![\"Galaxy\"](\"http://upload.wikimedia.org/wikipedia/commons/7/74/Ngc5194.jpg\")
You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.
\r\n\r\n Privately sharing code or data outside of teams is not permitted.\r\n It's okay to share code if made available to all participants on the forums.\r\n
\r\nKaggle and the competition host have the right to publicly disseminate any entries or models.
\r\n\r\n Winning solutions need to be made available under\r\n a popular OSI-approved license\r\n in order to be eligible for recognition and prize money.\r\n
\r\n\r\n Prizes will be awarded after the winners have posted their solutions to the competition forum.\r\n Winners must post or link to their solutions within seven (7) days of being notified of their winning status.\r\n
\r\n\r\n Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.
\r\n
There is no maximum team size.
\r\nYou may submit a maximum of 5 entries per day.
\r\nYou may select up to 2 final submissions for judging.
\r\nStart Date: 12/20/2013 11:25 PM UTC
\r\nMerger Deadline: 3/28/2014 11:59 PM UTC
\r\nEntry Deadline: 3/28/2014 11:59 PM UTC
\r\nEnd Date: 4/4/2014 11:59 PM UTC
\r\n\t\r\nExternal data is not allowed without explicit, public consent (via the competition forums). Participants agree to make no attempt to use additional data sources or data sources not provided on these competition pages. This includes any metadata associated with published Galaxy Zoo catalogs or the Sloan Digital Sky Survey. Participants may not use the earlier sets of training and test data (which had flawed constraints and were removed from the Kaggle Galaxy Zoo competition site on Jan 9, 2014) as part of their solution.
\r\nDeadline for new entrants to the competition and team mergers is Friday, March 14, 2014.
\r\nThis competition is subject to the Research Competition Standard Rules.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "The first column in each solution is labeled GalaxyID; this is a randomly-generated ID that only allows you to match the probability distributions with the images. The next 37 columns are all floating point numbers between 0 and 1 inclusive. These represent the morphology (or shape) of the galaxy in 37 different categories as identified by crowdsourced volunteer classifications as part of the Galaxy Zoo 2 project. These morphologies are related to probabilities for each category; a high number (close to 1) indicates that many users identified this morphology category for the galaxy with a high level of confidence. Low numbers for a category (close to 0) indicate the feature is likely not present.
\r\nVisit the Galaxy Zoo Decision Tree page for a detailed description of the data.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "Understanding how and why we are here is one of the fundamental questions for the human race. Part of the answer to this question lies in the origins of galaxies, such as our own Milky Way. Yet questions remain about how the Milky Way (or any of the other ~100 billion galaxies in our Universe) was formed and has evolved. Galaxies come in all shapes, sizes and colors: from beautiful spirals to huge ellipticals. Understanding the distribution, location and types of galaxies as a function of shape, size, and color are critical pieces for solving this puzzle.
\r\n
The Whirlpool Galaxy (M51). Credit: NASA and European Space Agency
\r\nWith each passing day telescopes around and above the Earth capture more and more images of distant galaxies. As better and bigger telescopes continue to collect these images, the datasets begin to explode in size. In order to better understand how the different shapes (or morphologies) of galaxies relate to the physics that create them, such images need to be sorted and classified. Kaggle has teamed up with Galaxy Zoo and Winton Capital to produce the Galaxy Challenge, where participants will help classify galaxies into categories.
\r\n ![\"Main](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/3175/media/mainimage.jpg\" "\\"Main")
Image Credit: ESA/Hubble & NASA
\r\nGalaxies in this set have already been classified once through the help of hundreds of thousands of volunteers, who collectively classified the shapes of these images by eye in a successful citizen science crowdsourcing project. However, this approach becomes less feasible as data sets grow to contain of hundreds of millions (or even billions) of galaxies. That's where you come in.
\r\nThis competition asks you to analyze the JPG images of galaxies to find automated metrics that reproduce the probability distributions derived from human classifications. For each galaxy, determine the probability that it belongs in a particular class. Can you write an algorithm that behaves as well as the crowd does?
