Changes to be committed: 데이터셋 추가 및 수정

modified: data/0.mid
modified: data/3.mid
new file: data/31.mid
new file: data/32.mid
new file: data/33.mid
modified: data/5.mid
modified: data/6.mid
modified: preprocessing.ipynb

preprocessing.ipynb

@@ -5,21 +5,63 @@
    "id": "7a9aa1cb",
    "metadata": {},
    "source": [
-    "## 미디 파일에 맞는 스타일 벡터 생성을 위한 곳\n",
-    "\n",
-    "### 스타일 벡터의 각 차원이 가지는 의미\n",
-    "- [Future Bounce 스러움(Bass House, J-POP 혼용 미디를 위해), 밝음어두움, 칠어그레시브]\n",
-    "\n",
-    "### 벡터값 기준\n",
-    "- 내 마음, Brooks 스타일 기준(Brooks 곡은 무조건 1,0.5,0.5), Future Bounce 스러움이 뭔데 임마(Brooks와 얼마나 비슷한가)\n"
+    "## 미디 파일에 맞는 스타일 벡터 생성을 위한 곳"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "19ba84e1",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "file name: 0.mid\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "                <div id=\"midiPlayerDiv3735\"></div>\n",
+       "                <link rel=\"stylesheet\" href=\"https://cuthbertLab.github.io/music21j/css/m21.css\">\n",
+       "                \n",
+       "                <script>\n",
+       "                require.config({\n",
+       "                    paths: {\n",
+       "                        'music21': 'https://cuthbertLab.github.io/music21j/releases/music21.debug',\n",
+       "                    }\n",
+       "                });\n",
+       "                require(['music21'], function(music21) {\n",
+       "                    mp = new music21.miditools.MidiPlayer();\n",
+       "                    mp.addPlayer(\"#midiPlayerDiv3735\");\n",
+       "                    mp.base64Load(\"data:audio/midi;base64,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\");\n",
+       "                });\n",
+       "                </script>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "ename": "KeyError",
+     "evalue": "'add4'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
+      "\u001b[31mKeyError\u001b[39m                                  Traceback (most recent call last)",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 21\u001b[39m\n\u001b[32m     11\u001b[39m     MIDI.set_midi(os.path.join(\u001b[33m\"\u001b[39m\u001b[33mdata\u001b[39m\u001b[33m\"\u001b[39m, filename))\n\u001b[32m     13\u001b[39m midiplayer.play_score(MIDI._midi) \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n\u001b[32m     15\u001b[39m tokenized_data.append({\n\u001b[32m     16\u001b[39m     \u001b[33m\"\u001b[39m\u001b[33mvector\u001b[39m\u001b[33m\"\u001b[39m:{ \u001b[38;5;66;03m# Max is 100\u001b[39;00m\n\u001b[32m     17\u001b[39m         \u001b[33m\"\u001b[39m\u001b[33mBPM\u001b[39m\u001b[33m\"\u001b[39m:\u001b[32m128\u001b[39m,\n\u001b[32m     18\u001b[39m         \u001b[33m\"\u001b[39m\u001b[33mAggressive\u001b[39m\u001b[33m\"\u001b[39m:\u001b[32m13\u001b[39m,\n\u001b[32m     19\u001b[39m \n\u001b[32m     20\u001b[39m     },\n\u001b[32m---> \u001b[39m\u001b[32m21\u001b[39m     \u001b[33m\"\u001b[39m\u001b[33mtoken\u001b[39m\u001b[33m\"\u001b[39m:\u001b[43mMIDI\u001b[49m\u001b[43m.\u001b[49m\u001b[43mtoken_id\u001b[49m\n\u001b[32m     22\u001b[39m     })\n",
