PROJECT 076 · PYTHON SOURCE

Fuel consumption unit conversion

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': 76, 'dataset': 'auto', 'title': 'Fuel consumption unit conversion', 'question': 'How do MPG summaries compare with fuel used per 100 kilometres?', 'method': 'Convert each observed vehicle before grouping; compare transformed observations with transforming the group average.', 'action': 'Use the appropriate aggregation for efficiency reports and state whether driving distance is known.', '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()
    assert df.mpg.gt(0).all()
    df['litres_per_100km']=235.214583/df.mpg
    t=df.groupby('cylinders').agg(vehicles=('row_id','size'),mean_mpg=('mpg','mean'),mean_litres_per_100km=('litres_per_100km','mean')).reset_index();t['conversion_of_mean_mpg']=235.214583/t.mean_mpg
    out=result(t,'cylinders','mean_litres_per_100km','Litres per 100 km','Uses US gallons. The nonlinear conversion of mean MPG differs from mean converted consumption; neither is fleet fuel use without distance weights.')
    return out

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