\r\nContributors: D. Harvey, C. Lintott, T. Kitching, P. Marshall, K. Willett, Galaxy Zoo
\r\nThe Contributors and the rest of the Galaxy Zoo and Kaggle teams would like to say a big thank you to Winton Capital for helping make this happen. Without their support, we would have not been able to make this competition go ahead.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "This competition uses Root Mean Squared Error as the evaluation metric.
\r\n\\[ \\mathrm{RMSE} = \\sqrt{\\frac{1}{N}\\sum_{i=1}^N(p_i - a_i)^2} \\]
\r\nWhere:
\r\n\\\\(N\\\\) is the number of galaxies times the total number of responses
\\\\(p_i\\\\) is your predicted value
\\\\(a_i\\\\) is the actual value
Your submission file must have a header and should be structured in the following format. The Data page provides some example solution files.
\r\nGalaxyId,Class1.1,Class1.2,Class1.3,Class2.1, ..., Class11.5, Class11.6", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "The Galaxy Zoo Decision Tree", "content": "
100002,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
100003,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
100004,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
etc...
Galaxy Zoo guides its citizen scientists through a nested decision tree - this is what constitutes the classification process. The decision tree consists of 11 questions, with each question having 2-7 responses.
\r\nQ1. Is the object a smooth galaxy, a galaxy with features/disk or a star? 3 responses
\r\nQ2. Is it edge-on? 2 responses
\r\nQ3. Is there a bar? 2 responses
\r\nQ4. Is there a spiral pattern? 2 responses
\r\nQ5. How prominent is the central bulge? 4 responses
\r\nQ6. Is there anything \"odd\" about the galaxy? 2 responses
\r\nQ7. How round is the smooth galaxy? 3 responses
\r\nQ8. What is the odd feature? 7 responses
\r\nQ9. What shape is the bulge in the edge-on galaxy? 3 responses
\r\nQ10. How tightly wound are the spiral arms? 3 responses
\r\nQ11. How many spiral arms are there? 6 responses
\r\nEach galaxy's classification is the result of a specific path down a decision tree. Multiple individuals (typically 40-50) all classified the same galaxy, resulting in multiple paths along the decision tree. These multiple paths generate probabilities for each node. Volunteers begin with general questions (eg, is it smooth?) and move on to more specific ones (eg, how many spiral arms are there?).
As a result, at each node or question, the total initial probability of a classification will sum to 1.0. Those initial probabilities are then weighted as follows.
\r\nThe values of the morphology categories in the solution file are computed as follows. For the first set of responses (smooth, features/disk, star/artifact), the values in each category are simply the likelihood of the galaxy falling in each category. These values sum to 1.0. For each subsequent question, the probabilities are first computed (these will sum to 1.0) and then multiplied by the value which led to that new set of responses.
\r\nHere is a simplified example: a galaxy had 80% of users identify it as smooth, 15% as having features/disk, and 5% as a star/artifact.
\r\n\r\n\r\nClass1.1 = 0.80
\r\nClass1.2 = 0.15
\r\nClass1.3 = 0.05
\r\n
For the 80% of users that identified the galaxy as \"smooth\", they also recorded responses for the galaxy's relative roundness. These votes were for 50% completely round, 25% in-between, and 25% cigar-shaped. The values in the solution file are thus:
\r\n\r\n\r\nClass 7.1 = 0.80 * 0.50 = 0.40
\r\nClass 7.2 = 0.80 * 0.25 = 0.20
\r\nClass 7.3 = 0.80 * 0.25 = 0.20
\r\n
This method of cumulatively multiplying probabilities applies for every morphology class, as mapped by the figure above. The sum of Class 1.1-1.3 each galaxy will always sum to 1.0, since this questions are answered for every galaxy. Class 6.1 and 6.2 have also been normalized to sum to 1.0, removing the effect of choosing 1.3 (star/artifact). For the remaining classes, the responses will always sum to <= 1.0.
\r\nThe reason for this weighting is to emphasize that a good solution must at a minimum get the high-level, large-scale morphology categories correct. The best solutions, though, will also have high levels of accuracy on the detailed solutions that are further down the decision tree.
\r\nThe Galaxy Zoo 2 project was described in a paper by Willett et al. (2013), MNRAS, 435, 2835. Contestants are welcome to read the paper, but are cautioned that use of any external data sets (including those in this paper) are strictly forbidden by the contest rules.
