File size: 2,301 Bytes
0d4f97b | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | import pandas as pd
import numpy as np
import joblib
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from xgboost import XGBClassifier
from sklearn.metrics import classification_report
# ---------------- Load & preprocess ----------------
df = pd.read_csv('../city_day_clean_dated.csv', parse_dates=['Date']).sort_values('Date')
# Fill missing hours
full = pd.DataFrame(pd.date_range(df['Date'].min(), df['Date'].max(), freq='h'), # 'H' → 'h'
columns=['DateTime'])
df = full.merge(df, left_on=full['DateTime'].dt.date,
right_on=df['Date'].dt.date, how='left').ffill()
df['Date'] = df['DateTime']
# Filter numeric gas columns only (avoid 'DateTime', etc.)
gas_cols = ['alcohol', 'NH3', 'CO', 'CO2', 'Toluene', 'acetone', 'lpg', 'smoke']
# Create danger flags
danger_thresholds = {col: np.percentile(df[col].dropna(), 95) for col in gas_cols}
for col in gas_cols:
df[f'{col}_danger'] = (df[col] > danger_thresholds[col]).astype(int)
df['Danger'] = df[[f'{col}_danger' for col in gas_cols]].max(axis=1)
# Time features
df['Hour'] = df['DateTime'].dt.hour
df['Weekday'] = df['DateTime'].dt.weekday
df['Month'] = df['DateTime'].dt.month
df['Afternoon'] = ((df['Hour'] >= 12) & (df['Hour'] <= 15)).astype(int)
# Simple demo features
features = ['Hour', 'Weekday', 'Month', 'Afternoon']
target = 'Danger'
train = df[df['DateTime'] < '2020-01-01']
test = df[df['DateTime'] >= '2020-01-01']
X_train, y_train = train[features], train[target]
X_test, y_test = test[features], test[target]
# ---------------- Build model ----------------
model = make_pipeline(
StandardScaler(),
XGBClassifier(
n_estimators=200,
max_depth=5,
learning_rate=0.1,
subsample=0.8,
colsample_bytree=0.8,
scale_pos_weight=10,
random_state=42,
eval_metric='logloss'
)
)
model.fit(X_train, y_train)
print('Training report:')
print(classification_report(y_train, model.predict(X_train)))
print('\nTest report:')
print(classification_report(y_test, model.predict(X_test)))
# ---------------- Save bundle ----------------
joblib.dump({'model': model, 'features': features}, 'gas_danger_model.pkl')
print('✔️ Model saved to gas_danger_model.pkl')
|