PROJECT 026 · PYTHON SOURCE

Campaign population drift

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': 26, 'dataset': 'bank', 'title': 'Campaign population drift', 'question': 'How do response and campaign intensity change across source-order quarters?', 'method': 'Four contiguous observation blocks with response intervals and contact-count summaries.', 'action': 'Test temporal stability rather than assuming a pooled response rate persists.', 'limitations': 'Observational marketing records do not identify campaign uplift. Month and row order are not precise timestamps; repeated-client identifiers are unavailable. Models are research diagnostics, not financial eligibility or automated contact decisions. '}

def analyze():
    df = load('bank').copy()
    df['block']=np.minimum(np.arange(len(df))*4//len(df)+1,4)
    t=rates(df,'block','subscribed')
    t=t.merge(df.groupby('block').agg(mean_campaign_contacts=('campaign','mean'),previously_contacted_share=('pdays',lambda s:s.ge(0).mean())).reset_index(),on='block')
    out=result(t,'block','rate','Subscription share','Source order is documented as chronological, but block sizes are counts, not equally spaced calendar durations.')
    return out

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