NBA_Predictions - Reworked NBA Predictions (in Python)

  •        719

(Note) Please note that this was written around January 2015. These scripts rely heavily on webscraping to access the required data. Websites regularly change their layouts and locations. Because of this, the webscraping may fail, which causes no updated predictions to be made. I will eventually get around this fall to making sure this runs. I've decided to rework my NBA Prediction code from R to Python. Mostly to see if I could do it, and also to see if I could speed it up a bit. I'll update here with current speed/accuracy results as the 2014-15 season plays out. The structure and format is pretty much the same, with the exception that it's cleaner code. I still need to comment it a bit more, but it's Git ready for now.



Related Projects

nba-go - 🏀 💻 The finest NBA CLI.

  •    Javascript

The finest NBA CLI. Watch NBA live play-by-play, game preview, box score and player information on your console. Best CLI tool for those who are both NBA fans and Engineers.

nba - JavaScript client for various API endpoints

  •    Javascript

It appears as though the NBA has blacklisted certain blocks of IP addresses, specifically those of cloud hosting providers including AWS. As such, you may hit a situation where an application using this package works fine on your local machine, but doesn't work at all when deployed to a cloud server. Annoyingly, requests from these IPs seem to just hang. More information here and here -- the second issue has a curl command somewhere which will quickly tell you if NBA is accepting requests from your IP. (Incidentally, this is also the same reason the TravisCI build is always "broken" but tests all pass locally). There is a simple pass-through server in scripts/proxy that can be used to get around this restriction; you can put the proxy server somewhere that can reach (e.g. not on AWS or Heroku or similar) and host your actual application on a cloud provider. The uses a large number of undocumented JSON endpoints to provide the statistics tables and charts displayed on that website. This library provides a JavaScript client for interacting with many of those API endpoints.

ballr - Interactive NBA and NCAA Shot Charts with R and Shiny

  •    R

BallR uses the NBA Stats API to visualize every shot taken by a player during an NBA season dating back to 1996. See also the college branch of this repo for men's college basketball shot charts.

nba.js - A Node.js library for current and historical NBA stats, scores, and data.

  •    Javascript

A Node.js library for current and historical NBA stats, scores, and data. Full documentation and usage guide can be found here.

NBAPlus - A concise APP about NBA News and Event with RxJava and EventBus

  •    Java

A concise APP about NBA News and Event with RxJava and EventBus

ImageAI - A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities

  •    Python

A python library built to empower developers to build applications and systems with self-contained Deep Learning and Computer Vision capabilities using simple and few lines of code. Built with simplicity in mind, ImageAI supports a list of state-of-the-art Machine Learning algorithms for image prediction, custom image prediction, object detection, video detection, video object tracking and image predictions trainings. ImageAI currently supports image prediction and training using 4 different Machine Learning algorithms trained on the ImageNet-1000 dataset. ImageAI also supports object detection, video detection and object tracking using RetinaNet, YOLOv3 and TinyYOLOv3 trained on COCO dataset. Eventually, ImageAI will provide support for a wider and more specialized aspects of Computer Vision including and not limited to image recognition in special environments and special fields.

ipython-soccer-predictions - Sample iPython notebook with soccer predictions

  •    Python

We’ve had a great time giving you our predictions for the World Cup (check out our post before the quarter finals and the one before the semi-finals). So far, we’ve gotten 13 of 14 games correct. But this shouldn’t be about what we did - it’s about what you can do with Google Cloud Platform. Now, we are open-sourcing our prediction model and packaging it up so you can do your own analysis and predictions.We have ingested raw touch-by-touch gameplay day from Opta for thousands of soccer matches using Google Cloud Dataflow and polished the raw data into predictive statistics using Google BigQuery. You can see BigQuery engineer Jordan Tigani (+JordanTigani) and developer advocate Felipe Hoffa (@felipehoffa) talk about how we did it in this video from Google I/O.

nba_py - Python client for NBA statistics located at

  •    Python

Requests-cache is nice to have when you are downloading very large datasets so that subsequent downloads take much less time, but again, it is by no means necessary.

react-native-nba-app - This is why we play

  •    Objective-C

The design is made by Sketch, you can find the original design file in Dropbox, it may help if someone wants to design new features.

