2

.idea/vcs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file

src1/linearclassification.py

@@ -22,16 +22,16 @@ class LinearClassification:
         """'
         需要你实现的部分
         """
-        self.W = np.zeros([1, 9])
+        N = train_features.shape[1]
+        self.W = np.zeros([1, N + 1])
         lc = np.ones([train_features.shape[0], 1])
         X = np.concatenate((lc, train_features), axis=1)
         for n in range(self.epochs):
             y = np.dot(X, np.transpose(self.W))
             delta = np.transpose(y - train_labels)
-            derivative = (np.dot(delta, X) + self.Lambda * self.W) / train_labels.size
+            derivative = 2 * (np.dot(delta, X) + self.Lambda * self.W) / train_labels.size
             self.W = self.W - self.lr * derivative
 
-
     '''根据训练好的参数对测试数据test_features进行预测，返回预测结果
     预测结果的数据类型应为np数组，shape=(test_num,1) test_num为测试数据的数目'''
     def predict(self, test_features):

src1/nBayesClassifier.py

@@ -2,25 +2,52 @@ import numpy as np
 import math
 from collections import Counter
 from process_data import load_and_process_data
-from evaluation import get_micro_F1,get_macro_F1,get_acc
+from evaluation import get_micro_F1, get_macro_F1, get_acc
+
 
 class NaiveBayes:
-    '''参数初始化
+    """参数初始化
     Pc: P(c) 每个类别c的概率分布
     Pxc: P(c|x) 每个特征的条件概率
-    '''
+    """
+
     def __init__(self):
-        self.Pc={}
-        self.Pxc={}
+        self.Pc = {}
+        self.Pxc = {}
 
     '''
     通过训练集计算先验概率分布p(c)和条件概率分布p(x|c)
     建议全部取log，避免相乘为0
     '''
-    def fit(self,traindata,trainlabel,featuretype):
-        '''
+
+    def fit(self, traindata, trainlabel, featuretype):
+        """
         需要你实现的部分
-        '''
+        """
+        c = Counter(trainlabel.flatten())
+        N = len(c)
+        for key, val in c.items():
+            self.Pc[key] = (val + 1) / (trainlabel.size + N)
+        for d in range(traindata.shape[1]):  # 对各个维度分别进行处理
+            column = traindata[:, d]
+            if featuretype[d] == 1:
+                xc = {}
+                for xi, cy in zip(column.flatten(), trainlabel.flatten()):
+                    if cy not in xc:
+                        xc[cy] = []
+                    xc[cy].append(xi)
+                for key, val in xc.items():
+                    temp = np.array(val)
+                    self.Pxc[(d, key)] = (np.average(temp), np.var(temp))
+            else:
+                xc = {}
+                Ni = len(np.unique(column))
+                for xi, cy in zip(column.flatten(), trainlabel.flatten()):
+                    if (xi, cy) not in xc:
+                        xc[(xi, cy)] = 0
+                    xc[(xi, cy)] += 1
+                for key, val in xc.items():
+                    self.Pxc[(d, key[0], key[1])] = (val + 1) / (c[key[1]] + Ni)
 
 
     '''
@@ -28,26 +55,49 @@ class NaiveBayes:
     返回预测结果,预测结果的数据类型应为np数组，shape=(test_num,1) test_num为测试数据的数目
     feature_type为0-1数组，表示特征的数据类型，0表示离散型，1表示连续型
     '''
-    def predict(self,features,featuretype):
-        '''
+
+    def predict(self, features, featuretype):
+        """
         需要你实现的部分
-        '''       
+        """
+        N = features.shape[0]
+        pred = []
 
+        def gauss(v, sigma, mu):
+            exponent = -(np.power(v-sigma, 2))/(2*np.power(mu, 2))
+            res = math.log((1/(np.sqrt(2*np.pi)*mu)))+exponent
+            return res
+        for x in features:
+            prob = {}
+            for k in self.Pc:
+                temp = math.log(self.Pc[k])
+                for i in range(x.shape[0]):
+                    if featuretype[i] == 1:
+                        n, p = self.Pxc[(i, k)]
+                        temp += gauss(x[i], n, p)
+                    else:
+                        temp += math.log(self.Pxc[(i, x[i], k)])
+                prob[k] = temp
+            pred.append(max(prob, key=prob.get))
+        pred = np.array(pred).reshape([features.shape[0], 1])
+        print(pred)
+        return pred
 
 
 def main():
     # 加载训练集和测试集
-    train_data,train_label,test_data,test_label=load_and_process_data()
-    feature_type=[0,1,1,1,1,1,1,1] #表示特征的数据类型，0表示离散型，1表示连续型
+    train_data, train_label, test_data, test_label = load_and_process_data()
+    feature_type = [0, 1, 1, 1, 1, 1, 1, 1]  # 表示特征的数据类型，0表示离散型，1表示连续型
 
-    Nayes=NaiveBayes()
-    Nayes.fit(train_data,train_label,feature_type) # 在训练集上计算先验概率和条件概率
+    Nayes = NaiveBayes()
+    Nayes.fit(train_data, train_label, feature_type)  # 在训练集上计算先验概率和条件概率
 
-    pred=Nayes.predict(test_data,feature_type)  # 得到测试集上的预测结果
+    pred = Nayes.predict(test_data, feature_type)  # 得到测试集上的预测结果
 
     # 计算准确率Acc及多分类的F1-score
-    print("Acc: "+str(get_acc(test_label,pred)))
-    print("macro-F1: "+str(get_macro_F1(test_label,pred)))
-    print("micro-F1: "+str(get_micro_F1(test_label,pred)))
+    print("Acc: " + str(get_acc(test_label, pred)))
+    print("macro-F1: " + str(get_macro_F1(test_label, pred)))
+    print("micro-F1: " + str(get_micro_F1(test_label, pred)))
+
 
-main()
\ No newline at end of file
+main()