Visualizing Generative Adversarial Networks

Yesterday, I wrote about Generative Adversarial Networks being all the rage at NIPS this year. I created a toy model using Tensorflow to wrap my head around how the idea works. Building on that example, I created a video to visualize the adversarial training process.

The top left panel shows samples from both the training and generated (eg counterfeit) data. Remember that the goal is to have the generator produce samples that the discriminator can not distinguish from the real (training) data. Top right shows the predicted energy function from the discriminator.  The bottom row shows the loss function for the discriminator (D) and generator (G).

I don’t fully understand why the dynamics of the adversarial training process are transiently unstable, but it seems to work overall. Another interesting observation is that the loss seems to continue to fall overall, even as it goes though the transient phases of instability when the fit of the generated data is qualitatively poor.

Categorizing NIPS papers using LDA topic modeling

The Annual Conference on Neural Information Processing Systems (NIPS) has recently listed this year’s accepted papers. There are 403 paper titles listed, which made for great morning coffee reading, trying to pick out the ones that most interest me.

Being a machine learning conference, it’s only reasonable that we apply a little machine learning to this (decidedly _small_) data.

Building off of the great example code in a post by Jordan Barber on Latent Dirichlet Allocation (LDA) with Python, I scraped the paper titles and built an LDA topic model with 5 topics. All of the code to reproduce this post is available on github. Here are the top 10 most probable words from each of the derived topics:

0 1 2 3 4
0 learning learning optimization learning via
1 models inference networks bayesian models
2 neural sparse time sample inference
3 high models stochastic analysis networks
4 stochastic non model data deep
5 dimensional optimization convex inference learning
6 networks algorithms monte spectral fast
7 graphs multi carlo networks variational
8 optimal linear neural bandits neural
9 sampling convergence information methods convolutional

Normally, we might try to attach some kind of label to each topic using our beefy human brains and subject matter expertise, but I didn’t bother with this — nothing too obvious stuck out at me. If you think that you have appropriate names for them feel free to let me know. Given that we are only working with the titles (no abstracts or full paper text), I think that there aren’t obvious human-interpretable topics jumping out. But let’s not let that stop us from proceeding.

We can also represent the inferred topics with the much maligned, but handy-dandy wordcloud visualization:

Topic: 0
Topic: 1
Topic: 2
Topic: 3
Topic: 4

Since we are modeling the paper title generating process as a probability distribution of topics, each of which is a probability distribution of words, we can use this generating process to suggest keywords for each title. These keywords may or may not show up in the title itself. Here are some from the first 10 titles:


Double or Nothing: Multiplicative Incentive Mechanisms for Crowdsourcing
Generated Keywords: [u'iteration', u'inference', u'theory']


Learning with Symmetric Label Noise: The Importance of Being Unhinged
Generated Keywords: [u'uncertainty', u'randomized', u'neural']


Algorithmic Stability and Uniform Generalization
Generated Keywords: [u'spatial', u'robust', u'dimensional']


Adaptive Low-Complexity Sequential Inference for Dirichlet Process Mixture Models
Generated Keywords: [u'rates', u'fast', u'based']


Covariance-Controlled Adaptive Langevin Thermostat for Large-Scale Bayesian Sampling
Generated Keywords: [u'monte', u'neural', u'stochastic']


Robust Portfolio Optimization
Generated Keywords: [u'learning', u'online', u'matrix']


Logarithmic Time Online Multiclass prediction
Generated Keywords: [u'complexity', u'problems', u'stein']


Planar Ultrametric Rounding for Image Segmentation
Generated Keywords: [u'deep', u'graphs', u'neural']


Expressing an Image Stream with a Sequence of Natural Sentences
Generated Keywords: [u'latent', u'process', u'stochastic']


Parallel Correlation Clustering on Big Graphs
Generated Keywords: [u'robust', u'learning', u'learning']

Entropy and the most “interdisciplinary” paper title

While some titles are strongly associated with a single topic, others seem to be generated from more even distributions over topics than others. Paper titles with more equal representation over topics could be considered to be, in some way, more interdisciplinary, or at least, intertopicular (yes, I just made that word up). To find these papers, we’ll find which paper titles have the highest information entropy in their inferred topic distribution.

Here are the top 10 along with their associated entropies:

1.22769364291 Where are they looking?
1.1794725784 Bayesian dark knowledge
1.11261338284 Stochastic Variational Information Maximisation
1.06836891546 Variational inference with copula augmentation
1.06224431711 Adaptive Stochastic Optimization: From Sets to Paths
1.04994413148 The Population Posterior and Bayesian Inference on Streams
1.01801236048 Revenue Optimization against Strategic Buyers
1.01652797194 Fast Convergence of Regularized Learning in Games
0.993789478925 Communication Complexity of Distributed Convex Learning and Optimization
0.990764728084 Local Expectation Gradients for Doubly Stochastic Variational Inference

So it looks like by this method, the ‘Where are they looking’ has the highest entropy as a result of topic uncertainty, more than any real multi-topic content.

