{
  "fetched_at": "2026-10-20T08:01:34Z",
  "source_url": "https://www.kaggle.com/competitions/breast-cancer-classification-prototype-fall-2025/data",
  "pages": [
    {
      "name": "data-description",
      "content": "This page provides an overview of the data files provided for the Wisconsin breast cancer dataset competition. It includes information about the files and their formats, as well as details about the columns and their definitions.\n\nParticipants should find the following information helpful in understanding the dataset:\n\n- File Descriptions:\n    - **train.csv**: Contains the training data.\n    - **test.csv**: Contains the test data. It has no labels, which is for students to test their models.\n    - **sample_submission.csv**: A sample submission file in the correct format.\n- Column Definitions:\n    - `id`: Unique identifier for each data instance.\n    - `label`: Target variable column indicating the diagnosis (`M`: Malignant, `B`: Benign).\n    - Other 30 columns: The 30 numeric features of the dataset. \n\nPlease note that specific details and additional information about the dataset may be provided in the respective file's documentation or in the competition's description.\n\nFor the purpose of this competition, participants should pay attention to the `id` column as it is used to correlate the predictions in the submission file.\n\nIf you have any questions regarding the dataset, feel free to ask in the discussion forums on canvas or consult the provided documentation.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "### **The evaluation metric for this competition is \"Accuracy\".**\n\nAccuracy measures the proportion of correctly classified instances out of the total number of instances.\n\n### **Submission Format**\n\nSubmission files should contain two columns: `id` and `label`. The `label` column contains the predicted labels for the test dataset. The labels should be encoded as follows: `M` for malignant and `B` for benign.\n\nPlease ensure that your submission adheres to the following requirements:\n\n1. The `id` column in your submission should correspond to the same ID numbers as provided in the `test.csv` file. Note that the IDs may not be in sequential order.\n2. Take a look at the example `sample_submission.csv` provided to understand the format and structure of the submission file.\n\nYour submission file should contain a header and have the following format:\n\n```\nid,label\n906564,B\n85715,M\n891670,B\n874217,M\n...\n```\n\nPlease make sure that your submission file follows the specified format and includes the correct predictions for the corresponding IDs in the `test.csv` file.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Participants in this competition are expected to adhere to the following rules:\n\n1. Original Code: Participants should develop their own code for this competition. Sharing or using code from external sources is not allowed. Any form of plagiarism or unauthorized collaboration will result in a grade of 0 for the assignment.\n2. Code Explanation: Participants are required to provide clear explanations for each part of their code. This includes commenting their code and providing meaningful descriptions for the steps taken and decisions made during the development process.\n3. Submission and Peer-Review: Once participants are satisfied with their code and have submitted it on Kaggle, they must download the final version of their code notebook. They are then required to upload this notebook, including all the code and their explanatory work, to Canvas for peer-review as outlined in the assignment description.\n4. Honor Code: Participants are expected to follow the honor code of the University of West Florida throughout the duration of this competition. Any violation of the honor code may result in appropriate disciplinary actions.\n\nBy participating in this competition, you agree to comply with these rules and guidelines, as well as the honor code of the University of West Florida. Failure to adhere to these rules may result in a grade of 0 for the assignment or other penalties as determined by the course instructor.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "# Mini-Kaggle Project 1: Breast Cancer Classification\nWelcome to the mini-Kaggle project on breast cancer classification! In this project, you will have the opportunity to apply your machine learning skills and techniques to predict the diagnosis of breast cancer based on various features.\n\n## About the Dataset\nThe dataset used in this project is the Wisconsin Breast Cancer dataset, which consists of various features extracted from breast mass samples. The goal is to classify the samples as either malignant (M) or benign (B) based on these features.\n\n## Project Tasks\n1. **Data Exploration**: Start by exploring the dataset, understanding the features, and identifying any missing or erroneous values.\n2. **Preprocessing and Feature Engineering**: Perform necessary preprocessing steps such as handling missing values, scaling features, and encoding the target variable.\n3. **Model Training and Evaluation**: Train different classifiers such as Perceptron, Logistic Regression, SVM, Decision Trees, KNN, and Random Forest on the preprocessed dataset. Evaluate their performance using appropriate metrics and select the best-performing model.\n4. **Model Deployment and Submission**: Deploy the selected model on the test dataset and generate predictions. Create a submission file in the required format for evaluation.\n5. **Peer Review and Discussion**: Engage in the peer review process to evaluate and provide feedback on other participants' submissions. Discuss your approaches, findings, and challenges faced during the project.\n\n## Competition Guidelines\n- Competition deadline on this website is set for the whole semester. The deadline for code submission is described on Canvas page.\n- Make sure to read the detailed instructions and guidelines provided in the competition pages for further information.\n- You have 10 trials per day on Kaggle, and you can select 1 final submission for the leaderboard.\n\n## **Additional Instructions:**\n- Remember to submit your final notebook for peer-review and upload it to Canvas.\n- Ensure that your code has comments in markdown to explain your work and choices for the peer-review process.\n- You need to submit your predictions file to the competition and be listed on the leaderboard with your name as \"FirstName LastName\". If you are not listed on the leaderboard by the end of the competition, you will lose the entire grade.\n- The peer-review period will start the day after the submission deadline, and you will have 3 days to complete the review.\n\nGet ready to showcase your machine learning skills! Best of luck!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Reference",
      "content": "## Reference Competition\nBrian Jalaian. (2023). Breast Cancer Classification: MAP 6990 - Fall 2023\nhttps://kaggle.com/competitions/breast-cancer-classification-map-6990-fall-2023\n\n## Original Dataset\nBreast Cancer Wisconsin (Diagnostic) Data Set\nhttps://www.kaggle.com/datasets/uciml/breast-cancer-wisconsin-data",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}