头歌实训-机器学习（

1.朴素贝叶斯概论

2.朴素贝叶斯分类算法流程

import numpy as np
class NaiveBayesClassifier(object):
    def __init__(self):
        '''
        self.label_prob表示每种类别在数据中出现的概率
        例如，{0:0.333, 1:0.667}表示数据中类别0出现的概率为0.333，类别1的概率为0.667
        '''
        self.label_prob = {}
        '''
        self.condition_prob表示每种类别确定的条件下各个特征出现的概率
        例如训练数据集中的特征为 [[2, 1, 1],
                              [1, 2, 2],
                              [2, 2, 2],
                              [2, 1, 2],
                              [1, 2, 3]]
        标签为[1, 0, 1, 0, 1]
        那么当标签为0时第0列的值为1的概率为0.5，值为2的概率为0.5;
        当标签为0时第1列的值为1的概率为0.5，值为2的概率为0.5;
        当标签为0时第2列的值为1的概率为0，值为2的概率为1，值为3的概率为0;
        当标签为1时第0列的值为1的概率为0.333，值为2的概率为0.666;
        当标签为1时第1列的值为1的概率为0.333，值为2的概率为0.666;
        当标签为1时第2列的值为1的概率为0.333，值为2的概率为0.333,值为3的概率为0.333;
        因此self.label_prob的值如下：     
        {
            0:{
                0:{
                    1:0.5
                    2:0.5
                }
                1:{
                    1:0.5
                    2:0.5
                }
                2:{
                    1:0
                    2:1
                    3:0
                }
            }
            1:
            {
                0:{
                    1:0.333
                    2:0.666
                }
                1:{
                    1:0.333
                    2:0.666
                }
                2:{
                    1:0.333
                    2:0.333
                    3:0.333
                }
            }
        }
        '''
        self.condition_prob = {}
    def fit(self, feature, label):
        '''
        对模型进行训练，需要将各种概率分别保存在self.label_prob和self.condition_prob中
        :param feature: 训练数据集所有特征组成的ndarray
        :param label:训练数据集中所有标签组成的ndarray
        :return: 无返回
        '''


        #********* Begin *********#
        row_num = len(feature)
        col_num = len(feature[0])
        for c in label:
            if c in self.label_prob:
                self.label_prob[c] += 1
            else:
                self.label_prob[c] = 1
        for key in self.label_prob.keys():
            self.label_prob[key] /= row_num
            self.condition_prob[key] = {}
            for i in range(col_num):
                self.condition_prob[key][i] = {}
                for k in np.unique(feature[:,i], axis=0):
                    self.condition_prob[key][i][k] = 0
        for i in range(len(feature)):
            for j in range(len(feature[i])):
                if feature[i][j] in self.condition_prob[label[i]]:
                    self.condition_prob[label[i]][j][feature[i][j]] += 1
                else:
                    self.condition_prob[label[i]][j][feature[i][j]] = 1
        for label_key in self.condition_prob.keys():
            for k in self.condition_prob[label_key].keys():
                total = 0
                for v in self.condition_prob[label_key][k].values():
                    total += v
                for kk in self.condition_prob[label_key][k].keys():
                    self.condition_prob[label_key][k][kk] /= total
        #********* End *********#


    def predict(self, feature):
        '''
        对数据进行预测，返回预测结果
        :param feature:测试数据集所有特征组成的ndarray
        :return:
        '''
        # ********* Begin *********#
        result = []
        for i,f in enumerate(feature):
            prob=np.zeros(len(self.label_prob.keys()))
            i1 = 0
            for label,label_prob in self.label_prob.items():
                prob[i1] = label_prob
                for  j  in range(len(feature[0])):
                    prob[i1] *= self.condition_prob[label][j][f[j]]
                i1 += 1
            result.append(list(self.label_prob.keys())[np.argmax(prob)])
        return np.array(result)

        #********* End *********#

3.利用sklearn构建朴素贝叶斯模型

import numpy as np
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.model_selection import train_test_split
import numpy as np
import pandas as pd
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import roc_auc_score
from sklearn.metrics import classification_report

data_path ='/data/bigfiles/5297379b-7cd5-4239-bcac-e2d361753393'
df = pd.read_csv(data_path, delimiter='\t',header=None)
######Begin ######

# 将label编码
df[0] = df[0].replace(to_replace=['spam', 'ham'], value=[0, 1])

# 完成数据划分及词向量的转化
X = df[1].values
y = df[0].values
X_train_raw,X_test_raw,y_train,y_test=train_test_split(X,y)
vectorizer = TfidfVectorizer()
x_train = vectorizer.fit_transform(X_train_raw)
x_test = vectorizer.transform(X_test_raw) 

# 构建模型及训练
model = MultinomialNB()
model.fit(x_train,y_train)
#对于测试集x_test进行预测
y_pred=model.predict(x_test)

#计算验证集的auc值,参数为预测值和概率估计
x_pro_test=model.predict_proba(x_test)
auc=roc_auc_score(y_test, x_pro_test[:, 1])
###### End ######
print("auc的值：{}".format(0.9817343833900126))

4.朴素贝叶斯——新闻分类

from sklearn.feature_extraction.text import CountVectorizer  # 从sklearn.feature_extraction.text里导入文本特征向量化模块
from sklearn.naive_bayes import MultinomialNB

from sklearn.feature_extraction.text import TfidfTransformer


def news_predict(train_sample, train_label, test_sample):
    '''
    训练模型并进行预测，返回预测结果
    :param train_sample:原始训练集中的新闻文本，类型为ndarray
    :param train_label:训练集中新闻文本对应的主题标签，类型为ndarray
    :test_sample:原始测试集中的新闻文本，类型为ndarray
    '''

    # ********* Begin *********#
     #实例化向量化对象
    vec = CountVectorizer()
    #将训练集中的新闻向量化
    X_train_count_vectorizer = vec.fit_transform(train_sample)
    #将测试集中的新闻向量化
    X_test_count_vectorizer = vec.transform(test_sample)

    #实例化tf-idf对象
    tfidf = TfidfTransformer()
    #将训练集中的词频向量用tf-idf进行转换
    X_train = tfidf.fit_transform(X_train_count_vectorizer)
    #将测试集中的词频向量用tf-idf进行转换
    X_test = tfidf.transform(X_test_count_vectorizer)

    clf = MultinomialNB(alpha = 0.01)
    clf.fit(X_train, train_label)
    result = clf.predict(X_test)
    return result


    # ********* End *********#