![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/inclass/5255/media/Screen-Shot15.jpg\")
Galaxy Zoo guides people through a nested decision tree.
\r\nThe 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. How tightly wound are the spiral arms? 3 responses
\r\nQ10. What shape is the bulge in the edge-on galaxy? 3 responses
\r\nQ11. How many spiral arms are there? 6 responses
Paths and the decision tree
Each galaxy's classification is the result of a specific path down a 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?).
\r\nAs 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.
Weighting the responses
The 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\nClass1.1 = 0.80
\r\nClass1.2 = 0.15
\r\nClass1.3 = 0.05
\r\nFor 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\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\nThis 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\nTable 1 explains the decision tree in words.
\r\n
Figure 1 shows the decision tree.
\r\n![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/inclass/5255/media/Screen%20Shot%202013-09-25%20at%2010.08.17.png\")
The problem
\r\nThere is a crowd-sourcing project which is named Galaxy Zoo that people describe morphology of galaxies based on their shapes. There is some questions that form a decision tree to classify the input galaxy into some categories.
Figure 1 shows the decision tree of galaxies.
![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/inclass/5255/media/Tree.png\")
In galaxyzoo website people classified galaxies and their answers can be aggregated into a set of probabilities for each galaxy.
Learning these probabilities helps us to evaluate people's choice accurately.
The goal of this challenge is to predict these probabilities from the training galaxy images. In other words, build a model of how “the crowd” perceive and classify these images.
We face a regression problem, not a classification one and we don’t have to determine which classes the galaxies belong to, but rather the fraction of people who would classify them as such.
Note:
You can can get more familiar with this competition by following the link:
https://www.galaxyzoo.org/
Evaluation
\r\nThis competition uses Root Mean Squared Error as the evaluation metric.
\r\nSubmission Format
\r\nYour submission file must have a header and should be structured in the format of \"Sample_Solution.csv\" in the Data page.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "\r\n\t\r\nYou 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\nTeam mergers are not allowed in this competition.
\r\n\r\nThere is no maximum team size.
\r\nYou may submit a maximum of 10 entries per day.
\r\nYou may select up to 2 final submissions for judging.
\r\nStart Date: 5/16/2016 2:39 AM UTC
\r\nMerger Deadline: None
\r\nEntry Deadline: None
\r\nEnd Date: 7/5/2016 11:59 PM UTC
\r\n\t\r\nYou are free to use any kind of tools and algorithms.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }