mirror of
https://github.com/bnair123/MusicAnalyser.git
synced 2026-02-25 11:46:07 +00:00
f4432154b6
- Refactor Database: Add `Artist` model, M2M relationship, and `AnalysisSnapshot` model. - Backend Services: Implement `StatsService` for computable metrics and `NarrativeService` for Gemini LLM integration. - Fix Ingestion: Correctly handle multiple artists per track and backfill existing data. - Testing: Add unit tests for statistics logic and live verification scripts. - Documentation: Add `PHASE_4_FRONTEND_GUIDE.md`.
79 lines
2.2 KiB
Python
79 lines
2.2 KiB
Python
from datetime import datetime, timedelta
|
|
import random
|
|
from app.database import SessionLocal
|
|
from app.models import Track, Artist, PlayHistory
|
|
from app.services.stats_service import StatsService
|
|
|
|
def seed_db():
|
|
db = SessionLocal()
|
|
|
|
# 1. Create Artists
|
|
artists = []
|
|
for i in range(10):
|
|
a = Artist(
|
|
id=f"artist_{i}",
|
|
name=f"Artist {i}",
|
|
genres=[random.choice(["pop", "rock", "jazz", "edm", "hip-hop"]) for _ in range(2)]
|
|
)
|
|
db.merge(a) # merge handles insert/update
|
|
artists.append(a)
|
|
|
|
db.commit()
|
|
print(f"Seeded {len(artists)} artists.")
|
|
|
|
# 2. Create Tracks
|
|
tracks = []
|
|
for i in range(50):
|
|
# Random artist
|
|
artist = random.choice(artists)
|
|
|
|
t = Track(
|
|
id=f"track_{i}",
|
|
name=f"Track {i}",
|
|
artist=artist.name, # Legacy
|
|
album=f"Album {i % 10}",
|
|
duration_ms=random.randint(180000, 300000), # 3-5 mins
|
|
popularity=random.randint(10, 90),
|
|
danceability=random.uniform(0.3, 0.9),
|
|
energy=random.uniform(0.3, 0.9),
|
|
valence=random.uniform(0.1, 0.9),
|
|
tempo=random.uniform(80, 160),
|
|
raw_data={"album": {"id": f"album_{i%10}", "release_date": f"{random.randint(2000, 2023)}-01-01"}}
|
|
)
|
|
# Link artist
|
|
t.artists.append(artist)
|
|
db.merge(t)
|
|
tracks.append(t)
|
|
|
|
db.commit()
|
|
print(f"Seeded {len(tracks)} tracks.")
|
|
|
|
# 3. Create Play History (Last 30 days)
|
|
plays = []
|
|
base_time = datetime.utcnow() - timedelta(days=25)
|
|
|
|
for i in range(200):
|
|
# Create sessions
|
|
# 80% chance next play is soon (2-5 mins), 20% chance gap (30-600 mins)
|
|
gap = random.randint(2, 6) if random.random() > 0.2 else random.randint(30, 600)
|
|
base_time += timedelta(minutes=gap)
|
|
|
|
if base_time > datetime.utcnow():
|
|
break
|
|
|
|
track = random.choice(tracks)
|
|
|
|
p = PlayHistory(
|
|
track_id=track.id,
|
|
played_at=base_time,
|
|
context_uri="spotify:playlist:fake"
|
|
)
|
|
db.add(p)
|
|
|
|
db.commit()
|
|
print(f"Seeded play history until {base_time}.")
|
|
db.close()
|
|
|
|
if __name__ == "__main__":
|
|
seed_db()
|