要求使用python语言，根据朴素贝叶斯原理，编写相应的程序，实现给定输入数据，预测是否患糖尿病，具体要求如下： （一）从CSV文件中载入数据，然后划分为训练集和测试集。 （二）提取训练数据集的属性特征，以便我们计算概率并做出预测。 （三）基于给定测试数据集和一个已提取特征的训练数据集生成预测。 （四）评估对于测试数据集的预测精度作为预测正确率。 （五）主要的核心处理功能封装称为一个类。

以下是基于朴素贝叶斯原理的糖尿病预测程序，满足你的要求，并且封装成一个类：

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split

class NaiveBayes:
    def __init__(self, file_path):
        self.data = pd.read_csv(file_path)
        self.X = self.data.iloc[:, :-1]
        self.y = self.data.iloc[:, -1]
        self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(self.X, self.y, test_size=0.2, random_state=42)
        self.classes = np.unique(self.y_train)
        self.parameters = []

    def fit(self):
        for i, c in enumerate(self.classes):
            X_where_c = self.X_train.where(self.y_train == c)
            self.parameters.append([])
            for col in self.X_train.columns:
                col_where_c = X_where_c[col].dropna()
                mean = col_where_c.mean()
                std = col_where_c.std()
                self.parameters[i].append({'mean': mean, 'std': std})

    def _calculate_probability(self, mean, std, x):
        exponent = np.exp(-((x-mean)**2 / (2 * std**2)))
        return (1 / (np.sqrt(2 * np.pi) * std)) * exponent

    def _calculate_class_probability(self, sample):
        probabilities = {}
        for i, c in enumerate(self.classes):
            probabilities[c] = 1
            for j, param in enumerate(self.parameters[i]):
                mean = param['mean']
                std = param['std']
                x = sample[j]
                probabilities[c] *= self._calculate_probability(mean, std, x)
        return probabilities

    def predict(self, X_test):
        y_pred = []
        for i in range(X_test.shape[0]):
            sample = X_test.iloc[i,:]
            probabilities = self._calculate_class_probability(sample)
            y = max(probabilities, key=probabilities.get)
            y_pred.append(y)
        return y_pred

    def accuracy(self, y_pred):
        correct = 0
        for i in range(len(y_pred)):
            if y_pred[i] == self.y_test.iloc[i]:
                correct += 1
        return correct / len(y_pred)

这个类的使用方法如下：

nb = NaiveBayes('diabetes.csv')
nb.fit()
y_pred = nb.predict(nb.X_test)
acc = nb.accuracy(y_pred)
print("Accuracy:", acc)

其中，`NaiveBayes('diabetes.csv')`传入的是糖尿病数据集的CSV文件路径，`nb.fit()`用于训练模型，`nb.predict(nb.X_test)`用于预测测试集的结果，`nb.accuracy(y_pred)`用于计算预测精度。