One datavis for you, ten for me

Over the years of my graduate studies I made a lot of plots. I mean tonnes. To get an extremely conservative estimate I grep’ed for every instance of “plot\(” in all of the many R scripts I wrote over the past five years.

find . -iname "*.R" -print0 | xargs -L1 -0 egrep -r "plot(" | wc -l


The actual number is very likely orders of magnitude larger as 1) many of these plot statements are in loops, 2) it doesn’t capture how many times I may have ran a given script, 3) it doesn’t look at previous versions, 4) plot is not the only command to generate figures in R (eg hist), and 5) early in my graduate career I mainly used gnuplot and near the end I was using more and more matplotlib. But even at this lower bound, that’s nearly 3,000 plots. A quick look at the TOC of my thesis reveals a grand total of 33 figures. Were all the rest a waste? (Hint: No.)

The overwhelming majority of the plots that I created served a very different function than these final, publication-ready figures. Generally, visualizations are either:

  • A) Communication between you and data, or
  • B) Communication between you and someone else, through data.

These two modes serve very different purposes and can require taking different approaches in their creation. Visualizations in the first mode need only be quick and dirty. You can often forget about all that nice axis labeling, optimal color contrast, and whiz-bang interactivity. As per my estimates above, this made up at the very least 10:1 of visuals created. The important thing is that, in this mode, you already have all of the context. You know what the variables are, you know what the colors, shapes, sizes, and layouts mean – after all, you just coded it. The beauty of this is that you can iterate on these plots very quickly. The conversation between you and the data can dialogue back and forth as you intrepidly explore and shine your light into all of it’s dark little corners.

In the second mode, you are telling a story to someone else. Much more thought and care needs to be placed on ensuring that the whole story is being told with the visualization. It is all too easy to produce something that makes sense to you, but is completely unintelligible to your intended audience. I’ve learned the hard way that this kind of visual should always be test-driven by someone who, ideally, is a member of your intended audience. When you are as steeped in the data as you most likely are, your mind will fill in any missing pieces of the story – something your audience won’t do.

In my new role as part of the Data Science team at Penn Medicine, I’ll be making more and more data visualizations in the second mode. A little less talking to myself with data, and a little more communicating with others through data. I’ll be sharing some of my experiences, tools, wins, and disasters here. Stay tuned!

Plot with ggplot2, interact, collaborate, and share online

Editor’s note: This is a guest post by Marianne Corvellec from Plotly. This post is based on an interactive Notebook (click to view) she presented at the R User Conference on July 1st, 2014.

Plotly is a platform for making, editing, and sharing graphs. If you are used to making plots with ggplot2, you can call ggplotly() to make your plots interactive, web-based, and collaborative. For example, see, shown below and in this Notebook. Notice the hover text!


0. Get started

Visit Here, you’ll find a GUI that lets you create graphs from data you enter manually, or upload as a spreadsheet (or CSV file). From there you can edit graphs! Change between types (from bar charts to scatter charts), change colors and formatting, add fits and annotations, try other themes…


Our R API lets you use Plotly with R. Once you have your R visualization in Plotly, you can use the web interface to edit it, or to extract its data. Install and load package “plotly” in your favourite R environment. For a quick start, follow:

Go social! Like, share, comment, fork and edit plots… Export them, embed them in your website. Collaboration has never been so sweet!


Not ready to publish? Set detailed permissions for who can view and who can edit your project.


1. Make a (static) plot with ggplot2

Baseball data is the best! Let’s plot a histogram of batting averages. I downloaded data here.

Load the CSV file of interest, take a look at the data, subset at will:


online_data <-

batting_table <-



batting_table <- 
 subset(batting_table, yearID >= 2004)

The batting average is defined by the number of hits divided by at bats:

batting_table$Avg <- 
 with(batting_table, H / AB)

You may want to explore the distribution of your new variable as follows:

 + geom_histogram(aes(Avg), binwidth=0.05)

# Let's filter out entries where players were at bat less than 10 times.

batting_table <- 
 subset(batting_table, AB >= 10)
hist <-
 ggplot(data=batting_table) + geom_histogram(aes(Avg),

We have created a basic histogram; let us share it, so we can get input from others!

2. Save your R plot to

# Install the latest version 
# of the “plotly” package and load it


# Open a Plotly connection

py <-
 plotly("ggplot2examples", "3gazttckd7")

Use your own credentials if you prefer. You can sign up for a Plotly account online.

Now call the `ggplotly()` method:

collab_hist <-

And boom!


You get a nice interactive version of your plot! Go ahead and hover…

Your plot lives at this URL (`collab_hist$response$url`) alongside the data. How great is that?!

If you wanted to keep your project private, you would use your own credentials and specify:

py <- plotly()


3. Edit your plot online


Now let us click “Fork and edit”. You (and whoever you’ve added as a collaborator) can make edits in the GUI. For instance, you can run a Gaussian fit on this distribution:


You can give a title, edit the legend, add notes, etc.


You can add annotations in a very flexible way, controlling what the arrow and text look like:


When you’re happy with the changes, click “Share” to get your plot’s URL.

If you append a supported extension to the URL, Plotly will translate your plot into that format. Use this to export static images, embed your graph as an iframe, or translate the code between languages. Supported file types include:

Isn’t life wonderful?