+      "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\rrayy\\anaconda3\\envs\\diva\\Lib\\site-packages\\HarmonyMIDIToken\\tokenizer.py:169\u001b[39m, in \u001b[36mHarmonyMIDIToken.token_id\u001b[39m\u001b[34m(self)\u001b[39m\n\u001b[32m    167\u001b[39m \u001b[38;5;250m\u001b[39m\u001b[33;03m\"\"\"HarmonyMIDIToken에 대한 토큰 ID를 반환한다.\"\"\"\u001b[39;00m\n\u001b[32m    168\u001b[39m melody_tokens = \u001b[38;5;28mself\u001b[39m._tokenize(\u001b[38;5;28mself\u001b[39m.melody)\n\u001b[32m--> \u001b[39m\u001b[32m169\u001b[39m chords_tokens = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_tokenize\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mchords\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    170\u001b[39m bass_tokens = \u001b[38;5;28mself\u001b[39m._tokenize(\u001b[38;5;28mself\u001b[39m.bass)\n\u001b[32m    172\u001b[39m token = [\u001b[38;5;28mself\u001b[39m.bpm, \u001b[32m100\u001b[39m] + melody_tokens +[\u001b[32m200\u001b[39m]+ chords_tokens +[\u001b[32m300\u001b[39m]+ bass_tokens\n",
+      "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\rrayy\\anaconda3\\envs\\diva\\Lib\\site-packages\\HarmonyMIDIToken\\tokenizer.py:113\u001b[39m, in \u001b[36mHarmonyMIDIToken._tokenize\u001b[39m\u001b[34m(self, data)\u001b[39m\n\u001b[32m    110\u001b[39m chord = pychord_chord(value)\n\u001b[32m    112\u001b[39m tokens.append(\u001b[38;5;28mself\u001b[39m._note_name_to_intpitch(chord._root+\u001b[33m\"\u001b[39m\u001b[33m4\u001b[39m\u001b[33m\"\u001b[39m))\n\u001b[32m--> \u001b[39m\u001b[32m113\u001b[39m tokens.append(\u001b[43mquality_map\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;28;43mstr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mchord\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_quality\u001b[49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m)\n\u001b[32m    115\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m j \u001b[38;5;129;01min\u001b[39;00m chord._appended:\n\u001b[32m    116\u001b[39m     tokens.append(\u001b[38;5;28mself\u001b[39m._note_name_to_intpitch(j+\u001b[33m\"\u001b[39m\u001b[33m4\u001b[39m\u001b[33m\"\u001b[39m))\n",
+      "\u001b[31mKeyError\u001b[39m: 'add4'"
+     ]
+    }
+   ],
    "source": [
     "from HarmonyMIDIToken import HarmonyMIDIToken as Tokenizer\n",
     "from utillity import midiplayer\n",
@@ -30,15 +72,17 @@
     "for filename in os.listdir(\"data\"):\n",
     "    if filename.endswith(\".mid\"):\n",
     "        MIDI = Tokenizer()\n",
+    "        print(f\"file name: {filename}\")\n",
     "        MIDI.set_midi(os.path.join(\"data\", filename))\n",
     "    \n",
     "    midiplayer.play_score(MIDI._midi) # type: ignore\n",
-    "    Future_Bounce_like = input(\"Future_Bounce_like\")\n",
-    "    Dark_Bright = input(\"Dark_Bright\")\n",
-    "    Chill_Agressive = input(\"Chill_Agressive\")\n",
     "\n",
     "    tokenized_data.append({\n",
-    "        \"vector\":[Future_Bounce_like, Dark_Bright, Chill_Agressive],\n",
+    "        \"vector\":{ # Max is 100\n",
+    "            \"BPM\":128,\n",
+    "            \"Aggressive\":13,\n",
+    "            \n",
+    "        },\n",
     "        \"token\":MIDI.token_id\n",
     "        })\n",
     "    "
@@ -46,7 +90,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "f79a6edf",
    "metadata": {},
    "outputs": [
@@ -64,7 +108,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "21a9ba89",
    "metadata": {},
    "outputs": [],
@@ -77,7 +121,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "dea532d4",
    "metadata": {},
    "outputs": [],
@@ -92,7 +136,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "34c244ab",
    "metadata": {},
    "outputs": [],