hotsixman/fumen-measure-analyze
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

.

Browse Source
This commit is contained in:
hotsixman
2026-04-24 15:42:54 +09:00
parent be4c383b6f
commit cd38fd49e2
18 changed files with 11609 additions and 235 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
predict.sh
View File

@@ -1,15 +1,15 @@
#!/bin/bash
# Arguments: script_dir working_dir tja_path difficulty
SCRIPT_DIR=${1:-"script"}
WORKING_DIR=${2:-"."}
TJA_PATH=${3}
DIFFICULTY=${4:-"oni"}
# Arguments: working_dir tja_path difficulty
WORKING_DIR=${1:-"."}
TJA_PATH=${2}
DIFFICULTY=${3:-"oni"}
if [ -z "$TJA_PATH" ]; then
echo "Usage: ./redict.sh <script_dir> <working_dir> <tja_path> [difficulty: oni|edit]"
echo "Usage: ./predict.sh <working_dir> <tja_path> [difficulty: oni|edit]"
exit 1
fi
echo "Running prediction for $TJA_PATH..."
bun "$SCRIPT_DIR/predict.ts" "$WORKING_DIR" "$SCRIPT_DIR" "$TJA_PATH" "$DIFFICULTY"
# script_dir 인자가 사라졌으므로, 예측 스크립트 실행 시 인자 순서에 맞춰 실행
bun script/predict.ts "$WORKING_DIR" "$TJA_PATH" "$DIFFICULTY"

19
script/extract.ts
View File

@@ -1,16 +1,23 @@
import { parseTja } from './parse';
import { factorize } from './factorize';
import { readdirSync, readFileSync, writeFileSync, existsSync } from 'fs';
import { join } from 'path';
import { readdirSync, readFileSync, writeFileSync, existsSync, mkdirSync } from 'fs';
import { join, dirname } from 'path';
import iconv from 'iconv-lite';
const [,, workingDir, dataDir] = process.argv;
if (existsSync(join(workingDir, 'features.json'))) {
console.log('features.json already exists. Skipping extraction.');
const featurePath = join(workingDir, 'factors.json');
if (existsSync(featurePath)) {
console.log('factors.json already exists. Skipping extraction.');
process.exit(0);
}
// 작업 디렉토리 존재 확인 및 생성
if (!existsSync(workingDir)) {
mkdirSync(workingDir, { recursive: true });
}
const tjaDir = join(dataDir, 'tja');
const results: any[] = [];
@@ -38,5 +45,5 @@ for (const file of readdirSync(tjaDir)) {
results.push({ songno, diff: diff === 'oni' ? 'oni' : 'ura', ...factors });
}
}
writeFileSync(join(workingDir, 'features.json'), JSON.stringify(results, null, 2));
console.log(`Features extracted to ${workingDir}/features.json`);
writeFileSync(featurePath, JSON.stringify(results, null, 2));
console.log(`Features extracted to ${featurePath}`);

7
script/factor.json
View File

@@ -1,7 +0,0 @@
{
"physical_density": 1,
"stamina_requirement": 1,
"pattern_complexity": 1,
"rhythmic_complexity": 1,
"reading_gimmick": 1
}

105
script/factorize.ts
View File

@@ -1,86 +1,55 @@
import { Bar, Course } from 'tja-parser';
export interface Factors {
physical_density: number;
stamina_requirement: number;
pattern_complexity: number;
rhythmic_complexity: number;
reading_gimmick: number;
}
import { Course, Bar } from 'tja-parser';
export namespace Factor {
export function getAllNotes(course: Course): any[] {
const notes: any[] = [];
// 노트 추출 및 정렬 (시간순)
export function getAllNotes(course: Course) {
const notes: { type: number, time: number }[] = [];
for (const group of course.noteGroups) {
if (group instanceof Bar) {
notes.push(...group.getNotes());
// 파서 구조에 따라 노트 추출 방식 조정 필요
notes.push(...group.getNotes().map((note) => {
return {
//@ts-expect-error
type: note.type,
time: note.getTimingMS()
}
}));
}
}
return notes;
return notes.sort((a, b) => a.time - b.time).filter(n => [1, 2, 3, 4].includes(n.type));
}
export function getPhysicalDensity(course: Course): number {
const notes = getAllNotes(course);
export function getAverageDensity(notes: { time: number }[]): number {
if (notes.length < 2) return 0;
const duration = (notes[notes.length - 1].time - notes[0].time) / 1000;
return duration > 0 ? notes.length / duration : 0;
}
export function getPeakDensity(notes: { time: number }[]): number {
if (notes.length === 0) return 0;
const bars = course.noteGroups.length;
return notes.length / (bars || 1);
}
export function getStaminaRequirement(course: Course): number {
const notes = getAllNotes(course);
let maxStream = 0;
let currentStream = 0;
for (const note of notes) {
if (note.type !== '0') {
currentStream++;
} else {
maxStream = Math.max(maxStream, currentStream);
currentStream = 0;
let maxPeak = 0;
const windowSize = 1000;
for (let i = 0; i < notes.length; i++) {
let count = 0;
const startTime = notes[i].time;
for (let j = i; j < notes.length && notes[j].time < startTime + windowSize; j++) {
count++;
}
maxPeak = Math.max(maxPeak, count);
}
return Math.max(maxStream, currentStream) / 100;
return maxPeak;
}
export function getPatternComplexity(course: Course): number {
const notes = getAllNotes(course).filter(n => n.type === '1' || n.type === '2');
let transitions = 0;
for (let i = 1; i < notes.length; i++) {
if (notes[i].type !== notes[i-1].type) {
transitions++;
}
}
return notes.length > 0 ? transitions / notes.length : 0;
}
export function getRhythmicComplexity(course: Course): number {
let complexNotes = 0;
const allNotes = getAllNotes(course);
for (const group of course.noteGroups) {
if (group instanceof Bar) {
const division = group.getNotes().length;
if (division % 4 !== 0 || division > 16) {
complexNotes += division;
}
}
}
return allNotes.length > 0 ? complexNotes / allNotes.length : 0;
}
export function getReadingGimmick(course: Course): number {
// BPM 변화나 Scroll 변화 빈도 측정
// tja-parser의 구조에 따라 구현 (여기서는 placeholder)
return 0;
export function getMaxCombo(notes: any[]): number {
return notes.length;
}
}
export function factorize(course: Course): Factors {
export function factorize(course: Course) {
const notes = Factor.getAllNotes(course);
return {
physical_density: Factor.getPhysicalDensity(course),
stamina_requirement: Factor.getStaminaRequirement(course),
pattern_complexity: Factor.getPatternComplexity(course),
rhythmic_complexity: Factor.getRhythmicComplexity(course),
reading_gimmick: Factor.getReadingGimmick(course)
average_density: Factor.getAverageDensity(notes),
peak_density: Factor.getPeakDensity(notes),
max_combo: Factor.getMaxCombo(notes)
};
}
}

105
script/predict.ts
View File

@@ -1,38 +1,97 @@
import { parseTja } from './parse';
import { factorize, Factors } from './factorize';
import { factorize } from './factorize';
import { join } from 'path';
import { readFileSync } from 'fs';
import { readFileSync, writeFileSync, unlinkSync, existsSync } from 'fs';
import { execSync } from 'child_process';
async function predict() {
const args = process.argv.slice(2);
const workingDir = args[0];
const scriptDir = args[1];
const tjaPath = args[2];
const difficulty = (args[3] || 'oni').toLowerCase() as 'oni' | 'edit';
/**
* 예측 엔진: 모델 실행을 위해 Python 환경을 호출
*/
function runInference(workingDir: string, factors: Record<string, number>): number {
const tempFactorPath = join(workingDir, `temp_feat_${Date.now()}.json`);
writeFileSync(tempFactorPath, JSON.stringify(factors));
if (!tjaPath) {
console.error('Usage: bun script/predict.ts <working_dir> <script_dir> <tja_path> <difficulty>');
const pythonScript = `
import json, torch, sys
import numpy as np
import torch.nn as nn
# 모델 정의 (학습된 구조와 동일해야 함)
class DifficultyNet(nn.Module):
def __init__(self, input_dim):
super().__init__()
self.net = nn.Sequential(
nn.Linear(input_dim, 128),
nn.BatchNorm1d(128),
nn.ReLU(),
nn.Dropout(0.4),
nn.Linear(128, 64),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(64, 32),
nn.ReLU(),
nn.Linear(32, 1),
nn.Sigmoid()
)
def forward(self, x): return self.net(x)
def predict():
try:
with open('${tempFactorPath}', 'r') as f: factors = json.load(f)
with open('${join(workingDir, 'scaler.json')}', 'r') as f: s = json.load(f)
X = np.array([[factors[col] for col in s['cols']]], dtype=np.float32)
# 정규화 (Robust/Standard 지원)
if 'center' in s: X_scaled = (X - np.array(s['center'])) / np.array(s['scale'])
else: X_scaled = (X - np.array(s.get('mean', 0))) / np.array(s.get('std', s.get('scale', 1)))
model = DifficultyNet(len(s['cols']))
model.load_state_dict(torch.load('${join(workingDir, 'model.pth')}', map_location='cpu'))
model.eval()
with torch.no_grad():
input_tensor = torch.from_numpy(X_scaled).float()
pred = model(input_tensor) * 11 + 1
print(float(pred.item()))
except Exception as e:
print(f"ERROR: {e}", file=sys.stderr)
sys.exit(1)
if __name__ == "__main__": predict()
`;
const tempPyPath = join(workingDir, `inference_${Date.now()}.py`);
writeFileSync(tempPyPath, pythonScript);
try {
const result = execSync(`python3 ${tempPyPath}`).toString().trim();
return parseFloat(result);
} finally {
if (existsSync(tempFactorPath)) unlinkSync(tempFactorPath);
if (existsSync(tempPyPath)) unlinkSync(tempPyPath);
}
}
function main() {
const [workingDir, tjaPath, difficulty = 'oni'] = process.argv.slice(2);
if (!workingDir || !tjaPath) {
console.log("Usage: bun run script/predict.ts <workingDir> <tjaPath> [difficulty]");
process.exit(1);
}
const factorJsonPath = join(scriptDir, 'factor.json');
const weights: Factors = JSON.parse(readFileSync(factorJsonPath, 'utf-8'));
const tjaContent = readFileSync(tjaPath, 'utf-8');
const parsed = parseTja(tjaContent);
const chart = parsed[difficulty.toLowerCase() as 'oni' | 'edit'];
if (!parsed || !parsed[difficulty]) {
console.error(`Error: Could not find difficulty '${difficulty}' in TJA.`);
if (!chart) {
console.error(`Error: Difficulty '${difficulty}' not found.`);
process.exit(1);
}
const factors = factorize(parsed[difficulty]!);
const prediction = Object.keys(factors).reduce((sum, key) =>
sum + (factors[key as keyof Factors] * weights[key as keyof Factors]), 0);
console.log(`Prediction for ${tjaPath} (${difficulty}):`);
console.log(`- Predicted Value: ${prediction.toFixed(4)}`);
console.log('- Factors:', factors);
const score = runInference(workingDir, factorize(chart));
console.log(`\n🎯 Predicted Difficulty: ${score.toFixed(2)}`);
}
predict();
main();

193
script/train.py
View File

@@ -1,67 +1,152 @@
import pandas as pd
import json, os, sys, joblib
import json, os, sys
import numpy as np
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.model_selection import train_test_split
import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.preprocessing import StandardScaler
def train(script_dir, working_dir, data_dir, train_count, val_count, margin):
features = pd.read_json(os.path.join(working_dir, 'features.json'))
measures = pd.read_csv(os.path.join(data_dir, 'measure.csv'))
features['songno'] = features['songno'].astype(int)
measures['songno'] = measures['songno'].astype(int)
measures['diff'] = measures['diff'].replace('ura', 'edit')
df = pd.merge(features, measures, on=['songno', 'diff'])
with open(os.path.join(script_dir, 'factor.json'), 'r') as f:
weights = json.load(f)
for col in ['physical_density', 'stamina_requirement', 'pattern_complexity', 'rhythmic_complexity', 'reading_gimmick']:
df[col] = df[col] * weights.get(col, 1.0)
MAX_MARGIN_LIMIT = 3
X_cols = ['physical_density', 'stamina_requirement', 'pattern_complexity', 'rhythmic_complexity', 'reading_gimmick']
model_path = os.path.join(working_dir, 'model.pkl')
model = joblib.load(model_path) if os.path.exists(model_path) else GradientBoostingRegressor(n_estimators=200, learning_rate=0.05, max_depth=3)
class DifficultyNet(nn.Module):
def __init__(self, input_dim):
super(DifficultyNet, self).__init__()
self.net = nn.Sequential(
nn.Linear(input_dim, 128),
nn.BatchNorm1d(128),
nn.ReLU(),
nn.Dropout(0.4),
nn.Linear(128, 64),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(64, 32),
nn.ReLU(),
nn.Linear(32, 1),
nn.Sigmoid()
)
def forward(self, x):
return self.net(x)
def train(script_dir, working_dir, data_dir, train_count, val_count, margin, val_iterations):
device = torch.device("mps" if torch.backends.mps.is_available() else "cpu")
print(f"🚀 Using Device: {device}")
# 데이터 로드 및 병합
factors_path = os.path.join(working_dir, 'factors.json')
if not os.path.exists(factors_path):
os.system(f"bun run {os.path.join(script_dir, 'factorize.ts')} {data_dir} {working_dir}")
df_feat = pd.read_json(factors_path)
df_meas = pd.read_csv(os.path.join(data_dir, 'measure.csv'))
df_meas['diff'] = df_meas['diff'].replace('ura', 'edit')
df_feat['songno'], df_meas['songno'] = df_feat['songno'].astype(int), df_meas['songno'].astype(int)
df = pd.merge(df_feat, df_meas, on=['songno', 'diff'])
exclude_cols = ['songno', 'diff', 'title', 'course', '상수', 'predicted_measure', 'error']
X_cols = [c for c in df_feat.columns if c not in exclude_cols]
scaler = StandardScaler()
df[X_cols] = scaler.fit_transform(df[X_cols])
with open(os.path.join(working_dir, 'scaler.json'), 'w') as f:
json.dump({'mean': scaler.mean_.tolist(), 'std': scaler.scale_.tolist(), 'cols': X_cols}, f)
model_path = os.path.join(working_dir, 'model.pth')
margin = float(margin)
val_iterations = int(val_iterations)
model = DifficultyNet(len(X_cols)).to(device)
attempt = 1
iteration = 1
while True:
# 3. 데이터 샘플링
df_sample = df.sample(n=int(train_count) + int(val_count))
train_df, val_df = train_test_split(df_sample, test_size=int(val_count))
print(f"\n[Attempt {attempt}] " + "-"*40)
if os.path.exists(model_path):
try: model.load_state_dict(torch.load(model_path, map_location=device))
except: pass
X_train, y_train = train_df[X_cols], train_df['상수']
X_val, y_val = val_df[X_cols], val_df['상수']
train_df = df.sample(n=min(int(train_count), len(df)))
X_train = torch.FloatTensor(train_df[X_cols].values).to(device)
y_train = torch.FloatTensor(((train_df['상수'].values - 1) / 11)).unsqueeze(1).to(device)
# 4. 학습 (최대 10회)
for attempt in range(1, 11):
model.fit(X_train, y_train)
train_err = np.max(np.abs(np.clip(model.predict(X_train), 1.0, 12.0) - y_train))
print(f"Iteration {iteration} - Attempt {attempt} - Train Error: {train_err:.4f}")
if train_err <= float(margin): break
model.set_params(n_estimators=model.n_estimators + 50)
base_lr = 0.001
optimizer = optim.Adam(model.parameters(), lr=base_lr, weight_decay=1e-5)
criterion = nn.L1Loss()
# 5. 검증
pred_val = np.clip(model.predict(X_val), 1.0, 12.0)
val_errors = np.abs(pred_val - y_val)
# 6. 검증 실패 시 재시도
if np.any(val_errors > float(margin)):
print(f"Validation failed (max error: {np.max(val_errors):.4f}). Retrying...")
iteration += 1
continue
model.train()
epoch = 0
while True:
optimizer.zero_grad()
preds_train = model(X_train)
loss = criterion(preds_train, y_train) # MSELoss 권장
loss.backward()
optimizer.step()
val_result = pd.DataFrame({
'songno': val_df['songno'],
'difficulty': val_df['diff'],
'measure': y_val,
'predicted_measure': pred_val,
'error': val_errors
})
val_result.to_csv(os.path.join(working_dir, f'validate_result_{iteration}.csv'), index=False)
val_result.to_csv(os.path.join(working_dir, 'validate_result.csv'), index=False)
break
# 현재 학습 데이터에 대한 오차 분석
with torch.no_grad():
diff = torch.abs((preds_train * 11 + 1) - (y_train * 11 + 1))
train_mae = torch.mean(diff).item()
train_max = torch.max(diff).item()
if epoch % 1000 == 0:
print(f" - Ep {epoch:5d} | MAE: {train_mae:.4f} | MAX: {train_max:.4f}")
# ✅ 조건 강화: MAE뿐만 아니라 MAX도 어느 정도 잡혔을 때만 검증으로 이동
if train_mae < margin and train_max < (margin * MAX_MARGIN_LIMIT):
print(f" ✅ Train Goal Reached (MAE: {train_mae} < {margin:.4f}, MAX: {train_max:.4f} < {(margin * MAX_MARGIN_LIMIT):.4f}). Moving to Val.")
break
epoch += 1
if epoch > 50000:
print(" ⚠️ Timed out. Resampling...")
break
if train_mae >= margin:
torch.save(model.state_dict(), model_path)
attempt += 1
continue
joblib.dump(model, model_path)
# 3. 검증 단계
print(f"3. Validating {val_iterations} iterations...")
model.eval()
all_passed = True
with torch.no_grad():
for i in range(1, val_iterations + 1):
val_df = df.sample(n=min(int(val_count), len(df)))
X_val = torch.FloatTensor(val_df[X_cols].values).to(device)
y_val_raw = val_df['상수'].values
preds = model(X_val) * 11 + 1
y_val_tensor = torch.FloatTensor(y_val_raw).unsqueeze(1).to(device)
diff_tensor = torch.abs(preds - y_val_tensor)
mae = torch.mean(diff_tensor).item()
max_error = torch.max(diff_tensor).item()
# csv 저장
# preds를 CPU 넘파이로 변환하고 1차원으로 펴주는 과정이 포함되어야 합니다.
preds_np = preds.detach().cpu().numpy().flatten() if torch.is_tensor(preds) else preds
res_df = val_df[['songno', 'diff', '상수']].copy()
res_df['predicted_measure'] = preds_np
res_df['error'] = np.abs(preds_np - y_val_raw)
output_file = os.path.join(working_dir, f'validate_result_{i}.csv')
res_df.to_csv(output_file, index=False)
if mae <= margin and max_error <= (margin * MAX_MARGIN_LIMIT):
print(f" [Iter {i}] ✅ PASS (MAE: {mae:.4f}, MAX: {max_error:.4f})")
else:
print(f" [Iter {i}] ❌ FAIL (MAE: {mae:.4f} > {margin}, MAX: {max_error:.4f} > {margin * MAX_MARGIN_LIMIT})")
all_passed = False
break
if all_passed:
print(f"\n✨ Final Success!")
torch.save(model.state_dict(), model_path)
return
else:
torch.save(model.state_dict(), model_path)
attempt += 1
if __name__ == "__main__":
train(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4], sys.argv[5], sys.argv[6])
if len(sys.argv) < 8: sys.exit(1)
train(*sys.argv[1:8])