4. Retrieve your plot in R

The JSON file specifies your plot completely (it contains all the data and layout info). You can view it as your plot’s DNA. The R file ( is a conversion of this JSON into a nested list in R. So we can interact with it by programming in R!

Access a plot which lives on with the well-named method `get_figure()`:

enhanc_hist <-
 py$get_figure("mkcor", 305)

Take a look:


# Data for second trace

The second trace is a vertical line at 0.300 named “Good”. Say we get more ambitious and we want to show a vertical line at 0.350 named “Very Good”. We overwrite old values with our new values:

enhanc_hist$data[[2]]$name <- "VeryGood"
enhanc_hist$data[[2]]$x[[1]] <- 0.35
enhanc_hist$data[[2]]$x[[2]] <- 0.35

Send this new plot back to!

enhanc_hist2 <-


Visit the above URL (`enhanc_hist2$url`).

How do you like this workflow? Let us know!

Tutorials are at You can see more examples and documentatation at and Our gallery has the following examples:



This presentation benefited tremendously from comments by Matt Sundquist and Xavier Saint-Mleux.

Plotly’s R API is part of rOpenSci. It is under active development; you can find it on GitHub. Your thoughts, issues, and pull requests are always welcome!

Online R and Plotly Graphs: Canadian and U.S. Maps, Old Faithful with Multiple Axes, & Overlaid Histograms

Guest post by Matt Sundquist of

Plotly is a social graphing and analytics platform. Plotly’s R library lets you make and share publication-quality graphs online. Your work belongs to you, you control privacy and sharing, and public use is free (like GitHub). We are in beta, and would love your feedback, thoughts, and advice.

1. Installing Plotly

Let’s install Plotly. Our documentation has more details.


Then signup online or like this:

response = signup (username = 'yourusername', email= 'youremail')

Thanks for signing up to plotly! Your username is: MattSundquist Your temporary password is: pw. You use this to log into your plotly account at Your API key is: “API_Key”. You use this to access your plotly account through the API.

2. Canadian Population Bubble Chart

Our first graph was made at a Montreal R Meetup by Plotly’s own Chris Parmer. We’ll be using the maps package. You may need to load it:



p <- plotly(username="MattSundquist", key="4om2jxmhmn")
trace1 <- list(x=map(regions="canada")$x,

trace2 <- list(x= canada.cities$long,

response <- p$plotly(trace1,trace2)
url <- response$url
filename <- response$filename

In our graph, the bubble size represents the city population size. Shown below is the GUI, where you can annotate, select colors, analyze and add data, style traces, place your legend, change fonts, and more.


Editing from the GUI, we make a styled version. You can zoom in and hover on the points to find out about the cities. Want to make one for another country? We’d love to see it.


And, here is said meetup, in action:


You can also add in usa and us.cities:


3. Old Faithful and Multiple Axes

Ben Chartoff’s graph shows the correlation between a bimodal eruption time and a bimodal distribution of eruption length. The key series are: a histogram scale of probability, Eruption Time scale in minutes, and a scatterplot showing points within each bin on the x axis. The graph was made with this gist.


4. Plotting Two Histograms Together

Suppose you are studying correlations in two series (Popular Stack Overflow ?). You want to find overlap. You can plot two histograms together, one for each series. The overlapping sections are the darker orange, automatically rendered if you set barmode to ‘overlay’.

p <- plotly(username="Username", key="API_KEY")

x0 <- rnorm(500)
x1 <- rnorm(500)+1

data0 <- list(x=x0,
  name = "Series One",
  opacity = 0.8)

data1 <- list(x=x1,
  name = "Series Two",
  opacity = 0.8)

layout <- list(
  xaxis = list(
  ticks = "",
  gridcolor = "white",zerolinecolor = "white",
  linecolor = "white"
 yaxis = list(
  ticks = "",
  gridcolor = "white",
  zerolinecolor = "white",
  linecolor = "white"
 # style background color. You can set the alpha by adding an a.
 plot_bgcolor = 'rgba(249,249,251,.85)'

response <- p$plotly(data0, data1, kwargs=list(layout=layout))
url <- response$url
filename <- response$filename


5. Plotting y1 and y2 in the Same Plot

Plotting two lines or graph types in Plotly is straightforward. Here we show y1 and y2 together (Popular SO ?). 

p <- plotly(username="Username", key="API_KEY")

# enter data
x <- seq(-2, 2, 0.05)
y1 <- pnorm(x)
y2 <- pnorm(x,1,1)

# format, listing y1 as your y.
First <- list(
  x = x,
  y = y1,
  type = 'scatter',
  mode = 'lines',
  marker = list(
   color = 'rgb(0, 0, 255)',
   opacity = 0.5)

# format again, listing y2 as your y.
Second <- list(
  x = x,
  y = y2,
  type = 'scatter',
  mode = 'lines',
  opacity = 0.8,
  marker = list(
   color = 'rgb(255, 0, 0)')


And a shot of the Plotly gallery, as seen at the Montreal meetup. Happy plotting!