PROJECT 059 · PYTHON SOURCE

One-hour-ahead CO forecast

Study-specific code. Shared modules, dependency versions, and reproduction instructions are included in all project files.

from pathlib import Path
import sys
ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(ROOT))
import numpy as np
import pandas as pd
from scipy.stats import spearmanr
from sklearn.decomposition import PCA
from sklearn.ensemble import IsolationForest
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import confusion_matrix, precision_score, recall_score
from portfolio.data import load
from portfolio.constants import *
from portfolio.methods import result, sql, rates, associations, distribution, regression, classification, cluster
from portfolio.engine import execute

META = {'id': 59, 'dataset': 'air', 'title': 'One-hour-ahead CO forecast', 'question': 'Can earlier observed CO and sensor responses improve a one-hour-ahead reference forecast?', 'method': 'Complete-grid lags and a chronological holdout, excluding contemporaneous target-hour observations.', 'action': 'Assess latency and later-period performance before testing an operational forecast.', 'limitations': 'The -200 sentinel is treated as missing. Reference instruments have incomplete coverage; comparisons use paired observations. Sensor calibration is retrospective, not a health or regulatory compliance assessment. '}

def analyze():
    df = load('air').copy()
    d=df.set_index('timestamp').reindex(pd.date_range(df.timestamp.min(),df.timestamp.max(),freq='h'))
    d['co_lag_1']=d.co_gt.shift(1);d['co_lag_24']=d.co_gt.shift(24);d['sensor_lag_1']=d.pt08_s1_co.shift(1)
    d=d.iloc[24:].dropna(subset=['row_id']).reset_index(drop=True)
    t,p,e=regression(d,['hour','co_lag_1','co_lag_24','sensor_lag_1'],'co_gt',split='ordered')
    out=result(t,'model','mae','CO reference-unit MAE','Origin is one observed hour before target. Lagged reference availability is assumed; production outages would change feasibility.',extra={'predictions':p},evaluation=e)
    return out

if __name__ == "__main__":
    execute(Path(__file__).parent, META, analyze)