detr - End-to-End Object Detection with Transformers

  •    Python

PyTorch training code and pretrained models for DETR (DEtection TRansformer). We replace the full complex hand-crafted object detection pipeline with a Transformer, and match Faster R-CNN with a ResNet-50, obtaining 42 AP on COCO using half the computation power (FLOPs) and the same number of parameters. Inference in 50 lines of PyTorch. What it is. Unlike traditional computer vision techniques, DETR approaches object detection as a direct set prediction problem. It consists of a set-based global loss, which forces unique predictions via bipartite matching, and a Transformer encoder-decoder architecture. Given a fixed small set of learned object queries, DETR reasons about the relations of the objects and the global image context to directly output the final set of predictions in parallel. Due to this parallel nature, DETR is very fast and efficient.

auto_ml - Automated machine learning for analytics & production

  •    Python

auto_ml is designed for production. Here's an example that includes serializing and loading the trained model, then getting predictions on single dictionaries, roughly the process you'd likely follow to deploy the trained model. All of these projects are ready for production. These projects all have prediction time in the 1 millisecond range for a single prediction, and are able to be serialized to disk and loaded into a new environment after training.

bitpredict - Machine learning for high frequency bitcoin price prediction

  •    Python

This project aims to make high frequency bitcoin price predictions from market microstructure data. The dataset is a series of one second snapshots of open buy and sell orders on the Bitfinex exchange, combined with a record of executed transactions. Data collection began 08/20/2015.A number of engineered features are used to train a Gradient Boosting model, and a theoretical trading strategy is simulated on historical and live data.

mind - A neural network library built in JavaScript

  •    Javascript

A flexible neural network library for Node.js and the browser. Check out a live demo of a movie recommendation engine built with Mind. Use plugins created by the Mind community to configure pre-trained networks that can go straight to making predictions.

android-yolo - Real-time object detection on Android using the YOLO network with TensorFlow

  •    C++

android-yolo is the first implementation of YOLO for TensorFlow on an Android device. It is compatible with Android Studio and usable out of the box. It can detect the 20 classes of objects in the Pascal VOC dataset: aeroplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, dining table, dog, horse, motorbike, person, potted plant, sheep, sofa, train and tv/monitor. The network only outputs one predicted bounding box at a time for now. The code can and will be extended in the future to output several predictions. To use this demo first clone the repository. Download the TensorFlow YOLO model and put it in android-yolo/app/src/main/assets. Then open the project on Android Studio. Once the project is open you can run the project on your Android device using the Run 'app' command and selecting your device.

food-inspections-evaluation - This repository contains the code to generate predictions of critical violations at food establishments in Chicago

  •    HTML

This is our model for predicting which food establishments are at most risk for the types of violations most likely to spread food-borne illness. Chicago Department of Public Health staff use these predictions to prioritize inspections. During a two month pilot period, we found that that using these predictions meant that inspectors found critical violations much faster. You can help improve the health of our city by improving this model. This repository contains a training and test set, along with the data used in the current model.

Toxtree: Toxic Hazard Estimation

  •    Java

Toxicity prediction for chemical compounds

seq2seq-signal-prediction - Signal prediction with a Sequence-to-Sequence (seq2seq) Recurrent Neural Network (RNN) model in TensorFlow - Guillaume Chevalier

  •    Jupyter

The goal of this project of mine is to bring users to try and experiment with the seq2seq neural network architecture. This is done by solving different simple toy problems about signal prediction. Normally, seq2seq architectures may be used for other more sophisticated purposes than for signal prediction, let's say, language modeling, but this project is an interesting tutorial in order to then get to more complicated stuff. Except the fact I made available an ".py" Python version of this tutorial within the repository, it is more convenient to run the code inside the notebook. The ".py" code exported feels a bit raw as an exportation.

MSDNet - Multi-Scale Dense Networks for Resource Efficient Image Classification (ICLR 2018 Oral)

  •    Lua

This repository provides the code for the paper Multi-Scale Dense Networks for Resource Efficient Image Classification. This paper studies convolutional networks that require limited computational resources at test time. We develop a new network architecture that performs on par with state-of-the-art convolutional networks, whilst facilitating prediction in two settings: (1) an anytime-prediction setting in which the network's prediction for one example is progressively updated, facilitating the output of a prediction at any time; and (2) a batch computational budget setting in which a fixed amount of computation is available to classify a set of examples that can be spent unevenly across 'easier' and 'harder' examples.

Stock-Prediction-Models - Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations

  •    Jupyter

Stock-Prediction-Models, Gathers machine learning and deep learning models for Stock forecasting, included trading bots and simulations. I code LSTM Recurrent Neural Network and Simple signal rolling agent inside Tensorflow JS, you can try it here,, you can download any historical CSV and upload dynamically.

We have large collection of open source products. Follow the tags from Tag Cloud >>

Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.