Upload 3 files

README.md

@@ -1,13 +1,30 @@
----
-title: Yannayguy
-emoji: 📊
-colorFrom: yellow
-colorTo: red
-sdk: gradio
-sdk_version: 5.37.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Movie Recommender
+
+A simple web app to recommend movies based on your text description, using embeddings and cosine similarity.
+
+## How it works
+
+- The app uses [SentenceTransformers](https://www.sbert.net/) to encode your text and the movie descriptions into embeddings.
+- Then it calculates the cosine similarity between your input and all movies in the dataset.
+- It shows the top 5 most similar movies.
+
+## How to run
+
+1. Make sure you have `movies.csv` in the same folder, with columns: `Title`, `Overview`, `embeddings` (as list of floats).
+2. Install dependencies:
+
+```bash
+pip install -r requirements.txt
+```
+
+3. Run the app:
+
+```bash
+python app.py
+```
+
+Then open the URL shown in your browser.
+
+## HuggingFace Spaces
+
+You can also upload this folder to [HuggingFace Spaces](https://huggingface.co/spaces) as a Gradio app.

app.py

@@ -0,0 +1,42 @@
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+import gradio as gr
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+import ast
+
+# טען את המודל
+model = SentenceTransformer("all-MiniLM-L6-v2")
+
+# טען את הדאטהסט מהלינק
+url = "https://huggingface.co/datasets/Pablinho/movies-dataset/resolve/main/9000plus.csv"
+print("Loading dataset...")
+dataset = pd.read_csv(url)
+
+# ודא שהעמודות קיימות
+assert "Title" in dataset.columns
+assert "Overview" in dataset.columns
+assert "embeddings" in dataset.columns
+
+# הפוך את הטקסט של embeddings לרשימות של מספרים
+dataset['embeddings'] = dataset['embeddings'].apply(ast.literal_eval)
+
+print("Dataset loaded!")
+
+def recommend_similar_movies(input_text, top_n=5):
+    input_embedding = model.encode([input_text])
+    similarities = cosine_similarity(input_embedding, np.vstack(dataset['embeddings'].to_numpy()))[0]
+    top_indices = similarities.argsort()[::-1][:top_n]
+    results = dataset.iloc[top_indices][['Title', 'Overview']]
+    return "\n\n".join(f"🎬 **{row['Title']}**\n{row['Overview']}" for _, row in results.iterrows())
+
+demo = gr.Interface(
+    fn=recommend_similar_movies,
+    inputs=gr.Textbox(lines=2, placeholder="Describe a movie..."),
+    outputs="text",
+    title="Movie Recommender",
+    description="Get movie recommendations based on your description. Powered by sentence-transformers and cosine similarity."
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+numpy
+pandas
+scikit-learn
+gradio
+sentence-transformers