Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
title: RestaurantRecommendation
|
| 3 |
-
emoji:
|
| 4 |
colorFrom: red
|
| 5 |
colorTo: red
|
| 6 |
sdk: docker
|
|
@@ -12,9 +12,34 @@ short_description: Restaurant recommender using TF-IDF and cosine similarity.
|
|
| 12 |
license: mit
|
| 13 |
---
|
| 14 |
|
| 15 |
-
#
|
| 16 |
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
-
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: RestaurantRecommendation
|
| 3 |
+
emoji: 🍽️
|
| 4 |
colorFrom: red
|
| 5 |
colorTo: red
|
| 6 |
sdk: docker
|
|
|
|
| 12 |
license: mit
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# 🍽️ Restaurant Recommendation System (TF-IDF + Cosine Similarity)
|
| 16 |
|
| 17 |
+
This project is a **content-based recommendation system** that suggests similar restaurants based on their features such as:
|
| 18 |
+
- Restaurant **Type**
|
| 19 |
+
- **Location**
|
| 20 |
+
- **Price Range**
|
| 21 |
+
- Customer **Comments**
|
| 22 |
|
| 23 |
+
The model uses:
|
| 24 |
+
- **TF-IDF Vectorization** to convert text into numerical vectors
|
| 25 |
+
- **Cosine Similarity** to find similar restaurants
|
| 26 |
+
|
| 27 |
+
## ✅ Files in this repository
|
| 28 |
+
- `app.py` → Streamlit application
|
| 29 |
+
- `tfidf.pkl` → saved TF-IDF vectorizer
|
| 30 |
+
- `restaurants_df.pkl` → dataset (including combined feature column)
|
| 31 |
+
- `requirements.txt` → dependencies
|
| 32 |
+
|
| 33 |
+
> Note: The similarity matrix is **not saved** as a file (it was too large).
|
| 34 |
+
> Instead, it is computed at runtime to keep the Space lightweight and deployment-friendly.
|
| 35 |
+
|
| 36 |
+
## ▶️ How to use
|
| 37 |
+
1. Choose a restaurant from the dropdown.
|
| 38 |
+
2. Click **Recommend**.
|
| 39 |
+
3. The app displays similar restaurants with useful details and TripAdvisor links.
|
| 40 |
+
|
| 41 |
+
## 🧠 Method
|
| 42 |
+
1. Combine text features: `Type + Location + Price_Range + Comments`
|
| 43 |
+
2. Apply TF-IDF
|
| 44 |
+
3. Compute cosine similarity
|
| 45 |
+
4. Recommend top-N most similar restaurants
|