PROJECT 072 · PYTHON SOURCE

Origin and model-year composition

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': 72, 'dataset': 'auto', 'title': 'Origin and model-year composition', 'question': 'Does the origin comparison change when model years are grouped into comparable periods?', 'method': 'Origin-stratified model-year bands with sample counts.', 'action': 'Check composition before presenting geographical comparisons of efficiency.', 'limitations': "Historical city-cycle vehicle observations are not current fleet performance. Vehicle mix and model year are confounded. A '?' horsepower value means missing, not zero. "}

def analyze():
    df = load('auto').copy()
    df['period']=pd.cut(df.model_year,[69,73,77,82]).astype(str)
    t=df.groupby(['period','origin']).mpg.agg(vehicles='size',mean_mpg='mean').reset_index();t['group']=t.period+' / origin '+t.origin.astype(str)
    out=result(t,'group','mean_mpg','Miles per US gallon','Origin codes are source categories, not a measure of driver behavior or modern national fleets.')
    return out

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