From 261b7d3bcf1a32a6915ad02e1ea2729f2a548313 Mon Sep 17 00:00:00 2001 From: jack <2170067548@qq.com> Date: Sun, 3 Nov 2024 17:22:45 +0800 Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- function.py | 120 +++++++++++++++++++++++----------------------------- 1 file changed, 54 insertions(+), 66 deletions(-) diff --git a/function.py b/function.py index 21c3d82..61b706e 100644 --- a/function.py +++ b/function.py @@ -26,69 +26,57 @@ name = "周佳成" # 这里写自己的代码实现 -import pandas as pd -import requests - -# 下载病马数据 -def download_horse_colic_data(url, filename): - response = requests.get(url) - with open(filename, 'wb') as f: - f.write(response.content) - -# 处理并加载数据 -def load_and_preprocess_horse_colic_data(train_filename, test_filename): - # 定义列名 - column_names = [ - 'surgery', 'age', 'hospital_number', 'rectal_temperature', - 'pulse', 'respiratory_rate', 'temperature_of_extremities', - 'peripheral_pulse', 'mucous_membrane', 'capillary_refill_time', - 'pain', 'surgical_lesion', 'type_of_lesion', 'surgical_lesion_location', - 'outcome' # 假设'outcome'是目标变量，1=lived, 2=died, 3=euthanized - ] - - # 读取训练数据 - train_data = pd.read_csv(train_filename, delim_whitespace=True, header=None, names=column_names) - # 读取测试数据 - test_data = pd.read_csv(test_filename, delim_whitespace=True, header=None, names=column_names) - - # 处理缺失值：用0填充（这里假设除了'outcome'之外的所有特征都可能有缺失值） - for column in train_data.columns[:-1]: # 排除目标变量列 - train_data[column].fillna(0, inplace=True) - for column in test_data.columns[:-1]: # 排除目标变量列 - test_data[column].fillna(0, inplace=True) - - # 处理目标变量'outcome'的缺失值 - train_data['outcome'].fillna(0, inplace=True) # 可以选择适合的填充方法 - test_data['outcome'].fillna(0, inplace=True) - - # 将目标变量'outcome'转换为数值型 - train_data['outcome'] = train_data['outcome'].astype(int) - test_data['outcome'] = test_data['outcome'].astype(int) - - return train_data, test_data - -# 主函数 -def main(): - # 数据集URL - train_url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/horse-colic/horse-colic.data' - test_url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/horse-colic/horse-colic-test.data' - - # 保存数据集的文件名 - train_filename = 'horse_colic_train.data' - test_filename = 'horse_colic_test.data' - - # 下载数据集 - download_horse_colic_data(train_url, train_filename) - download_horse_colic_data(test_url, test_filename) - - # 加载并预处理数据 - train_data, test_data = load_and_preprocess_horse_colic_data(train_filename, test_filename) - - # 打印前几行数据以验证 - print("训练数据预览：") - print(train_data.head()) - print("测试数据预览：") - print(test_data.head()) - -if __name__ == "__main__": - main() +import pandas as pd +import numpy as np +from sklearn.model_selection import train_test_split +from sklearn.linear_model import LogisticRegression +from sklearn.metrics import accuracy_score + +def load_data(): + # 下载并加载病马数据集 + url = "http://archive.ics.uci.edu/ml/machine-learning-databases/horse-colic/horse-colic.data" + columns = [ + "surgery", "age", "hospital_number", "rectal_temp", "pulse", "respiratory_rate", + "temp_of_extremities", "peripheral_pulse", "mucous_membrane_color", + "capillary_refill_time", "pain", "peristalsis", "abdominal_distention", + "nasal_discharge", "vomit", "heart_rate", "rectal_exam_fecal", "packed_cell_volume", + "total_protein", "abdominal_fluid_type", "abdominal_fluid_color", "outcome" + ] + ["unused_" + str(i) for i in range(1, 9)] # 忽略最后8个无用特征 + + data = pd.read_csv(url, header=None, names=columns, na_values="?") + + # 处理缺失值，用0填充 + data.fillna(0, inplace=True) + + # 转换目标变量，将2（死亡）和3（安乐死）合并为0（死亡），1（存活）保持不变 + data["outcome"] = data["outcome"].apply(lambda x: 0 if x in [2, 3] else 1) + + # 去掉特征3（hospital_number）和特征24~28（unused_1 到 unused_8） + data.drop(columns=["hospital_number"] + ["unused_" + str(i) for i in range(1, 9)], inplace=True) + + # 特征和标签 + X = data.drop(columns=["outcome"]) + y = data["outcome"] + + # 划分训练集和测试集（这里简单按7:3划分，实际应用中应与原数据集划分保持一致） + X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42) + + return X_train, X_test, y_train, y_test + +def train_logreg(X_train, y_train): + # 训练对率回归模型 + model = LogisticRegression(max_iter=10000) # 设置足够多的迭代次数以确保收敛 + model.fit(X_train, y_train) + return model + +def predict_logreg(model, X_test): + # 使用模型进行预测 + y_pred = model.predict(X_test) + return y_pred + +# 示例调用（注：这些调用在自动评测时不会执行，仅供测试使用） +if __name__ == "__main__": + X_train, X_test, y_train, y_test = load_data() + model = train_logreg(X_train, y_train) + y_pred = predict_logreg(model, X_test) + print(f"Accuracy: {accuracy_score(y_test, y_pred)}")