pip install ndx-hierarchical-behavioral-data
Use pre-made hierarchical transcription tables:
from ndx_hierarchical_behavioral_data.definitions.transcription import TIPhonemes, HBTSyllables, HBTWords, HBTSentences
# Phonemes level
phonemes = TIPhonemes()
phonemes.add_column('max_pitch', 'maximum pitch for this phoneme. NaN for unvoiced')
for i, p in enumerate('abcdefghijkl'):
phonemes.add_interval(label=p, start_time=float(i), stop_time=float(i+1), max_pitch=i**2)
# Syllables level
syllables = HBTSyllables(lower_tier_table=phonemes)
syllables.add_interval(label='abc', next_tier=[0, 1, 2])
syllables.add_interval(label='def', next_tier=[3, 4, 5])
syllables.add_interval(label='ghi', next_tier=[6, 7, 8])
syllables.add_interval(label='jkl', next_tier=[9, 10, 11])
# Words level
words = HBTWords(lower_tier_table=syllables)
words.add_column('emphasis', 'boolean indicating whether this word was emphasized')
words.add_interval(label='A-F', next_tier=[0, 1], emphasis=False)
words.add_interval(label='G-L', next_tier=[2, 3], emphasis=True)
# Sentences level
sentences = HBTSentences(lower_tier_table=words)
sentences.add_interval(label='A-L', next_tier=[0, 1])View individual tiers:
sentences.to_dataframe()| label | start_time | stop_time | next_tier | |
|---|---|---|---|---|
| id | ||||
| 0 | A-L | 0.0 | 12.0 | label start_time stop_time \\id ... |
words.to_dataframe()| label | start_time | stop_time | next_tier | emphasis | |
|---|---|---|---|---|---|
| id | |||||
| 0 | A-F | 0.0 | 6.0 | label start_time stop_time \\ id 0 abc 0.0 3.0 1 def 3.0 6.0 next_tier id 0 start_time stop_time label max_pitch id 0 0.0 1.0 a 0 1 1.0 2.0 b 1 2 2.0 3.0 c 4 1 start_time stop_time label max_pitch id 3 3.0 4.0 d 9 4 4.0 5.0 e 16 5 5.0 6.0 f 25 | False |
| 1 | G-L | 6.0 | 12.0 | label start_time stop_time \\ id 2 ghi 6.0 9.0 3 jkl 9.0 12.0 next_tier id 2 start_time stop_time label max_pitch id 6 6.0 7.0 g 36 7 7.0 8.0 h 49 8 8.0 9.0 i 64 3 start_time stop_time label max_pitch id 9 9.0 10.0 j 81 10 10.0 11.0 k 100 11 11.0 12.0 l 121 | True |
syllables.to_dataframe()| label | start_time | stop_time | next_tier | |
|---|---|---|---|---|
| id | ||||
| 0 | abc | 0.0 | 3.0 | start_time stop_time label id 0 0.0 1.0 a 1 1.0 2.0 b 2 2.0 3.0 c |
| 1 | def | 3.0 | 6.0 | start_time stop_time label id 3 3.0 4.0 d 4 4.0 5.0 e 5 5.0 6.0 f |
| 2 | ghi | 6.0 | 9.0 | start_time stop_time label id 6 6.0 7.0 g 7 7.0 8.0 h 8 8.0 9.0 i |
| 3 | jkl | 9.0 | 12.0 | start_time stop_time label id 9 9.0 10.0 j 10 10.0 11.0 k 11 11.0 12.0 l |
phonemes.to_dataframe()| start_time | stop_time | label | max_pitch | |
|---|---|---|---|---|
| id | ||||
| 0 | 0.0 | 1.0 | a | 0 |
| 1 | 1.0 | 2.0 | b | 1 |
| 2 | 2.0 | 3.0 | c | 4 |
| 3 | 3.0 | 4.0 | d | 9 |
| 4 | 4.0 | 5.0 | e | 16 |
| 5 | 5.0 | 6.0 | f | 25 |
| 6 | 6.0 | 7.0 | g | 36 |
| 7 | 7.0 | 8.0 | h | 49 |
| 8 | 8.0 | 9.0 | i | 64 |
| 9 | 9.0 | 10.0 | j | 81 |
| 10 | 10.0 | 11.0 | k | 100 |
| 11 | 11.0 | 12.0 | l | 121 |
Hierarchical dataframe:
sentences.to_hierarchical_dataframe()| source_table | phonemes | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| label | id | start_time | stop_time | label | max_pitch | ||||||||||||
| sentences_id | sentences_label | sentences_start_time | sentences_stop_time | words_id | words_label | words_start_time | words_stop_time | words_emphasis | syllables_id | syllables_label | syllables_start_time | syllables_stop_time | |||||
| 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 0 | abc | 0.0 | 3.0 | 0 | 0.0 | 1.0 | a | 0 |
| 3.0 | 1 | 1.0 | 2.0 | b | 1 | ||||||||||||
| 3.0 | 2 | 2.0 | 3.0 | c | 4 | ||||||||||||
| 1 | def | 3.0 | 6.0 | 3 | 3.0 | 4.0 | d | 9 | |||||||||
| 6.0 | 4 | 4.0 | 5.0 | e | 16 | ||||||||||||
| 6.0 | 5 | 5.0 | 6.0 | f | 25 | ||||||||||||
| 1 | G-L | 6.0 | 12.0 | True | 2 | ghi | 6.0 | 9.0 | 6 | 6.0 | 7.0 | g | 36 | ||||
| 9.0 | 7 | 7.0 | 8.0 | h | 49 | ||||||||||||
| 9.0 | 8 | 8.0 | 9.0 | i | 64 | ||||||||||||
| 3 | jkl | 9.0 | 12.0 | 9 | 9.0 | 10.0 | j | 81 | |||||||||
| 12.0 | 10 | 10.0 | 11.0 | k | 100 | ||||||||||||
| 12.0 | 11 | 11.0 | 12.0 | l | 121 | ||||||||||||
Hierachical columns, flattened rows:
sentences.to_hierarchical_dataframe(flat_column_index=True)| id | start_time | stop_time | label | max_pitch | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| sentences_id | sentences_label | sentences_start_time | sentences_stop_time | words_id | words_label | words_start_time | words_stop_time | words_emphasis | syllables_id | syllables_label | syllables_start_time | syllables_stop_time | |||||
| 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 0 | abc | 0.0 | 3.0 | 0 | 0.0 | 1.0 | a | 0 |
| 3.0 | 1 | 1.0 | 2.0 | b | 1 | ||||||||||||
| 3.0 | 2 | 2.0 | 3.0 | c | 4 | ||||||||||||
| 1 | def | 3.0 | 6.0 | 3 | 3.0 | 4.0 | d | 9 | |||||||||
| 6.0 | 4 | 4.0 | 5.0 | e | 16 | ||||||||||||
| 6.0 | 5 | 5.0 | 6.0 | f | 25 | ||||||||||||
| 1 | G-L | 6.0 | 12.0 | True | 2 | ghi | 6.0 | 9.0 | 6 | 6.0 | 7.0 | g | 36 | ||||
| 9.0 | 7 | 7.0 | 8.0 | h | 49 | ||||||||||||
| 9.0 | 8 | 8.0 | 9.0 | i | 64 | ||||||||||||
| 3 | jkl | 9.0 | 12.0 | 9 | 9.0 | 10.0 | j | 81 | |||||||||
| 12.0 | 10 | 10.0 | 11.0 | k | 100 | ||||||||||||
| 12.0 | 11 | 11.0 | 12.0 | l | 121 |
Denormalized dataframe:
sentences.to_denormalized_dataframe()| source_table | sentences | words | syllables | phonemes | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| label | id | label | start_time | stop_time | id | label | start_time | stop_time | emphasis | id | label | start_time | stop_time | id | start_time | stop_time | label | max_pitch |
| 0 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 0 | abc | 0.0 | 3.0 | 0 | 0.0 | 1.0 | a | 0 |
| 1 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 0 | abc | 0.0 | 3.0 | 1 | 1.0 | 2.0 | b | 1 |
| 2 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 0 | abc | 0.0 | 3.0 | 2 | 2.0 | 3.0 | c | 4 |
| 3 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 1 | def | 3.0 | 6.0 | 3 | 3.0 | 4.0 | d | 9 |
| 4 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 1 | def | 3.0 | 6.0 | 4 | 4.0 | 5.0 | e | 16 |
| 5 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 1 | def | 3.0 | 6.0 | 5 | 5.0 | 6.0 | f | 25 |
| 6 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 2 | ghi | 6.0 | 9.0 | 6 | 6.0 | 7.0 | g | 36 |
| 7 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 2 | ghi | 6.0 | 9.0 | 7 | 7.0 | 8.0 | h | 49 |
| 8 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 2 | ghi | 6.0 | 9.0 | 8 | 8.0 | 9.0 | i | 64 |
| 9 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 3 | jkl | 9.0 | 12.0 | 9 | 9.0 | 10.0 | j | 81 |
| 10 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 3 | jkl | 9.0 | 12.0 | 10 | 10.0 | 11.0 | k | 100 |
| 11 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 3 | jkl | 9.0 | 12.0 | 11 | 11.0 | 12.0 | l | 121 |
Denormalized dataframe with flattened columns:
sentences.to_denormalized_dataframe(flat_column_index=True)| sentences_id | sentences_label | sentences_start_time | sentences_stop_time | words_id | words_label | words_start_time | words_stop_time | words_emphasis | syllables_id | syllables_label | syllables_start_time | syllables_stop_time | id | start_time | stop_time | label | max_pitch | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 0 | abc | 0.0 | 3.0 | 0 | 0.0 | 1.0 | a | 0 |
| 1 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 0 | abc | 0.0 | 3.0 | 1 | 1.0 | 2.0 | b | 1 |
| 2 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 0 | abc | 0.0 | 3.0 | 2 | 2.0 | 3.0 | c | 4 |
| 3 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 1 | def | 3.0 | 6.0 | 3 | 3.0 | 4.0 | d | 9 |
| 4 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 1 | def | 3.0 | 6.0 | 4 | 4.0 | 5.0 | e | 16 |
| 5 | 0 | A-L | 0.0 | 12.0 | 0 | A-F | 0.0 | 6.0 | False | 1 | def | 3.0 | 6.0 | 5 | 5.0 | 6.0 | f | 25 |
| 6 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 2 | ghi | 6.0 | 9.0 | 6 | 6.0 | 7.0 | g | 36 |
| 7 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 2 | ghi | 6.0 | 9.0 | 7 | 7.0 | 8.0 | h | 49 |
| 8 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 2 | ghi | 6.0 | 9.0 | 8 | 8.0 | 9.0 | i | 64 |
| 9 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 3 | jkl | 9.0 | 12.0 | 9 | 9.0 | 10.0 | j | 81 |
| 10 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 3 | jkl | 9.0 | 12.0 | 10 | 10.0 | 11.0 | k | 100 |
| 11 | 0 | A-L | 0.0 | 12.0 | 1 | G-L | 6.0 | 12.0 | True | 3 | jkl | 9.0 | 12.0 | 11 | 11.0 | 12.0 | l | 121 |
This extension was created using ndx-template.