30
script/train.ts
View File

@@ -30,10 +30,12 @@ async function train() {
console.log(`Training with ${trainFiles.length} files...`);
// 학습 로직 (단순화된 경사 하강법 또는 반복 최적화)
// 학습 로직 (Sigmoid + [1, 12] scaling)
const sigmoid = (x: number) => 1 / (1 + Math.exp(-x));
let error = Infinity;
let iterations = 0;
while (error > margin && iterations < 100) {
while (error > margin && iterations < 10) { // Spec에 따라 10번 반복
let totalError = 0;
let count = 0;
@@ -48,24 +50,32 @@ async function train() {
if (!course) continue;
const target = records.find((r: any) => r.songno === songno && (r.diff === (diff === 'oni' ? 'oni' : 'ura')));
if (!target) {
// console.log(`[!] No target for ${songno} diff=${diff}`);
continue;
}
if (!target) continue;
const factors = factorize(course);
const prediction = Object.keys(factors).reduce((sum, key) =>
sum + (factors[key as keyof Factors] * weights[key as keyof Factors]), 0);
// 가중치 적용 전 정규화 (임의 값으로 가정)
const normalizedFactors = {
physical_density: Math.min(factors.physical_density / 20, 1),
stamina_requirement: Math.min(factors.stamina_requirement, 1),
pattern_complexity: Math.min(factors.pattern_complexity, 1),
rhythmic_complexity: Math.min(factors.rhythmic_complexity, 1),
reading_gimmick: Math.min(factors.reading_gimmick, 1)
};
const rawPrediction = Object.keys(normalizedFactors).reduce((sum, key) =>
sum + (normalizedFactors[key as keyof Factors] * weights[key as keyof Factors]), 0);
const prediction = (sigmoid(rawPrediction) * 11) + 1; // [1, 12]
const targetValue = parseFloat(target.상수);
const diff_val = targetValue - prediction;
totalError += Math.abs(diff_val);
count++;
// 가중치 업데이트
// 가중치 업데이트 (간단한 경사 하강법)
for (const key in weights) {
const k = key as keyof Factors;
weights[k] += diff_val * factors[k] * 0.05; // 학습률 조정
weights[k] += diff_val * normalizedFactors[k] * 0.01;
}
}
}

80
spec.md
View File

@@ -7,69 +7,47 @@
- data_dir
- train_data_count = 100
- validate_data_count = 20
- margin = 0.1
- margin = 0.5
- validate_iterations = 5
## 학습 모델
- **추천:** PyTorch 기반의 **Deep MLP** (Dropout 및 Weight Decay 필수 적용)
- **과적합 방지 전략:**
- **Dropout (0.3 ~ 0.5):** 학습 시 뉴런을 의도적으로 꺼서 특정 데이터 암기를 방지한다.
- **L2 Regularization (Weight Decay):** 가중치가 비정상적으로 커지는 것을 막는다.
- **Output Mapping:** 최종 출력에 `Sigmoid`를 걸고 (y * 11) + 1을 적용해 [1, 12] 범위를 강제한다.
## 학습 과정
1. `{data_dir}/tja`의 tja를 파싱한다.
- `{script_dir}/parse.ts`를 사용한다.
2. `oni`와 `edit` course를 factorize한다.
- `{script_dir}/factorize.ts`를 사용하며, `{working_dir}/features.json`에 저장한다. 이 때, songno와 난이도(oni | edit)을 같이 저장하여야한다.
- `{working_dir}/features.json`이 이미 존재하면 이 과정은 생략한다.
3. factorized된 데이터를 `train_data_count` 만큼 랜덤으로 가져온다.
4. train data로 학습을 진행한다.
- 예측 값이 [1, 12]에 없으면 완전히 잘못 트레이닝 된 것이다.
- `{data_dir}/measure.csv`로 오차 확인
- course가 `edit`이면 measure.json에서는 `ura`이므로 적절히 매칭한다.
- Train error를 계속 로깅한다.
- Train error가 `margin`보다 클 경우 이 과정(4번)을 다시 진행한다.
- 최대 10번만 진행한다.
5. validate_data_count 만큼 랜덤으로 validate data를 가져온 후 validate data로 각각의 measure, 예측한 measure, 오차를 `validate_result_{n}.csv`로 저장한다.
- `validate_result_{n}.csv`에는 `songno`, `difficulty`, `measure`, `predicted_measure`, `error`을 작성한다. (중요)
- `n`에는 몇번째 iteration인지 적는다.
6. 만약 validate한 데이터 중 오차가 `margin`보다 큰 것이 있다면 3~5과정을 다시 반복한다.
7. 모델 파일을 저장한다.
1. `{data_dir}/tja`의 tja를 파싱한다. (`{script_dir}/parse.ts`)
2. `oni`와 `edit` course를 factorize하여 `{working_dir}/factors.json`에 저장한다.
- 이미 존재하면 생략하되, Factor 로직 수정 시 삭제 후 재실행한다.
3. 데이터 표준화(Standardization)를 위한 스케일링 파라미터를 계산하고 `{working_dir}/scaler.json`에 저장한다.
4. **학습 단계:** 전체 데이터 중 `train_data_count`만큼 데이터를 랜덤하게 추출하여 학습을 진행한다.
- `edit` 코스는 `ura`와 매칭하여 오차를 계산한다.
- 모델이 충분히 수렴할 때까지 학습을 수행하며, 기존 모델 존재 시 가중치를 로드하여 업데이트한다.
5. **검증 단계:** 학습이 완료된 모델을 대상으로 아래 과정을 수행한다.
- `validate_data_count`만큼의 데이터를 랜덤하게 추출하여 오차를 계산하고 `validate_result_{n}.csv`에 저장한다.
- 이 과정을 `validate_iterations` 횟수만큼 반복한다.
- **재시도 조건:** 검증 루프 도중 단 한 번이라도 Mean Absolute Error(MAE)가 `margin`보다 크다면, 즉시 검증을 중단하고 4번(학습 단계)으로 돌아가 데이터를 새로 샘플링하여 재학습한다.
6. **성공 및 종료:** 모든 `validate_iterations` 회차에서 MAE가 `margin` 이하일 경우에만 학습 성공으로 간주하고 최종 모델 파일을 저장한다.
### 유의 사항
- 모든 출력되는 데이터는 working_dir에 저장한다.
- 이미 working_dir에 모델이 존재하면 모델을 삭제하지 않고 업데이트하는 식으로 학습한다.
- 애플 실리콘 cpu를 사용할 경우 적극적으로 gpu를 사용할 수 있도록 한다.
- 모든 데이터는 `working_dir`에 저장한다.
- Apple Silicon 환경에서 `mps` 디바이스를 할당하여 GPU 가속을 사용한다.
# 예측
## CLi
- cli로 예측 데이터를 뽑을 수 있는 쉘 스크립트를 작성한다.
- argument
- working_dir
- tja
- difficulty: oni | edit
## CLI
- argument: `working_dir`, `tja`, `difficulty` (oni | edit)
## 예측 과정
- `working_dir`에 있는 model로 예측을 진행한다.
- `tja` argument에 tja파일이 존재한다.
- `difficulty`로 예측을 진행할 난이도를 선택한다.
- 로드된 모델과 학습 시 사용했던 스케일링 파라미터(Mean, Std)를 동일하게 적용하여 예측을 진행한다.
# Factor
## 종류
- physical_density: 곡의 전반적인 및 순간적인 타격 밀도 (Global NPS, Peak NPS)
- stamina_requirement: 긴 연타 구간과 휴식 구간의 비율을 통한 체력 소모량
- pattern_complexity: 색상 전환 및 손 배치 전환(Hand-switching)의 복잡도
- rhythmic_complexity: 엇박, 다양한 음표 단위 사용 등으로 인한 리듬의 난해함
- reading_gimmick: BPM 변화, 스크롤 속도(SV) 변동 등 시각적 요소 및 기믹
## 가중치 (하이퍼 파라미터)
`script/factor.json`에 `Record<factor 이름, 가중치>`를 기록한다.
- average_density: 평균 밀도
- peak_density: 최고 초당 밀도
- max_combo: 노트의 수
# Scripts
## `script/parse.ts`
- `parseTja` 함수
- tja를 string으로 받는다.
- `Partial<Record<'oni' | 'edit', Course>> | null`을 반환한다.
- null이 반환되면 에러가 나온 것이므로 무시한다.
## `script/factorize.ts`
- `factorize` 함수
- course를 input으로 받는다.
- factor들을 반환한다.
- `Factor` namespace
- 각 factor을 반환하는 함수의 namespace이다.
- `factorize` 함수는 `Factor` namespace에서 함수들을 호출하여 factor들을 반환한다.
- `parse.ts`: TJA 문자열을 `Course` 객체로 변환.
- `factorize.ts`: `Course`를 입력받아 확장된 `Factor` 세트를 반환.

10264
test/factors.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
test/model.pth Normal file
View File

Binary file not shown.

1
test/scaler.json Normal file
View File

@@ -0,0 +1 @@
{"mean": [5.390975807838123, 11.135695764909247, 630.3327571305099], "std": [1.4301422132137462, 3.0709973724562003, 211.64659003608378], "cols": ["average_density", "peak_density", "max_combo"]}

1
test/temp_factors.json Normal file
View File

@@ -0,0 +1 @@
{"average_density":6.492187500000001,"peak_density":14,"max_combo":831}

