上传新文件

%% Cell type:code id: tags:

``` python

# You are encouraged to follow this template as a guide, but feel free to make reasonable modifications as needed.

# The key requirement is that your code runs successfully and produces the expected results.

```

%% Cell type:code id: tags:

``` python

# NOTE:

# You may choose to use ChatGPT (or any AI-based tool) to assist with your assignment,

# but you must ensure that you fully understand the entire code.

# You are solely responsible for the work you submit.

# Please keep in mind: ChatGPT will not be available during the exam.

```

%% Cell type:code id: tags:

``` python

import pandas

import pytorch_lightning as pl

import torch

import torch.nn as nn

from pytorch_lightning.callbacks import EarlyStopping

from sklearn.metrics import accuracy_score

from torch.utils.data import DataLoader, TensorDataset, random_split

class SoybeanDiseaseClassification(pl.LightningModule):

    def __init__(self):

        super(SoybeanDiseaseClassification, self).__init__()

        # TODO: Implement this function

    def forward(self, x):

        # TODO: Implement this function

        return 0

    def configure_optimizers(self):

        # TODO: Implement this function

        return 0

    def training_step(self, batch, batch_idx):

        # TODO: Implement this function

        return 0

    def validation_step(self, batch, batch_idx):

        # TODO: Implement this function

        return 0

    def test_step(self, batch, batch_idx):

        # TODO: Implement this function

        return 0

    def test_epoch_end(self, outputs):

        # TODO: Implement this function

        return 0

def preprocess_dataset(dataset):

    dataset = dataset.replace("?", -1)

    dataset.iloc[:, 0] = dataset.iloc[:, 0].astype("category")

    cat_columns = dataset.select_dtypes(["category"]).columns

    dataset[cat_columns] = dataset[cat_columns].apply(lambda x: x.cat.codes)

    dataset = dataset.astype("float64")

    X = dataset.iloc[:, 1:]

    y = dataset.iloc[:, 0]

    data = torch.Tensor(X.to_numpy()).float()

    labels = torch.Tensor(y.to_numpy()).long()

    dataset = TensorDataset(data, labels)

    return dataset

if __name__ == "__main__":

    # Main function of script

    train = pandas.read_csv("/home/jovyan/data/IntroML/Chapter8_data/Assignment_1/soybean-large.data.csv", header=None)

    test = pandas.read_csv("/home/jovyan/data/IntroML/Chapter8_data/Assignment_1/soybean-large.test.csv", header=None)

    train_set = preprocess_dataset(train)

    train_set, val_set = random_split(train_set, [267, 40])

    test_set = preprocess_dataset(test)

    # TODO: Implement data loader, learning and prediction

```