PROJECT 081 · PYTHON SOURCE

Regional customer basket comparison

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': 81, 'dataset': 'wholesale', 'title': 'Regional customer basket comparison', 'question': 'How does observed total annual spending differ across recorded regions?', 'method': 'Regional sample sizes, medians and quartiles of customer totals.', 'action': 'Validate regional coverage before interpreting observed mix as market opportunity.', 'limitations': 'Annual customer spending uses source monetary units, not an assumed currency. There are no margins, transactions or dates. Customer segments are descriptive and do not establish promotion response. '}

def analyze():
    df = load('wholesale').copy()
    df['total_spend']=df[SPEND].sum(axis=1)
    t=df.groupby('region').total_spend.agg(customers='size',median='median',p25=lambda s:s.quantile(.25),p75=lambda s:s.quantile(.75)).reset_index()
    out=result(t,'region','median','Source monetary units','Region codes remain as documented source categories; unequal samples are not representative market sizes.')
    return out

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