File size: 7,519 Bytes
151b875 |
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 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from pathlib import Path\n",
"import numpy as np\n",
"import util as u\n",
"import json\n",
"import pickle\n",
"\n",
"\n",
"BASE_PATH = \"../\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"all_df = pd.read_csv(Path(BASE_PATH,\"metadata.csv\"))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"int"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def is_manually_checked(row):\n",
" #check based on the audio click files\n",
" if Path(BASE_PATH,row[\"midi_performance\"][:-4]+ \"_click.wav\").exists():\n",
" return False\n",
" else:\n",
" return True\n",
" \n",
"def key_number_from_number_of_sharps(nos):\n",
" if nos >= 0:\n",
" return int((nos * 7)%12)\n",
" else:\n",
" return int((np.abs(nos)*5)%12)\n",
" \n",
"type(key_number_from_number_of_sharps(-3))"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def get_beats_from_txt(ann_path):\n",
" ann_df = pd.read_csv(Path(BASE_PATH,ann_path),header=None, names=[\"time\",\"time2\",\"type\"],sep='\\t')\n",
" return ann_df[\"time\"].tolist()\n",
"\n",
"def get_downbeats_from_txt(ann_path):\n",
" ann_df = pd.read_csv(Path(BASE_PATH,ann_path),header=None, names=[\"time\",\"time2\",\"type\"],sep='\\t')\n",
" downbeats = [a[\"time\"] for i,a in ann_df.iterrows() if a[\"type\"].split(\",\")[0] == \"db\"]\n",
" return downbeats\n",
"\n",
"def get_beats_db_dict_from_txt(ann_path):\n",
" ann_df = pd.read_csv(Path(BASE_PATH,ann_path),header=None, names=[\"time\",\"time2\",\"type\"],sep='\\t')\n",
" out_dict = {str(a[\"time\"]): a[\"type\"].split(\",\")[0] for i,a in ann_df.iterrows()}\n",
" return out_dict\n",
"\n",
"def get_key_from_txt(ann_path):\n",
" ann_df = pd.read_csv(Path(BASE_PATH,ann_path),header=None, names=[\"time\",\"time2\",\"type\"],sep='\\t')\n",
" keys = {}\n",
" for i, r in ann_df.iterrows():\n",
" if len(r[\"type\"].split(\",\"))==3:\n",
" number_of_sharps = int(r[\"type\"].split(\",\")[2])\n",
" key_number = key_number_from_number_of_sharps(number_of_sharps)\n",
" keys[str(r[\"time\"])] = [key_number, number_of_sharps]\n",
" return keys\n",
"\n",
"def get_ts_from_txt(ann_path):\n",
" ann_df = pd.read_csv(Path(BASE_PATH,ann_path),header=None, names=[\"time\",\"time2\",\"type\"],sep='\\t')\n",
" tss = {}\n",
" for i, r in ann_df.iterrows():\n",
" if len(r[\"type\"].split(\",\"))>1 and r[\"type\"].split(\",\")[1]!=\"\":\n",
" ts = r[\"type\"].split(\",\")[1]\n",
" beat_n = int(u.ts2n_of_beats(ts))\n",
" tss[str(r[\"time\"])] = [ts, beat_n]\n",
" return tss\n",
"\n",
"def midi_and_score_aligned(row):\n",
" return len(get_beats_from_txt(row[\"performance_annotations\"])) == len(get_beats_from_txt(row[\"midi_score_annotations\"]))\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Creating json\n",
"###########################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################################"
]
}
],
"source": [
"asap_ann = {}\n",
"print(\"Creating json\")\n",
"\n",
"counter = 0\n",
"for i,row in all_df.iterrows():\n",
" asap_ann[row[\"midi_performance\"]] = {\n",
" \"performance_beats\" : get_beats_from_txt(row[\"performance_annotations\"]),\n",
" \"performance_downbeats\" : get_downbeats_from_txt(row[\"performance_annotations\"]),\n",
" \"performance_beats_type\" : get_beats_db_dict_from_txt(row[\"performance_annotations\"]),\n",
" \"perf_time_signatures\" : get_ts_from_txt(row[\"performance_annotations\"]),\n",
" \"perf_key_signatures\" : get_key_from_txt(row[\"performance_annotations\"]),\n",
" \"midi_score_beats\" : get_beats_from_txt(row[\"midi_score_annotations\"]),\n",
" \"midi_score_downbeats\" : get_downbeats_from_txt(row[\"midi_score_annotations\"]),\n",
" \"midi_score_beats_type\" : get_beats_db_dict_from_txt(row[\"midi_score_annotations\"]),\n",
" \"midi_score_time_signatures\" : get_ts_from_txt(row[\"midi_score_annotations\"]),\n",
" \"midi_score_key_signatures\" : get_key_from_txt(row[\"midi_score_annotations\"]),\n",
" \"downbeats_score_map\" : u.same_number_of_measures_with_repetitions(row[\"xml_score\"], str(Path(BASE_PATH,row[\"midi_score_annotations\"])), base_path=BASE_PATH),\n",
" \"score_and_performance_aligned\" : midi_and_score_aligned(row) ,\n",
"# \"manually_checked\" : is_manually_checked(row)\n",
" }\n",
" counter +=1\n",
" print(\"#\",end=\"\")\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"with open(Path('../asap_annotations.json'), 'w') as outfile:\n",
" json.dump(asap_ann, outfile)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.2"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|