KNN算法代码实现 + 皮马人数据集

# -*- coding:utf-8 -*- import pandas as pd import numpy as np import sys from sklearn.model_selection import train_test_split from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor from sklearn.metrics import accuracy_score, recall_score, precision_score, r2_score from sklearn.preprocessing import LabelEncoder # 1. 加载数据 df = pd.read_csv('iris.data', header=None, sep=",") # 2. 数据预览 print(df.head()) print(df.shape) # 3. 数据预处理 X = df.iloc[:, 0:4] Y = df.iloc[:, -1] # 4. 数据清洗 label_encoder = LabelEncoder() Y = label_encoder.fit_transform(Y) # 5. 数据分割 x_train, x_test, y_train, y_test = train_test_split(X, Y, train_size=0.8, random_state=1) print("训练数据X的shape:{}, 以及类型:{}".format(x_train.shape, type(x_train))) print("测试数据X的shape:{}, 以及类型:{}".format(x_test.shape, type(x_test))) print("训练数据Y的shape:{}，以及类型:{}".format(y_train.shape, type(y_train))) # 6. 模型对象的构建 KNN = KNeighborsClassifier(n_neighbors=5, weights='uniform', algorithm='kd_tree') # 7. 模型的训练 KNN.fit(x_train, y_train) # 8. 模型效果评估 train_predict = KNN.predict(x_train) test_predict = KNN.predict(x_test) print("KNN算法：测试集上的效果(F1-score):{}".format(KNN.score(x_test, y_test))) print("KNN算法：训练集上的效果(F1-score):{}".format(KNN.score(x_train, y_train))) print("KNN算法：训练集上的效果(准确率):{}".format(accuracy_score(y_true=y_train, y_pred=train_predict))) # 9.模型的保存与加载(pip install joblib) import joblib # 保存模型 joblib.dump(KNN, "./knn.m") # 加载模型 # joblib.load("./knn.m")