An open API service indexing awesome lists of open source software.

https://github.com/adrianmarino/knn-cf-rec-sys

Similarity CF based RecSys examples
https://github.com/adrianmarino/knn-cf-rec-sys

python recommender-system scikit-learn

Last synced: about 2 months ago
JSON representation

Similarity CF based RecSys examples

Awesome Lists containing this project

README

          

# Collaborative filtering KNN based recommendation systems

Similarity collaborative filtering based RecSys.

[Notebook](https://github.com/adrianmarino/cf-rec-sys-examples/blob/master/notebooks/knn-cf-rec-sys.ipynb)

## Sources

* **Collaborative filtering**
* [Medium: Collaborative Filtering based Recommendation Systems exemplified..](https://towardsdatascience.com/collaborative-filtering-based-recommendation-systems-exemplified-ecbffe1c20b1)
* This project is base in: [CF Recommendation System-Examples.ipynb](https://github.com/csaluja/JupyterNotebooks-Medium/blob/master/CF%20Recommendation%20System-Examples.ipynb)
* **Metrics**
* [Precision@k: The Overlooked Metric for Fraud and Lead Scoring Models](https://towardsdatascience.com/precision-k-the-overlooked-metric-for-fraud-and-lead-scoring-models-fabad2893c01)
* [Popular evaluation metrics in recommender systems explained](https://medium.com/qloo/popular-evaluation-metrics-in-recommender-systems-explained-324ff2fb427d)
* [How mean Average Precision at k (mAP@k) can be more useful than other evaluation metrics](https://medium.com/@misty.mok/how-mean-average-precision-at-k-map-k-can-be-more-useful-than-other-evaluation-metrics-6881e0ee21a9)

## Getting started

**Step 1**: Clone repo.

```bash
$ git clone https://github.com/adrianmarino/knn-cf-rec-sys.git
$ cd knn-cf-rec-sys
```

**Step 2**: Create environment.

```bash
$ conda env create -f environment.yml
```

## Open notebooks locally

**Step 1**: Enable project environment.

```bash
$ conda activate knn-cf-rec-sys
```

**Step 2**: Under project directory boot jupyter lab.

```bash
$ jupyter lab

Jupyter Notebook 6.1.4 is running at:
http://localhost:8888/?token=45efe99607fa6......
```

**Step 3**: Go to http://localhost:8888.... as indicated in the shell output.