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 numpy as np

import pandas

def init_layers():

    # TODO: Implement this function

    return 0

def activation_function():

    # TODO: Implement this function

    return 0

def activation_derivative():

    # TODO: Implement this function

    return 0

def single_layer_forward_propagation():

    # TODO: Implement this function

    return 0

def full_forward_propagation():

    # TODO: Implement this function

    return 0

def get_loss_value():

    # TODO: Implement this function

    return 0

def single_layer_backward_propagation():

    # TODO: Implement this function

    return 0

def full_backward_propagation():

    # TODO: Implement this function

    return 0

def update():

    # TODO: Implement this function

    return 0

def train():

    # TODO: Implement this function

    return 0

def preprocess_dataset(dataset):

    filtered_dataset = dataset.loc[

        (dataset.iloc[:, 0] == "phytophthora-rot")

        | (dataset.iloc[:, 0] == "alternarialeaf-spot")

    ]

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

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

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

    filtered_dataset[cat_columns] = filtered_dataset[cat_columns].apply(

        lambda x: x.cat.codes

    )

    filtered_dataset = filtered_dataset.astype("float64")

    X = filtered_dataset.iloc[:, 1:]

    y = filtered_dataset.iloc[:, 0]

    return X, y

# an auxiliary function that converts probability into class

def convert_prob_into_class(probs):

    probs_ = np.copy(probs)

    probs_[probs_ > 0.5] = 1

    probs_[probs_ <= 0.5] = 0

    return probs_

def get_accuracy_value(Y_hat, Y):

    Y_hat_ = convert_prob_into_class(Y_hat)

    return (Y_hat_ == Y).all(axis=0).mean()

if __name__ == "__main__":

    # Main function of script

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

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

    X_train, y_train = preprocess_dataset(train_data)

    X_test, y_test = preprocess_dataset(test_data)

    # TODO: Implement learning and prediction

```