201
test/validate_result_1.csv Normal file
View File

@@ -0,0 +1,201 @@
songno,diff,상수,predicted_measure,error
247,oni,5.5,5.2725,0.22749996185302734
246,oni,1.1,3.596659,2.496658945083618
1199,oni,4.3,2.9755948,1.324405241012573
860,oni,10.6,9.705553,0.8944469451904293
39,oni,5.6,6.1024475,0.5024475097656254
1279,oni,8.4,8.08667,0.31333007812500036
1178,oni,3.5,3.5068276,0.006827592849731445
1155,oni,4.3,3.6213677,0.6786323070526121
63,oni,6.1,5.844149,0.25585088729858363
641,oni,8.4,7.899804,0.5001958847045902
647,oni,7.8,7.7702703,0.02972965240478498
1026,oni,4.1,4.470079,0.37007894515991246
488,oni,5.7,5.910693,0.21069316864013654
773,oni,4.0,4.5387897,0.5387897491455078
1201,oni,1.9,3.921908,2.021907901763916
177,oni,2.0,2.8112068,0.8112068176269531
1039,oni,9.2,9.261316,0.06131629943847727
108,oni,6.8,7.2224617,0.4224617004394533
1059,oni,5.6,4.5673223,1.0326777458190914
1125,oni,3.6,3.8051248,0.20512475967407218
345,oni,4.5,4.752472,0.252471923828125
1186,oni,1.9,2.9006872,1.0006872177124024
1179,oni,5.0,5.2376785,0.23767852783203125
1411,oni,9.1,8.738385,0.36161479949951136
1145,oni,7.2,6.407096,0.7929040908813478
417,oni,3.3,3.5370734,0.23707337379455584
74,oni,4.5,5.398354,0.8983540534973145
544,oni,5.9,6.0266037,0.1266036987304684
935,oni,9.5,9.191151,0.3088493347167969
110,oni,10.9,7.6176825,3.2823175430297855
1319,oni,8.8,8.815666,0.01566619873046804
1228,oni,4.1,4.2427197,0.14271965026855504
615,oni,9.0,8.767521,0.23247909545898438
1146,oni,7.5,7.4651394,0.03486061096191406
405,oni,3.1,5.056039,1.9560388565063476
8,oni,2.2,3.7271776,1.5271776199340819
285,oni,4.3,4.8761697,0.5761696815490724
1286,oni,2.2,3.0876362,0.8876362323760985
259,oni,6.6,6.396202,0.2037979125976559
1274,oni,4.8,6.104219,1.3042189598083498
886,oni,1.9,3.2270806,1.3270805835723878
1118,oni,1.2,2.8580723,1.658072280883789
1176,oni,4.0,3.527431,0.47256898880004883
42,oni,1.1,3.3398852,2.2398852348327636
799,oni,5.7,4.7683806,0.9316193580627443
967,oni,8.8,7.698433,1.1015670776367195
539,oni,6.0,6.0380173,0.03801727294921875
445,oni,7.1,6.515002,0.5849982261657711
482,oni,1.8,3.32895,1.5289499282836914
1355,oni,9.0,7.8457313,1.154268741607666
22,oni,5.5,6.1377096,0.6377096176147461
113,oni,5.7,5.555111,0.1448890686035158
739,oni,7.1,7.8227615,0.7227615356445316
794,oni,7.6,7.0705323,0.529467678070068
355,oni,10.0,8.396488,1.6035118103027344
455,oni,5.7,5.748408,0.04840784072875959
775,oni,10.6,9.172316,1.42768440246582
1418,oni,8.0,7.8505096,0.1494903564453125
478,oni,5.8,4.8743525,0.9256475448608397
236,oni,2.2,4.2807217,2.0807216644287108
1311,oni,6.7,7.5999484,0.8999484062194822
790,oni,2.5,3.3790677,0.8790676593780518
88,oni,8.1,7.4207373,0.6792627334594723
660,oni,6.6,6.459454,0.14054594039916957
939,oni,7.4,7.2584605,0.1415394783020023
1100,oni,3.9,4.6481123,0.7481122970581056
1001,oni,3.6,3.5810204,0.018979644775390714
248,oni,6.2,6.3501973,0.15019731521606428
341,oni,3.3,4.576923,1.27692289352417
644,oni,4.4,4.404581,0.004581069946288707
472,oni,5.9,6.3437867,0.4437867164611813
792,oni,3.7,3.8640676,0.16406755447387678
428,oni,6.5,6.3807287,0.11927127838134766
754,oni,5.0,5.1724863,0.1724863052368164
1133,oni,5.7,6.4210324,0.7210324287414549
1235,oni,7.8,7.6141486,0.18585138320922834
1317,oni,11.2,10.63248,0.5675203323364251
1106,oni,9.1,8.950381,0.14961872100830043
601,oni,3.5,4.1207476,0.6207475662231445
1432,oni,10.0,8.503614,1.4963855743408203
1207,oni,7.8,7.735499,0.06450109481811506
1208,oni,4.3,5.267852,0.9678518295288088
578,oni,6.5,5.0540576,1.4459424018859863
1031,oni,4.7,4.8403573,0.1403573036193846
491,oni,8.2,8.015301,0.18469924926757741
843,oni,10.0,9.856177,0.14382266998291016
1261,oni,7.3,7.2535615,0.04643850326538068
816,oni,8.2,8.119859,0.08014125823974538
1337,oni,3.9,4.6578474,0.7578474044799806
1072,oni,9.8,7.600742,2.1992581367492683
37,oni,5.3,5.2767086,0.023291397094726385
556,oni,4.4,4.318159,0.08184089660644567
596,oni,6.8,6.5767,0.22329978942871076
933,oni,7.1,7.283629,0.18362894058227575
270,oni,6.9,6.4714212,0.42857875823974645
911,oni,4.7,4.7063766,0.006376552581786932
160,oni,5.3,5.3374934,0.037493419647216975
399,oni,7.6,7.693502,0.09350194931030309
1080,oni,8.0,7.970645,0.02935504913330078
746,oni,8.0,8.314695,0.3146953582763672
427,oni,9.1,8.443438,0.6565624237060543
1296,oni,7.9,8.019875,0.1198745727539059
380,oni,4.6,4.371937,0.22806320190429652
1004,oni,5.9,5.448553,0.4514469146728519
266,oni,6.3,8.509695,2.209695053100586
624,oni,5.6,5.243518,0.3564821243286129
750,oni,8.8,8.119534,0.6804664611816413
1105,oni,5.5,4.0916586,1.408341407775879
1362,oni,6.1,5.757848,0.3421522140502926
1202,oni,4.8,4.697151,0.10284881591796857
396,oni,5.8,6.155394,0.35539407730102557
219,oni,5.1,4.664316,0.4356838226318356
124,oni,5.5,5.801539,0.30153894424438477
32,oni,6.8,6.472562,0.32743816375732404
33,oni,10.5,8.676422,1.823577880859375
819,oni,8.6,7.86986,0.7301398277282711
506,oni,5.6,3.7444363,1.8555637359619137
364,oni,5.2,5.2186875,0.018687534332275213
218,oni,7.7,7.626425,0.07357521057128924
55,oni,8.7,7.312134,1.3878662109374993
1225,oni,5.3,4.8498535,0.4501464843749998
150,oni,6.3,5.750553,0.5494468688964842
689,oni,4.3,4.3800893,0.08008928298950213
1356,oni,9.4,8.77751,0.6224903106689457
339,oni,6.8,3.677099,3.1229010105133055
571,oni,9.1,7.775726,1.3242741584777828
1336,oni,2.9,3.8107193,0.9107192516326905
360,oni,9.2,8.764785,0.4352151870727532
762,oni,10.3,10.230464,0.06953601837158274
1095,oni,6.2,4.828952,1.371048164367676
1422,oni,5.6,5.737846,0.1378458976745609
1150,oni,4.1,4.486331,0.3863309860229496
738,oni,7.9,7.607025,0.29297485351562536
95,oni,7.3,7.3256226,0.025622558593750178
1173,oni,9.2,8.770874,0.4291259765624993
611,oni,3.8,3.7210314,0.07896857261657697
415,oni,1.8,3.6390128,1.8390128135681152
420,oni,4.3,4.0958514,0.20414857864379865
1450,oni,2.9,3.2371683,0.337168312072754
312,oni,1.1,2.8274343,1.7274343013763427
193,oni,4.4,6.1280093,1.7280093193054196
925,oni,5.2,3.687907,1.5120930194854738
846,oni,8.5,8.5911455,0.09114551544189453
549,oni,8.3,8.18619,0.1138103485107429
103,oni,8.2,8.056568,0.14343185424804616
517,oni,8.2,8.255187,0.055187034606934304
627,oni,11.5,9.760542,1.7394580841064453
60,oni,7.9,7.881064,0.018936061859131215
948,oni,8.3,8.36591,0.06590957641601491
1019,oni,5.5,5.212821,0.28717899322509766
680,oni,7.9,7.9404883,0.04048833847045863
142,oni,3.0,3.7907765,0.7907764911651611
460,oni,2.7,2.6523027,0.047697257995605646
315,oni,3.2,4.228785,1.0287850379943846
1149,oni,3.8,6.2704215,2.4704215049743654
887,oni,7.2,6.998309,0.20169086456298846
1177,oni,3.4,4.0435953,0.643595314025879
1018,oni,4.9,4.9320893,0.032089328765868785
1252,oni,4.9,4.427538,0.47246208190918004
1250,oni,6.0,6.7224565,0.7224564552307129
1172,oni,11.9,10.33794,1.5620597839355472
167,oni,7.1,8.270915,1.1709150314331058
1074,oni,3.1,2.9782546,0.1217454433441163
931,oni,7.7,6.1198707,1.5801293373107912
1412,oni,6.2,6.288117,0.08811693191528303
955,oni,10.5,8.674553,1.8254470825195312
220,oni,9.3,8.375487,0.9245126724243171
1153,oni,1.8,2.7926855,0.9926855087280273
214,oni,7.8,7.8332896,0.033289623260498225
1119,oni,5.2,4.9443893,0.2556106567382814
824,oni,1.3,2.3053257,1.0053257465362548
757,oni,10.5,9.727542,0.7724580764770508
943,oni,9.6,8.187772,1.4122282028198239
1403,oni,5.0,3.9427001,1.0572998523712158
93,oni,5.9,5.960514,0.06051406860351527
79,oni,3.2,4.004117,0.8041170120239256
820,oni,10.7,9.254421,1.44557876586914
756,oni,10.3,9.224383,1.075616645812989
661,oni,2.9,3.5737593,0.6737593173980714
621,oni,8.2,7.816741,0.3832590103149407
414,oni,5.8,6.573568,0.7735678672790529
1162,oni,3.9,4.0557995,0.15579948425292978
127,oni,5.9,5.9219584,0.02195844650268519
358,oni,7.5,6.487585,1.0124149322509766
1163,oni,8.3,7.0331225,1.266877460479737
676,oni,2.6,3.9374194,1.3374194145202636
504,oni,6.1,6.345606,0.24560585021972692
344,oni,5.2,5.3761797,0.17617969512939435
1301,oni,2.0,2.720481,0.7204809188842773
169,oni,3.7,4.180386,0.4803860664367674
1370,oni,8.6,8.240398,0.35960159301757777
346,oni,6.4,7.2758265,0.8758264541625973
605,oni,6.9,7.0425806,0.1425806045532223
479,oni,4.9,4.89305,0.0069498062133792615
106,oni,5.1,5.164285,0.06428518295288121
1313,oni,5.3,5.9597716,0.6597716331481935
462,oni,7.3,6.5050087,0.7949913024902342
662,oni,7.4,7.203708,0.19629182815551793
998,oni,5.0,5.630293,0.6302928924560547
436,oni,3.7,3.9809625,0.28096251487731916
1 songno diff 상수 predicted_measure error
2 247 oni 5.5 5.2725 0.22749996185302734
3 246 oni 1.1 3.596659 2.496658945083618
4 1199 oni 4.3 2.9755948 1.324405241012573
5 860 oni 10.6 9.705553 0.8944469451904293
6 39 oni 5.6 6.1024475 0.5024475097656254
7 1279 oni 8.4 8.08667 0.31333007812500036
8 1178 oni 3.5 3.5068276 0.006827592849731445
9 1155 oni 4.3 3.6213677 0.6786323070526121
10 63 oni 6.1 5.844149 0.25585088729858363
11 641 oni 8.4 7.899804 0.5001958847045902
12 647 oni 7.8 7.7702703 0.02972965240478498
13 1026 oni 4.1 4.470079 0.37007894515991246
14 488 oni 5.7 5.910693 0.21069316864013654
15 773 oni 4.0 4.5387897 0.5387897491455078
16 1201 oni 1.9 3.921908 2.021907901763916
17 177 oni 2.0 2.8112068 0.8112068176269531
18 1039 oni 9.2 9.261316 0.06131629943847727
19 108 oni 6.8 7.2224617 0.4224617004394533
20 1059 oni 5.6 4.5673223 1.0326777458190914
21 1125 oni 3.6 3.8051248 0.20512475967407218
22 345 oni 4.5 4.752472 0.252471923828125
23 1186 oni 1.9 2.9006872 1.0006872177124024
24 1179 oni 5.0 5.2376785 0.23767852783203125
25 1411 oni 9.1 8.738385 0.36161479949951136
26 1145 oni 7.2 6.407096 0.7929040908813478
27 417 oni 3.3 3.5370734 0.23707337379455584
28 74 oni 4.5 5.398354 0.8983540534973145
29 544 oni 5.9 6.0266037 0.1266036987304684
30 935 oni 9.5 9.191151 0.3088493347167969
31 110 oni 10.9 7.6176825 3.2823175430297855
32 1319 oni 8.8 8.815666 0.01566619873046804
33 1228 oni 4.1 4.2427197 0.14271965026855504
34 615 oni 9.0 8.767521 0.23247909545898438
35 1146 oni 7.5 7.4651394 0.03486061096191406
36 405 oni 3.1 5.056039 1.9560388565063476
37 8 oni 2.2 3.7271776 1.5271776199340819
38 285 oni 4.3 4.8761697 0.5761696815490724
39 1286 oni 2.2 3.0876362 0.8876362323760985
40 259 oni 6.6 6.396202 0.2037979125976559
41 1274 oni 4.8 6.104219 1.3042189598083498
42 886 oni 1.9 3.2270806 1.3270805835723878
43 1118 oni 1.2 2.8580723 1.658072280883789
44 1176 oni 4.0 3.527431 0.47256898880004883
45 42 oni 1.1 3.3398852 2.2398852348327636
46 799 oni 5.7 4.7683806 0.9316193580627443
47 967 oni 8.8 7.698433 1.1015670776367195
48 539 oni 6.0 6.0380173 0.03801727294921875
49 445 oni 7.1 6.515002 0.5849982261657711
50 482 oni 1.8 3.32895 1.5289499282836914
51 1355 oni 9.0 7.8457313 1.154268741607666
52 22 oni 5.5 6.1377096 0.6377096176147461
53 113 oni 5.7 5.555111 0.1448890686035158
54 739 oni 7.1 7.8227615 0.7227615356445316
55 794 oni 7.6 7.0705323 0.529467678070068
56 355 oni 10.0 8.396488 1.6035118103027344
57 455 oni 5.7 5.748408 0.04840784072875959
58 775 oni 10.6 9.172316 1.42768440246582
59 1418 oni 8.0 7.8505096 0.1494903564453125
60 478 oni 5.8 4.8743525 0.9256475448608397
61 236 oni 2.2 4.2807217 2.0807216644287108
62 1311 oni 6.7 7.5999484 0.8999484062194822
63 790 oni 2.5 3.3790677 0.8790676593780518
64 88 oni 8.1 7.4207373 0.6792627334594723
65 660 oni 6.6 6.459454 0.14054594039916957
66 939 oni 7.4 7.2584605 0.1415394783020023
67 1100 oni 3.9 4.6481123 0.7481122970581056
68 1001 oni 3.6 3.5810204 0.018979644775390714
69 248 oni 6.2 6.3501973 0.15019731521606428
70 341 oni 3.3 4.576923 1.27692289352417
71 644 oni 4.4 4.404581 0.004581069946288707
72 472 oni 5.9 6.3437867 0.4437867164611813
73 792 oni 3.7 3.8640676 0.16406755447387678
74 428 oni 6.5 6.3807287 0.11927127838134766
75 754 oni 5.0 5.1724863 0.1724863052368164
76 1133 oni 5.7 6.4210324 0.7210324287414549
77 1235 oni 7.8 7.6141486 0.18585138320922834
78 1317 oni 11.2 10.63248 0.5675203323364251
79 1106 oni 9.1 8.950381 0.14961872100830043
80 601 oni 3.5 4.1207476 0.6207475662231445
81 1432 oni 10.0 8.503614 1.4963855743408203
82 1207 oni 7.8 7.735499 0.06450109481811506
83 1208 oni 4.3 5.267852 0.9678518295288088
84 578 oni 6.5 5.0540576 1.4459424018859863
85 1031 oni 4.7 4.8403573 0.1403573036193846
86 491 oni 8.2 8.015301 0.18469924926757741
87 843 oni 10.0 9.856177 0.14382266998291016
88 1261 oni 7.3 7.2535615 0.04643850326538068
89 816 oni 8.2 8.119859 0.08014125823974538
90 1337 oni 3.9 4.6578474 0.7578474044799806
91 1072 oni 9.8 7.600742 2.1992581367492683
92 37 oni 5.3 5.2767086 0.023291397094726385
93 556 oni 4.4 4.318159 0.08184089660644567
94 596 oni 6.8 6.5767 0.22329978942871076
95 933 oni 7.1 7.283629 0.18362894058227575
96 270 oni 6.9 6.4714212 0.42857875823974645
97 911 oni 4.7 4.7063766 0.006376552581786932
98 160 oni 5.3 5.3374934 0.037493419647216975
99 399 oni 7.6 7.693502 0.09350194931030309
100 1080 oni 8.0 7.970645 0.02935504913330078
101 746 oni 8.0 8.314695 0.3146953582763672
102 427 oni 9.1 8.443438 0.6565624237060543
103 1296 oni 7.9 8.019875 0.1198745727539059
104 380 oni 4.6 4.371937 0.22806320190429652
105 1004 oni 5.9 5.448553 0.4514469146728519
106 266 oni 6.3 8.509695 2.209695053100586
107 624 oni 5.6 5.243518 0.3564821243286129
108 750 oni 8.8 8.119534 0.6804664611816413
109 1105 oni 5.5 4.0916586 1.408341407775879
110 1362 oni 6.1 5.757848 0.3421522140502926
111 1202 oni 4.8 4.697151 0.10284881591796857
112 396 oni 5.8 6.155394 0.35539407730102557
113 219 oni 5.1 4.664316 0.4356838226318356
114 124 oni 5.5 5.801539 0.30153894424438477
115 32 oni 6.8 6.472562 0.32743816375732404
116 33 oni 10.5 8.676422 1.823577880859375
117 819 oni 8.6 7.86986 0.7301398277282711
118 506 oni 5.6 3.7444363 1.8555637359619137
119 364 oni 5.2 5.2186875 0.018687534332275213
120 218 oni 7.7 7.626425 0.07357521057128924
121 55 oni 8.7 7.312134 1.3878662109374993
122 1225 oni 5.3 4.8498535 0.4501464843749998
123 150 oni 6.3 5.750553 0.5494468688964842
124 689 oni 4.3 4.3800893 0.08008928298950213
125 1356 oni 9.4 8.77751 0.6224903106689457
126 339 oni 6.8 3.677099 3.1229010105133055
127 571 oni 9.1 7.775726 1.3242741584777828
128 1336 oni 2.9 3.8107193 0.9107192516326905
129 360 oni 9.2 8.764785 0.4352151870727532
130 762 oni 10.3 10.230464 0.06953601837158274
131 1095 oni 6.2 4.828952 1.371048164367676
132 1422 oni 5.6 5.737846 0.1378458976745609
133 1150 oni 4.1 4.486331 0.3863309860229496
134 738 oni 7.9 7.607025 0.29297485351562536
135 95 oni 7.3 7.3256226 0.025622558593750178
136 1173 oni 9.2 8.770874 0.4291259765624993
137 611 oni 3.8 3.7210314 0.07896857261657697
138 415 oni 1.8 3.6390128 1.8390128135681152
139 420 oni 4.3 4.0958514 0.20414857864379865
140 1450 oni 2.9 3.2371683 0.337168312072754
141 312 oni 1.1 2.8274343 1.7274343013763427
142 193 oni 4.4 6.1280093 1.7280093193054196
143 925 oni 5.2 3.687907 1.5120930194854738
144 846 oni 8.5 8.5911455 0.09114551544189453
145 549 oni 8.3 8.18619 0.1138103485107429
146 103 oni 8.2 8.056568 0.14343185424804616
147 517 oni 8.2 8.255187 0.055187034606934304
148 627 oni 11.5 9.760542 1.7394580841064453
149 60 oni 7.9 7.881064 0.018936061859131215
150 948 oni 8.3 8.36591 0.06590957641601491
151 1019 oni 5.5 5.212821 0.28717899322509766
152 680 oni 7.9 7.9404883 0.04048833847045863
153 142 oni 3.0 3.7907765 0.7907764911651611
154 460 oni 2.7 2.6523027 0.047697257995605646
155 315 oni 3.2 4.228785 1.0287850379943846
156 1149 oni 3.8 6.2704215 2.4704215049743654
157 887 oni 7.2 6.998309 0.20169086456298846
158 1177 oni 3.4 4.0435953 0.643595314025879
159 1018 oni 4.9 4.9320893 0.032089328765868785
160 1252 oni 4.9 4.427538 0.47246208190918004
161 1250 oni 6.0 6.7224565 0.7224564552307129
162 1172 oni 11.9 10.33794 1.5620597839355472
163 167 oni 7.1 8.270915 1.1709150314331058
164 1074 oni 3.1 2.9782546 0.1217454433441163
165 931 oni 7.7 6.1198707 1.5801293373107912
166 1412 oni 6.2 6.288117 0.08811693191528303
167 955 oni 10.5 8.674553 1.8254470825195312
168 220 oni 9.3 8.375487 0.9245126724243171
169 1153 oni 1.8 2.7926855 0.9926855087280273
170 214 oni 7.8 7.8332896 0.033289623260498225
171 1119 oni 5.2 4.9443893 0.2556106567382814
172 824 oni 1.3 2.3053257 1.0053257465362548
173 757 oni 10.5 9.727542 0.7724580764770508
174 943 oni 9.6 8.187772 1.4122282028198239
175 1403 oni 5.0 3.9427001 1.0572998523712158
176 93 oni 5.9 5.960514 0.06051406860351527
177 79 oni 3.2 4.004117 0.8041170120239256
178 820 oni 10.7 9.254421 1.44557876586914
179 756 oni 10.3 9.224383 1.075616645812989
180 661 oni 2.9 3.5737593 0.6737593173980714
181 621 oni 8.2 7.816741 0.3832590103149407
182 414 oni 5.8 6.573568 0.7735678672790529
183 1162 oni 3.9 4.0557995 0.15579948425292978
184 127 oni 5.9 5.9219584 0.02195844650268519
185 358 oni 7.5 6.487585 1.0124149322509766
186 1163 oni 8.3 7.0331225 1.266877460479737
187 676 oni 2.6 3.9374194 1.3374194145202636
188 504 oni 6.1 6.345606 0.24560585021972692
189 344 oni 5.2 5.3761797 0.17617969512939435
190 1301 oni 2.0 2.720481 0.7204809188842773
191 169 oni 3.7 4.180386 0.4803860664367674
192 1370 oni 8.6 8.240398 0.35960159301757777
193 346 oni 6.4 7.2758265 0.8758264541625973
194 605 oni 6.9 7.0425806 0.1425806045532223
195 479 oni 4.9 4.89305 0.0069498062133792615
196 106 oni 5.1 5.164285 0.06428518295288121
197 1313 oni 5.3 5.9597716 0.6597716331481935
198 462 oni 7.3 6.5050087 0.7949913024902342
199 662 oni 7.4 7.203708 0.19629182815551793
200 998 oni 5.0 5.630293 0.6302928924560547
201 436 oni 3.7 3.9809625 0.28096251487731916

