PROJECT 031 · PYTHON SOURCE

Free and total sulfur consistency

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': 31, 'dataset': 'wine', 'title': 'Free and total sulfur consistency', 'question': 'How variable is the free-to-total sulfur measurement ratio?', 'method': 'Positive-denominator ratios, quantiles and an out-of-range audit.', 'action': 'Investigate measurement or recording explanations for unusual ratios.', 'limitations': 'Sensory scores are ordinal and concentrated in the middle. Producer and batch IDs are unavailable. Associations are not recipes for changing quality or evidence of market price. '}

def analyze():
    df = load('wine').copy()
    valid=df[df.total_sulfur_dioxide>0].copy();valid['free_fraction']=valid.free_sulfur_dioxide/valid.total_sulfur_dioxide
    t=distribution(valid.free_fraction,'free_to_total_ratio')
    audit=valid.groupby('wine_type').free_fraction.agg(samples='size',over_one=lambda s:int(s.gt(1).sum())).reset_index()
    out=result(t,'statistic','free_to_total_ratio','Ratio','Total sulfur must be positive; ratios over one are flagged for review, not automatically deleted.',extra={'consistency_audit':audit})
    return out

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