01 貝葉斯演算法 - 樸素貝葉斯

常規操作：

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 GaussianNB, MultinomialNB#高斯貝葉斯和多項式樸素貝葉斯
from sklearn.pipeline import Pipeline
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier

## 設定屬性防止中文亂碼
mpl.rcParams['font.sans-serif'] = [u'SimHei']
mpl.rcParams['axes.unicode_minus'] = False

# 花萼長度、花萼寬度，花瓣長度，花瓣寬度
iris_feature_E = 'sepal length', 'sepal width', 'petal length', 'petal width'
iris_feature_C = u'花萼長度', u'花萼寬度', u'花瓣長度', u'花瓣寬度'
iris_class = 'Iris-setosa', 'Iris-versicolor', 'Iris-virginica'
features = [2,3]

## 讀取資料
path = './datas/iris.data'  # 資料檔案路徑
data = pd.read_csv(path, header=None)
x = data[list(range(4))]
x = x[features]
y = pd.Categorical(data[4]).codes ## 直接將資料特徵轉換為0，1,2
print ("總樣本數目：%d；特徵屬性數目：%d" % x.shape)
 

總樣本數目：150；特徵屬性數目：2

資料分割，形成模型訓練資料和測試資料

x_train1, x_test1, y_train1, y_test1 = train_test_split(x, y, train_size=0.8, random_state=14)
x_train, x_test, y_train, y_test = x_train1, x_test1, y_train1, y_test1
print ("訓練資料集樣本數目：%d, 測試資料集樣本數目：%d" % (x_train.shape[0], x_test.shape[0]))

訓練資料集樣本數目：120, 測試資料集樣本數目：30

高斯貝葉斯模型構建

clf = Pipeline([
        ('sc', StandardScaler()),#標準化，把它轉化成了高斯分佈
        ('poly', PolynomialFeatures(degree=1)),
        ('clf', GaussianNB())]) # MultinomialNB多項式貝葉斯演算法中要求特徵屬性的取值不能為負數
## 訓練模型
clf.fit(x_train, y_train)

Pipeline(memory=None,

 steps=[('sc', StandardScaler(copy=True, with_mean=True, with_std=True)), ('poly', PolynomialFeatures(degree=1, include_bias=True, interaction_only=False)), ('clf', GaussianNB(priors=None))])
 

計算預測值並計算準確率

y_train_hat = clf.predict(x_train)
print ('訓練集準確度: %.2f%%' % (100 * accuracy_score(y_train, y_train_hat)))
y_test_hat = clf.predict(x_test)
print ('測試集準確度：%.2f%%' % (100 * accuracy_score(y_test, y_test_hat)))

訓練集準確度: 95.83%
測試集準確度：96.67%

產生區域圖

N, M = 500, 500     # 橫縱各取樣多少個值
x1_min1, x2_min1 = x_train.min()
x1_max1, x2_max1 = x_train.max()
x1_min2, x2_min2 = x_test.min()
x1_max2, x2_max2 = x_test.max()
x1_min = np.min((x1_min1, x1_min2))
x1_max = np.max((x1_max1, x1_max2))
x2_min = np.min((x2_min1, x2_min2))
x2_max = np.max((x2_max1, x2_max2))

t1 = np.linspace(x1_min, x1_max, N)
t2 = np.linspace(x2_min, x2_max, N)
x1, x2 = np.meshgrid(t1, t2)  # 生成網格取樣點
x_show = np.dstack((x1.flat, x2.flat))[0] # 測試點

cm_light = mpl.colors.ListedColormap(['#77E0A0', '#FF8080', '#A0A0FF'])
cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
y_show_hat = clf.predict(x_show)      # 預測值
y_show_hat = y_show_hat.reshape(x1.shape)

畫圖

plt.figure(facecolor='w')
plt.pcolormesh(x1, x2, y_show_hat, cmap=cm_light)     # 預測值的顯示
plt.scatter(x_train[features[0]], x_train[features[1]], c=y_train, edgecolors='k', s=50, cmap=cm_dark)
plt.scatter(x_test[features[0]], x_test[features[1]], c=y_test, marker='^', edgecolors='k', s=120, cmap=cm_dark)
plt.xlabel(iris_feature_C[features[0]], fontsize=13)
plt.ylabel(iris_feature_C[features[1]], fontsize=13)
plt.xlim(x1_min, x1_max)
plt.ylim(x2_min, x2_max)
plt.title(u'GaussianNB對鳶尾花資料的分類結果, 正確率:%.3f%%' % (100 * accuracy_score(y_test, y_test_hat)), fontsize=18)
plt.grid(True)
plt.show()

03 貝葉斯演算法 - 案例二 - 新聞資料分類