Video Engagement × Mavera Scoring Correlation

import os, requests, time

VM = os.environ["VIMEO_ACCESS_TOKEN"]
MV = os.environ["MAVERA_API_KEY"]
VM_BASE = "https://api.vimeo.com"
MV_BASE = "https://app.mavera.io/api/v1"
VM_H = {"Authorization": f"Bearer {VM}", "Accept": "application/vnd.vimeo.*+json;version=3.4"}
MV_H = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"}

# 1. Pull videos with engagement stats
resp = requests.get(f"{VM_BASE}/me/videos", headers=VM_H, params={
    "per_page": 50, "sort": "plays", "direction": "desc",
    "fields": "uri,name,link,duration,stats,metadata.connections.likes.total,"
              "metadata.connections.comments.total",
}).json()

videos = []
for v in resp.get("data", []):
    vid_id = v["uri"].split("/")[-1]
    stats = v.get("stats", {})
    videos.append({
        "id": vid_id, "name": v["name"], "link": v["link"],
        "duration": v.get("duration", 0),
        "plays": stats.get("plays", 0),
        "finishes": stats.get("finishes", 0),
        "avg_watched": round(stats.get("finishes", 0) / max(stats.get("plays", 1), 1) * 100, 1),
        "likes": v.get("metadata", {}).get("connections", {}).get("likes", {}).get("total", 0),
        "comments": v.get("metadata", {}).get("connections", {}).get("comments", {}).get("total", 0),
    })

print(f"Pulled engagement data for {len(videos)} videos")

# 2. Run Mavera Video Analysis on top 15
combined = []
for video in videos[:15]:
    upload = requests.post(f"{MV_BASE}/assets", headers=MV_H, json={
        "url": video["link"], "name": video["name"][:80], "type": "video",
    }).json()

    analysis = requests.post(f"{MV_BASE}/video-analysis", headers=MV_H, json={
        "asset_id": upload["id"],
        "analysis_types": [
            "message_clarity", "emotional_impact", "hook_score",
            "behavioral_effectiveness", "pacing", "cognitive_load",
        ],
    }).json()

    for _ in range(30):
        time.sleep(3)
        status = requests.get(
            f"{MV_BASE}/video-analysis/{analysis['id']}", headers=MV_H
        ).json()
        if status.get("status") == "completed":
            break

    r = status.get("results", {})
    combined.append({
        **video,
        "clarity": r.get("message_clarity", {}).get("score", 0),
        "emotion": r.get("emotional_impact", {}).get("score", 0),
        "hook": r.get("hook_score", {}).get("score", 0),
        "behavior": r.get("behavioral_effectiveness", {}).get("score", 0),
        "pacing_score": r.get("pacing", {}).get("score", 0),
        "cog_load": r.get("cognitive_load", {}).get("average", 0),
    })
    time.sleep(1)

# 3. Build correlation dataset for Mave
data_block = "\n".join(
    f"Video: \"{c['name'][:40]}\" | "
    f"Plays: {c['plays']:,} | Finish%: {c['avg_watched']}% | Likes: {c['likes']} | Comments: {c['comments']} || "
    f"Clarity: {c['clarity']} | Emotion: {c['emotion']} | Hook: {c['hook']} | "
    f"Behavior: {c['behavior']} | Pacing: {c['pacing_score']} | CogLoad: {c['cog_load']}"
    for c in combined
)

correlation = requests.post(f"{MV_BASE}/mave/chat", headers=MV_H, json={
    "message": f"""Analyze the correlation between Mavera creative scores and real Vimeo engagement.

DATASET ({len(combined)} videos — engagement metrics || Mavera scores):
{data_block}

Produce:
1. **Best Predictor**: Which single Mavera metric most strongly predicts real engagement (plays, finish rate, likes)?
2. **Metric-by-Metric Correlation**: For each Mavera metric, how well does it predict each engagement metric? (strong/moderate/weak/none)
3. **Surprising Findings**: Any metrics that DON'T correlate with engagement despite seeming important?
4. **Composite Formula**: Suggest a weighted combination of Mavera metrics that best predicts finish rate
5. **Actionable Rule**: "If you optimize for [X Mavera metric], you'll see the biggest lift in [Y engagement metric]"
6. **Outliers**: Videos where Mavera scores and engagement diverge — what explains the gap?""",
}).json()

print("VIDEO ENGAGEMENT × MAVERA SCORING CORRELATION")
print("=" * 65)
print(f"{'Video':<35} {'Plays':>8} {'Finish%':>8} {'Emotion':>8} {'Hook':>6} {'Clarity':>8}")
print("-" * 65)
for c in combined:
    print(f"  {c['name'][:33]:<35} {c['plays']:>8,} {c['avg_watched']:>7.1f}% "
          f"{c['emotion']:>7} {c['hook']:>5} {c['clarity']:>7}")
print("\n" + correlation.get("content", "")[:2000])