201
test/validate_result_2.csv Normal file
View File

@@ -0,0 +1,201 @@
songno,diff,상수,predicted_measure,error
407,oni,7.4,7.7118516,0.31185159683227504
639,oni,7.0,7.128337,0.12833690643310547
1126,oni,3.9,4.162916,0.2629161834716798
555,oni,11.3,9.773656,1.5263441085815437
874,oni,7.0,7.1630692,0.1630692481994629
90,oni,5.6,6.219878,0.619878196716309
1043,oni,9.8,9.010322,0.7896783828735359
680,oni,7.9,8.108603,0.20860252380371058
418,oni,8.2,6.1271896,2.0728103637695305
1348,oni,6.7,4.6488576,2.0511424064636232
39,oni,5.6,6.254499,0.6544989585876468
1403,oni,5.0,4.69633,0.30366992950439453
1208,oni,4.3,4.714694,0.4146940231323244
652,oni,3.7,3.638977,0.06102294921875018
266,oni,6.3,8.5091305,2.2091304779052736
1032,oni,3.9,4.147311,0.2473112106323243
1053,oni,4.6,4.974226,0.37422599792480504
278,oni,3.8,4.252946,0.4529458999633791
381,oni,2.3,4.2555227,1.9555227279663088
1044,oni,5.3,3.7092085,1.5907915115356444
927,oni,8.9,8.400599,0.4994014739990238
363,oni,8.1,8.048794,0.05120620727539027
980,oni,8.8,8.687542,0.11245803833007884
699,oni,9.7,9.935864,0.235864448547364
914,oni,8.7,8.6761675,0.023832511901854758
1199,oni,4.3,2.9498258,1.3501742362976072
765,oni,11.9,10.781875,1.1181253433227543
753,oni,5.3,5.75474,0.45474023818969744
779,oni,8.5,8.14912,0.3508796691894531
1425,oni,7.9,8.336508,0.4365077972412106
324,oni,5.6,5.707896,0.10789623260498082
974,oni,1.5,2.5264485,1.0264484882354736
1104,oni,9.7,9.071495,0.6285049438476555
462,oni,7.3,6.2004747,1.0995252609252928
627,oni,11.5,9.855917,1.644083023071289
968,oni,7.0,7.2786546,0.2786545753479004
1410,oni,3.0,3.9265063,0.9265062808990479
972,oni,7.5,6.7958617,0.7041382789611816
569,oni,7.2,8.108791,0.9087913513183592
574,oni,8.6,8.728794,0.12879409790039098
118,oni,3.0,3.6167395,0.6167395114898682
561,oni,5.5,5.479089,0.020911216735839844
990,oni,10.9,9.822301,1.0776990890502933
1067,oni,9.2,8.314178,0.8858215332031243
17,oni,7.3,7.1151476,0.1848524093627928
256,oni,4.9,4.069125,0.8308748245239261
846,oni,8.5,8.806922,0.30692195892333984
1243,oni,1.1,2.1853628,1.0853628158569335
76,oni,3.5,4.2370133,0.7370133399963379
1414,oni,5.2,4.528089,0.6719109535217287
43,oni,8.1,7.666461,0.4335390090942379
1280,oni,3.9,4.175297,0.2752967834472657
1066,oni,11.0,9.642129,1.3578710556030273
1160,oni,6.3,6.311124,0.011123847961425959
571,oni,9.1,7.8507853,1.2492147445678707
572,oni,8.3,7.7374845,0.5625155448913581
137,oni,6.1,6.2259655,0.12596549987793004
673,oni,8.9,7.898995,1.001005077362061
668,oni,3.4,3.8651383,0.46513829231262216
1407,oni,2.8,3.590128,0.7901279449462892
483,oni,7.1,6.679802,0.4201980590820309
307,oni,4.1,4.5094666,0.409466648101807
1352,oni,8.0,9.46934,1.4693403244018555
155,oni,7.2,6.6420507,0.5579492568969728
1233,oni,4.1,4.225732,0.1257318496704105
623,oni,5.0,4.3235593,0.6764407157897949
1450,oni,2.9,3.1810834,0.28108344078063974
777,oni,10.8,9.084598,1.7154024124145515
1322,oni,7.9,8.072512,0.17251167297363246
593,oni,10.6,9.33769,1.262309646606445
1426,oni,6.2,5.1146894,1.0853106498718263
526,oni,7.9,7.9039993,0.003999328613280895
1451,oni,5.1,5.3727984,0.2727984428405765
1018,oni,4.9,4.897191,0.002808952331543324
139,oni,4.8,5.9494166,1.1494166374206545
988,oni,5.3,7.3648434,2.0648433685302736
1052,oni,8.1,7.9982395,0.10176048278808558
148,oni,9.7,9.190443,0.5095569610595696
781,oni,10.1,9.420827,0.6791730880737301
136,oni,9.1,8.9569,0.1431003570556637
1138,oni,4.1,4.5386105,0.4386104583740238
573,oni,8.0,7.7697043,0.23029565811157227
689,oni,4.3,4.3181367,0.018136692047119318
823,oni,5.8,5.803063,0.0030629158020021308
1319,oni,8.8,8.832512,0.03251190185546804
1447,oni,10.4,8.193739,2.2062610626220707
771,oni,3.3,3.8071642,0.5071641921997072
920,oni,4.9,5.6871243,0.7871242523193356
928,oni,10.3,8.788698,1.511301803588868
100,oni,5.3,5.470746,0.17074604034423846
1305,oni,7.8,7.1164837,0.6835163116455076
1465,oni,6.8,6.7193513,0.08064870834350568
1081,oni,5.4,5.8754663,0.4754663467407223
1264,oni,7.5,7.5121713,0.012171268463134766
1026,oni,4.1,4.4330683,0.3330682754516605
856,oni,8.8,8.940483,0.14048309326171804
214,oni,7.8,7.827591,0.027590942382812678
714,oni,9.4,6.447624,2.9523757934570316
1183,oni,6.5,6.3542147,0.14578533172607422
1336,oni,2.9,3.8588686,0.9588685989379884
626,oni,6.3,6.305609,0.005609226226806818
754,oni,5.0,5.492872,0.4928722381591797
364,oni,5.2,5.2130685,0.013068485260009588
352,oni,2.5,4.5982647,2.098264694213867
1192,oni,5.7,5.5247087,0.17529125213623065
1281,oni,2.2,2.4992957,0.2992957115173338
1241,oni,5.0,4.964304,0.03569602966308594
120,oni,11.9,9.389377,2.510623359680176
467,oni,2.9,3.4955206,0.5955205917358399
758,oni,10.8,9.998916,0.8010843276977546
1191,oni,5.4,5.5138097,0.11380968093872035
747,oni,7.3,6.978402,0.32159786224365217
969,oni,5.6,5.6307874,0.030787372589111683
773,oni,4.0,4.538554,0.5385541915893555
1110,oni,1.7,2.6193855,0.9193854808807373
1335,oni,4.0,4.2992277,0.2992277145385742
630,oni,9.3,8.60483,0.6951702117919929
115,oni,2.3,4.1506577,1.850657653808594
1394,oni,10.3,9.72695,0.5730503082275398
745,oni,10.4,9.549488,0.8505119323730472
1423,oni,4.7,4.4789248,0.2210752487182619
1145,oni,7.2,6.2197733,0.9802267074584963
67,oni,7.6,7.0234313,0.5765686988830563
1202,oni,4.8,4.632943,0.16705684661865217
126,oni,4.6,4.020031,0.5799690246582028
1096,oni,5.1,4.463463,0.6365371704101559
1301,oni,2.0,2.8766239,0.8766238689422607
141,oni,4.6,4.6933184,0.09331836700439489
1275,oni,4.1,6.1221576,2.0221575736999515
424,oni,6.3,6.322995,0.02299518585205096
215,oni,6.6,6.9068832,0.3068832397460941
1310,oni,6.0,4.274131,1.7258691787719727
314,oni,1.3,2.937756,1.637756061553955
808,oni,6.2,5.1405373,1.0594627380371096
1244,oni,1.6,3.5983038,1.9983037948608398
686,oni,8.7,7.853119,0.8468811035156243
152,oni,7.9,8.261536,0.36153564453124964
1412,oni,6.2,6.2849617,0.08496170043945295
446,oni,6.8,6.535924,0.2640760421752928
1136,oni,2.7,3.8286126,1.1286125659942625
449,oni,8.1,7.7637753,0.33622465133666957
86,oni,6.8,6.7608147,0.03918533325195295
194,oni,9.4,7.5551414,1.844858551025391
1413,oni,7.6,7.0943885,0.5056115150451657
159,oni,7.5,7.6529474,0.15294742584228516
1146,oni,7.5,7.5121713,0.012171268463134766
984,oni,4.2,4.733321,0.5333211898803709
53,oni,6.4,6.609403,0.20940313339233363
861,oni,4.2,4.521036,0.3210361480712889
1424,oni,6.4,6.31289,0.0871099472045902
85,oni,7.4,5.647832,1.7521680831909183
55,oni,8.7,7.400382,1.299617958068847
1307,oni,6.9,7.1966534,0.29665336608886683
1333,oni,1.7,2.1893477,0.48934774398803715
1313,oni,5.3,5.455302,0.15530176162719744
21,oni,8.1,7.816301,0.28369913101196254
1103,oni,4.8,4.99246,0.19245977401733416
1054,oni,3.9,4.2977943,0.3977943420410157
1193,oni,4.4,4.5527945,0.15279445648193324
1050,oni,9.2,8.187371,1.0126287460327141
672,oni,2.4,3.8383086,1.4383085727691651
432,oni,6.6,6.8880315,0.28803148269653356
650,oni,6.4,6.191967,0.20803298950195348
1420,oni,3.7,3.585551,0.11444897651672381
940,oni,9.1,8.561063,0.5389371871948239
10,oni,7.8,7.303648,0.49635200500488263
309,oni,6.6,5.9738116,0.6261883735656735
114,oni,7.0,7.161101,0.1611008644104004
261,oni,7.4,7.657537,0.2575369834899899
477,oni,9.3,9.070963,0.22903709411621165
670,oni,8.1,8.589176,0.489176177978516
536,oni,6.7,6.779605,0.07960491180419904
113,oni,5.7,5.5914326,0.10856742858886737
575,oni,9.8,6.3821473,3.417852687835694
179,oni,10.2,9.090903,1.109096717834472
693,oni,4.6,4.6827374,0.08273735046386754
107,oni,4.6,4.8170347,0.21703472137451207
384,oni,2.1,3.6001546,1.5001546382904052
146,oni,4.1,4.492044,0.3920439720153812
178,oni,6.8,6.463874,0.336126136779785
1174,oni,6.2,6.399553,0.19955282211303693
1271,oni,4.8,4.3153443,0.4846556663513182
1343,oni,1.4,2.935083,1.5350829124450684
798,oni,9.1,8.743355,0.3566452026367184
963,oni,7.1,6.6011505,0.49884948730468714
850,oni,10.7,9.177441,1.5225593566894524
1402,oni,5.8,4.785289,1.0147111892700194
367,oni,5.8,6.2457614,0.4457613945007326
1362,oni,6.1,5.7599487,0.34005126953124964
1370,oni,8.6,8.127836,0.47216377258300746
1175,oni,4.5,4.550432,0.05043220520019531
345,oni,4.5,4.60553,0.10552978515625
800,oni,7.3,6.731179,0.5688207626342772
1411,oni,9.1,8.82227,0.2777296066284176
380,oni,4.6,4.054151,0.5458489418029782
1250,oni,6.0,6.232577,0.23257684707641602
886,oni,1.9,3.3799245,1.4799245357513429
427,oni,9.1,8.462549,0.6374507904052731
1286,oni,2.2,3.2965052,1.0965052127838133
321,oni,6.3,6.2949524,0.005047607421874822
1 songno diff 상수 predicted_measure error
2 407 oni 7.4 7.7118516 0.31185159683227504
3 639 oni 7.0 7.128337 0.12833690643310547
4 1126 oni 3.9 4.162916 0.2629161834716798
5 555 oni 11.3 9.773656 1.5263441085815437
6 874 oni 7.0 7.1630692 0.1630692481994629
7 90 oni 5.6 6.219878 0.619878196716309
8 1043 oni 9.8 9.010322 0.7896783828735359
9 680 oni 7.9 8.108603 0.20860252380371058
10 418 oni 8.2 6.1271896 2.0728103637695305
11 1348 oni 6.7 4.6488576 2.0511424064636232
12 39 oni 5.6 6.254499 0.6544989585876468
13 1403 oni 5.0 4.69633 0.30366992950439453
14 1208 oni 4.3 4.714694 0.4146940231323244
15 652 oni 3.7 3.638977 0.06102294921875018
16 266 oni 6.3 8.5091305 2.2091304779052736
17 1032 oni 3.9 4.147311 0.2473112106323243
18 1053 oni 4.6 4.974226 0.37422599792480504
19 278 oni 3.8 4.252946 0.4529458999633791
20 381 oni 2.3 4.2555227 1.9555227279663088
21 1044 oni 5.3 3.7092085 1.5907915115356444
22 927 oni 8.9 8.400599 0.4994014739990238
23 363 oni 8.1 8.048794 0.05120620727539027
24 980 oni 8.8 8.687542 0.11245803833007884
25 699 oni 9.7 9.935864 0.235864448547364
26 914 oni 8.7 8.6761675 0.023832511901854758
27 1199 oni 4.3 2.9498258 1.3501742362976072
28 765 oni 11.9 10.781875 1.1181253433227543
29 753 oni 5.3 5.75474 0.45474023818969744
30 779 oni 8.5 8.14912 0.3508796691894531
31 1425 oni 7.9 8.336508 0.4365077972412106
32 324 oni 5.6 5.707896 0.10789623260498082
33 974 oni 1.5 2.5264485 1.0264484882354736
34 1104 oni 9.7 9.071495 0.6285049438476555
35 462 oni 7.3 6.2004747 1.0995252609252928
36 627 oni 11.5 9.855917 1.644083023071289
37 968 oni 7.0 7.2786546 0.2786545753479004
38 1410 oni 3.0 3.9265063 0.9265062808990479
39 972 oni 7.5 6.7958617 0.7041382789611816
40 569 oni 7.2 8.108791 0.9087913513183592
41 574 oni 8.6 8.728794 0.12879409790039098
42 118 oni 3.0 3.6167395 0.6167395114898682
43 561 oni 5.5 5.479089 0.020911216735839844
44 990 oni 10.9 9.822301 1.0776990890502933
45 1067 oni 9.2 8.314178 0.8858215332031243
46 17 oni 7.3 7.1151476 0.1848524093627928
47 256 oni 4.9 4.069125 0.8308748245239261
48 846 oni 8.5 8.806922 0.30692195892333984
49 1243 oni 1.1 2.1853628 1.0853628158569335
50 76 oni 3.5 4.2370133 0.7370133399963379
51 1414 oni 5.2 4.528089 0.6719109535217287
52 43 oni 8.1 7.666461 0.4335390090942379
53 1280 oni 3.9 4.175297 0.2752967834472657
54 1066 oni 11.0 9.642129 1.3578710556030273
55 1160 oni 6.3 6.311124 0.011123847961425959
56 571 oni 9.1 7.8507853 1.2492147445678707
57 572 oni 8.3 7.7374845 0.5625155448913581
58 137 oni 6.1 6.2259655 0.12596549987793004
59 673 oni 8.9 7.898995 1.001005077362061
60 668 oni 3.4 3.8651383 0.46513829231262216
61 1407 oni 2.8 3.590128 0.7901279449462892
62 483 oni 7.1 6.679802 0.4201980590820309
63 307 oni 4.1 4.5094666 0.409466648101807
64 1352 oni 8.0 9.46934 1.4693403244018555
65 155 oni 7.2 6.6420507 0.5579492568969728
66 1233 oni 4.1 4.225732 0.1257318496704105
67 623 oni 5.0 4.3235593 0.6764407157897949
68 1450 oni 2.9 3.1810834 0.28108344078063974
69 777 oni 10.8 9.084598 1.7154024124145515
70 1322 oni 7.9 8.072512 0.17251167297363246
71 593 oni 10.6 9.33769 1.262309646606445
72 1426 oni 6.2 5.1146894 1.0853106498718263
73 526 oni 7.9 7.9039993 0.003999328613280895
74 1451 oni 5.1 5.3727984 0.2727984428405765
75 1018 oni 4.9 4.897191 0.002808952331543324
76 139 oni 4.8 5.9494166 1.1494166374206545
77 988 oni 5.3 7.3648434 2.0648433685302736
78 1052 oni 8.1 7.9982395 0.10176048278808558
79 148 oni 9.7 9.190443 0.5095569610595696
80 781 oni 10.1 9.420827 0.6791730880737301
81 136 oni 9.1 8.9569 0.1431003570556637
82 1138 oni 4.1 4.5386105 0.4386104583740238
83 573 oni 8.0 7.7697043 0.23029565811157227
84 689 oni 4.3 4.3181367 0.018136692047119318
85 823 oni 5.8 5.803063 0.0030629158020021308
86 1319 oni 8.8 8.832512 0.03251190185546804
87 1447 oni 10.4 8.193739 2.2062610626220707
88 771 oni 3.3 3.8071642 0.5071641921997072
89 920 oni 4.9 5.6871243 0.7871242523193356
90 928 oni 10.3 8.788698 1.511301803588868
91 100 oni 5.3 5.470746 0.17074604034423846
92 1305 oni 7.8 7.1164837 0.6835163116455076
93 1465 oni 6.8 6.7193513 0.08064870834350568
94 1081 oni 5.4 5.8754663 0.4754663467407223
95 1264 oni 7.5 7.5121713 0.012171268463134766
96 1026 oni 4.1 4.4330683 0.3330682754516605
97 856 oni 8.8 8.940483 0.14048309326171804
98 214 oni 7.8 7.827591 0.027590942382812678
99 714 oni 9.4 6.447624 2.9523757934570316
100 1183 oni 6.5 6.3542147 0.14578533172607422
101 1336 oni 2.9 3.8588686 0.9588685989379884
102 626 oni 6.3 6.305609 0.005609226226806818
103 754 oni 5.0 5.492872 0.4928722381591797
104 364 oni 5.2 5.2130685 0.013068485260009588
105 352 oni 2.5 4.5982647 2.098264694213867
106 1192 oni 5.7 5.5247087 0.17529125213623065
107 1281 oni 2.2 2.4992957 0.2992957115173338
108 1241 oni 5.0 4.964304 0.03569602966308594
109 120 oni 11.9 9.389377 2.510623359680176
110 467 oni 2.9 3.4955206 0.5955205917358399
111 758 oni 10.8 9.998916 0.8010843276977546
112 1191 oni 5.4 5.5138097 0.11380968093872035
113 747 oni 7.3 6.978402 0.32159786224365217
114 969 oni 5.6 5.6307874 0.030787372589111683
115 773 oni 4.0 4.538554 0.5385541915893555
116 1110 oni 1.7 2.6193855 0.9193854808807373
117 1335 oni 4.0 4.2992277 0.2992277145385742
118 630 oni 9.3 8.60483 0.6951702117919929
119 115 oni 2.3 4.1506577 1.850657653808594
120 1394 oni 10.3 9.72695 0.5730503082275398
121 745 oni 10.4 9.549488 0.8505119323730472
122 1423 oni 4.7 4.4789248 0.2210752487182619
123 1145 oni 7.2 6.2197733 0.9802267074584963
124 67 oni 7.6 7.0234313 0.5765686988830563
125 1202 oni 4.8 4.632943 0.16705684661865217
126 126 oni 4.6 4.020031 0.5799690246582028
127 1096 oni 5.1 4.463463 0.6365371704101559
128 1301 oni 2.0 2.8766239 0.8766238689422607
129 141 oni 4.6 4.6933184 0.09331836700439489
130 1275 oni 4.1 6.1221576 2.0221575736999515
131 424 oni 6.3 6.322995 0.02299518585205096
132 215 oni 6.6 6.9068832 0.3068832397460941
133 1310 oni 6.0 4.274131 1.7258691787719727
134 314 oni 1.3 2.937756 1.637756061553955
135 808 oni 6.2 5.1405373 1.0594627380371096
136 1244 oni 1.6 3.5983038 1.9983037948608398
137 686 oni 8.7 7.853119 0.8468811035156243
138 152 oni 7.9 8.261536 0.36153564453124964
139 1412 oni 6.2 6.2849617 0.08496170043945295
140 446 oni 6.8 6.535924 0.2640760421752928
141 1136 oni 2.7 3.8286126 1.1286125659942625
142 449 oni 8.1 7.7637753 0.33622465133666957
143 86 oni 6.8 6.7608147 0.03918533325195295
144 194 oni 9.4 7.5551414 1.844858551025391
145 1413 oni 7.6 7.0943885 0.5056115150451657
146 159 oni 7.5 7.6529474 0.15294742584228516
147 1146 oni 7.5 7.5121713 0.012171268463134766
148 984 oni 4.2 4.733321 0.5333211898803709
149 53 oni 6.4 6.609403 0.20940313339233363
150 861 oni 4.2 4.521036 0.3210361480712889
151 1424 oni 6.4 6.31289 0.0871099472045902
152 85 oni 7.4 5.647832 1.7521680831909183
153 55 oni 8.7 7.400382 1.299617958068847
154 1307 oni 6.9 7.1966534 0.29665336608886683
155 1333 oni 1.7 2.1893477 0.48934774398803715
156 1313 oni 5.3 5.455302 0.15530176162719744
157 21 oni 8.1 7.816301 0.28369913101196254
158 1103 oni 4.8 4.99246 0.19245977401733416
159 1054 oni 3.9 4.2977943 0.3977943420410157
160 1193 oni 4.4 4.5527945 0.15279445648193324
161 1050 oni 9.2 8.187371 1.0126287460327141
162 672 oni 2.4 3.8383086 1.4383085727691651
163 432 oni 6.6 6.8880315 0.28803148269653356
164 650 oni 6.4 6.191967 0.20803298950195348
165 1420 oni 3.7 3.585551 0.11444897651672381
166 940 oni 9.1 8.561063 0.5389371871948239
167 10 oni 7.8 7.303648 0.49635200500488263
168 309 oni 6.6 5.9738116 0.6261883735656735
169 114 oni 7.0 7.161101 0.1611008644104004
170 261 oni 7.4 7.657537 0.2575369834899899
171 477 oni 9.3 9.070963 0.22903709411621165
172 670 oni 8.1 8.589176 0.489176177978516
173 536 oni 6.7 6.779605 0.07960491180419904
174 113 oni 5.7 5.5914326 0.10856742858886737
175 575 oni 9.8 6.3821473 3.417852687835694
176 179 oni 10.2 9.090903 1.109096717834472
177 693 oni 4.6 4.6827374 0.08273735046386754
178 107 oni 4.6 4.8170347 0.21703472137451207
179 384 oni 2.1 3.6001546 1.5001546382904052
180 146 oni 4.1 4.492044 0.3920439720153812
181 178 oni 6.8 6.463874 0.336126136779785
182 1174 oni 6.2 6.399553 0.19955282211303693
183 1271 oni 4.8 4.3153443 0.4846556663513182
184 1343 oni 1.4 2.935083 1.5350829124450684
185 798 oni 9.1 8.743355 0.3566452026367184
186 963 oni 7.1 6.6011505 0.49884948730468714
187 850 oni 10.7 9.177441 1.5225593566894524
188 1402 oni 5.8 4.785289 1.0147111892700194
189 367 oni 5.8 6.2457614 0.4457613945007326
190 1362 oni 6.1 5.7599487 0.34005126953124964
191 1370 oni 8.6 8.127836 0.47216377258300746
192 1175 oni 4.5 4.550432 0.05043220520019531
193 345 oni 4.5 4.60553 0.10552978515625
194 800 oni 7.3 6.731179 0.5688207626342772
195 1411 oni 9.1 8.82227 0.2777296066284176
196 380 oni 4.6 4.054151 0.5458489418029782
197 1250 oni 6.0 6.232577 0.23257684707641602
198 886 oni 1.9 3.3799245 1.4799245357513429
199 427 oni 9.1 8.462549 0.6374507904052731
200 1286 oni 2.2 3.2965052 1.0965052127838133
201 321 oni 6.3 6.2949524 0.005047607421874822

