PROJECT 068 · PYTHON SOURCE

Browser conversion diagnostics

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': 68, 'dataset': 'shoppers', 'title': 'Browser conversion diagnostics', 'question': 'Which browser categories warrant investigation of their purchase experience?', 'method': 'Conversion intervals among browser categories with at least 100 sessions.', 'action': 'Prioritize browser QA using real session evidence, then control for visitor and traffic mix.', 'limitations': 'One observation is a completed session. End-of-session behavior cannot support an early-session prediction claim. PageValues is excluded from purchase models because it can encode downstream purchase information. Associations are not experiment results. '}

def analyze():
    df = load('shoppers').copy()
    t=rates(df,'browser','revenue',minimum=100)
    t=t.merge(df.groupby('browser').agg(median_exit_rate=('exitrates','median')).reset_index(),on='browser')
    out=result(t,'browser','rate','Purchase-session share','Numeric browser codes are not mapped to invented names. Differences do not prove a browser defect.')
    return out

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