{ "fetched_at": "2026-10-20T02:08:40Z", "source_url": "https://www.kaggle.com/competitions/datamining-2021/data", "pages": [ { "name": "data-description", "content": "

File descriptions

\n\n\n

Data fields

\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "# EE359 2021 Spring\nIn this project, you are given 50000 papers’ feature vectors and each vector has 100 dimensions. These papers belong to 5 areas, e.g., Data Mining, Knowledge Management, Operation Research, Information Retrieval, Natural Language Processing. We have already hidden the ground truth of the areas, and your task is to implement a clustering algorithm in Python to divide these papers into 5 clusters. Click the \"Join Competition\" button to join us now.\n\n## Attention\nBefore submitting your predictions, please update your account name with \"STUDENTID_NAME\" before submitting your predictions. You can update your name in the \"Team\" tab.\n\nBefore the submission deadline (2021/3/28), you can only view the accuracy evaluated on 30% of the dataset on the leaderboard. After the deadline, we will reveal your model accuracy evaluated on the entire dataset. 👉 **Remember that your score depends on the ranges that your accuracy falls into, and the running time of your algorithm.**👈 For fairness, we set a few rules for you to obey --- violation against the rules will lead to scoring deduction:\n\n1. Please do not use any existing clustering API directly from libraries. Clustering algorithms should be implemented on your own.\n2. Please do not copy someone else's code. We will run a plagiarism check after submission.\n3. Please do not download the dataset somewhere else to train your model. A violation would be considered if there is a big gap between your reported results and our reproduced results.\n4. Please do not use the pre-trained model. Everything should be built from scratch.\n5. For us to reproduce your code, please follow the \"Environment\" instruction.\n\n## Environment\nYou need to use \"Python\" to write the neural network model, and we highly recommend you to use \"Python3.8.0\" for us to reproduce your code.\n\n## DataSet\nYou can click the \"Data\" button to get more information about our dataset and download it.\n\nThere is one CSV file containing all papers’ feature vectors. First, you need to divide all papers into 5 categories using a clustering algorithm. Second, you need to sort the clusters according to their radiuses \\(Euclidean distance\\\\) in ascending order. Last, you should label each paper according to the cluster indices. For example, if the ordered cluster list is [[paper1, paper6], [paper2, paper8], [paper3, paper7], [paper4, paper9], [paper5, paper10]], you should provide its cluster indices as follows: {paper1: 0, paper2: 1, paper3: 2, paper4: 3, paper5: 4, paper6: 0, paper7: 2, paper8: 1, paper9: 3, paper10: 4}.\n\n## Submission\nYou can click the \" Submit Prediction\" button on the upper-right corner, and upload your prediction. The prediction file should be a CSV file, and the first column name is \"ID,\" the second is \"Category.\"\n\nWhen you upload the CSV file successfully, you can get a score about the Category Accuracy \\(CA\\\\) for your prediction simultaneously.\n\n$$CA = \\frac {N_{true}}{N}$$\n\n, where N is the number of papers, and N_true is the number of papers whose category index is equal to the groundtruth. Typically, clustering algorithms do not have `accuracy.’ Here we just need a way to evaluate your algorithm performance.\nTwo submissions are allowed for each account per day. Please carefully arrange your submission schedule.\n\n## Requirements for uploading\nYou need to zip and upload the following files before the deadline: ①your codes ②a readme.txt, which includes the scripts or instructions to run your codes. Specifically, your file structure should meet the following requirements: \n1. Your file should be named as student-id_clustering.zip, and it only contains a folder with the same name;\n2. This folder contains four files/folders, “src” \\(folder\\\\), “data” \\(folder\\\\), “readme.txt” and “requirements.txt” \\(optional\\\\); \n3. you should put your code files in “src” and data files in “data,” and “requirements.txt” records the used libraries and their version; \n4. the main code on which we reproduce your algorithm should be put in a file named “main.py.” You can find the example of the uploaded file by clicking the \"Data\" button. The final zip file should be uploaded via our course website: https://oc.sjtu.edu.cn\n\n## Deadline of this project\nDeadline for submitting your predictions on Kaggle: 2021/3/28\nDeadline for uploading your readme and code via our course website: 2021/3/28", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The evaluation metric for this competition is Category Accuracy. The Category Accuracy, commonly used in the classification task, measures accuaccuracy of prediction. The Category Accuracy is given by:\n\n$$CA = \\frac {N_{true}}{N} $$\n\n## Submission Format\nThe file should contain a header and have the following format:\n
id,category
0,1
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }