PROJECT 055 · PYTHON SOURCE

Hourly carbon monoxide pattern

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': 55, 'dataset': 'air', 'title': 'Hourly carbon monoxide pattern', 'question': 'What daily pattern appears in observed reference carbon monoxide measurements?', 'method': 'Hour-of-day reference summaries with paired observation counts and quantiles.', 'action': 'Compare traffic and meteorology data before explaining a diurnal pattern.', '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()
    t=df.groupby('hour').co_gt.agg(observed_hours='count',median_co='median',mean_co='mean',p90_co=lambda s:s.quantile(.9)).reset_index()
    out=result(t,'hour','mean_co','CO reference concentration (source units)','Each hour-of-day mean uses available reference readings only. This is not an exposure or compliance assessment.',kind='line')
    return out

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