201
test/validate_result_3.csv Normal file
View File

@@ -0,0 +1,201 @@
songno,diff,상수,predicted_measure,error
1333,oni,1.7,2.1903424,0.4903424263000489
503,oni,11.3,9.012293,2.287707138061524
273,oni,3.3,3.3733163,0.07331628799438494
1043,oni,9.8,8.805077,0.994923400878907
82,oni,5.7,3.7766702,1.923329782485962
973,oni,4.0,5.0434604,1.0434603691101074
1076,oni,2.1,2.9520278,0.8520277976989745
512,oni,3.4,4.0293465,0.6293464660644532
367,oni,5.8,5.824023,0.024022769927978693
1334,oni,4.0,4.304007,0.30400705337524414
246,oni,1.1,3.409812,2.3098119735717773
438,oni,7.7,7.679233,0.020766925811767756
764,oni,11.2,9.896853,1.30314655303955
19,oni,7.5,6.6001863,0.8998136520385742
422,oni,3.0,4.4134846,1.4134845733642578
1014,oni,5.3,5.425547,0.12554712295532244
1307,oni,6.9,7.224358,0.3243580818176266
1149,oni,3.8,5.3673983,1.567398262023926
819,oni,8.6,7.9465976,0.6534024238586422
998,oni,5.0,5.2953377,0.2953376770019531
1417,oni,4.2,4.0317307,0.16826934814453143
1268,oni,6.3,6.2643814,0.03561859130859357
1450,oni,2.9,2.9973252,0.09732518196105966
80,oni,8.4,8.044008,0.35599174499511754
1337,oni,3.9,5.037738,1.1377378463745118
83,oni,6.0,5.979888,0.020112037658691406
465,oni,6.9,7.4996314,0.5996314048767086
323,oni,4.3,4.1757064,0.12429361343383771
396,oni,5.8,6.364714,0.5647141456604006
207,oni,4.2,3.5814035,0.6185965061187746
546,oni,6.8,6.922099,0.12209911346435565
886,oni,1.9,3.2264843,1.3264842987060548
5,oni,8.3,8.024653,0.27534656524658274
259,oni,6.6,6.3496404,0.25035963058471644
470,oni,5.0,5.19226,0.1922597885131836
689,oni,4.3,4.29064,0.009360122680663885
537,oni,6.9,7.8368387,0.9368387222290036
748,oni,10.8,9.44193,1.3580701828002937
558,oni,8.5,8.089595,0.41040515899658203
339,oni,6.8,3.8407266,2.9592733860015867
1171,oni,6.1,5.2119055,0.8880945205688473
430,oni,1.5,3.211008,1.711008071899414
40,oni,4.6,4.4078455,0.192154502868652
266,oni,6.3,8.231991,1.9319908142089846
1162,oni,3.9,3.978352,0.07835206985473642
997,oni,4.0,4.5425763,0.5425763130187988
908,oni,6.0,5.789243,0.21075677871704102
1080,oni,8.0,8.286018,0.28601837158203125
487,oni,3.5,5.0209293,1.5209293365478516
552,oni,6.5,6.185847,0.31415319442749023
852,oni,6.6,5.719363,0.8806367874145504
267,oni,3.6,3.7225535,0.12255349159240714
898,oni,3.8,4.8149214,1.0149213790893556
1391,oni,7.8,7.943273,0.1432730674743654
1042,oni,10.1,8.874695,1.2253051757812496
823,oni,5.8,5.9181585,0.11815853118896502
1370,oni,8.6,8.115248,0.48475227355956996
264,oni,4.8,5.9249053,1.124905300140381
491,oni,8.2,7.98736,0.21263999938964773
753,oni,5.3,5.92183,0.6218301773071291
383,oni,6.1,5.850947,0.24905309677123988
310,oni,6.2,6.476375,0.276375102996826
1081,oni,5.4,5.913851,0.5138507843017575
610,oni,6.0,6.194362,0.19436216354370117
8,oni,2.2,3.7589507,1.5589507102966307
716,oni,6.8,4.285139,2.514860916137695
1452,oni,8.1,8.181307,0.08130683898925817
698,oni,9.9,9.351179,0.5488208770751957
843,oni,10.0,9.872733,0.12726688385009766
1181,oni,3.3,3.4767451,0.17674512863159197
739,oni,7.1,7.91916,0.8191598892211918
933,oni,7.1,7.2560177,0.1560176849365238
540,oni,5.9,6.3700414,0.47004137039184535
1206,oni,7.6,7.545701,0.05429897308349574
108,oni,6.8,7.3288846,0.5288846015930178
685,oni,10.4,9.550256,0.8497442245483402
52,oni,5.2,7.3442254,2.1442254066467283
573,oni,8.0,7.9685845,0.031415462493896484
948,oni,8.3,8.540495,0.24049491882324148
115,oni,2.3,3.847257,1.547256898880005
672,oni,2.4,3.7155921,1.3155921459198
817,oni,8.0,8.163437,0.1634368896484375
1245,oni,8.4,7.0591817,1.340818309783936
124,oni,5.5,5.8749466,0.37494659423828125
578,oni,6.5,5.2521996,1.247800350189209
1120,oni,8.2,8.444323,0.24432258605957102
251,oni,8.1,7.758801,0.34119901657104457
374,oni,5.4,5.484437,0.08443698883056605
184,oni,5.2,5.0207753,0.17922468185424822
193,oni,4.4,5.0985303,0.698530292510986
1164,oni,5.4,5.888622,0.4886218070983883
1348,oni,6.7,4.703537,1.9964630126953127
248,oni,6.2,6.2511435,0.051143455505370916
1218,oni,1.4,3.0043902,1.6043902397155763
993,oni,10.0,9.044949,0.9550514221191406
416,oni,6.0,5.5991735,0.40082645416259766
215,oni,6.6,6.7813444,0.18134441375732457
1227,oni,10.8,9.060002,1.7399976730346687
980,oni,8.8,8.230598,0.5694015502929695
1173,oni,9.2,8.644381,0.5556194305419915
858,oni,11.1,9.593632,1.506368255615234
467,oni,2.9,3.0634747,0.16347465515136728
142,oni,3.0,3.8290024,0.8290023803710938
496,oni,6.1,5.730025,0.36997518539428675
542,oni,4.2,4.336454,0.1364539146423338
697,oni,9.9,9.066247,0.8337530136108402
989,oni,6.4,6.5791917,0.17919168472290004
199,oni,3.1,3.9743605,0.8743604660034179
283,oni,8.5,8.147985,0.35201454162597656
1347,oni,6.9,6.7535005,0.14649953842163121
614,oni,6.4,6.2811537,0.11884632110595739
9,oni,2.0,3.9813426,1.9813425540924072
640,oni,8.5,7.8518143,0.6481857299804688
758,oni,10.8,9.828485,0.9715154647827156
421,oni,7.9,7.7221074,0.17789258956909215
293,oni,3.9,4.4382343,0.5382343292236329
939,oni,7.4,7.338523,0.06147708892822301
706,oni,3.3,3.3895915,0.0895914554595949
824,oni,1.3,2.5118618,1.211861801147461
405,oni,3.1,5.136325,2.036324882507324
1099,oni,11.0,8.952359,2.047640800476074
778,oni,11.0,9.19712,1.8028802871704102
575,oni,9.8,6.442831,3.3571689605712898
478,oni,5.8,4.6577578,1.1422422409057615
809,oni,3.4,3.8239646,0.4239645957946778
1393,oni,5.2,5.08671,0.11329002380371112
1086,oni,10.6,9.258747,1.3412528991699215
1157,oni,4.6,4.127116,0.4728837966918942
403,oni,5.3,5.630022,0.3300220489501955
551,oni,4.5,4.34725,0.15275001525878906
762,oni,10.3,10.338216,0.03821582794189382
1437,oni,7.5,7.6820364,0.1820363998413086
431,oni,7.6,7.6921387,0.09213867187500036
1278,oni,11.7,9.379224,2.320776176452636
307,oni,4.1,4.407159,0.3071588516235355
523,oni,5.1,4.0887995,1.0112005233764645
168,oni,8.6,8.250107,0.34989318847656214
609,oni,5.8,5.091381,0.708618927001953
1001,oni,3.6,3.6851382,0.08513822555541983
1168,oni,4.0,4.1760807,0.17608070373535156
878,oni,9.7,8.739927,0.9600727081298821
1389,oni,1.2,3.206175,2.006175088882446
1233,oni,4.1,4.099706,0.00029382705688441035
677,oni,8.9,8.329707,0.5702928543090824
181,oni,8.5,8.747985,0.2479848861694336
1240,oni,4.2,4.060649,0.1393510818481447
121,oni,9.3,7.560639,1.7393610954284675
1318,oni,8.9,8.384992,0.5150083541870121
138,oni,7.7,7.6900344,0.009965610504150568
406,oni,7.7,4.9832273,2.716772747039795
477,oni,9.3,8.961975,0.3380249023437507
1297,oni,9.4,8.435677,0.9643234252929691
1249,oni,8.3,8.439436,0.13943595886230398
695,oni,8.3,8.01719,0.28281002044677805
1217,oni,4.7,5.1999345,0.4999344825744627
498,oni,6.7,3.6178725,3.0821275234222414
447,oni,4.0,4.4167833,0.41678333282470703
1305,oni,7.8,7.000083,0.7999170303344725
79,oni,3.2,4.5878086,1.3878086090087889
1012,oni,9.7,8.778496,0.9215042114257805
662,oni,7.4,7.043864,0.3561362266540531
445,oni,7.1,6.4310493,0.6689506530761715
1201,oni,1.9,3.5991864,1.699186420440674
305,oni,3.7,4.0024614,0.30246143341064435
306,oni,6.3,6.189409,0.11059122085571271
418,oni,8.2,6.2207007,1.9792992591857903
1036,oni,6.5,6.179061,0.3209390640258789
87,oni,5.6,5.6751432,0.07514324188232457
101,oni,1.4,2.8444297,1.4444297313690186
1062,oni,5.0,3.9868214,1.0131785869598389
629,oni,7.3,7.7802644,0.4802643775939943
230,oni,7.4,6.63587,0.7641300201416019
828,oni,4.1,5.226594,1.1265939712524418
1117,oni,2.9,3.8603442,0.9603441715240479
135,oni,4.1,3.329655,0.7703450679779049
1418,oni,8.0,7.9330883,0.06691169738769531
1237,oni,4.5,4.542555,0.04255485534667969
1193,oni,4.4,4.488823,0.0888229370117184
1373,oni,2.1,3.6980665,1.598066473007202
660,oni,6.6,6.3700333,0.2299667358398434
666,oni,6.7,7.559406,0.8594058036804197
1169,oni,3.6,4.3033247,0.7033246994018554
380,oni,4.6,3.8044093,0.7955907344818112
1084,oni,2.6,3.501814,0.9018138885498046
513,oni,8.4,8.012544,0.38745632171630895
281,oni,4.2,4.9308815,0.7308815002441404
587,oni,5.2,5.157128,0.042872142791748225
1040,oni,11.6,9.7729645,1.8270355224609371
186,oni,10.9,9.611557,1.2884429931640629
1229,oni,9.7,8.602953,1.097047042846679
139,oni,4.8,5.99956,1.1995598793029787
1449,oni,8.9,8.878569,0.021431350708008168
964,oni,2.4,3.0497062,0.6497062206268311
745,oni,10.4,9.4432955,0.9567045211791996
1004,oni,5.9,5.352998,0.547002220153809
732,oni,2.4,3.0829518,0.6829517841339112
1267,oni,4.7,4.5356736,0.1643263816833498
1435,oni,5.2,4.3815727,0.8184272766113283
680,oni,7.9,8.044945,0.1449447631835934
1013,oni,8.3,6.855718,1.4442818641662605
1 songno diff 상수 predicted_measure error
2 1333 oni 1.7 2.1903424 0.4903424263000489
3 503 oni 11.3 9.012293 2.287707138061524
4 273 oni 3.3 3.3733163 0.07331628799438494
5 1043 oni 9.8 8.805077 0.994923400878907
6 82 oni 5.7 3.7766702 1.923329782485962
7 973 oni 4.0 5.0434604 1.0434603691101074
8 1076 oni 2.1 2.9520278 0.8520277976989745
9 512 oni 3.4 4.0293465 0.6293464660644532
10 367 oni 5.8 5.824023 0.024022769927978693
11 1334 oni 4.0 4.304007 0.30400705337524414
12 246 oni 1.1 3.409812 2.3098119735717773
13 438 oni 7.7 7.679233 0.020766925811767756
14 764 oni 11.2 9.896853 1.30314655303955
15 19 oni 7.5 6.6001863 0.8998136520385742
16 422 oni 3.0 4.4134846 1.4134845733642578
17 1014 oni 5.3 5.425547 0.12554712295532244
18 1307 oni 6.9 7.224358 0.3243580818176266
19 1149 oni 3.8 5.3673983 1.567398262023926
20 819 oni 8.6 7.9465976 0.6534024238586422
21 998 oni 5.0 5.2953377 0.2953376770019531
22 1417 oni 4.2 4.0317307 0.16826934814453143
23 1268 oni 6.3 6.2643814 0.03561859130859357
24 1450 oni 2.9 2.9973252 0.09732518196105966
25 80 oni 8.4 8.044008 0.35599174499511754
26 1337 oni 3.9 5.037738 1.1377378463745118
27 83 oni 6.0 5.979888 0.020112037658691406
28 465 oni 6.9 7.4996314 0.5996314048767086
29 323 oni 4.3 4.1757064 0.12429361343383771
30 396 oni 5.8 6.364714 0.5647141456604006
31 207 oni 4.2 3.5814035 0.6185965061187746
32 546 oni 6.8 6.922099 0.12209911346435565
33 886 oni 1.9 3.2264843 1.3264842987060548
34 5 oni 8.3 8.024653 0.27534656524658274
35 259 oni 6.6 6.3496404 0.25035963058471644
36 470 oni 5.0 5.19226 0.1922597885131836
37 689 oni 4.3 4.29064 0.009360122680663885
38 537 oni 6.9 7.8368387 0.9368387222290036
39 748 oni 10.8 9.44193 1.3580701828002937
40 558 oni 8.5 8.089595 0.41040515899658203
41 339 oni 6.8 3.8407266 2.9592733860015867
42 1171 oni 6.1 5.2119055 0.8880945205688473
43 430 oni 1.5 3.211008 1.711008071899414
44 40 oni 4.6 4.4078455 0.192154502868652
45 266 oni 6.3 8.231991 1.9319908142089846
46 1162 oni 3.9 3.978352 0.07835206985473642
47 997 oni 4.0 4.5425763 0.5425763130187988
48 908 oni 6.0 5.789243 0.21075677871704102
49 1080 oni 8.0 8.286018 0.28601837158203125
50 487 oni 3.5 5.0209293 1.5209293365478516
51 552 oni 6.5 6.185847 0.31415319442749023
52 852 oni 6.6 5.719363 0.8806367874145504
53 267 oni 3.6 3.7225535 0.12255349159240714
54 898 oni 3.8 4.8149214 1.0149213790893556
55 1391 oni 7.8 7.943273 0.1432730674743654
56 1042 oni 10.1 8.874695 1.2253051757812496
57 823 oni 5.8 5.9181585 0.11815853118896502
58 1370 oni 8.6 8.115248 0.48475227355956996
59 264 oni 4.8 5.9249053 1.124905300140381
60 491 oni 8.2 7.98736 0.21263999938964773
61 753 oni 5.3 5.92183 0.6218301773071291
62 383 oni 6.1 5.850947 0.24905309677123988
63 310 oni 6.2 6.476375 0.276375102996826
64 1081 oni 5.4 5.913851 0.5138507843017575
65 610 oni 6.0 6.194362 0.19436216354370117
66 8 oni 2.2 3.7589507 1.5589507102966307
67 716 oni 6.8 4.285139 2.514860916137695
68 1452 oni 8.1 8.181307 0.08130683898925817
69 698 oni 9.9 9.351179 0.5488208770751957
70 843 oni 10.0 9.872733 0.12726688385009766
71 1181 oni 3.3 3.4767451 0.17674512863159197
72 739 oni 7.1 7.91916 0.8191598892211918
73 933 oni 7.1 7.2560177 0.1560176849365238
74 540 oni 5.9 6.3700414 0.47004137039184535
75 1206 oni 7.6 7.545701 0.05429897308349574
76 108 oni 6.8 7.3288846 0.5288846015930178
77 685 oni 10.4 9.550256 0.8497442245483402
78 52 oni 5.2 7.3442254 2.1442254066467283
79 573 oni 8.0 7.9685845 0.031415462493896484
80 948 oni 8.3 8.540495 0.24049491882324148
81 115 oni 2.3 3.847257 1.547256898880005
82 672 oni 2.4 3.7155921 1.3155921459198
83 817 oni 8.0 8.163437 0.1634368896484375
84 1245 oni 8.4 7.0591817 1.340818309783936
85 124 oni 5.5 5.8749466 0.37494659423828125
86 578 oni 6.5 5.2521996 1.247800350189209
87 1120 oni 8.2 8.444323 0.24432258605957102
88 251 oni 8.1 7.758801 0.34119901657104457
89 374 oni 5.4 5.484437 0.08443698883056605
90 184 oni 5.2 5.0207753 0.17922468185424822
91 193 oni 4.4 5.0985303 0.698530292510986
92 1164 oni 5.4 5.888622 0.4886218070983883
93 1348 oni 6.7 4.703537 1.9964630126953127
94 248 oni 6.2 6.2511435 0.051143455505370916
95 1218 oni 1.4 3.0043902 1.6043902397155763
96 993 oni 10.0 9.044949 0.9550514221191406
97 416 oni 6.0 5.5991735 0.40082645416259766
98 215 oni 6.6 6.7813444 0.18134441375732457
99 1227 oni 10.8 9.060002 1.7399976730346687
100 980 oni 8.8 8.230598 0.5694015502929695
101 1173 oni 9.2 8.644381 0.5556194305419915
102 858 oni 11.1 9.593632 1.506368255615234
103 467 oni 2.9 3.0634747 0.16347465515136728
104 142 oni 3.0 3.8290024 0.8290023803710938
105 496 oni 6.1 5.730025 0.36997518539428675
106 542 oni 4.2 4.336454 0.1364539146423338
107 697 oni 9.9 9.066247 0.8337530136108402
108 989 oni 6.4 6.5791917 0.17919168472290004
109 199 oni 3.1 3.9743605 0.8743604660034179
110 283 oni 8.5 8.147985 0.35201454162597656
111 1347 oni 6.9 6.7535005 0.14649953842163121
112 614 oni 6.4 6.2811537 0.11884632110595739
113 9 oni 2.0 3.9813426 1.9813425540924072
114 640 oni 8.5 7.8518143 0.6481857299804688
115 758 oni 10.8 9.828485 0.9715154647827156
116 421 oni 7.9 7.7221074 0.17789258956909215
117 293 oni 3.9 4.4382343 0.5382343292236329
118 939 oni 7.4 7.338523 0.06147708892822301
119 706 oni 3.3 3.3895915 0.0895914554595949
120 824 oni 1.3 2.5118618 1.211861801147461
121 405 oni 3.1 5.136325 2.036324882507324
122 1099 oni 11.0 8.952359 2.047640800476074
123 778 oni 11.0 9.19712 1.8028802871704102
124 575 oni 9.8 6.442831 3.3571689605712898
125 478 oni 5.8 4.6577578 1.1422422409057615
126 809 oni 3.4 3.8239646 0.4239645957946778
127 1393 oni 5.2 5.08671 0.11329002380371112
128 1086 oni 10.6 9.258747 1.3412528991699215
129 1157 oni 4.6 4.127116 0.4728837966918942
130 403 oni 5.3 5.630022 0.3300220489501955
131 551 oni 4.5 4.34725 0.15275001525878906
132 762 oni 10.3 10.338216 0.03821582794189382
133 1437 oni 7.5 7.6820364 0.1820363998413086
134 431 oni 7.6 7.6921387 0.09213867187500036
135 1278 oni 11.7 9.379224 2.320776176452636
136 307 oni 4.1 4.407159 0.3071588516235355
137 523 oni 5.1 4.0887995 1.0112005233764645
138 168 oni 8.6 8.250107 0.34989318847656214
139 609 oni 5.8 5.091381 0.708618927001953
140 1001 oni 3.6 3.6851382 0.08513822555541983
141 1168 oni 4.0 4.1760807 0.17608070373535156
142 878 oni 9.7 8.739927 0.9600727081298821
143 1389 oni 1.2 3.206175 2.006175088882446
144 1233 oni 4.1 4.099706 0.00029382705688441035
145 677 oni 8.9 8.329707 0.5702928543090824
146 181 oni 8.5 8.747985 0.2479848861694336
147 1240 oni 4.2 4.060649 0.1393510818481447
148 121 oni 9.3 7.560639 1.7393610954284675
149 1318 oni 8.9 8.384992 0.5150083541870121
150 138 oni 7.7 7.6900344 0.009965610504150568
151 406 oni 7.7 4.9832273 2.716772747039795
152 477 oni 9.3 8.961975 0.3380249023437507
153 1297 oni 9.4 8.435677 0.9643234252929691
154 1249 oni 8.3 8.439436 0.13943595886230398
155 695 oni 8.3 8.01719 0.28281002044677805
156 1217 oni 4.7 5.1999345 0.4999344825744627
157 498 oni 6.7 3.6178725 3.0821275234222414
158 447 oni 4.0 4.4167833 0.41678333282470703
159 1305 oni 7.8 7.000083 0.7999170303344725
160 79 oni 3.2 4.5878086 1.3878086090087889
161 1012 oni 9.7 8.778496 0.9215042114257805
162 662 oni 7.4 7.043864 0.3561362266540531
163 445 oni 7.1 6.4310493 0.6689506530761715
164 1201 oni 1.9 3.5991864 1.699186420440674
165 305 oni 3.7 4.0024614 0.30246143341064435
166 306 oni 6.3 6.189409 0.11059122085571271
167 418 oni 8.2 6.2207007 1.9792992591857903
168 1036 oni 6.5 6.179061 0.3209390640258789
169 87 oni 5.6 5.6751432 0.07514324188232457
170 101 oni 1.4 2.8444297 1.4444297313690186
171 1062 oni 5.0 3.9868214 1.0131785869598389
172 629 oni 7.3 7.7802644 0.4802643775939943
173 230 oni 7.4 6.63587 0.7641300201416019
174 828 oni 4.1 5.226594 1.1265939712524418
175 1117 oni 2.9 3.8603442 0.9603441715240479
176 135 oni 4.1 3.329655 0.7703450679779049
177 1418 oni 8.0 7.9330883 0.06691169738769531
178 1237 oni 4.5 4.542555 0.04255485534667969
179 1193 oni 4.4 4.488823 0.0888229370117184
180 1373 oni 2.1 3.6980665 1.598066473007202
181 660 oni 6.6 6.3700333 0.2299667358398434
182 666 oni 6.7 7.559406 0.8594058036804197
183 1169 oni 3.6 4.3033247 0.7033246994018554
184 380 oni 4.6 3.8044093 0.7955907344818112
185 1084 oni 2.6 3.501814 0.9018138885498046
186 513 oni 8.4 8.012544 0.38745632171630895
187 281 oni 4.2 4.9308815 0.7308815002441404
188 587 oni 5.2 5.157128 0.042872142791748225
189 1040 oni 11.6 9.7729645 1.8270355224609371
190 186 oni 10.9 9.611557 1.2884429931640629
191 1229 oni 9.7 8.602953 1.097047042846679
192 139 oni 4.8 5.99956 1.1995598793029787
193 1449 oni 8.9 8.878569 0.021431350708008168
194 964 oni 2.4 3.0497062 0.6497062206268311
195 745 oni 10.4 9.4432955 0.9567045211791996
196 1004 oni 5.9 5.352998 0.547002220153809
197 732 oni 2.4 3.0829518 0.6829517841339112
198 1267 oni 4.7 4.5356736 0.1643263816833498
199 1435 oni 5.2 4.3815727 0.8184272766113283
200 680 oni 7.9 8.044945 0.1449447631835934
201 1013 oni 8.3 6.855718 1.4442818641662605

