sklearn之樸素貝葉斯進行分類

參考：https://www.cnblogs.com/youngsea/p/9327972.html

from sklearn import preprocessing
import numpy as np
import pandas as pd
from sklearn.metrics import classification_report
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.preprocessing import LabelEncoder

'''
使用樸素貝葉斯對adult數據集進行歸一化，選取其中選出對收入影響較大的七個特徵屬性，包括：Age、Workclass、Education、Occupation、race、Sex、Native_country，以這七個屬性做爲特徵屬性
'''

col_names = ['age', 'workclass', 'education', 'occupation', 'race', 'sex', 'native-country', 'income']

data = pd.read_csv('D:\\python_project\\classifier-master\\adult.csv', header=None, names=col_names)
col_numbers = 'age'

#先把數據集中的字符串轉換成數字
for col in col_names:
    if col not in col_numbers:
        data[col] = LabelEncoder().fit_transform(data[col])

x, y = data[col_names], data['income']
print(x)

#歸一化
min_max_scaler = preprocessing.MinMaxScaler()
X_minMax = min_max_scaler.fit_transform(x)
print(X_minMax)

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.1, random_state=0)

mnb = MultinomialNB()   # 使用默認配置初始化樸素貝葉斯
mnb.fit(x_train,y_train)    # 利用訓練數據對模型參數進行估計
y_predict = mnb.predict(x_test)     # 對參數進行預測

#獲取結果報告
print('樸素貝葉斯準確率爲', mnb.score(x_test,y_test))
print(classification_report(y_test, y_predict))

結果如下：

補充：
x矩陣：

歸一化後的：x_minMax矩陣