Praat-Note-Parser/phrase_parser.py at master · bridge-exe/Praat-Note-Parser · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
#takes note data and parses into phrases based on rest time between
#takes in file_info = (float, int, str): (timestamp, length in ms, note/undef)

def phrase_parser(file_info):
 #go through times, find undef sequences, parse out undef rest length, use to create chunks of 'phrases', use those phrases to make definite and relative frequency phrases
  phrase_info = []
  phrase = []

  note_time_variance = 1000

  for info in file_info:
    note = info[2]
    note_length = int(info[1])
    start_time = float(info[0])
    note_a = [start_time, note_length, note]

    #checks if the phrase is a rest
    if 'undefined' in info:
      #if it is over 1 sec, consider it a phrase break

      if note_length > note_time_variance:
        phrase_info.append(phrase)
        phrase = []
        phrase_break = [start_time, note_length, 'phrase_break']
        phrase_info.append(phrase_break)

      #if it is not a rest, consider it a phrase, have the notes and rests appended to phrase info as lists in a list
      else:
        phrase.append(note_a)

    #appends undefined notes as info
    else:
      phrase.append(note_a)

  if 'phrase_break' not in info:
    phrase_info.append(phrase)

  #removes empty strings
  phrase_info = [x for x in phrase_info if x != []]
  # print(phrase_info)

  #compare notes relative to each other, broken up by phrase breaks
  phrase_and_length_info = []
  phrase_notes = []

  #goes through and creates TextGrid-able lists
  for phrase in phrase_info:

    phrase_start = phrase[0]
    if type(phrase_start) == list:
      phrase_start = phrase_start[0]

    phrase_length = 0
    phrase_notes = []

    if 'phrase_break' in phrase:
      phrase_and_length_info.append(phrase)

    else:
      for note in phrase:

        phrase_length += note[1]
        note_val = str(note[2])
        phrase_notes.append(note_val)

      phrase_and_length_info.append([phrase_start, phrase_length, phrase_notes])


  return(phrase_and_length_info, phrase_info)
#--------------------------#
  # for x in phrase_info:
  #  print(x)


  # for x in phrase_and_length_info:
  #   print(x)
    # print(phrase_and_length_info)


#returns file info of type (float, int, str): (timestamp, length, notes in sequence)
                                             #(11.0,      30.0s,  '5 4 5 5 3')
                                             #(11.0,      30.0s,  'F E F F D')