201
test/validate_result_4.csv Normal file
View File

@@ -0,0 +1,201 @@
songno,diff,상수,predicted_measure,error
1337,oni,3.9,4.9201913,1.0201912879943849
1207,oni,7.8,7.6752043,0.1247957229614256
34,oni,6.3,5.754303,0.5456970214843748
1033,oni,4.3,4.294703,0.005296993255615057
493,oni,3.8,4.2889194,0.48891944885253924
1201,oni,1.9,3.9247124,2.024712419509888
705,oni,5.4,5.307041,0.09295883178710973
126,oni,4.6,3.4666567,1.1333433151245114
397,oni,7.9,7.927455,0.027454948425292613
117,oni,8.0,7.2873235,0.7126765251159668
1166,oni,7.8,7.3694544,0.43054561614990217
52,oni,5.2,6.9084826,1.7084825515747069
1001,oni,3.6,3.6689627,0.06896271705627433
363,oni,8.1,7.9964867,0.10351333618164027
221,oni,6.7,6.3216214,0.3783785820007326
1096,oni,5.1,3.9809358,1.1190641880035397
348,oni,3.9,4.004658,0.10465822219848642
163,oni,5.8,5.8238277,0.023827743530273615
1329,oni,7.4,6.373964,1.0260361671447757
963,oni,7.1,6.7132926,0.3867074012756344
399,oni,7.6,7.8508854,0.2508853912353519
826,oni,10.5,9.921691,0.5783090591430664
526,oni,7.9,7.8841443,0.015855693817139027
1364,oni,7.7,7.1662784,0.5337216377258303
843,oni,10.0,8.314847,1.6851530075073242
360,oni,9.2,8.815349,0.3846513748168938
181,oni,8.5,8.725624,0.22562408447265625
558,oni,8.5,8.070021,0.4299793243408203
1029,oni,1.6,2.0737321,0.4737321376800536
1178,oni,3.5,3.5148704,0.014870405197143555
1333,oni,1.7,2.0008903,0.3008902549743653
401,oni,11.3,8.855692,2.4443080902099616
411,oni,4.8,3.94091,0.8590898990631102
942,oni,5.5,5.424328,0.07567214965820312
268,oni,5.1,3.6398425,1.460157489776611
968,oni,7.0,7.418691,0.41869115829467773
112,oni,6.5,6.4688077,0.031192302703857422
420,oni,4.3,4.05865,0.24134998321533185
1352,oni,8.0,9.510268,1.510268211364746
1402,oni,5.8,4.687088,1.1129119873046873
1136,oni,2.7,3.6673882,0.9673882007598875
1377,oni,4.9,4.631454,0.26854600906372106
134,oni,6.4,6.522638,0.122637844085693
459,oni,5.6,4.9065027,0.693497276306152
1262,oni,4.3,4.293586,0.006414222717284979
487,oni,3.5,4.7952247,1.295224666595459
551,oni,4.5,3.831213,0.6687870025634766
951,oni,4.2,4.3512354,0.15123538970947248
1279,oni,8.4,8.2399845,0.1600154876708988
286,oni,10.0,8.290865,1.7091350555419922
408,oni,3.6,4.492062,0.8920620918273925
1012,oni,9.7,8.790352,0.909648132324218
159,oni,7.5,8.047567,0.5475673675537109
926,oni,3.7,4.282581,0.5825808525085447
1098,oni,5.9,4.214736,1.6852640151977543
45,oni,7.9,8.278758,0.3787580490112301
284,oni,3.8,3.6999052,0.10009484291076642
105,oni,2.9,3.1325843,0.2325843334197999
1366,oni,4.7,4.6957006,0.004299354553222834
111,oni,4.7,5.4332376,0.7332375526428221
641,oni,8.4,8.34599,0.054009819030762074
764,oni,11.2,9.98334,1.2166597366333
504,oni,6.1,6.6229615,0.522961521148682
76,oni,3.5,4.1206527,0.6206526756286621
681,oni,7.0,6.803703,0.19629716873168945
1212,oni,1.4,1.9212408,0.5212408065795899
709,oni,2.5,4.042969,1.5429692268371582
1034,oni,5.9,5.8697777,0.03022232055664098
337,oni,7.2,7.195378,0.0046221733093263495
294,oni,4.3,5.326409,1.0264088630676271
276,oni,3.7,4.33384,0.6338398933410643
1382,oni,3.2,3.2742395,0.07423954010009748
1408,oni,4.5,6.658769,2.158769130706787
547,oni,3.8,3.8565905,0.05659050941467303
233,oni,3.1,3.5813994,0.48139944076538077
338,oni,9.3,8.389843,0.9101570129394538
422,oni,3.0,4.6032124,1.6032123565673828
388,oni,9.0,8.323626,0.6763744354248047
881,oni,7.7,7.1750007,0.5249993324279787
108,oni,6.8,7.4059315,0.6059314727783205
801,oni,4.6,2.9960365,1.603963470458984
1130,oni,5.9,6.076717,0.17671689987182582
482,oni,1.8,2.9453332,1.1453332424163818
1369,oni,11.8,10.97657,0.8234298706054695
1400,oni,1.6,2.9903936,1.3903936386108398
1192,oni,5.7,5.3933945,0.3066055297851564
723,oni,9.9,9.048461,0.8515390396118168
680,oni,7.9,7.9447618,0.044761753082275035
1200,oni,2.4,3.3235924,0.9235924243927003
457,oni,6.5,6.2823706,0.21762943267822266
1202,oni,4.8,4.7704597,0.029540348052978338
456,oni,8.2,8.089962,0.11003799438476491
574,oni,8.6,8.3967705,0.20322952270507777
1375,oni,1.1,2.0934286,0.993428611755371
644,oni,4.4,4.321287,0.07871284484863317
67,oni,7.6,6.8966484,0.7033515930175778
572,oni,8.3,7.814058,0.4859421730041511
274,oni,4.3,4.5839643,0.28396434783935565
196,oni,5.3,5.485792,0.18579216003417987
991,oni,6.3,6.10526,0.1947401046752928
213,oni,6.1,5.7994084,0.30059156417846644
253,oni,5.0,5.378026,0.37802600860595703
410,oni,6.6,7.13773,0.5377301216125492
1349,oni,6.3,4.7093983,1.5906017303466795
553,oni,4.7,7.3266306,2.6266305923461912
109,oni,4.6,4.961087,0.36108722686767614
267,oni,3.6,3.946393,0.3463930130004882
36,oni,1.6,2.5664647,0.9664646625518798
833,oni,9.6,9.078208,0.5217920303344723
579,oni,7.2,5.035543,2.1644570350646974
1311,oni,6.7,6.150234,0.5497657775878908
861,oni,4.2,4.4580975,0.258097457885742
887,oni,7.2,7.168689,0.03131122589111346
1431,oni,7.8,7.4101872,0.3898127555847166
1293,oni,3.8,3.8643973,0.06439728736877459
454,oni,7.7,7.0873404,0.6126596450805666
1021,oni,7.0,5.7251973,1.2748026847839355
236,oni,2.2,4.3378987,2.1378987312316893
273,oni,3.3,3.7149804,0.4149803638458254
35,oni,3.1,3.2889068,0.1889068126678466
1073,oni,2.3,2.8221462,0.5221461772918703
1283,oni,2.2,2.7143157,0.5143156528472899
1297,oni,9.4,8.1483135,1.2516864776611332
1159,oni,7.1,6.1028767,0.9971233367919918
1277,oni,5.0,4.8191442,0.18085575103759766
831,oni,1.2,1.9079987,0.7079986810684205
1122,oni,7.8,7.187955,0.612045097351074
146,oni,4.1,4.8564696,0.7564696311950687
1048,oni,9.4,8.600496,0.7995037078857425
1417,oni,4.2,4.5280714,0.3280714035034178
317,oni,2.9,3.8885484,0.9885483741760255
1409,oni,2.1,3.1322389,1.0322388648986816
1362,oni,6.1,5.5937595,0.5062404632568356
782,oni,2.7,3.47081,0.7708099365234373
671,oni,2.6,3.5076156,0.907615566253662
489,oni,4.7,2.9095883,1.79041166305542
1193,oni,4.4,4.468303,0.06830320358276332
1306,oni,4.9,4.706141,0.1938590049743656
344,oni,5.2,5.4134874,0.21348743438720685
136,oni,9.1,8.873852,0.22614822387695277
150,oni,6.3,5.7487135,0.5512865066528319
1160,oni,6.3,6.4175167,0.11751670837402362
1452,oni,8.1,8.06595,0.03404960632324183
20,oni,8.3,8.227083,0.0729167938232429
47,oni,5.1,5.2534966,0.15349664688110387
725,oni,4.4,4.80065,0.4006501197814938
842,oni,2.1,2.0496144,0.050385570526123136
568,oni,7.5,7.3907185,0.10928153991699219
805,oni,7.5,6.580787,0.919212818145752
541,oni,5.6,5.596122,0.003878211975097301
442,oni,10.3,7.816672,2.4833281517028816
186,oni,10.9,9.709377,1.190622711181641
732,oni,2.4,2.9659953,0.5659953117370606
450,oni,9.0,8.494814,0.5051860809326172
1198,oni,7.0,6.8871975,0.11280250549316406
1061,oni,3.9,3.971574,0.0715740680694581
324,oni,5.6,5.6469517,0.04695167541503942
618,oni,5.0,5.210742,0.21074199676513672
520,oni,6.7,6.91257,0.21256999969482404
81,oni,4.4,4.985347,0.5853467941284176
1280,oni,3.9,3.9405086,0.040508604049682706
182,oni,6.4,4.7033157,1.696684265136719
571,oni,9.1,7.9525375,1.147462463378906
1393,oni,5.2,5.470408,0.2704079627990721
1139,oni,5.9,5.873014,0.02698602676391637
1235,oni,7.8,7.894454,0.09445400238037127
785,oni,8.5,7.9694014,0.5305986404418945
1080,oni,8.0,8.286955,0.2869548797607422
1415,oni,3.6,3.6400633,0.04006328582763663
959,oni,7.0,7.0137677,0.013767719268798828
1225,oni,5.3,4.5744944,0.7255056381225584
524,oni,8.9,8.816952,0.08304824829101598
505,oni,3.0,5.910715,2.910715103149414
747,oni,7.3,7.429628,0.1296278953552248
1004,oni,5.9,5.3191657,0.5808342933654789
1095,oni,6.2,4.935845,1.2641551017761232
171,oni,9.6,8.53109,1.068910217285156
305,oni,3.7,4.1035676,0.40356760025024396
1090,oni,4.2,2.588543,1.6114570617675783
792,oni,3.7,3.6583996,0.04160041809082049
1105,oni,5.5,3.8440816,1.6559183597564697
907,oni,7.9,8.013366,0.11336574554443324
451,oni,7.2,6.9618473,0.23815269470214862
372,oni,6.4,6.331269,0.06873121261596715
384,oni,2.1,3.56338,1.4633800029754638
474,oni,5.3,4.0164423,1.2835577011108397
173,oni,6.0,6.407813,0.40781307220458984
1328,oni,9.9,8.836618,1.0633815765380863
243,oni,11.0,9.193796,1.806203842163086
1405,oni,10.3,9.006471,1.2935293197631843
212,oni,5.7,5.429469,0.2705308914184572
761,oni,10.4,8.84694,1.5530599594116214
653,oni,6.7,6.433655,0.2663452148437502
797,oni,8.8,6.237135,2.562865066528321
1006,oni,5.3,6.056387,0.7563869476318361
12,oni,7.5,8.258375,0.7583751678466797
1250,oni,6.0,6.185741,0.18574094772338867
207,oni,4.2,3.9828024,0.21719760894775408
629,oni,7.3,7.686902,0.38690204620361346
1389,oni,1.2,3.2218568,2.0218568325042723
1 songno diff 상수 predicted_measure error
2 1337 oni 3.9 4.9201913 1.0201912879943849
3 1207 oni 7.8 7.6752043 0.1247957229614256
4 34 oni 6.3 5.754303 0.5456970214843748
5 1033 oni 4.3 4.294703 0.005296993255615057
6 493 oni 3.8 4.2889194 0.48891944885253924
7 1201 oni 1.9 3.9247124 2.024712419509888
8 705 oni 5.4 5.307041 0.09295883178710973
9 126 oni 4.6 3.4666567 1.1333433151245114
10 397 oni 7.9 7.927455 0.027454948425292613
11 117 oni 8.0 7.2873235 0.7126765251159668
12 1166 oni 7.8 7.3694544 0.43054561614990217
13 52 oni 5.2 6.9084826 1.7084825515747069
14 1001 oni 3.6 3.6689627 0.06896271705627433
15 363 oni 8.1 7.9964867 0.10351333618164027
16 221 oni 6.7 6.3216214 0.3783785820007326
17 1096 oni 5.1 3.9809358 1.1190641880035397
18 348 oni 3.9 4.004658 0.10465822219848642
19 163 oni 5.8 5.8238277 0.023827743530273615
20 1329 oni 7.4 6.373964 1.0260361671447757
21 963 oni 7.1 6.7132926 0.3867074012756344
22 399 oni 7.6 7.8508854 0.2508853912353519
23 826 oni 10.5 9.921691 0.5783090591430664
24 526 oni 7.9 7.8841443 0.015855693817139027
25 1364 oni 7.7 7.1662784 0.5337216377258303
26 843 oni 10.0 8.314847 1.6851530075073242
27 360 oni 9.2 8.815349 0.3846513748168938
28 181 oni 8.5 8.725624 0.22562408447265625
29 558 oni 8.5 8.070021 0.4299793243408203
30 1029 oni 1.6 2.0737321 0.4737321376800536
31 1178 oni 3.5 3.5148704 0.014870405197143555
32 1333 oni 1.7 2.0008903 0.3008902549743653
33 401 oni 11.3 8.855692 2.4443080902099616
34 411 oni 4.8 3.94091 0.8590898990631102
35 942 oni 5.5 5.424328 0.07567214965820312
36 268 oni 5.1 3.6398425 1.460157489776611
37 968 oni 7.0 7.418691 0.41869115829467773
38 112 oni 6.5 6.4688077 0.031192302703857422
39 420 oni 4.3 4.05865 0.24134998321533185
40 1352 oni 8.0 9.510268 1.510268211364746
41 1402 oni 5.8 4.687088 1.1129119873046873
42 1136 oni 2.7 3.6673882 0.9673882007598875
43 1377 oni 4.9 4.631454 0.26854600906372106
44 134 oni 6.4 6.522638 0.122637844085693
45 459 oni 5.6 4.9065027 0.693497276306152
46 1262 oni 4.3 4.293586 0.006414222717284979
47 487 oni 3.5 4.7952247 1.295224666595459
48 551 oni 4.5 3.831213 0.6687870025634766
49 951 oni 4.2 4.3512354 0.15123538970947248
50 1279 oni 8.4 8.2399845 0.1600154876708988
51 286 oni 10.0 8.290865 1.7091350555419922
52 408 oni 3.6 4.492062 0.8920620918273925
53 1012 oni 9.7 8.790352 0.909648132324218
54 159 oni 7.5 8.047567 0.5475673675537109
55 926 oni 3.7 4.282581 0.5825808525085447
56 1098 oni 5.9 4.214736 1.6852640151977543
57 45 oni 7.9 8.278758 0.3787580490112301
58 284 oni 3.8 3.6999052 0.10009484291076642
59 105 oni 2.9 3.1325843 0.2325843334197999
60 1366 oni 4.7 4.6957006 0.004299354553222834
61 111 oni 4.7 5.4332376 0.7332375526428221
62 641 oni 8.4 8.34599 0.054009819030762074
63 764 oni 11.2 9.98334 1.2166597366333
64 504 oni 6.1 6.6229615 0.522961521148682
65 76 oni 3.5 4.1206527 0.6206526756286621
66 681 oni 7.0 6.803703 0.19629716873168945
67 1212 oni 1.4 1.9212408 0.5212408065795899
68 709 oni 2.5 4.042969 1.5429692268371582
69 1034 oni 5.9 5.8697777 0.03022232055664098
70 337 oni 7.2 7.195378 0.0046221733093263495
71 294 oni 4.3 5.326409 1.0264088630676271
72 276 oni 3.7 4.33384 0.6338398933410643
73 1382 oni 3.2 3.2742395 0.07423954010009748
74 1408 oni 4.5 6.658769 2.158769130706787
75 547 oni 3.8 3.8565905 0.05659050941467303
76 233 oni 3.1 3.5813994 0.48139944076538077
77 338 oni 9.3 8.389843 0.9101570129394538
78 422 oni 3.0 4.6032124 1.6032123565673828
79 388 oni 9.0 8.323626 0.6763744354248047
80 881 oni 7.7 7.1750007 0.5249993324279787
81 108 oni 6.8 7.4059315 0.6059314727783205
82 801 oni 4.6 2.9960365 1.603963470458984
83 1130 oni 5.9 6.076717 0.17671689987182582
84 482 oni 1.8 2.9453332 1.1453332424163818
85 1369 oni 11.8 10.97657 0.8234298706054695
86 1400 oni 1.6 2.9903936 1.3903936386108398
87 1192 oni 5.7 5.3933945 0.3066055297851564
88 723 oni 9.9 9.048461 0.8515390396118168
89 680 oni 7.9 7.9447618 0.044761753082275035
90 1200 oni 2.4 3.3235924 0.9235924243927003
91 457 oni 6.5 6.2823706 0.21762943267822266
92 1202 oni 4.8 4.7704597 0.029540348052978338
93 456 oni 8.2 8.089962 0.11003799438476491
94 574 oni 8.6 8.3967705 0.20322952270507777
95 1375 oni 1.1 2.0934286 0.993428611755371
96 644 oni 4.4 4.321287 0.07871284484863317
97 67 oni 7.6 6.8966484 0.7033515930175778
98 572 oni 8.3 7.814058 0.4859421730041511
99 274 oni 4.3 4.5839643 0.28396434783935565
100 196 oni 5.3 5.485792 0.18579216003417987
101 991 oni 6.3 6.10526 0.1947401046752928
102 213 oni 6.1 5.7994084 0.30059156417846644
103 253 oni 5.0 5.378026 0.37802600860595703
104 410 oni 6.6 7.13773 0.5377301216125492
105 1349 oni 6.3 4.7093983 1.5906017303466795
106 553 oni 4.7 7.3266306 2.6266305923461912
107 109 oni 4.6 4.961087 0.36108722686767614
108 267 oni 3.6 3.946393 0.3463930130004882
109 36 oni 1.6 2.5664647 0.9664646625518798
110 833 oni 9.6 9.078208 0.5217920303344723
111 579 oni 7.2 5.035543 2.1644570350646974
112 1311 oni 6.7 6.150234 0.5497657775878908
113 861 oni 4.2 4.4580975 0.258097457885742
114 887 oni 7.2 7.168689 0.03131122589111346
115 1431 oni 7.8 7.4101872 0.3898127555847166
116 1293 oni 3.8 3.8643973 0.06439728736877459
117 454 oni 7.7 7.0873404 0.6126596450805666
118 1021 oni 7.0 5.7251973 1.2748026847839355
119 236 oni 2.2 4.3378987 2.1378987312316893
120 273 oni 3.3 3.7149804 0.4149803638458254
121 35 oni 3.1 3.2889068 0.1889068126678466
122 1073 oni 2.3 2.8221462 0.5221461772918703
123 1283 oni 2.2 2.7143157 0.5143156528472899
124 1297 oni 9.4 8.1483135 1.2516864776611332
125 1159 oni 7.1 6.1028767 0.9971233367919918
126 1277 oni 5.0 4.8191442 0.18085575103759766
127 831 oni 1.2 1.9079987 0.7079986810684205
128 1122 oni 7.8 7.187955 0.612045097351074
129 146 oni 4.1 4.8564696 0.7564696311950687
130 1048 oni 9.4 8.600496 0.7995037078857425
131 1417 oni 4.2 4.5280714 0.3280714035034178
132 317 oni 2.9 3.8885484 0.9885483741760255
133 1409 oni 2.1 3.1322389 1.0322388648986816
134 1362 oni 6.1 5.5937595 0.5062404632568356
135 782 oni 2.7 3.47081 0.7708099365234373
136 671 oni 2.6 3.5076156 0.907615566253662
137 489 oni 4.7 2.9095883 1.79041166305542
138 1193 oni 4.4 4.468303 0.06830320358276332
139 1306 oni 4.9 4.706141 0.1938590049743656
140 344 oni 5.2 5.4134874 0.21348743438720685
141 136 oni 9.1 8.873852 0.22614822387695277
142 150 oni 6.3 5.7487135 0.5512865066528319
143 1160 oni 6.3 6.4175167 0.11751670837402362
144 1452 oni 8.1 8.06595 0.03404960632324183
145 20 oni 8.3 8.227083 0.0729167938232429
146 47 oni 5.1 5.2534966 0.15349664688110387
147 725 oni 4.4 4.80065 0.4006501197814938
148 842 oni 2.1 2.0496144 0.050385570526123136
149 568 oni 7.5 7.3907185 0.10928153991699219
150 805 oni 7.5 6.580787 0.919212818145752
151 541 oni 5.6 5.596122 0.003878211975097301
152 442 oni 10.3 7.816672 2.4833281517028816
153 186 oni 10.9 9.709377 1.190622711181641
154 732 oni 2.4 2.9659953 0.5659953117370606
155 450 oni 9.0 8.494814 0.5051860809326172
156 1198 oni 7.0 6.8871975 0.11280250549316406
157 1061 oni 3.9 3.971574 0.0715740680694581
158 324 oni 5.6 5.6469517 0.04695167541503942
159 618 oni 5.0 5.210742 0.21074199676513672
160 520 oni 6.7 6.91257 0.21256999969482404
161 81 oni 4.4 4.985347 0.5853467941284176
162 1280 oni 3.9 3.9405086 0.040508604049682706
163 182 oni 6.4 4.7033157 1.696684265136719
164 571 oni 9.1 7.9525375 1.147462463378906
165 1393 oni 5.2 5.470408 0.2704079627990721
166 1139 oni 5.9 5.873014 0.02698602676391637
167 1235 oni 7.8 7.894454 0.09445400238037127
168 785 oni 8.5 7.9694014 0.5305986404418945
169 1080 oni 8.0 8.286955 0.2869548797607422
170 1415 oni 3.6 3.6400633 0.04006328582763663
171 959 oni 7.0 7.0137677 0.013767719268798828
172 1225 oni 5.3 4.5744944 0.7255056381225584
173 524 oni 8.9 8.816952 0.08304824829101598
174 505 oni 3.0 5.910715 2.910715103149414
175 747 oni 7.3 7.429628 0.1296278953552248
176 1004 oni 5.9 5.3191657 0.5808342933654789
177 1095 oni 6.2 4.935845 1.2641551017761232
178 171 oni 9.6 8.53109 1.068910217285156
179 305 oni 3.7 4.1035676 0.40356760025024396
180 1090 oni 4.2 2.588543 1.6114570617675783
181 792 oni 3.7 3.6583996 0.04160041809082049
182 1105 oni 5.5 3.8440816 1.6559183597564697
183 907 oni 7.9 8.013366 0.11336574554443324
184 451 oni 7.2 6.9618473 0.23815269470214862
185 372 oni 6.4 6.331269 0.06873121261596715
186 384 oni 2.1 3.56338 1.4633800029754638
187 474 oni 5.3 4.0164423 1.2835577011108397
188 173 oni 6.0 6.407813 0.40781307220458984
189 1328 oni 9.9 8.836618 1.0633815765380863
190 243 oni 11.0 9.193796 1.806203842163086
191 1405 oni 10.3 9.006471 1.2935293197631843
192 212 oni 5.7 5.429469 0.2705308914184572
193 761 oni 10.4 8.84694 1.5530599594116214
194 653 oni 6.7 6.433655 0.2663452148437502
195 797 oni 8.8 6.237135 2.562865066528321
196 1006 oni 5.3 6.056387 0.7563869476318361
197 12 oni 7.5 8.258375 0.7583751678466797
198 1250 oni 6.0 6.185741 0.18574094772338867
199 207 oni 4.2 3.9828024 0.21719760894775408
200 629 oni 7.3 7.686902 0.38690204620361346
201 1389 oni 1.2 3.2218568 2.0218568325042723

