--Jean Arreola--Personal website with all my crazy ideas.
http://jean9208.github.io/
Fri, 13 Jul 2018 22:40:35 +0000Fri, 13 Jul 2018 22:40:35 +0000Jekyll v3.7.3Variational Gaussian Mixtures for Face Detection<h2 id="mixture-model">Mixture model</h2> <p>A Gaussian mixture model is a probabilistic way of representing subpopulations within an overall population. We only observe the data, not the subpopulation from which observation belongs.</p> <p>We have $N$ random variables observed, each distributed according to a mixture of K gaussian components. Each gaussian has its own parameters, and we should be able to estimate the category using Expectation Maximization, as we are using a latent variables model.</p> <p>Now, in a bayesian scenario, each parameter of each gaussian is also a random variable, as well as the mixture weights. To estimate the distributions we use Variational...Fri, 13 Jul 2018 00:00:00 +0000
http://jean9208.github.io/vgmm_fd/
http://jean9208.github.io/vgmm_fd/RHighchartsVariational InferenceAlgorithmsCorrespondence Analysis of Mexican Discourses<h2 id="correspondence-analysis">Correspondence Analysis</h2> <p>Correspondence analysis is a multivariate statistical technique that summarizes a set of categorical data in a two dimensional form. It’s like the equivalent of Principal Component Analysis but for categorical data.</p> <p>Correspondence analysis is usually applied to contigency tables. In this post, we will apply it to a frequency matrix (term document matrix from bag of words representation).</p> <p>The analysis can be done by row or by column. Below is an implementation of correspondence analysis, where row and column analysis are done at the same time.</p> <div class="language-r highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">correspondence</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span...Sun, 24 Jun 2018 00:00:00 +0000
http://jean9208.github.io/ca_mexdis/
http://jean9208.github.io/ca_mexdis/RHighchartsPoliticsAlgorithmsPostgresql + R Sandbox<h2 id="elephantsql">ElephantSQL</h2> <p><a href="https://www.elephantsql.com/">ElephantSQL</a> offers a free instance of Postgresql, with a limit of 20 MB and 5 concurrent connections. For example, you can upload a shiny application that depends on data from ElephantSQL.</p> <p>You only need to register to the site and automatically you can acces your free instance.</p> <p>In this post we will see how to take advantage of this cloud database.</p> <h2 id="getting-the-data">Getting the data</h2> <p>For this example I will use the open data of air quality available in the page of SEDEMA (Environment Secretary) of Mexico City.</p> <p>The data is structured by one csv file per...Sun, 24 Sep 2017 00:00:00 +0000
http://jean9208.github.io/postgresqlR_Sandbox/
http://jean9208.github.io/postgresqlR_Sandbox/RSQLDatabasesGradient Descent<h2 id="trying-gradient-descent-for-linear-regression">Trying gradient descent for linear regression</h2> <p>The best way to learn an algorith is to code it. So here it is, my take on Gradient Descent Algorithm for simple linear regression.</p> <p>First, we fit a simple linear model with lm for comparison with gradient descent values.</p> <div class="language-r highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="c1">#Load libraries</span><span class="w"> </span><span class="n">library</span><span class="p">(</span><span class="n">dplyr</span><span class="p">)</span><span class="w"> </span><span class="n">library</span><span class="p">(</span><span class="n">highcharter</span><span class="p">)</span><span class="w"> </span><span class="c1">#Scaling length variables from iris dataset.</span><span class="w"> </span><span class="n">iris_demo</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">iris</span><span class="p">[,</span><span class="nf">c</span><span class="p">(</span><span class="s2">"Sepal.Length"</span><span class="p">,</span><span class="s2">"Petal.Length"</span><span class="p">)]</span><span class="w"> </span><span class="o">%>%</span><span class="w"> </span><span class="n">mutate</span><span class="p">(</span><span class="n">sepal_length</span><span class="w"> </span><span...Wed, 29 Mar 2017 00:00:00 +0000
http://jean9208.github.io/gradient_descent/
http://jean9208.github.io/gradient_descent/RHighchartsAlgorithmsBuilding a pokemon graph database<h2 id="what-happens-when-you-combine-pokemon-with-neo4j">What happens when you combine Pokemon with Neo4j?</h2> <p>I’m a huge Pokemon fan. So, when I found about <a href="http://jkunst.com/r/pokemon-visualize-em-all/">this awesome post</a> from <em>Joshua Kunst</em>, I just couldn’t wait to throw all that data into Neo4j.</p> <p>It also happens to be a great way to learn how to build a graph database from scratch. The objective of this exercise is to build a graph database where the nodes are the pokemon and the types, and the relationships are the effectiveness between the pokemon based only on their types.</p> <h2 id="getting-the-data">Getting the data</h2> <p>First of all, be sure to check...Mon, 13 Feb 2017 00:00:00 +0000
http://jean9208.github.io/pokemon_graph/
http://jean9208.github.io/pokemon_graph/RNeo4jPokemonR-Bloggers<h2 id="what-is-r-bloggers">What is R-Bloggers?</h2>
<p>R-Bloggers is a blog aggregator of content about R. You can find tons of cool stuff, like statistics, web scraping, finance, plots, etc.</p>
<p>Finally this blog was accepted into R-Bloggers! I encourage you to follow R-Bloggers. It is updated everyday and all the post are interesting.</p>
<p>You can enter R-Bloggers <a href="https://www.r-bloggers.com/">following this link</a>.</p>
<p>Also be sure to check this <a href="https://www.r-users.com">job-board</a> for R-users.</p>
Sun, 12 Feb 2017 00:00:00 +0000
http://jean9208.github.io/welcome_rbloggers/
http://jean9208.github.io/welcome_rbloggers/NewsNews