BeatsPerMinutePrediction / src /streamlit_app.py
EnYa32's picture
Update src/streamlit_app.py
60029ba verified
Raw History Blame Contribute Delete
4.98 kB
import numpy as np
import pandas as pd
import streamlit as st
import joblib
from pathlib import Path
# --------------------------------------------------
# Page config
# --------------------------------------------------
st.set_page_config(
page_title='BPM Predictor (LightGBM)',
page_icon='🎵',
layout='centered'
)
st.title('🎵 BPM Predictor')
st.write('Predict **Beats Per Minute (BPM)** from audio features using a trained **LightGBM** regression model.')
BASE_DIR = Path(__file__).resolve().parent
MODEL_PATH = BASE_DIR / 'lgbm_model.pkl'
FEATURES_PATH = BASE_DIR / 'feature_names.pkl'
# --------------------------------------------------
# Load artifacts
# --------------------------------------------------
@st.cache_resource
def load_artifacts():
if not MODEL_PATH.exists():
raise FileNotFoundError(
f'Model not found: {MODEL_PATH.name}. Put it in the repo root (same folder as app.py).'
)
if not FEATURES_PATH.exists():
raise FileNotFoundError(
f'Feature list not found: {FEATURES_PATH.name}. Put it in the repo root (same folder as app.py).'
)
model = joblib.load(MODEL_PATH)
feature_names = joblib.load(FEATURES_PATH)
if not isinstance(feature_names, list) or len(feature_names) == 0:
raise ValueError('feature_names.pkl must contain a non-empty list of feature names.')
return model, feature_names
model, feature_names = load_artifacts()
# --------------------------------------------------
# Feature engineering (MUST match training)
# --------------------------------------------------
def add_features(df: pd.DataFrame) -> pd.DataFrame:
df = df.copy()
# required base columns
required = [
'RhythmScore', 'AudioLoudness', 'VocalContent', 'AcousticQuality',
'InstrumentalScore', 'LivePerformanceLikelihood', 'MoodScore',
'TrackDurationMs', 'Energy'
]
missing = [c for c in required if c not in df.columns]
if missing:
raise ValueError(f'Missing required base columns: {missing}')
# engineered columns (same as training)
df['Rhythm_Energy'] = df['RhythmScore'] * df['Energy']
df['Mood_Energy'] = df['MoodScore'] * df['Energy']
df['Loudness_Energy'] = df['AudioLoudness'] * df['Energy']
return df
def make_single_row_input(values: dict) -> pd.DataFrame:
df = pd.DataFrame([values])
df = add_features(df)
# align to training columns exactly
missing = [c for c in feature_names if c not in df.columns]
if missing:
raise ValueError(f'Missing engineered columns after feature engineering: {missing}')
extra = [c for c in df.columns if c not in feature_names]
if extra:
df = df.drop(columns=extra)
df = df[feature_names]
return df
# --------------------------------------------------
# UI
# --------------------------------------------------
with st.expander('ℹ️ Model info', expanded=False):
st.write('**Model:** LightGBM Regressor')
st.write('**Target:** BeatsPerMinute')
st.write('**Features:** numeric audio descriptors + interaction features')
st.caption('Note: In this dataset, features show limited predictive signal, so predictions may be close to the mean BPM.')
st.subheader('Enter audio feature values')
col1, col2 = st.columns(2)
with col1:
rhythm = st.slider('RhythmScore', min_value=0.0, max_value=1.0, value=0.6, step=0.001)
energy = st.slider('Energy', min_value=0.0, max_value=1.0, value=0.6, step=0.001)
mood = st.slider('MoodScore', min_value=0.0, max_value=1.0, value=0.6, step=0.001)
live = st.slider('LivePerformanceLikelihood', min_value=0.0, max_value=1.0, value=0.2, step=0.001)
with col2:
loudness = st.number_input('AudioLoudness (dB)', value=-10.0, step=0.1)
vocal = st.slider('VocalContent', min_value=0.0, max_value=1.0, value=0.08, step=0.001)
acoustic = st.slider('AcousticQuality', min_value=0.0, max_value=1.0, value=0.25, step=0.001)
instrumental = st.slider('InstrumentalScore', min_value=0.0, max_value=1.0, value=0.10, step=0.001)
track_ms = st.number_input('TrackDurationMs', value=240000, step=1000, min_value=10000)
input_values = {
'RhythmScore': float(rhythm),
'AudioLoudness': float(loudness),
'VocalContent': float(vocal),
'AcousticQuality': float(acoustic),
'InstrumentalScore': float(instrumental),
'LivePerformanceLikelihood': float(live),
'MoodScore': float(mood),
'TrackDurationMs': float(track_ms),
'Energy': float(energy)
}
st.divider()
if st.button('Predict BPM'):
try:
X = make_single_row_input(input_values)
pred = float(model.predict(X)[0])
st.success(f'Predicted BPM: **{pred:.2f}**')
with st.expander('See model input (after feature engineering)'):
st.dataframe(X)
except Exception as e:
st.error(str(e))
st.caption('Tip: Keep `lgbm_model.pkl` and `feature_names.pkl` in the repo root next to `app.py`.')