201
test/validate_result_5.csv Normal file
View File

@@ -0,0 +1,201 @@
songno,diff,상수,predicted_measure,error
47,oni,5.1,5.2534966,0.15349664688110387
1419,oni,9.8,8.721249,1.0787513732910163
955,oni,10.5,8.647183,1.8528165817260742
831,oni,1.2,1.9079987,0.7079986810684205
1375,oni,1.1,2.0934286,0.993428611755371
617,oni,5.6,5.59698,0.003019905090331676
705,oni,5.4,5.307041,0.09295883178710973
67,oni,7.6,6.8966484,0.7033515930175778
773,oni,4.0,4.5175767,0.5175766944885254
230,oni,7.4,6.8955503,0.5044497489929203
499,oni,8.8,7.927165,0.8728349685668952
492,oni,1.9,1.962193,0.06219301223754892
1039,oni,9.2,9.199211,0.0007888793945305395
741,oni,3.5,3.9448667,0.4448666572570801
1024,oni,3.3,3.8212879,0.5212878704071047
95,oni,7.3,7.038092,0.2619078636169432
352,oni,2.5,4.765403,2.2654027938842773
1380,oni,6.9,6.3376403,0.562359714508057
623,oni,5.0,4.3754272,0.62457275390625
834,oni,9.7,7.9294763,1.7705237388610833
27,oni,3.1,3.4906878,0.3906878471374511
952,oni,10.0,9.086574,0.913426399230957
1364,oni,7.7,7.1662784,0.5337216377258303
709,oni,2.5,4.042969,1.5429692268371582
783,oni,6.0,6.1265764,0.12657642364501953
472,oni,5.9,6.1718836,0.2718835830688473
268,oni,5.1,3.6398425,1.460157489776611
1284,oni,2.3,3.4071481,1.1071481227874758
253,oni,5.0,5.378026,0.37802600860595703
1229,oni,9.7,8.730095,0.9699050903320305
913,oni,2.1,4.303384,2.2033838272094726
260,oni,8.8,7.734481,1.0655191421508796
1149,oni,3.8,4.7081175,0.9081174850463869
982,oni,9.9,8.680321,1.2196792602539066
852,oni,6.6,5.918449,0.6815510749816891
157,oni,3.3,3.2840455,0.015954542160034002
1139,oni,5.9,5.873014,0.02698602676391637
738,oni,7.9,6.910413,0.9895872116088871
1414,oni,5.2,4.401258,0.7987420082092287
220,oni,9.3,8.128048,1.1719520568847663
964,oni,2.4,2.8287916,0.42879161834716806
607,oni,4.8,3.5413032,1.2586968421936033
348,oni,3.9,4.004658,0.10465822219848642
707,oni,6.4,6.368574,0.03142585754394567
534,oni,4.0,4.703994,0.7039937973022461
1356,oni,9.4,8.823965,0.5760349273681644
1031,oni,4.7,4.6495457,0.050454330444336115
1302,oni,1.4,2.4271264,1.027126407623291
895,oni,1.0,2.0652208,1.065220832824707
1446,oni,8.0,6.1807137,1.8192863464355469
1208,oni,4.3,5.1682663,0.8682662963867189
171,oni,9.6,8.53109,1.068910217285156
793,oni,3.1,4.031206,0.9312061309814452
1381,oni,7.3,8.54008,1.2400800704956056
510,oni,5.3,4.995711,0.30428915023803693
1179,oni,5.0,5.2024164,0.20241641998291016
1344,oni,4.7,3.441657,1.2583429336547853
1172,oni,11.9,10.288958,1.611042404174805
614,oni,6.4,6.02956,0.37043991088867223
797,oni,8.8,6.237135,2.562865066528321
1411,oni,9.1,8.657645,0.4423547744750973
525,oni,6.6,6.05448,0.545519924163818
166,oni,6.0,5.198671,0.8013291358947754
399,oni,7.6,7.8508854,0.2508853912353519
424,oni,6.3,6.354681,0.054681015014648615
805,oni,7.5,6.580787,0.919212818145752
1077,oni,3.9,4.035681,0.13568077087402353
269,oni,9.5,8.653259,0.84674072265625
246,oni,1.1,3.7854612,2.685461187362671
408,oni,3.6,4.492062,0.8920620918273925
967,oni,8.8,7.3684626,1.4315374374389656
1160,oni,6.3,6.4175167,0.11751670837402362
1196,oni,6.6,6.2342176,0.3657823562622067
601,oni,3.5,3.8300495,0.3300495147705078
1384,oni,9.3,8.139645,1.1603553771972663
1146,oni,7.5,7.588489,0.08848905563354492
660,oni,6.6,6.580023,0.019977188110351207
183,oni,7.0,7.9340434,0.9340434074401855
321,oni,6.3,6.504965,0.20496482849121112
610,oni,6.0,6.1496606,0.14966058731079102
2,oni,2.7,4.2753067,1.575306701660156
124,oni,5.5,5.522645,0.022644996643066406
89,oni,7.6,7.4246254,0.17537460327148402
1400,oni,1.6,2.9903936,1.3903936386108398
722,oni,9.4,8.443125,0.9568752288818363
558,oni,8.5,8.070021,0.4299793243408203
291,oni,5.9,5.6488047,0.25119533538818395
1250,oni,6.0,6.185741,0.18574094772338867
367,oni,5.8,5.942817,0.14281721115112322
1405,oni,10.3,9.006471,1.2935293197631843
1204,oni,3.1,3.5766625,0.4766625404357909
32,oni,6.8,6.5780144,0.22198562622070295
98,oni,3.1,3.626054,0.5260540485382079
437,oni,2.6,3.8291004,1.2291003704071044
1033,oni,4.3,4.294703,0.005296993255615057
844,oni,8.1,8.019684,0.08031616210937464
1191,oni,5.4,5.417873,0.017872905731200817
826,oni,10.5,9.921691,0.5783090591430664
297,oni,6.0,5.827567,0.17243289947509766
1070,oni,3.5,3.8753223,0.3753223419189453
462,oni,7.3,6.147337,1.1526630401611326
1100,oni,3.9,4.7135897,0.8135896682739259
154,oni,7.7,7.755892,0.055891799926757635
1334,oni,4.0,4.3223553,0.3223552703857422
970,oni,7.2,7.4047165,0.20471649169921857
43,oni,8.1,7.5882587,0.5117412567138668
113,oni,5.7,5.523327,0.1766731262207033
757,oni,10.5,9.775933,0.7240667343139648
765,oni,11.9,10.6989155,1.2010845184326175
1373,oni,2.1,3.1051126,1.0051125526428222
1315,oni,5.9,6.302742,0.4027420043945309
1390,oni,5.7,5.430671,0.26932878494262713
1393,oni,5.2,5.470408,0.2704079627990721
197,oni,1.7,3.4464536,1.7464535713195801
1264,oni,7.5,7.588489,0.08848905563354492
734,oni,8.6,8.141268,0.45873222351074183
1252,oni,4.9,4.4269466,0.4730533599853519
1274,oni,4.8,5.910712,1.1107117652893068
1119,oni,5.2,4.7606645,0.4393355369567873
1134,oni,9.6,8.895782,0.7042175292968746
860,oni,10.6,9.677244,0.9227558135986325
732,oni,2.4,2.9659953,0.5659953117370606
256,oni,4.9,3.8098686,1.0901314258575443
1404,oni,9.5,8.608601,0.8913993835449219
5,oni,8.3,7.915822,0.3841779708862312
264,oni,4.8,5.8318787,1.0318786621093752
1144,oni,2.7,3.9332407,1.2332406520843504
349,oni,6.8,7.0981984,0.29819841384887713
910,oni,7.3,7.0472574,0.2527425765991209
8,oni,2.2,3.9980168,1.798016834259033
1096,oni,5.1,3.9809358,1.1190641880035397
342,oni,4.8,6.7383738,1.9383737564086916
821,oni,6.5,4.3094015,2.190598487854004
1231,oni,5.7,4.9177494,0.7822505950927736
259,oni,6.6,6.527813,0.07218704223632777
1082,oni,5.0,5.1440825,0.14408254623413086
750,oni,8.8,7.968265,0.8317349433898933
1260,oni,8.8,7.968265,0.8317349433898933
1365,oni,7.3,6.621416,0.6785839080810545
517,oni,8.2,7.9367185,0.2632815361022942
1383,oni,9.3,8.730703,0.5692966461181648
140,oni,3.3,3.902748,0.6027481079101564
1199,oni,4.3,2.8895078,1.4104922294616697
857,oni,7.7,7.418688,0.28131217956542987
677,oni,8.9,8.347812,0.5521883010864261
991,oni,6.3,6.10526,0.1947401046752928
512,oni,3.4,3.837741,0.4377408981323243
1361,oni,1.5,3.2702508,1.7702507972717285
333,oni,1.1,2.4639604,1.3639604091644286
62,oni,6.1,5.3351364,0.7648635864257809
1385,oni,3.2,3.4457886,0.24578862190246564
1451,oni,5.1,5.803734,0.7037338256835941
1013,oni,8.3,6.485044,1.8149559974670417
160,oni,5.3,5.4540377,0.15403766632080096
1083,oni,7.5,5.3125267,2.1874732971191406
764,oni,11.2,9.98334,1.2166597366333
81,oni,4.4,4.985347,0.5853467941284176
745,oni,10.4,9.457144,0.9428562164306644
874,oni,7.0,7.124093,0.12409305572509766
1304,oni,4.7,4.7660456,0.06604557037353498
173,oni,6.0,6.407813,0.40781307220458984
363,oni,8.1,7.9964867,0.10351333618164027
988,oni,5.3,7.1791115,1.8791114807128908
1258,oni,4.6,4.581854,0.018146133422851207
39,oni,5.6,6.2476506,0.6476506233215336
770,oni,6.9,7.2992153,0.3992153167724606
1211,oni,6.0,4.8941193,1.1058807373046875
1130,oni,5.9,6.076717,0.17671689987182582
1271,oni,4.8,4.005638,0.7943618774414061
1112,oni,3.8,3.117308,0.6826920986175535
818,oni,10.4,9.009138,1.3908618927001957
270,oni,6.9,5.952505,0.9474948883056644
233,oni,3.1,3.5813994,0.48139944076538077
1409,oni,2.1,3.1322389,1.0322388648986816
817,oni,8.0,8.098137,0.09813690185546875
1314,oni,4.4,4.808567,0.40856704711914027
1062,oni,5.0,4.040713,0.959287166595459
400,oni,7.6,7.8508854,0.2508853912353519
1452,oni,8.1,8.06595,0.03404960632324183
3,oni,3.6,3.764412,0.16441192626953116
520,oni,6.7,6.91257,0.21256999969482404
1003,oni,5.1,3.142159,1.9578410148620602
1057,oni,6.4,6.2039685,0.19603147506713903
944,oni,7.0,6.1415854,0.8584146499633789
156,oni,5.8,6.273828,0.47382802963256854
1095,oni,6.2,4.935845,1.2641551017761232
1353,oni,2.8,4.0457916,1.2457916259765627
1020,oni,5.0,5.089527,0.08952713012695312
799,oni,5.7,4.5762277,1.1237723350524904
1251,oni,4.5,4.580452,0.08045196533203125
17,oni,7.3,6.817699,0.48230104446411115
1268,oni,6.3,6.331679,0.03167886734008807
641,oni,8.4,8.34599,0.054009819030762074
168,oni,8.6,8.051297,0.5487028121948239
971,oni,10.3,9.249512,1.0504882812500007
1027,oni,3.9,4.5194917,0.6194916725158692
112,oni,6.5,6.4688077,0.031192302703857422
177,oni,2.0,2.7901425,0.7901425361633301
60,oni,7.9,8.010049,0.1100488662719723
441,oni,10.7,9.515421,1.1845790863037102
1 songno diff 상수 predicted_measure error
2 47 oni 5.1 5.2534966 0.15349664688110387
3 1419 oni 9.8 8.721249 1.0787513732910163
4 955 oni 10.5 8.647183 1.8528165817260742
5 831 oni 1.2 1.9079987 0.7079986810684205
6 1375 oni 1.1 2.0934286 0.993428611755371
7 617 oni 5.6 5.59698 0.003019905090331676
8 705 oni 5.4 5.307041 0.09295883178710973
9 67 oni 7.6 6.8966484 0.7033515930175778
10 773 oni 4.0 4.5175767 0.5175766944885254
11 230 oni 7.4 6.8955503 0.5044497489929203
12 499 oni 8.8 7.927165 0.8728349685668952
13 492 oni 1.9 1.962193 0.06219301223754892
14 1039 oni 9.2 9.199211 0.0007888793945305395
15 741 oni 3.5 3.9448667 0.4448666572570801
16 1024 oni 3.3 3.8212879 0.5212878704071047
17 95 oni 7.3 7.038092 0.2619078636169432
18 352 oni 2.5 4.765403 2.2654027938842773
19 1380 oni 6.9 6.3376403 0.562359714508057
20 623 oni 5.0 4.3754272 0.62457275390625
21 834 oni 9.7 7.9294763 1.7705237388610833