\r\nAs a possible benchmark, we also point out a recent paper from the astronomical literature. Banerji et al. (2010), MNRAS, 406, 342 were able to distinguish smooth galaxies from feature/disks at greater than 90% accuracy. This corresponds to Class1.1 - 1.3 in this data set, and a good solution should be able to at least match that for this challenge. The expected challenge will be to get accurate predictions for the remaining 34 categories, most of which center on smaller structures in the image.
\r\nThis contest is centered on image analysis; given the JPG files used by the volunteers, analyze them and see how well you can reproduce their classifications in the various classes.
\r\nTable 1 describes the decision tree in words. Figure 1 depicts the decision tree schematically.
\r\n![\"GalaxtZooTreeWord\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/3175/media/Screen%20Shot%202013-09-25%20at%2010.15.06.png\")
Table 1: The Galaxy Zoo 2 decision tree in words
\r\n![\"DecisionTreeImage\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/3175/media/Screen%20Shot%202013-09-25%20at%2010.08.17.png\")
Figure 1: Decision tree of classifications (Willett et al. 2013)
\r\nFor more information on this decision tree and the project in general, please consult the GALAXY ZOO PAPER.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "About Winton Capital", "content": "![](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/3175/media/winton_logo%20block.jpg\")
Winton Capital is a data science company operating at the forefront of finance. We build automated trading systems by analysing large volumes of historical time series data covering everything from currency exchange rates to weather patterns.
\r\nWe are a research-driven business home to over 100 scientists and engineers working collaboratively in a dynamic, productive research environment. Our research centres are located in the UK (London and Oxford), Switzerland (Zürich) and Hong Kong.
\r\nOur focus is on a robust, scientific approach to investment management and this has allowed our company to grow into one of the most successful alternative investment firms in the world. Despite coming from a wide range of scientific disciplines (physics, statistics, computer science, engineering etc), our scientists all share the creative drive and technical know-how to seek patterns and signals in data that can be used to develop novel algorithms for predicting movements in financial markets.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "Winners will be determined by the final standings of the private leaderboard. In order to claim a prize, the model code and documentation must be provided to Galaxy Zoo and posted to the competition forums within 15 days of the competition's close, as described in the competition Rules.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "About Galaxy Zoo", "content": "In July 2007, astronomers from Oxford University had in their possession a data set of ~ 1 million galaxies imaged by the Sloan Digital Sky Survey. But the galaxies in this data set needed to have their morphologies (shapes) classified in order to be used to better understand galactic processes. With so many galaxies, it would have taken an individual a thousand lifetimes to classify all of them. Instead, Galaxy Zoo was born.
\r\nGalaxy Zoo took an innovative approach that brought astronomy to the general public: log on and help classify a galaxy.
\r\nIt was initially assumed that despite outsourcing the work to thousands in the general public, it would still take years for all of the images to be classified. Within the first 24 hours of launch, Galaxy Zoo founders were stunned to be receiving nearly 70,000 classifications an hour. In the end, more than 50 million classifications were received by the project during its first year, contributed by more than 150,000 people.
\r\nThe Galaxy Zoo project has gone through four iterations. The first was focused on deciding if a galaxy was elliptical, spiral (including direction), or a merger of two galaxies.
\r\nGalaxy Zoo 2 asked for more details on bright SDSS galaxies. These detailed classifications include (amongst others) measurements of the bulge size, presence of bars, and the structure of spiral arms. Data from this phase is being used for the Kaggle challenge.
\r\nThe present day Galaxy Zoo combines new imaging from the SDSS, giving the best-ever view of the local Universe, with the most distant images yet from Hubble's CANDELS project. CANDELS makes use of the new Wide Field Camera 3 - installed during the final shuttle mission to Hubble - to take ultra-deep images of the Universe. Who knows what's out there to be found?
\r\nFor more information, please visit Galaxy Zoo.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline", "content": "All deadlines are at 11:59 PM UTC on the corresponding day unless otherwise noted. The organizers reserve the right to update the contest timeline if they deem it necessary as the contest progresses.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Winners", "content": "First Place:
\r\nSecond Place:
\r\nThird Place:
\r\n