1、调库实现
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import cross_val_score
from sklearn import datasets
iris = datasets.load_iris()
gnb = GaussianNB()
scores=cross_val_score(gnb, iris.data, iris.target, cv=10)
print("Accuracy:%.3f"%scores.mean())
Accuracy:0.953
2、手写实现
数据集如下所示:
X1,X2,Y
1,S,-1
1,M,-1
1,M,1
1,S,1
1,S,-1
2,S,-1
2,M,-1
2,M,1
2,L,1
2,L,1
3,L,1
3,M,1
3,M,1
3,L,1
3,L,-1
代码示例如下:
import pandas as pd
df = pd.read_csv('../datas/bayes_lihang.txt',delimiter=',')
X = df.iloc[:,:-1]
y = df.iloc[:,-1]
y = list(set(y.values)) # 【1,-1】
# 预测数据
X_predict = [2,'S']
x1 = X_predict[0]
x2 = X_predict[1]
dis = []
for df_y in y:
# 1.统计标签为df_y的所有数据
df_y_count =df[df['Y']==df_y]['Y'].count()
# 2.统计所有样本的个数
m = df.shape[0]
# 3.统计df_y中,所有x1的数据个数
x1_y = df[(df['Y']==df_y) & (df['X1']==x1)]['X1'].count()
# 4.统计df_y中,所有x2的数据的个数
x2_y = df[(df['Y']==df_y) & (df['X2']==x2)]['X2'].count()
p = (df_y_count/m) * (x1_y/df_y_count) * (x2_y/df_y_count)
dis.append([p,df_y])
# 排序
dis.sort(key=lambda s:s[0],reverse=True)
print(dis[0][1])
#---结果为
-1