22 27 oni 3.1 3.4906878 0.3906878471374511
23 952 oni 10.0 9.086574 0.913426399230957
24 1364 oni 7.7 7.1662784 0.5337216377258303
25 709 oni 2.5 4.042969 1.5429692268371582
26 783 oni 6.0 6.1265764 0.12657642364501953
27 472 oni 5.9 6.1718836 0.2718835830688473
28 268 oni 5.1 3.6398425 1.460157489776611
29 1284 oni 2.3 3.4071481 1.1071481227874758
30 253 oni 5.0 5.378026 0.37802600860595703
31 1229 oni 9.7 8.730095 0.9699050903320305
32 913 oni 2.1 4.303384 2.2033838272094726
33 260 oni 8.8 7.734481 1.0655191421508796
34 1149 oni 3.8 4.7081175 0.9081174850463869
35 982 oni 9.9 8.680321 1.2196792602539066
36 852 oni 6.6 5.918449 0.6815510749816891
37 157 oni 3.3 3.2840455 0.015954542160034002
38 1139 oni 5.9 5.873014 0.02698602676391637
39 738 oni 7.9 6.910413 0.9895872116088871
40 1414 oni 5.2 4.401258 0.7987420082092287
41 220 oni 9.3 8.128048 1.1719520568847663
42 964 oni 2.4 2.8287916 0.42879161834716806
43 607 oni 4.8 3.5413032 1.2586968421936033
44 348 oni 3.9 4.004658 0.10465822219848642
45 707 oni 6.4 6.368574 0.03142585754394567
46 534 oni 4.0 4.703994 0.7039937973022461
47 1356 oni 9.4 8.823965 0.5760349273681644
48 1031 oni 4.7 4.6495457 0.050454330444336115
49 1302 oni 1.4 2.4271264 1.027126407623291
50 895 oni 1.0 2.0652208 1.065220832824707
51 1446 oni 8.0 6.1807137 1.8192863464355469
52 1208 oni 4.3 5.1682663 0.8682662963867189
53 171 oni 9.6 8.53109 1.068910217285156
54 793 oni 3.1 4.031206 0.9312061309814452
55 1381 oni 7.3 8.54008 1.2400800704956056
56 510 oni 5.3 4.995711 0.30428915023803693
57 1179 oni 5.0 5.2024164 0.20241641998291016
58 1344 oni 4.7 3.441657 1.2583429336547853
59 1172 oni 11.9 10.288958 1.611042404174805
60 614 oni 6.4 6.02956 0.37043991088867223
61 797 oni 8.8 6.237135 2.562865066528321
62 1411 oni 9.1 8.657645 0.4423547744750973
63 525 oni 6.6 6.05448 0.545519924163818
64 166 oni 6.0 5.198671 0.8013291358947754
65 399 oni 7.6 7.8508854 0.2508853912353519
66 424 oni 6.3 6.354681 0.054681015014648615
67 805 oni 7.5 6.580787 0.919212818145752
68 1077 oni 3.9 4.035681 0.13568077087402353
69 269 oni 9.5 8.653259 0.84674072265625
70 246 oni 1.1 3.7854612 2.685461187362671
71 408 oni 3.6 4.492062 0.8920620918273925
72 967 oni 8.8 7.3684626 1.4315374374389656
73 1160 oni 6.3 6.4175167 0.11751670837402362
74 1196 oni 6.6 6.2342176 0.3657823562622067
75 601 oni 3.5 3.8300495 0.3300495147705078
76 1384 oni 9.3 8.139645 1.1603553771972663
77 1146 oni 7.5 7.588489 0.08848905563354492
78 660 oni 6.6 6.580023 0.019977188110351207
79 183 oni 7.0 7.9340434 0.9340434074401855
80 321 oni 6.3 6.504965 0.20496482849121112
81 610 oni 6.0 6.1496606 0.14966058731079102
82 2 oni 2.7 4.2753067 1.575306701660156
83 124 oni 5.5 5.522645 0.022644996643066406
84 89 oni 7.6 7.4246254 0.17537460327148402
85 1400 oni 1.6 2.9903936 1.3903936386108398
86 722 oni 9.4 8.443125 0.9568752288818363
87 558 oni 8.5 8.070021 0.4299793243408203
88 291 oni 5.9 5.6488047 0.25119533538818395
89 1250 oni 6.0 6.185741 0.18574094772338867
90 367 oni 5.8 5.942817 0.14281721115112322
91 1405 oni 10.3 9.006471 1.2935293197631843
92 1204 oni 3.1 3.5766625 0.4766625404357909
93 32 oni 6.8 6.5780144 0.22198562622070295
94 98 oni 3.1 3.626054 0.5260540485382079
95 437 oni 2.6 3.8291004 1.2291003704071044
96 1033 oni 4.3 4.294703 0.005296993255615057
97 844 oni 8.1 8.019684 0.08031616210937464
98 1191 oni 5.4 5.417873 0.017872905731200817
99 826 oni 10.5 9.921691 0.5783090591430664
100 297 oni 6.0 5.827567 0.17243289947509766
101 1070 oni 3.5 3.8753223 0.3753223419189453
102 462 oni 7.3 6.147337 1.1526630401611326
103 1100 oni 3.9 4.7135897 0.8135896682739259
104 154 oni 7.7 7.755892 0.055891799926757635
105 1334 oni 4.0 4.3223553 0.3223552703857422
106 970 oni 7.2 7.4047165 0.20471649169921857
107 43 oni 8.1 7.5882587 0.5117412567138668
108 113 oni 5.7 5.523327 0.1766731262207033
109 757 oni 10.5 9.775933 0.7240667343139648
110 765 oni 11.9 10.6989155 1.2010845184326175
111 1373 oni 2.1 3.1051126 1.0051125526428222
112 1315 oni 5.9 6.302742 0.4027420043945309
113 1390 oni 5.7 5.430671 0.26932878494262713
114 1393 oni 5.2 5.470408 0.2704079627990721
115 197 oni 1.7 3.4464536 1.7464535713195801
116 1264 oni 7.5 7.588489 0.08848905563354492
117 734 oni 8.6 8.141268 0.45873222351074183
118 1252 oni 4.9 4.4269466 0.4730533599853519
119 1274 oni 4.8 5.910712 1.1107117652893068
120 1119 oni 5.2 4.7606645 0.4393355369567873
121 1134 oni 9.6 8.895782 0.7042175292968746
122 860 oni 10.6 9.677244 0.9227558135986325
123 732 oni 2.4 2.9659953 0.5659953117370606
124 256 oni 4.9 3.8098686 1.0901314258575443
125 1404 oni 9.5 8.608601 0.8913993835449219
126 5 oni 8.3 7.915822 0.3841779708862312
127 264 oni 4.8 5.8318787 1.0318786621093752
128 1144 oni 2.7 3.9332407 1.2332406520843504
129 349 oni 6.8 7.0981984 0.29819841384887713
130 910 oni 7.3 7.0472574 0.2527425765991209
131 8 oni 2.2 3.9980168 1.798016834259033
132 1096 oni 5.1 3.9809358 1.1190641880035397
133 342 oni 4.8 6.7383738 1.9383737564086916
134 821 oni 6.5 4.3094015 2.190598487854004
135 1231 oni 5.7 4.9177494 0.7822505950927736
136 259 oni 6.6 6.527813 0.07218704223632777
137 1082 oni 5.0 5.1440825 0.14408254623413086
138 750 oni 8.8 7.968265 0.8317349433898933
139 1260 oni 8.8 7.968265 0.8317349433898933
140 1365 oni 7.3 6.621416 0.6785839080810545
141 517 oni 8.2 7.9367185 0.2632815361022942
142 1383 oni 9.3 8.730703 0.5692966461181648
143 140 oni 3.3 3.902748 0.6027481079101564
144 1199 oni 4.3 2.8895078 1.4104922294616697
145 857 oni 7.7 7.418688 0.28131217956542987
146 677 oni 8.9 8.347812 0.5521883010864261
147 991 oni 6.3 6.10526 0.1947401046752928
148 512 oni 3.4 3.837741 0.4377408981323243
149 1361 oni 1.5 3.2702508 1.7702507972717285
150 333 oni 1.1 2.4639604 1.3639604091644286
151 62 oni 6.1 5.3351364 0.7648635864257809
152 1385 oni 3.2 3.4457886 0.24578862190246564
153 1451 oni 5.1 5.803734 0.7037338256835941
154 1013 oni 8.3 6.485044 1.8149559974670417
155 160 oni 5.3 5.4540377 0.15403766632080096
156 1083 oni 7.5 5.3125267 2.1874732971191406
157 764 oni 11.2 9.98334 1.2166597366333
158 81 oni 4.4 4.985347 0.5853467941284176
159 745 oni 10.4 9.457144 0.9428562164306644
160 874 oni 7.0 7.124093 0.12409305572509766
161 1304 oni 4.7 4.7660456 0.06604557037353498
162 173 oni 6.0 6.407813 0.40781307220458984
163 363 oni 8.1 7.9964867 0.10351333618164027
164 988 oni 5.3 7.1791115 1.8791114807128908
165 1258 oni 4.6 4.581854 0.018146133422851207
166 39 oni 5.6 6.2476506 0.6476506233215336
167 770 oni 6.9 7.2992153 0.3992153167724606
168 1211 oni 6.0 4.8941193 1.1058807373046875
169 1130 oni 5.9 6.076717 0.17671689987182582
170 1271 oni 4.8 4.005638 0.7943618774414061
171 1112 oni 3.8 3.117308 0.6826920986175535
172 818 oni 10.4 9.009138 1.3908618927001957
173 270 oni 6.9 5.952505 0.9474948883056644
174 233 oni 3.1 3.5813994 0.48139944076538077
175 1409 oni 2.1 3.1322389 1.0322388648986816
176 817 oni 8.0 8.098137 0.09813690185546875
177 1314 oni 4.4 4.808567 0.40856704711914027
178 1062 oni 5.0 4.040713 0.959287166595459
179 400 oni 7.6 7.8508854 0.2508853912353519
180 1452 oni 8.1 8.06595 0.03404960632324183
181 3 oni 3.6 3.764412 0.16441192626953116
182 520 oni 6.7 6.91257 0.21256999969482404
183 1003 oni 5.1 3.142159 1.9578410148620602
184 1057 oni 6.4 6.2039685 0.19603147506713903
185 944 oni 7.0 6.1415854 0.8584146499633789
186 156 oni 5.8 6.273828 0.47382802963256854
187 1095 oni 6.2 4.935845 1.2641551017761232
188 1353 oni 2.8 4.0457916 1.2457916259765627
189 1020 oni 5.0 5.089527 0.08952713012695312
190 799 oni 5.7 4.5762277 1.1237723350524904
191 1251 oni 4.5 4.580452 0.08045196533203125
192 17 oni 7.3 6.817699 0.48230104446411115
193 1268 oni 6.3 6.331679 0.03167886734008807
194 641 oni 8.4 8.34599 0.054009819030762074
195 168 oni 8.6 8.051297 0.5487028121948239
196 971 oni 10.3 9.249512 1.0504882812500007
197 1027 oni 3.9 4.5194917 0.6194916725158692
198 112 oni 6.5 6.4688077 0.031192302703857422
199 177 oni 2.0 2.7901425 0.7901425361633301
200 60 oni 7.9 8.010049 0.1100488662719723
201 441 oni 10.7 9.515421 1.1845790863037102

20
train.sh
View File

@@ -1,23 +1,25 @@
#!/bin/bash
# Arguments: script_dir working_dir data_dir train_data_count validate_data_count margin
# Arguments: script_dir working_dir data_dir train_count validate_count margin validate_iterations
SCRIPT_DIR=${1:-"script"}
WORKING_DIR=${2:-"."}
DATA_DIR=${3:-"datas"}
TRAIN_COUNT=${4:-100}
VAL_COUNT=${5:-20}
MARGIN=${6:-0.1}
MARGIN=${6:-0.5}
VAL_ITERATIONS=${7:-5}
# 작업 디렉토리가 없으면 생성
if [ ! -d "$WORKING_DIR" ]; then
echo "Creating directory: $WORKING_DIR"
echo "Creating working directory: $WORKING_DIR"
mkdir -p "$WORKING_DIR"
fi
# 피처 추출 (존재 시 생략)
if [ ! -f "$WORKING_DIR/features.json" ]; then
echo "Extracting features..."
bun "$SCRIPT_DIR/extract.ts" "$WORKING_DIR" "$DATA_DIR" "$TRAIN_COUNT" "$VAL_COUNT"
# factors.json이 없으면 생성
if [ ! -f "$WORKING_DIR/factors.json" ]; then
echo "Factors file not found. Running factorization..."
bun run "$SCRIPT_DIR/extract.ts" "$WORKING_DIR" "$DATA_DIR"
fi
echo "Training model..."
python3 "$SCRIPT_DIR/train.py" "$SCRIPT_DIR" "$WORKING_DIR" "$DATA_DIR" "$TRAIN_COUNT" "$VAL_COUNT" "$MARGIN"
echo "Starting training..."
python3 "$SCRIPT_DIR/train.py" "$SCRIPT_DIR" "$WORKING_DIR" "$DATA_DIR" "$TRAIN_COUNT" "$VAL_COUNT" "$MARGIN" "$VAL_ITERATIONS"