朴素贝叶斯处理鸢尾花数据集分类.pdfVIP

朴素贝叶斯处理鸢尾花数据集分类 ⼀、实验 ⽬的 (1) 掌握贝叶斯算法原理 ； ( ) 掌握朴素贝叶斯原理 ； (3) 使⽤朴素贝叶斯处理鸢尾花数据集分类 ⼆、实验内容 （1）导⼊库，加载鸢尾花数据，输出样本和鸢尾花特征 （）数据分割，数据分割，形成模型训练数据和测试数据 （3）⾼斯贝叶斯模型构建 （4）计算预测值并计算准确率 （5）画图 三、实验代码 import numpy as np import pandas as pd import matplotlib.pyplot as plt import matplotlib as mpl from sklearn.preprocessing import StandardScaler, MinMaxScaler, PolynomialFeatures from sklearn.naive_ bayes import GaussianN from sklearn.pipeline import Pipeline from sklearn.metrics import accuracy_score from sklearn.model_selection import train_test_split from sklearn.neighbors import KNeighborsClassifier data = pd.read_csv(iris.csv,header=None) x = data.drop([4],axis=1) x = x.drop([0],axis=0) x = np.array(x,dtype=float) print(x) y=pd.Categorical(data[4]).codes print(data[4]) y=y[1:151] print(y) p=x[:,2 :5] x_train1,x_test 1,y_train1,y_test 1=train_test_split(x,y,train_size=0.8,random_state=14) x_train,x_test,y_train,y_test=x_train1,x_test 1,y_train1,y_test 1 print(训练数据集样本数 ⽬：%d ，测试数据集样本数 ⽬：%d%(x_train.shape[0],x_test.shape[0])) clf=GaussianN () ir=clf.fit(x_train,y_train) y_ pred=ir.predict(x_test) acc = np.sum(y_test == y_ pred)/x_test.shape[0] print(测试集准确度 ：%.3f% acc) y_ pred = ir.predict(x_train) acc = np.sum(y_train == y_ pred)/x_train.shape[0] print(训练集准确度 ：%.3f% acc) print(选取前两个特征值) p=x[:,:2] p_train1,p_test 1,y_train1,y_test 1=train_test_split(p,y,train_size=0.8,random_state=1) p_train,p_test,y_train,y_test=p_train1,p_test 1,y_train1,y_test 1 print(训练数据集样本数 ⽬：%d ，测试数据集样本数 ⽬：%d%(p_train.shape[0],p_test.shape[0])) clf=GaussianN () ir=clf.fit(p_train,y_train) y_ pred=ir.predict(p_test) acc = np.sum(y_test == y_ pred)/p_test.shape[0] print(测试集准确度 ：%.3f% acc) y_ pred = ir.predict(p_train) acc = np.sum(y_train == y_ pred)/p_train.shape[0] acc = np.sum(y_train == y_ pred)/p_train.shape[0] print(训练集准确度 ：%.3f% acc) p1_ max,p1_ min = max(p_test[:,0]),min(p_test[:,0]) p2_ ma