add mnist test

Author: WenDesi

AdaBoost/adaboost.py

@@ -100,7 +100,7 @@ def _init_parameters_(self,features,labels):
 
         self.n = len(features[0])
         self.N = len(features)
-        self.M = 10000                            # 分类器数目
+        self.M = 100000                            # 分类器数目
 
         self.w = [1.0/self.N]*self.N
         self.alpha = []
@@ -170,11 +170,34 @@ def predict(self,features):
         return results
 
 if __name__ == '__main__':
-    features = [[0],[1],[2],[3],[4],[5],[6],[7],[8],[9]]
-    labels = [1,1,1,-1,-1,-1,1,1,1,-1]
+    print 'Start read data'
 
+    time_1 = time.time()
 
+    raw_data = pd.read_csv('../data/train_binary.csv',header=0)
+    data = raw_data.values
 
+    imgs = data[0::,1::]
+    labels = data[::,0]
 
+
+    # 选取 2/3 数据作为训练集， 1/3 数据作为测试集
+    train_features, test_features, train_labels, test_labels = train_test_split(imgs, labels, test_size=0.33, random_state=23323)
+
+    time_2 = time.time()
+    print 'read data cost ',time_2 - time_1,' second','\n'
+
+    print 'Start training'
     ada = AdaBoost()
-    ada.train(features,labels)
+    ada.train(train_features, train_labels)
+
+    time_3 = time.time()
+    print 'training cost ',time_3 - time_2,' second','\n'
+
+    print 'Start predicting'
+    test_predict = ada.predict(test_features)
+    time_4 = time.time()
+    print 'predicting cost ',time_4 - time_3,' second','\n'
+
+    score = accuracy_score(test_labels,test_predict)
+    print "The accruacy socre is ", score