diff --git "a/preprocessing.ipynb" "b/preprocessing.ipynb"
new file mode 100644--- /dev/null
+++ "b/preprocessing.ipynb"
@@ -0,0 +1,1448 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "19ba84e1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "from utillity import miditokenizer, midiplayer\n",
+ "\n",
+ "tokenized_data = {}\n",
+ "\n",
+ "for midi, filename in miditokenizer.get_midi_scores(\"data\"):\n",
+ " Score = midiplayer.load_score(filename)\n",
+ " token = miditokenizer.tokenize_midi(midi)\n",
+ "\n",
+ " midiplayer.play_score(Score) # 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[(Future_Bounce_like, Dark_Bright, Chill_Agressive)] = token"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "f79a6edf",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Tokenized MIDI data: 31\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(\"Tokenized MIDI data:\", len(tokenized_data))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "21a9ba89",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import json # JSON 파일로 토크나이저 미디 데이터 저장\n",
+ "\n",
+ "\n",
+ "\n",
+ "with open('tokenized_midi_data.json', 'w') as f:\n",
+ " json.dump(tokenized_data, f, indent=4)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "dea532d4",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import json # JSON으로 저장한 토크나이저 미디 데이터 불러오기\n",
+ "\n",
+ "with open('tokenized_midi_data.json', 'r') as f:\n",
+ " tokenized_data = json.load(f)\n",
+ "# Convert string keys back to tuple\n",
+ "tokenized_data = {tuple(key.split(\"|\")): value for key, value in tokenized_data.items()}\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "34c244ab",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# value로 key 찾기\n",
+ "def get_key_by_value(D:dict, value):\n",
+ " for k, v in D.items():\n",
+ " if v == value:\n",
+ " return k\n",
+ " return None"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "d6ffbdaf",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " "
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "from utillity import miditokenizer, midiplayer\n",
+ "# 손실된 데이터 복구용\n",
+ "already_tokenized:dict = tokenized_data\n",
+ "tokenized_data = []\n",
+ "\n",
+ "for midi, filename in miditokenizer.get_midi_scores(\"data\"):\n",
+ " Score = midiplayer.load_score(filename)\n",
+ " token = miditokenizer.tokenize_midi(midi)\n",
+ "\n",
+ " if token in already_tokenized.values():\n",
+ " key = get_key_by_value(already_tokenized, token)\n",
+ " tokenized_data.append({\"vector\":list(key),\"token\":token}) # type: ignore\n",
+ " continue\n",
+ " else:\n",
+ " midiplayer.play_score(Score) # 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({\"vector\":[Future_Bounce_like, Dark_Bright, Chill_Agressive],\"token\":token})"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "660054fb",
+ "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"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": ".conda",
+ "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": "3.12.9"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}