AccidentRiskPredictor / src /streamlit_app.py
EnYa32's picture
Update src/streamlit_app.py
4b1651b verified
Raw History Blame Contribute Delete
6.79 kB
# app.py
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='Road Accident Risk Predictor', page_icon='πŸš—', layout='centered')
st.title('πŸš— Road Accident Risk Predictor')
st.write('Predicts **accident_risk (0–1)** using a trained **LightGBM** regression model.')
BASE_DIR = Path(__file__).resolve().parent
MODEL_PATH = BASE_DIR / 'lgbm_model.pkl'
FEATURE_NAMES_PATH = BASE_DIR / 'feature_names.pkl'
# -------------------------
# Load artifacts
# -------------------------
@st.cache_resource
def load_artifacts():
if not MODEL_PATH.exists():
raise FileNotFoundError(f'Missing model file: {MODEL_PATH.name} (put it in the repo root).')
if not FEATURE_NAMES_PATH.exists():
raise FileNotFoundError(f'Missing feature file: {FEATURE_NAMES_PATH.name} (put it in the repo root).')
model = joblib.load(MODEL_PATH)
feature_names = joblib.load(FEATURE_NAMES_PATH)
return model, feature_names
model, FEATURE_NAMES = load_artifacts()
# -------------------------
# Feature engineering + encoding (must match notebook logic)
# -------------------------
def build_features(raw_df: pd.DataFrame) -> pd.DataFrame:
df = raw_df.copy()
# Ensure expected base columns exist
required = [
'road_type', 'num_lanes', 'curvature', 'speed_limit', 'lighting', 'weather',
'road_signs_present', 'public_road', 'time_of_day', 'holiday', 'school_season',
'num_reported_accidents'
]
missing = [c for c in required if c not in df.columns]
if missing:
raise ValueError(f'Missing columns: {missing}')
# Force numeric/bool-friendly types
num_cols = ['num_lanes', 'curvature', 'speed_limit', 'num_reported_accidents']
for c in num_cols:
df[c] = pd.to_numeric(df[c], errors='coerce')
bool_cols = ['road_signs_present', 'public_road', 'holiday', 'school_season']
for c in bool_cols:
# accept True/False, 0/1, 'true'/'false'
df[c] = df[c].astype(str).str.lower().map({'true': 1, 'false': 0})
df[c] = df[c].fillna(0).astype(int)
# Fill any numeric NaNs defensively (even if your dataset had none)
df['curvature'] = df['curvature'].fillna(df['curvature'].median())
df['speed_limit'] = df['speed_limit'].fillna(df['speed_limit'].median())
df['num_lanes'] = df['num_lanes'].fillna(df['num_lanes'].median())
df['num_reported_accidents'] = df['num_reported_accidents'].fillna(df['num_reported_accidents'].median())
# ---- Feature engineering you used ----
df['curvature_speed'] = df['curvature'] * df['speed_limit']
df['lanes_speed'] = df['num_lanes'] * df['speed_limit']
df['accidents_lane'] = df['num_reported_accidents'] / (df['num_lanes'] + 1)
df['holiday_school'] = (df['holiday'].astype(int) & df['school_season'].astype(int)).astype(int)
df['signs_public'] = (df['road_signs_present'].astype(int) & df['public_road'].astype(int)).astype(int)
# ---- One-hot encoding (same style as notebook) ----
df_encoded = pd.get_dummies(df, drop_first=True)
# Align to training feature order (critical for Streamlit / deployment)
df_encoded = df_encoded.reindex(columns=FEATURE_NAMES, fill_value=0)
return df_encoded
def predict_one(raw_row: dict) -> float:
raw_df = pd.DataFrame([raw_row])
X = build_features(raw_df)
pred = float(model.predict(X)[0])
pred = float(np.clip(pred, 0, 1))
return pred
# -------------------------
# UI
# -------------------------
st.subheader('Input')
tab1, tab2 = st.tabs(['Manual input', 'Upload CSV'])
with tab1:
col1, col2 = st.columns(2)
with col1:
road_type = st.selectbox('Road type', ['highway', 'urban', 'rural'], index=0)
lighting = st.selectbox('Lighting', ['daylight', 'dim', 'night'], index=0)
weather = st.selectbox('Weather', ['clear', 'foggy', 'rainy'], index=0)
time_of_day = st.selectbox('Time of day', ['morning', 'afternoon', 'evening'], index=0)
with col2:
num_lanes = st.slider('Number of lanes', min_value=1, max_value=6, value=2, step=1)
curvature = st.slider('Curvature (0–1)', min_value=0.0, max_value=1.0, value=0.30, step=0.01)
speed_limit = st.slider('Speed limit', min_value=10, max_value=130, value=50, step=5)
num_reported_accidents = st.slider('Reported accidents', min_value=0, max_value=10, value=1, step=1)
st.markdown('**Flags**')
c1, c2, c3, c4 = st.columns(4)
road_signs_present = c1.checkbox('Road signs present', value=True)
public_road = c2.checkbox('Public road', value=True)
holiday = c3.checkbox('Holiday', value=False)
school_season = c4.checkbox('School season', value=False)
raw_row = {
'road_type': road_type,
'num_lanes': num_lanes,
'curvature': curvature,
'speed_limit': speed_limit,
'lighting': lighting,
'weather': weather,
'road_signs_present': int(road_signs_present),
'public_road': int(public_road),
'time_of_day': time_of_day,
'holiday': int(holiday),
'school_season': int(school_season),
'num_reported_accidents': num_reported_accidents
}
if st.button('Predict'):
try:
pred = predict_one(raw_row)
st.success(f'Predicted accident_risk: **{pred:.6f}**')
st.progress(min(max(pred, 0.0), 1.0))
except Exception as e:
st.error(str(e))
with tab2:
st.write('Upload a CSV with the raw columns (same as Kaggle test.csv, without `accident_risk`).')
up = st.file_uploader('Upload CSV', type=['csv'])
if up is not None:
try:
raw_df = pd.read_csv(up)
# If user accidentally includes id or target, drop safely
for col in ['id', 'accident_risk']:
if col in raw_df.columns:
raw_df = raw_df.drop(columns=[col])
X = build_features(raw_df)
preds = model.predict(X)
preds = np.clip(preds, 0, 1)
out = raw_df.copy()
out['accident_risk_pred'] = preds
st.write('Preview:')
st.dataframe(out.head(20), use_container_width=True)
csv_bytes = out.to_csv(index=False).encode('utf-8')
st.download_button(
label='Download predictions CSV',
data=csv_bytes,
file_name='predictions.csv',
mime='text/csv'
)
except Exception as e:
st.error(str(e))
st.caption('Note: This app reproduces the same feature engineering + one-hot encoding logic as the notebook and then aligns features using feature_names.pkl.')