EnYa32 commited on
Commit
6bd5679
·
verified ·
1 Parent(s): ffbd9f6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -5
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
- # Welcome to Streamlit!
16
 
17
- Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
 
 
 
 
18
 
19
- If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
20
- forums](https://discuss.streamlit.io).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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