# Praktikum 6

1. Lakukan percobaan penggunaan ANNOY, FAISS, dan HNSWLIB pada dataset sekunder berukuran besar (Micro Spotify) pada link berikut: <https://www.kaggle.com/datasets/bwandowando/spotify-songs-with-attributes-and-lyrics/data> . Download data dan load CSV filenya (pilih dataset yg pertama dari dua dataset). pilih hanya fitur numerik saja, dan lakukan normalisasi menggunakan StandardScaler. Lakukan pencarian track terdekat dan bandingkan hasilnya.

```python
import pandas as pd
import numpy as np
import time
import faiss
from annoy import AnnoyIndex
import hnswlib
from sklearn.neighbors import NearestNeighbors
from sklearn.preprocessing import StandardScaler

# -------------------------------
# Load dataset
# -------------------------------
df = pd.read_csv('/content/drive/MyDrive/Kuliah/2025 ML/spotify_songs.csv')  # ganti path sesuai lokasi file
features = ['danceability', 'energy', 'loudness', 'speechiness', 
            'acousticness', 'instrumentalness', 'liveness', 'valence', 'tempo']
X = df[features].values

# Standarisasi fitur
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

k = 10  # jumlah nearest neighbors

# -------------------------------
# Exact Nearest Neighbor (brute-force)
# -------------------------------
start = time.time()
nn = NearestNeighbors(n_neighbors=k, algorithm='brute', metric='euclidean')
nn.fit(X_scaled)
dist_exact, idx_exact = nn.kneighbors(X_scaled)
time_exact = time.time() - start
print(f"Exact NN done in {time_exact:.3f} s")

# -------------------------------
# Annoy
# -------------------------------
start = time.time()
f = X_scaled.shape[1]
index_annoy = AnnoyIndex(f, 'euclidean')
for i, v in enumerate(X_scaled):
    index_annoy.add_item(i, v)
index_annoy.build(10)
idx_annoy = [index_annoy.get_nns_by_vector(v, k) for v in X_scaled]
time_annoy = time.time() - start
print(f"Annoy done in {time_annoy:.3f} s")

# -------------------------------
# HNSW
# -------------------------------
start = time.time()
p_hnsw = hnswlib.Index(space='l2', dim=X_scaled.shape[1])
p_hnsw.init_index(max_elements=X_scaled.shape[0], ef_construction=200, M=16)
p_hnsw.add_items(X_scaled)
p_hnsw.set_ef(200)
idx_hnsw, dist_hnsw = p_hnsw.knn_query(X_scaled, k=k)
time_hnsw = time.time() - start
print(f"HNSW done in {time_hnsw:.3f} s")

# -------------------------------
# FAISS IVF
# -------------------------------
start = time.time()
quantizer = faiss.IndexFlatL2(X_scaled.shape[1])
index_faiss = faiss.IndexIVFFlat(quantizer, X_scaled.shape[1], nlist=100, metric=faiss.METRIC_L2)
index_faiss.train(X_scaled)
index_faiss.add(X_scaled)
index_faiss.nprobe = 10
dist_faiss, idx_faiss = index_faiss.search(X_scaled, k)
time_faiss = time.time() - start
print(f"FAISS IVF done in {time_faiss:.3f} s")

# -------------------------------
# Contoh tampilkan top-5 neighbors dari item pertama
# -------------------------------
print("\nTop-5 neighbors for first song:")
print(f"Exact NN: {idx_exact[0][:5]}")
print(f"Annoy:    {idx_annoy[0][:5]}")
print(f"HNSW:     {idx_hnsw[0][:5]}")
print(f"FAISS:    {idx_faiss[0][:5]}")
```

Buat dan tuliskan analisa anda terhadap code diatas.