tf

lessonThree/Anti-Fraud-App/VAE.py

@@ -25,7 +25,9 @@ def read_data(source_file):
 keep_prob = tf.placeholder(dtype=tf.float32, shape=(), name='keep_prob')
 
 dec_in_channels = 1
-n_latent = 8
+#encoder输出的数据维度
+n_latent = gConfig['encoutlen']
+print(n_latent)
 reshaped_dim = [-1, 7, 7, dec_in_channels]
 inputs_decoder = 49 * dec_in_channels // 2
 
@@ -91,6 +93,6 @@ def decoder(sampled_z, keep_prob):
 
 #保存训练的encode的结果，就是要进行特征压缩后的特征
 sampled_data=pd.DataFrame(sampled_data)
-sampled_data.to_csv('sampled_data.csv')
+sampled_data.to_csv(gConfig['sampled_path'])
 
 

lessonThree/Anti-Fraud-App/app.py

@@ -16,10 +16,14 @@
 #
 app = Flask(__name__) 
 #路由注解，我们这里使用的是path的形式进行传参
+#示例url:http://0.0.0.0:8088/predict/1/2/3/4/5/6/7/8/9/10/11/12 这里的1...12换成需要进行聚类的值就可以了
 @app.route('/predict/<a>/<b>/<c>/<d>/<e>/<f>/<g>/<h>/<i>/<j>/<k>/<l>', methods=['GET'])
 def predict(a,b,c,d,e,f,g,h,i,j,k,l):
+	#获取url传来的需要进行预测的数据
 	line=[a,b,c,d,e,f,g,h,i,j,k,l]
-	lines=range(12)
+
+	k=len(line)
+	lines=range(k)
 	lines=[int(i) for i in line]
 	lines=[lines]
 	predict_result=execute.predicts(lines)

lessonThree/Anti-Fraud-App/config.ini

@@ -1,21 +1,27 @@
 
 [ints]
 #聚类的数量
-k_num=10
+num_clusters=10
 #聚类最大训练的步数
 num_epochs=10
 #聚类训练步数
 steps=10
 #VAE训练步数
 vae_steps=300
+#需要聚类的序列的长度,如果要将vae和clustering串起来用这个值要和enc_out_len保持一致
 seqlen=12
+#vae encoder输出的中间向量的长度
+encoutlen=8
+
 [floats]
 learning_rate = 0.01
 [strings]
 mode = train
 working_directory=working_directory/
 input_file=train_data/train_data.csv
-model_path=kmeansMode/1542127988
+#这里model的文件路径，要根据kmeansMode中的文件夹的来设置
+model_path=kmeansMode/1542258970
+sampled_path=train_data/sampled_data.csv
 
 
 

lessonThree/Anti-Fraud-App/kmeansModel.py

@@ -45,19 +45,23 @@ def trainAndSaveModel(input_set,steps):
 
     gConfig={}
     gConfig=getConfig.get_config(config_file='config.ini')
-
-    input_fn = lambda: tf.train.limit_epochs(tf.convert_to_tensor(input_set, dtype=tf.float32), num_epochs=gConfig['num_epochs'])
-    kmeans = tf.contrib.factorization.KMeansClustering(num_clusters=gConfig['k_num'], use_mini_batch=False)
+
+    num_epochs=gConfig['num_epochs']
+    num_clusters=gConfig['num_clusters']  
+    #定义input_fn函数     
+    input_fn = lambda: tf.train.limit_epochs(tf.convert_to_tensor(input_set, dtype=tf.float32), num_epochs=num_epochs)
+    #实例化KMeansClustering
+    kmeans = tf.contrib.factorization.KMeansClustering(num_clusters=num_clusters, use_mini_batch=False)
     previous_centers = None
     for _ in xrange(gConfig['steps']):
         kmeans.train(input_fn)#调用train对训练数据进行训练
         centers = kmeans.cluster_centers()#保存质心
         if previous_centers is not None:
-            print ('delta:', centers - previous_centers)
-            previous_centers = centers
-            print ('score:', kmeans.score(input_fn))
-            #将模型保存下来
-            modelPath = kmeans.export_savedmodel(export_dir_base="kmeansMode/",serving_input_receiver_fn=serving_input_receiver_fn)
+            print ("质心变化幅度:", centers - previous_centers)
+        previous_centers = centers
+        print ("模型评估得分:", kmeans.score(input_fn))
+        #将模型保存下来ˇ
+        modelPath = kmeans.export_savedmodel(export_dir_base="kmeansMode/",serving_input_receiver_fn=serving_input_receiver_fn)
 
     print("训练完成,model文件存放在：")
     print(modelPath)

lessonThree/Anti-Fraud-App/test.py

@@ -0,0 +1,28 @@
+import numpy as np
+import tensorflow as tf
+
+from six.moves import xrange
+
+num_points = 100
+dimensions = 2
+points = np.random.uniform(0, 1000, [num_points, dimensions])
+
+def input_fn():
+  return tf.train.limit_epochs(
+      tf.convert_to_tensor(points, dtype=tf.float32), num_epochs=1)
+
+num_clusters = 5
+kmeans = tf.contrib.factorization.KMeansClustering(
+    num_clusters=num_clusters, use_mini_batch=False)
+
+# train
+num_iterations = 10
+previous_centers = None
+for _ in xrange(num_iterations):
+  kmeans.train(input_fn)
+  cluster_centers = kmeans.cluster_centers()
+  if previous_centers is not None:
+    print ('delta:', cluster_centers - previous_centers)
+  previous_centers = cluster_centers
+  print ('score:', kmeans.score(input_fn))
+print ('cluster centers:', cluster_centers)

lessonThree/Anti-Fraud-App/train_data/sampled_data.csv

@@ -0,0 +1,10 @@
+,0,1,2,3,4,5,6,7
+0,0.38341895,-1.7428886,0.29892516,0.14158645,0.043346316,0.52457184,-0.51498866,-0.0033487156
+1,0.2401895,-1.6238832,-0.03735471,-0.32811102,0.85901475,0.61071527,1.7249069,0.19866326
+2,-2.120377,-0.7846775,-0.44127777,-2.8433104,1.7282515,1.3949893,0.006724566,1.5689514
+3,-0.24871545,-0.117795594,0.46943024,0.5850498,-1.8775313,0.5547079,1.5917208,-0.013330079
+4,0.048848335,-1.1120182,-1.05481,1.7671635,-0.8837705,-1.0044992,-0.6401813,1.51355
+5,0.23896244,1.2703017,0.56299645,-0.6899086,0.117588595,2.318331,0.55303776,-0.8386042
+6,0.42145008,1.4267052,0.037153464,1.5952226,0.32282645,-0.17458007,1.6561109,-0.68001455
+7,-1.9073356,0.4853596,-0.75159425,0.25134057,1.8075538,0.056467056,0.44442064,-1.3499131
+8,-0.7253678,-0.53390133,0.10448843,0.15717143,1.7451864,-0.6664468,1.6801159,0.1358863