# Assignment3 (BAU, AIN3002, Spring23) — Data

来源：https://www.kaggle.com/competitions/bau-ain3002-spring23-a3/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The dataset consists of pathology reports and corresponding Fuhrman grades of renal cell carcinoma patients in The Cancer Genome Atlas. The dataset is modified from the dataset provided in [1] by Hakan Kıymaz (graduate student, BAU). The labels (Fuhrman grades: G1, G2, G3, or G4) for the training set samples are provided.

## Example from the dataset

**Pathology report text:**
```
procedure: right radical nephrectomy tumor type: papillary renal cell carcinoma nuclear grade: grade iii tumor size: 12 x 11.5 x 9 cm renal vein invasion: not present lymph nodes: not examined phthologic stage: t2 nx mx
```

**Fuhrman grade:**
```
G3
```

The file ``data.tsv`` provides the list of patients and corresponding pathology reports. The file ``train.csv`` provides the list of patients and corresponding Fuhrman grades as one-hot vectors in the training set. The file ``test.csv`` provides the list of patients in the test set.

## Files

* **data.tsv** - all pathology reports
     * *pateint_id* - patient id
     * *pathology_report_text* - unstructured text inside a pathology report
* **train.csv** - the training set
     * *patient_id* - patient id
     * *G1* - the value of class G1 bit in the one-hot vector
     * *G2* - the value of class G2 bit in the one-hot vector
     * *G3* - the value of class G3 bit in the one-hot vector
     * *G4* - the value of class G4 bit in the one-hot vector
*   **test.csv** - the test set
     * *patient_id* - patient id
*   **sample_submission.csv** - a sample submission file in the correct format
     * *patient_id* - patient id
     * *likelihood_G1* - a sample's predicted likelihood of belonging to the class G1
     * *likelihood_G2* - a sample's predicted likelihood of belonging to the class G2
     * *likelihood_G3* - a sample's predicted likelihood of belonging to the class G3
     * *likelihood_G4* - a sample's predicted likelihood of belonging to the class G4

[1] Wu, J., Tang, K., Zhang, H., Wang, C., & Li, C. (2020, December). Structured information extraction of pathology reports with attention-based graph convolutional network. In *2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)* (pp. 2395-2402). IEEE.