Skip to content

Instantly share code, notes, and snippets.

Francois Vanderseypen Orbifold

Block or report user

Report or block Orbifold

Hide content and notifications from this user.

Learn more about blocking users

Contact Support about this user’s behavior.

Learn more about reporting abuse

Report abuse
View GitHub Profile
@Orbifold
Orbifold / GraphFrames.ipynb
Last active Aug 16, 2019
GraphFrames.ipynb
View GraphFrames.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
View WalmartStock.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@Orbifold
Orbifold / Logistic_Regression_Titanic.ipynb
Last active Aug 11, 2019
Most basic example of Using MLlib on Spark.
View Logistic_Regression_Titanic.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@Orbifold
Orbifold / QuiverPublisher.js
Created Jun 9, 2019
Script to publish Quiver markdown notebooks to WordPress.
View QuiverPublisher.js
// You need to export first a notebook from Quiver (https://happenapps.com) to markdown.
// Use the directory path below to publish all the markdown files and the images to a WordPress site.
// Make sure you install lodash, wordpress and fs-extra.
// Set the ur, username and password of WordPress and run `node QuiverPublisher.js'.
// Note that images are deleted and recreated since the overwrite flag of the xmlrpc wp-method does not work.
const wordpress = require('wordpress');
const fs = require('fs-extra');
const _ = require('lodash');
const path = require('path');
@Orbifold
Orbifold / MathematicaLSTM.nb
Last active Aug 16, 2019
Learning to add with LSTM
View MathematicaLSTM.nb
(* Content-type: application/vnd.wolfram.mathematica *)
(*** Wolfram Notebook File ***)
(* http://www.wolfram.com/nb *)
(* CreatedBy='Mathematica 11.3' *)
(*CacheID: 234*)
(* Internal cache information:
NotebookFileLineBreakTest
View TensorFlow hello world.md
	import tensorflow as tf


	import numpy as np
	x_input = np.array([[1,2,3,4,5]])
	y_input = np.array([[10]])
View Pytorch hello world.md
	import torch


	batch_size = 32
	input_shape = 5
	output_shape = 10
View Keras hello world.md

Using Keras (now part of TensorFlow) is really easy. The complexity comes when you deal with large amounts of data figuring out the topology of a neural network. With the topology comes hyperparameter tuning and all that. It's a bit like painting: it's easy to hold a brush but it takes years to paint something worth looking at.

	import tensorflow as tf
	from tensorflow.keras.models import Sequential
	from tensorflow.keras.layers import Dense
View Gluon hello world.md
	from mxnet import gluon

	import mxnet as mx
	import numpy as np
	x_input = mx.nd.empty((1, 5), mx.cpu())
	x_input[:] = np.array([[1,2,3,4,5]], np.float32)

	y_input = mx.nd.empty((1, 5), mx.cpu())
	y_input[:] = np.array([[10, 15, 20, 22.5, 25]], np.float32)
@Orbifold
Orbifold / TFjsCosine.html
Created Aug 24, 2018
Learning the cosine function with TensorFlow.js
View TFjsCosine.html
<!DOCTYPE html>
<html lang="en" xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta charset="utf-8" />
<title></title>
<script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.2.1/jquery.min.js"></script>
<script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/lodash.js/4.17.4/lodash.min.js"></script>
<script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/Faker/3.1.0/faker.min.js"></script>
<script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/4.0.0-beta/js/bootstrap.min.js"></script>
You can’t perform that action at this time.