Notebook Gallery

Links to the best IPython and Jupyter Notebooks.

Loading web page ...

Doc2Vec

Doc2Vec

Word2vec is not a single algorithm but consists of two techniques – CBOW(Continuous bag of words) and Skip-gram model. Both of these techniques learn weights which act as word vector representations. With a corpus, CBOW model predicts the current word ...

Train / Dev / Test Split

Train / Dev / Test Split

The ratio I decided to split my data is 98/1/1, 98% of data as the training set, and 1% for the dev set, and the final 1% for the test set. The rationale behind this ratio comes from the size ...

800 rows × 10 columns

800 rows × 10 columns

This website does not host notebooks, it only renders notebooks available on other websites.

Gate Expansions

Gate Expansions

The expansions used by Qubiter were all discovered long ago. They can all be found in the following 1995 quantum computing paper:

Algorithms Comparison

Algorithms Comparison

Let's first look at Term Frequency. We have already looked at term frequency above with count vectorizer, but this time, we need one more step to calculate relative frequency. Let's say we have two documents in total as below.

DeepMind 's Demis Hassabis - Mind Interpreted the World

DeepMind 's Demis Hassabis - Mind Interpreted the World

Delivered by Fastly , Rendered by Rackspace

Movielens

Movielens

We're working with the movielens data, which contains one rating per row, like this:

This website does not host notebooks, it only renders notebooks available on other websites.

This website does not host notebooks, it only renders notebooks available on other websites.

Delivered by Fastly , Rendered by Rackspace

Capstone Part 2: Data Preparation

Capstone Part 2: Data Preparation

By looking at the description of the dataset from the link, the information on each field can be found.

Zipf's Law

Zipf's Law

In other words, the rth most frequent word has a frequency f(r) that scales according to $${f(r)} \propto \frac{1}{r^\alpha}$$ for $$\alpha \approx {1}$$

Captstone Part 3

Captstone Part 3

The first issue I realised is that, during the cleaning process, negation words are split into two parts, and the 't' after the apostrophe vanishes when I filter tokens with length more than one syllable. This makes words like "can't" ...

Experiments with Memory Access and Matrices

Experiments with Memory Access and Matrices

In this notebook, we'll explore these performance issues with a few typical matrix algorithms, implemented in Julia.

In this notebook, we will show how to load pre-trained models and draw things with sketch-rnn

In this notebook, we will show how to load pre-trained models and draw things with sketch-rnn

define the path of the model you want to load, and also the path of the dataset

Testing REST API with for Robot Framework

Testing REST API with for Robot Framework

Let's start learning it by importing the library and configuring it to test our example service: a Plone CMS demo site hosted at http://plonedemo.kitconcept.com :

Table of Contents

Table of Contents

http://docs.juliaplots.org/latest/examples/pyplot/

Star Wars API

Star Wars API

This notebook is all about exploratory data analyses based on the new and awesome Star Wars API by Paul Hallett.

This website does not host notebooks, it only renders notebooks available on other websites.

This website does not host notebooks, it only renders notebooks available on other websites.

Delivered by Fastly , Rendered by Rackspace

This website does not host notebooks, it only renders notebooks available on other websites.

This website does not host notebooks, it only renders notebooks available on other websites.

Delivered by Fastly , Rendered by Rackspace

Word2Vec with Skip-Gram and TensorFlow

Word2Vec with Skip-Gram and TensorFlow

The goal of the model is to train it embeddings layer in a way that similar by meaning words are close to each other in their N-dimensional vector representation. The model has two layers: the embeddings layer and a linear ...

VQE algorithm: Application to quantum chemistry

VQE algorithm: Application to quantum chemistry

Antonio Mezzacapo, Jay Gambetta

data

data

Delivered by Fastly , Rendered by Rackspace

Capsule Networks (CapsNets)

Capsule Networks (CapsNets)

Inspired in part from Huadong Liao's implementation: CapsNet-TensorFlow .

Jupyter Blogging in 5 minutes.

Jupyter Blogging in 5 minutes.

Q: Why Jupyter Blogging? A: As a Data Scientists, I use jupyter to create notebooks with code, equations, visualizations, documentation, etc. "Jupyter Blogging" allows me to share those notebooks with the world without any additional work.

Experiments with Memory Access and Matrices

Experiments with Memory Access and Matrices

In this notebook, we'll explore these performance issues with a few typical matrix algorithms, implemented in Julia.

Load raw data

Load raw data

This website does not host notebooks, it only renders notebooks available on other websites.

Embeddings in TensorFlow

Embeddings in TensorFlow

Using embeddings for a sparse data often results in more efficient representation as compared to the one-hot encoding approach. For example, a typical vocabulary size for NLP problems is usually from 20,000 to 200,000 unique words. It will be very ...

Gridfonts

Gridfonts

This data was used in both Gary McGraw's and Douglas Blank's theses to train neural networks. See section 6.3.2 of McGraw's thesis , and Blank's thesis Learning to See Analogies: a Connectionist Exploration .

Theano implementation of Gumbel Softmax / Concrete VAE with BayesFlow

Theano implementation of Gumbel Softmax / Concrete VAE with BayesFlow

Tensorflow version: 17 Feb 2017

UK Immigration Raids: Migrating the Data

UK Immigration Raids: Migrating the Data

We need to skip at least 3 rows. If there are initial blank lines at the top of the sheet, these will be ignored automatically - so it may be more...

Plots with Plots

Plots with Plots

... did I mention I'm a bit of a geek?