Create collaborative_filtering.py (#386)

<!-- ISSUE & PR TITLE SHOULD BE SAME-->
## Description
<!--Please include a brief description of the changes-->


## Related Issues

<!--Cite any related issue(s) this pull request addresses. If none,
simply state “None”-->
- Closes #

## Type of PR
<!-- Mention PR Type according to the issue in brackets below and check
the below box -->
- [ ] ()

## Screenshots / videos (if applicable)
<!--Attach any relevant screenshots or videos demonstrating the
changes-->


## Checklist
<!-- [X] - put a cross/X inside [] to check the box -->
- [ ] I have gone through the [contributing
guide](https://github.com/Anjaliavv51/Retro)
- [ ] I have updated my branch and synced it with project `main` branch
before making this PR
- [ ] I have performed a self-review of my code
- [ ] I have tested the changes thoroughly before submitting this pull
request.
- [ ] I have provided relevant issue numbers, screenshots, and videos
after making the changes.
- [ ] I have commented my code, particularly in hard-to-understand
areas.


## Additional context:
<!--Include any additional information or context that might be helpful
for reviewers.-->

collaborative_filtering.py

@@ -0,0 +1,20 @@
+from surprise import Dataset, Reader, SVD
+from surprise.model_selection import train_test_split, accuracy
+
+# Load data from database
+data = cursor.execute('SELECT user_id, item_id, interaction_type FROM user_interactions').fetchall()
+
+# Convert to Surprise dataset
+reader = Reader(rating_scale=(1, 5))
+dataset = Dataset.load_from_df(pd.DataFrame(data, columns=['user_id', 'item_id', 'interaction_type']), reader)
+
+# Train-test split
+trainset, testset = train_test_split(dataset, test_size=0.25)
+
+# Train model
+algo = SVD()
+algo.fit(trainset)
+
+# Test model
+predictions = algo.test(testset)
+accuracy.rmse(predictions)