User Profile Clustering → Personas

import os, requests, time, base64
from collections import defaultdict

MP_SA = os.environ["MIXPANEL_SERVICE_ACCOUNT"]
MP_SECRET = os.environ["MIXPANEL_SECRET"]
MP_PROJECT = os.environ["MIXPANEL_PROJECT_ID"]
MV = os.environ["MAVERA_API_KEY"]
MB = "https://app.mavera.io/api/v1"
MH = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"}

mp_auth = (MP_SA, MP_SECRET)

profiles = []
page = 0
session_id = None

while True:
    payload = {
        "project_id": MP_PROJECT,
        "filter_by_cohort": "",
        "output_properties": [
            "$email", "$name", "$city", "$country_code",
            "plan", "company_size", "role", "signup_source",
            "total_events", "last_seen", "sessions_count",
        ],
        "page": page,
    }
    if session_id:
        payload["session_id"] = session_id

    r = requests.post(
        "https://mixpanel.com/api/query/engage",
        auth=mp_auth,
        json=payload,
    )
    if r.status_code == 429:
        time.sleep(60)
        continue
    r.raise_for_status()
    data = r.json()

    session_id = data.get("session_id")
    results = data.get("results", [])
    profiles.extend(results)

    if len(results) < 1000 or len(profiles) >= 5000:
        break
    page += 1
    time.sleep(1)

print(f"Fetched {len(profiles)} profiles")

clusters = {"power_user": [], "regular": [], "casual": [], "dormant": []}
for p in profiles:
    props = p.get("$properties", {})
    events = int(props.get("total_events", 0) or 0)
    sessions = int(props.get("sessions_count", 0) or 0)

    if events > 500 and sessions > 50:
        clusters["power_user"].append(props)
    elif events > 100 and sessions > 10:
        clusters["regular"].append(props)
    elif events > 10:
        clusters["casual"].append(props)
    else:
        clusters["dormant"].append(props)

def cluster_profile(users):
    roles = defaultdict(int)
    plans = defaultdict(int)
    sizes = defaultdict(int)
    sources = defaultdict(int)
    for u in users:
        if u.get("role"): roles[u["role"]] += 1
        if u.get("plan"): plans[u["plan"]] += 1
        if u.get("company_size"): sizes[u["company_size"]] += 1
        if u.get("signup_source"): sources[u["signup_source"]] += 1
    top = lambda d, n=3: sorted(d, key=d.get, reverse=True)[:n]
    avg_events = sum(int(u.get("total_events", 0) or 0) for u in users) / max(len(users), 1)
    avg_sessions = sum(int(u.get("sessions_count", 0) or 0) for u in users) / max(len(users), 1)
    return {
        "n": len(users), "avg_events": avg_events, "avg_sessions": avg_sessions,
        "top_roles": top(roles), "top_plans": top(plans),
        "top_sizes": top(sizes), "top_sources": top(sources),
    }

created = []
for cluster_name, users in clusters.items():
    if not users:
        continue
    prof = cluster_profile(users)
    label = cluster_name.replace("_", " ").title()

    persona = requests.post(f"{MB}/personas", headers=MH, json={
        "name": f"Mixpanel: {label}",
        "description": (
            f"{label} segment from Mixpanel ({prof['n']} users). "
            f"Avg events: {prof['avg_events']:.0f}, Avg sessions: {prof['avg_sessions']:.0f}. "
            f"Roles: {', '.join(prof['top_roles'])}. "
            f"Plans: {', '.join(prof['top_plans'])}. "
            f"Company sizes: {', '.join(prof['top_sizes'])}. "
            f"Signup sources: {', '.join(prof['top_sources'])}."
        ),
        "demographic": {
            "job_titles": prof["top_roles"],
            "company_sizes": prof["top_sizes"],
        },
        "psychographic": {
            "usage_intensity": cluster_name,
            "avg_events": prof["avg_events"],
            "avg_sessions": prof["avg_sessions"],
        },
    }).json()

    created.append({"cluster": label, "id": persona["id"], "n": prof["n"]})
    print(f"  {label}: {persona['id']} ({prof['n']} users, avg {prof['avg_events']:.0f} events)")
    time.sleep(0.3)

print(f"\nCreated {len(created)} behavior-based personas")