实现功能：
python建立KNN模型预测肾脏疾病完整代码和实现效果
实现代码：
import pandas as pdimport warningswarnings.filterwarnings('ignore')pd.set_option('display.max_columns', 26)#==========================读取数据======================================df = pd.read_csv('E:\数据杂坛\datasets\kidney_disease.csv')df=pd.DataFrame(df)pd.set_option('display.max_rows', None)pd.set_option('display.width', None)df.drop('id',axis=1,inplace=True)print(df.head())print(df.dtypes)df['classification'] = df['classification'].apply(lambda x: x if x == 'notckd' else 'ckd')# 分类型变量名cat_cols = [col for col in df.columns if df[col].dtype == 'object']# 数值型变量名num_cols = [col for col in df.columns if df[col].dtype != 'object']# ========================缺失值处理============================def random_value_imputate(col): ''' 函数：随机填充方法（缺失值较多的字段） ''' # 1、确定填充的数量；在取出缺失值随机选择缺失值数量的样本 random_sample = df[col].dropna().sample(df[col].isna().sum()) # 2、索引号就是原缺失值记录的索引号 random_sample.index = df[df[col].isnull()].index # 3、通过loc函数定位填充 df.loc[df[col].isnull(), col] = random_sampledef mode_impute(col): ''' 函数：众数填充缺失值 ''' # 1、确定众数 mode = df[col].mode()[0] # 2、fillna函数填充众数 df[col] = df[col].fillna(mode)for col in num_cols: random_value_imputate(col)for col in cat_cols: if col in ['rbc','pc']: # 随机填充 random_value_imputate('rbc') random_value_imputate('pc') else: mode_impute(col)# ======================特征编码============================from sklearn.preprocessing import MinMaxScalermms = MinMaxScaler()df[num_cols] = mms.fit_transform(df[num_cols])from sklearn.preprocessing import LabelEncoderled = LabelEncoder()for col in cat_cols: df[col] = led.fit_transform(df[col])print(df.head())#===========================数据集划分===============================X = df.drop('classification',axis=1)y = df['classification']from sklearn.utils import shuffledf = shuffle(df)from sklearn.model_selection import train_test_splitX_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state = 0)#===========================建模=====================================def create_model(model): # 模型训练 model.fit(X_train, y_train) # 模型预测 y_pred = model.predict(X_test) # 准确率acc acc = accuracy_score(y_test, y_pred) # 混淆矩阵 cm = confusion_matrix(y_test, y_pred) # 分类报告 cr = classification_report(y_test, y_pred) print(f'Test Accuracy of {model} : {acc}') print(f'Confusion Matrix of {model}: \n{cm}') print(f'Classification Report of {model} : \n {cr}')from sklearn.neighbors import KNeighborsClassifierknn = KNeighborsClassifier()create_model(knn)实现效果：
本人读研期间发表5篇SCI数据挖掘相关论文，现在某研究院从事数据挖掘相关科研工作，对数据挖掘有一定认知和理解，会结合自身科研实践经历不定期分享关于python机器学习、深度学习、数据挖掘基础知识与案例。致力于只做原创，以最简单的方式理解和学习，关注我一起交流成长。关注 订阅号（数据杂坛） 可在后台联系我获取相关数据集和源码，送有关数据分析、数据挖掘、机器学习、深度学习相关的电子书籍。联系客服
