Spaces:
Sleeping
Sleeping
File size: 3,459 Bytes
9c1217e 3bef182 9c1217e 3bef182 9c1217e 3bef182 9c1217e 3bef182 b17635f 3bef182 9c1217e 3bef182 b17635f 3bef182 9c1217e 59c01b6 cb5bab3 9c1217e 3bef182 b17635f 9c1217e b17635f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 | import streamlit as st
from huggingface_hub import hf_hub_download
import numpy as np
import pandas as pd
from annoy import AnnoyIndex
PLACEHOLDER_POSTER = "https://upload.wikimedia.org/wikipedia/commons/3/3f/Placeholder_view_vector.svg"
movies_path = hf_hub_download(repo_id="Smiley0707/Movie-recommendation", filename="movies_df.csv")
feature_path = hf_hub_download(repo_id="Smiley0707/Movie-recommendation", filename="feature_array.npz")
index_path = hf_hub_download(repo_id="Smiley0707/Movie-recommendation", filename="my_index.ann")
# --- Caching Data Loading ---
@st.cache_data
def load_movie_data():
"""Loads the movie dataframe and performs initial cleaning."""
movies_df = pd.read_csv(movies_path)
movies_df['title'] = movies_df['title'].fillna('')
movies_df['poster_path'] = movies_df['poster_path'].fillna('')
return movies_df
@st.cache_data
def load_feature_array():
"""Loads the feature array from the .npz file."""
return np.load(feature_path)['arr_0']
@st.cache_resource
def load_annoy_index(_feature_array):
"""Loads the Annoy index from file."""
f = _feature_array.shape[1]
annoy_index = AnnoyIndex(f, 'angular')
# In a real app, you might need to download this file first if not present
annoy_index.load(index_path)
return annoy_index
# Main UI
st.set_page_config(page_title="🎬 Movie Recommender", layout="wide")
st.title("🎬 Movie Recommendation System")
# Load data using cached functions
new_movies = load_movie_data()
feature_array = load_feature_array()
annoy_index = load_annoy_index(feature_array)
def get_poster(idx):
url = new_movies.iloc[idx]['poster_path']
if not url or str(url).strip() == "":
return PLACEHOLDER_POSTER
print(url)
url = f'https://image.tmdb.org/t/p/w342{url}'
return url
# --- App Layout ---
query = st.text_input("Search for a movie:")
if query:
mask = new_movies['title'].str.lower().str.contains(query.lower(), na=False)
results = new_movies[mask]
if results.empty:
st.info("No movies found.")
else:
st.subheader("Search Results:")
cols = st.columns(5)
movie_indices = list(results.index[:5])
for i, idx in enumerate(movie_indices):
with cols[i]:
st.markdown(
f"""<div style="border-radius:15px;border:2px solid #eee;padding:10px;text-align:center;">
<img src="{get_poster(idx)}" alt="poster" style="width:100px;height:150px;border-radius:10px;"><br>
<b>{new_movies.iloc[idx]['title']}</b>
</div>
""",
unsafe_allow_html=True
)
recommend_for_idx = movie_indices[0]
st.markdown(f"### Recommendations for {new_movies.iloc[recommend_for_idx]['title']}:")
recs = annoy_index.get_nns_by_item(recommend_for_idx, 6)[1:]
rec_cols = st.columns(min(len(recs), 5))
for i, r in enumerate(recs):
with rec_cols[i]:
st.markdown(
f"""<div style="border-radius:15px;border:2px solid #eee;padding:10px;text-align:center;">
<img src="{get_poster(r)}" alt="poster" style="width:100px;height:150px;border-radius:10px;"><br>
<b>{new_movies.iloc[r]['title']}</b>
</div>
""",
unsafe_allow_html=True
) |