汽车评估的数据集

汽车评估的数据集，包含了6个属性和1个分类目标。这6个属性是购买价格、维修价格、门数量、座位数量、载货能力和安全性，分类目标是汽车的评估，包括4个取值：不可接受（unacc）、一般（acc）、好（good）、很好（vgood）。数据集共有1728个样本。这个数据集是由K. Sakthivel和S. Balakrishnam在1997年发布的。这个数据集被广泛用于分类算法的研究和实践。

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

def naive_bayes(X_train, y_train, X_test):
    # Get unique labels from train_data
    labels = set(y_train)
    # Calculate prior probability for each label
    priors = {label: sum(y_train == label) / len(y_train)
              for label in labels}
    # Get unique feature values for each feature
    feature_values = [set(X_train[:, i]) for i in range(X_train.shape[1])]
    # Train the model by calculating likelihood probability for each feature
    likelihoods = {(label, i, value): (sum(np.logical_and(y_train == label, X_train[:, i] == value)) + 1)
                                      / (sum(y_train == label) + len(feature_values[i]))
                   for label in labels
                   for i in range(X_train.shape[1])
                   for value in feature_values[i]}

    # Calculate posterior probability for each label and return the label with highest probability
    predictions = []
    for test in X_test:
        probabilities = {label: math.log(priors[label])
                         + sum(math.log(likelihoods.get((label, i, test[i]), 1e-10)) for i in range(X_train.shape[1]))
                         for label in labels}
        predictions.append(max(probabilities, key=probabilities.get))
    return predictions

# Load the Car Evaluation dataset
df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/car/car.data', header=None)

# Convert string values to numerical values
df = df.replace({'vhigh': 4, 'high': 3, 'med': 2, 'low': 1, '5more': 5, 'more': 6, 'small': 1, 'big': 3, 'high': 3,
                 'low': 1, 'unacc': 0, 'acc': 1, 'good': 2, 'vgood': 3})

# Extract features and target
X = np.array(df.iloc[:, :-1])
y = np.array(df.iloc[:, -1])

# Split the data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Fit the model
predictions = naive_bayes(X_train, y_train, X_test)

# Evaluate the accuracy of the model
accuracy = metrics.accuracy_score(y_test, predictions)
print(f"Accuracy: {accuracy}")

读取数据集：`df = pd.read_csv(‘https://archive.ics.uci.edu/ml/machine-learning-databases/car/car.data’, header=None)