(f"Dataset contains no annotations.")
mc mn quarterbeats duration_qb mc_onset mn_onset timesig staff voice label ... globalkey_is_minor localkey_is_minor chord_tones added_tones root bass_note alt_label volta pedalend special
corpus fname interval
scarlatti_sonatas K001 [0.0, 1.5) 1 1 0 1.5 0 0 4/4 2 1 d.i{ ... True True (0, -3, 1) () 0 0 <NA> <NA> NaN <NA>
[1.5, 2.0) 1 1 3/2 0.5 3/8 3/8 4/4 2 1 V ... True True (1, 5, 2) () 1 1 <NA> <NA> NaN <NA>
[2.0, 3.5) 1 1 2 1.5 1/2 1/2 4/4 2 1 i ... True True (0, -3, 1) () 0 0 <NA> <NA> NaN <NA>
[3.5, 4.0) 1 1 7/2 0.5 7/8 7/8 4/4 2 1 V ... True True (1, 5, 2) () 1 1 <NA> <NA> NaN <NA>
[4.0, 5.5) 2 2 4 1.5 0 0 4/4 2 1 i ... True True (0, -3, 1) () 0 0 <NA> <NA> NaN <NA>

5 rows × 32 columns

Concatenated annotation tables contains 12439 rows.
197 of them are not chords. Their values are: {'{': 157, '}': 26, '|HC': 5, '}{': 3, 'ii%6(9)/i': 2, '|PAC': 2, '|EC{': 1, 'ii%/vi': 1}
Dataset contains 12242 tokens and 732 types over 69 documents.