first version

app.py

@@ -0,0 +1,64 @@
+import numpy as np
+import pandas as pd
+import streamlit as st
+
+from utils import get_index, get_movie_info
+
+MAX_OVERVIEW_LENGTH = 280
+IMAGE_WIDTH = 170
+
+
+@st.cache()
+def init() -> None:
+    movies = pd.read_csv("movies.csv")
+    st.session_state["movies"] = movies
+    st.session_state["titles"] = movies["original_title"].values
+    st.session_state["sim_matrix"] = np.load("sim.npy")
+
+
+def run() -> None:
+    st.title("Movie Recommender")
+    with st.form("search"):
+        title = st.selectbox("Recommend movies based on:", st.session_state["titles"])
+        num_recommendations = st.number_input(
+            "Number of recommendations:", min_value=1, max_value=20, value=6
+        )
+        search = st.form_submit_button("Search")
+    if search:
+        recommend(title, num_recommendations)
+
+
+def recommend(based_on: str, num_recommendations: int) -> None:
+    movie_index = get_index(based_on)
+    similarities = list(enumerate(st.session_state["sim_matrix"][movie_index]))
+    similarities.pop(movie_index)
+    sorted_similarities = sorted(similarities, key=lambda x: x[1], reverse=True)
+    recommendations = sorted_similarities[:num_recommendations]
+    st.markdown("---")
+    for idx, _ in recommendations:
+        show_movie_info(idx)
+
+
+def show_movie_info(movie_index: str) -> None:
+    info = get_movie_info(movie_index)
+    im_col, info_col = st.columns([2, 4])
+    im_col.image(
+        f"https://a.ltrbxd.com/resized/{info['image_url']}.jpg", width=IMAGE_WIDTH
+    )
+    info_col.markdown(
+        f"### {info['original_title']} ({info['release_date'].split('-')[0]})"
+    )
+    info_col.markdown(f"*{int(info['runtime'])} min*")
+    short_overview = (
+        f"{info['overview'][:MAX_OVERVIEW_LENGTH]} ..."
+        if len(info["overview"]) > MAX_OVERVIEW_LENGTH
+        else info["overview"]
+    )
+    info_col.markdown(short_overview)
+    info_col.caption(", ".join(eval(info["genres"])))
+    st.markdown("---")
+
+
+if __name__ == "__main__":
+    init()
+    run()

sim.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b80ed1781ba5b653ff99a95c67a14aa040265fe5a4fc2b89162219154ba8cc8
+size 168838816

utils.py

@@ -0,0 +1,10 @@
+import streamlit as st
+
+
+def get_index(title: str) -> int:
+    movies = st.session_state["movies"]
+    return movies[movies["original_title"] == title].index.values[0]
+
+
+def get_movie_info(movie_index: int) -> dict:
+    return st.session_state["movies"].iloc[movie_index].to_dict()