实现功能：
python机器学习-朴素贝叶斯（Naive Bayes）模型建立及评估。
实现代码：
# 导入需要的库from warnings import simplefiltersimplefilter(action='ignore', category=FutureWarning)import pandas as pdfrom sklearn.model_selection import train_test_splitimport seaborn as snsimport matplotlib.pyplot as pltfrom sklearn import metricsfrom sklearn.metrics import roc_curve, aucfrom sklearn.naive_bayes import GaussianNB# =============读取数据===========def Read_data(file):dt = pd.read_csv(file)dt.columns = ['age', 'sex', 'chest_pain_type', 'resting_blood_pressure', 'cholesterol','fasting_blood_sugar', 'rest_ecg', 'max_heart_rate_achieved','exercise_induced_angina','st_depression', 'st_slope', 'num_major_vessels', 'thalassemia', 'target']data =dtreturn data# ===========数据清洗==============def data_clean(data):# 重复值处理print('存在' if any(data.duplicated()) else '不存在', '重复观测值')data.drop_duplicates()# 缺失值处理print('不存在' if any(data.isnull()) else '存在', '缺失值')data.dropna() # 直接删除记录data.fillna(method='ffill') # 前向填充data.fillna(method='bfill') # 后向填充data.fillna(value=2) # 值填充data.fillna(value={'resting_blood_pressure': data['resting_blood_pressure'].mean()}) # 统计值填充# 异常值处理data1 = data['resting_blood_pressure']# 标准差监测xmean = data1.mean()xstd = data1.std()print('存在' if any(data1 > xmean + 2 * xstd) else '不存在', '上限异常值')print('存在' if any(data1 < xmean - 2 * xstd) else '不存在', '下限异常值')# 箱线图监测q1 = data1.quantile(0.25)q3 = data1.quantile(0.75)up = q3 + 1.5 * (q3 - q1)dw = q1 - 1.5 * (q3 - q1)print('存在' if any(data1 > up) else '不存在', '上限异常值')print('存在' if any(data1 < dw) else '不存在', '下限异常值')data1[data1 > up] = data1[data1 < up].max()data1[data1 < dw] = data1[data1 > dw].min()return data#==============数据编码=============def data_encoding(data):data = data[["age", 'sex', "chest_pain_type", "resting_blood_pressure", "cholesterol","fasting_blood_sugar", "rest_ecg","max_heart_rate_achieved", "exercise_induced_angina","st_depression", "st_slope", "num_major_vessels","thalassemia","target"]]Discretefeature=['sex',"chest_pain_type", "fasting_blood_sugar", "rest_ecg","exercise_induced_angina", "st_slope", "thalassemia"]Continuousfeature=["age", "resting_blood_pressure", "cholesterol","max_heart_rate_achieved","st_depression","num_major_vessels"]df = pd.get_dummies(data,columns=Discretefeature)df[Continuousfeature]=(df[Continuousfeature]-df[Continuousfeature].mean())/(df[Continuousfeature].std())df["target"]=data[["target"]]return df#=============数据集划分==============def data_partition(data):# 1.4查看样本是否平衡print(data["target"].value_counts())# X提取变量特征；Y提取目标变量X = data.drop('target', axis=1)y = data['target']X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.2,random_state=10)feature=list(X.columns)return X_train, y_train, X_test, y_test#===========绘制ROC曲线================def Draw_ROC(list1,list2):fpr_model,tpr_model,thresholds=roc_curve(list1,list2,pos_label=1)roc_auc_model=auc(fpr_model,tpr_model)font = {'family': 'Times New Roman','size': 12,}sns.set(font_scale=1.2)plt.rc('font',family='Times New Roman')plt.plot(fpr_model,tpr_model,'blue',label='AUC = %0.2f'% roc_auc_model)plt.legend(loc='lower right',fontsize = 12)plt.plot([0,1],[0,1],'r--')plt.ylabel('True Positive Rate',fontsize = 14)plt.xlabel('Flase Positive Rate',fontsize = 14)plt.show()return# =============朴素贝叶斯====================def NB(X_train, y_train, X_test, y_test):GNB1 = GaussianNB()GNB1.fit(X_train, y_train)print("Accuracy on training set: {:.3f}".format(GNB1.score(X_train, y_train)))print("Accuracy on test set: {:.3f}".format(GNB1.score(X_test, y_test)))predict_target=GNB1.predict(X_test)predict_target_prob=GNB1.predict_proba(X_test) # 输出分类概率predict_target_prob_gnb = predict_target_prob[:, 1]print(sum(predict_target==y_test))print(metrics.classification_report(y_test,predict_target))print(metrics.confusion_matrix(y_test, predict_target))return list(y_test), list(predict_target_prob_gnb)#============主函数==============if __name__=="__main__":data1=Read_data("F:\数据杂坛\\0504\heartdisease\Heart-Disease-Data-Set-main\\UCI Heart Disease Dataset.csv")data1=data_clean(data1)data2=data_encoding(data1)X_train, y_train, X_test, y_test= data_partition(data2)y_test, predict_target_prob_gnb=NB(X_train, y_train, X_test, y_test)Draw_ROC(y_test,predict_target_prob_gnb)
实现效果：
喜欢记得点赞，在看，收藏，
关注V订阅号：数据杂坛，获取数据集，完整代码和效果，将持续更新！
如果觉得《python机器学习-朴素贝叶斯（Naive Bayes）模型建立及评估（完整代码+实现效果）》对你有帮助，请点赞、收藏，并留下你的观点哦！
