PROJECT 063 · PYTHON SOURCE

Traffic source quality

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': 63, 'dataset': 'shoppers', 'title': 'Traffic source quality', 'question': 'Which recorded traffic categories combine meaningful volume with higher observed conversion?', 'method': 'Category conversion and uncertainty, restricted to at least 100 sessions.', 'action': 'Investigate acquisition-channel composition before allocating a test budget.', '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,'traffictype','revenue',minimum=100).sort_values('rate',ascending=False)
    out=result(t,'traffictype','rate','Purchase-session share','Source codes are retained without inventing channel names. Spend and attribution are absent, so ROI cannot be calculated.')
    return out

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