RestaurantRecommendation / src /streamlit_app.py
EnYa32's picture
Update src/streamlit_app.py
7c49cf4 verified
Raw History Blame Contribute Delete
5.41 kB
import numpy as np
import pandas as pd
import joblib
import streamlit as st
from sklearn.metrics.pairwise import cosine_similarity
st.set_page_config(page_title="Restaurant Recommendation System", page_icon="🍽️", layout="wide")
st.title("🍽️ Restaurant Recommendation System")
st.write("Select a restaurant and get similar restaurant recommendations using **TF-IDF + Cosine Similarity**.")
# ----------------------------
# Load artifacts (cached)
# ----------------------------
@st.cache_resource
def load_artifacts():
# If your files are in repo root, remove 'src/' from these paths
tfidf = joblib.load("src/tfidf.pkl")
df = pd.read_pickle("src/restaurants_df.pkl")
# Ensure required columns exist
required_cols = {"Name", "Type", "Location", "Price_Range", "Comments", "Trip_advisor Url"}
missing = required_cols - set(df.columns)
if missing:
raise ValueError(f"Missing required columns in DataFrame: {missing}")
# Ensure combined text column exists
if "combined_columns" not in df.columns:
df["Type"] = df["Type"].fillna("Unknown")
df["Comments"] = df["Comments"].fillna("")
df["combined_columns"] = (
df["Type"].astype(str) + " " +
df["Location"].astype(str) + " " +
df["Price_Range"].astype(str) + " " +
df["Comments"].astype(str)
)
# Normalize text
text = df["combined_columns"].astype(str).str.lower()
# Build similarity matrix at runtime (lightweight deployment)
X = tfidf.transform(text)
sim = cosine_similarity(X)
return df, sim
# ----------------------------
# Recommender with scores
# ----------------------------
def recommend_with_scores(name, df, sim, top_n=5, same_location_only=False, price_filter="All"):
# Safety: if list is empty or name not found
matches = df.index[df["Name"] == name].tolist()
if not matches:
return pd.DataFrame({"Message": [f"'{name}' not found in dataset."]})
idx = matches[0]
scores = sim[idx]
# Sort indices by similarity (desc), exclude itself
ranked_idx = np.argsort(scores)[::-1]
ranked_idx = ranked_idx[ranked_idx != idx]
# Build candidates dataframe
candidates = df.loc[
ranked_idx,
["Name", "Type", "Location", "Price_Range", "Trip_advisor Url"]
].copy()
candidates["Similarity"] = scores[ranked_idx]
# Optional filters
if same_location_only:
selected_loc = df.loc[idx, "Location"]
candidates = candidates[candidates["Location"] == selected_loc]
if price_filter and price_filter != "All":
candidates = candidates[candidates["Price_Range"] == price_filter]
# Take top_n
result = candidates.head(top_n).copy()
result["Similarity"] = result["Similarity"].round(3)
# Clickable link column (Markdown)
result["TripAdvisor Link"] = result["Trip_advisor Url"].apply(
lambda u: f"[Open]({u})" if isinstance(u, str) and u.startswith("http") else ""
)
# Keep clean columns
result = result[["Name", "Type", "Location", "Price_Range", "Similarity", "TripAdvisor Link"]]
result.reset_index(drop=True, inplace=True)
result.index += 1
return result
# ----------------------------
# Main app
# ----------------------------
try:
df, sim_matrix = load_artifacts()
except Exception as e:
st.error("❌ Could not load artifacts. Please check file paths and required columns.")
st.exception(e)
st.stop()
# ✅ DEBUG (damit du sofort siehst, ob df geladen wurde)
with st.expander("🔍 Debug (open if app looks empty)"):
st.write("Number of rows:", len(df))
st.write("Columns:", list(df.columns))
st.dataframe(df.head(5), use_container_width=True)
# Sidebar settings (optional but stable)
st.sidebar.header("⚙️ Settings")
top_n = st.sidebar.slider("Number of recommendations", 3, 20, 5, 1)
same_location_only = st.sidebar.checkbox("Recommend only from the same location", value=False)
price_options = ["All"] + sorted(df["Price_Range"].dropna().astype(str).unique().tolist())
price_filter = st.sidebar.selectbox("Price range filter", price_options, index=0)
# Dropdown (IMPORTANT: ensure list not empty)
restaurant_list = df["Name"].dropna().astype(str).unique().tolist()
restaurant_list.sort()
if len(restaurant_list) == 0:
st.error("No restaurant names found. Please check your dataset.")
st.stop()
selected_restaurant = st.selectbox("Select a restaurant", restaurant_list)
if st.button("Recommend"):
st.subheader(f"Recommendations for: {selected_restaurant}")
recs = recommend_with_scores(
selected_restaurant,
df,
sim_matrix,
top_n=top_n,
same_location_only=same_location_only,
price_filter=price_filter
)
# Use markdown table so links are visible
st.dataframe(recs, use_container_width=True)
st.caption("Similarity closer to 1.0 means stronger similarity.")
st.divider()
with st.expander("ℹ️ How it works"):
st.write(
"""
- This is a **content-based recommendation system**.
- Restaurant data (type, location, price range, comments) is combined into one text feature.
- Text is vectorized using **TF-IDF**.
- Similar restaurants are found with **Cosine Similarity**.
- The similarity matrix is computed at runtime to keep the Space lightweight.
"""
)