PROJECT 065 · PYTHON SOURCE

Bounce and exit measurement audit

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': 65, 'dataset': 'shoppers', 'title': 'Bounce and exit measurement audit', 'question': 'How do bounce and exit rates relate, and where are their recorded values unusual?', 'method': 'Rate-range validation and rank associations with completed-session outcomes.', 'action': 'Clarify the analytics platform definitions before treating these fields as interchangeable.', '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=associations(df,'revenue',['bouncerates','exitrates','productrelated_duration','administrative_duration','informational_duration'])
    audit=pd.DataFrame([{'field':c,'outside_0_1':int((~df[c].between(0,1)).sum()),'zeros':int(df[c].eq(0).sum()),'observations':len(df)} for c in ['bouncerates','exitrates']])
    out=result(t,'feature','spearman_rho','Spearman correlation','Correlation is descriptive. The source metrics summarize pages visited during an already completed session.',extra={'rate_audit':audit})
    return out

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