From 0339f52a39d6d7a0256483dd3e54cc05e4e28a55 Mon Sep 17 00:00:00 2001
From: Newnius <newnius.cn@gmail.com>
Date: Fri, 1 May 2020 18:18:18 +0800
Subject: [PATCH] update

---
 .idea/workspace.xml |  2 +-
 serve.py            | 36 +++++++++++++++---------------------
 2 files changed, 16 insertions(+), 22 deletions(-)

diff --git a/.idea/workspace.xml b/.idea/workspace.xml
index 60921e1..be99bb2 100644
--- a/.idea/workspace.xml
+++ b/.idea/workspace.xml
@@ -215,7 +215,7 @@
   <component name="PropertiesComponent">
     <property name="WebServerToolWindowFactoryState" value="false" />
     <property name="aspect.path.notification.shown" value="true" />
-    <property name="com.android.tools.idea.instantapp.provision.ProvisionBeforeRunTaskProvider.myTimeStamp" value="1588327999670" />
+    <property name="com.android.tools.idea.instantapp.provision.ProvisionBeforeRunTaskProvider.myTimeStamp" value="1588328026943" />
     <property name="go.gopath.indexing.explicitly.defined" value="true" />
     <property name="nodejs_interpreter_path.stuck_in_default_project" value="undefined stuck path" />
     <property name="nodejs_npm_path_reset_for_default_project" value="true" />
diff --git a/serve.py b/serve.py
index 15f817d..cfec87d 100644
--- a/serve.py
+++ b/serve.py
@@ -137,41 +137,35 @@ class Data:
 # add end
 
 
-def draw_yqy(config, origin_data, predict_norm_data, mean_yqy, std_yqy):
-	return
+def draw_yqy(config2, origin_data, predict_norm_data, mean_yqy, std_yqy):
 	label_norm_data = (origin_data - mean_yqy) / std_yqy
 	assert label_norm_data.shape[0] == predict_norm_data.shape[
 		0], "The element number in origin and predicted data is different"
 
+	print("dsa")
 	# label_norm_data=label_norm_data[:,1]
-	label_names = ['pre', 'main', 'post']
+	label_name = 'high'
 	label_column_num = 1
 
-	loss1 = \
-		np.mean((label_norm_data[config.predict_day:][:, 5] - predict_norm_data[:-config.predict_day][0:]) ** 2,
-		        axis=0)[5]
-	loss2 = \
-		np.mean((label_norm_data[config.predict_day:][:, 6] - predict_norm_data[:-config.predict_day][0:]) ** 2,
-		        axis=0)[6]
-	loss3 = \
-		np.mean((label_norm_data[config.predict_day:][:, 7] - predict_norm_data[:-config.predict_day][0:]) ** 2,
-		        axis=0)[7]
-	print("The mean squared error of stock {} is ".format(label_names[0]), loss1)
-	print("The mean squared error of stock {} is ".format(label_names[1]), loss2)
-	print("The mean squared error of stock {} is ".format(label_names[2]), loss3)
+	loss = \
+		np.mean((label_norm_data[config.predict_day:][:, 1] - predict_norm_data[:-config.predict_day][0:]) ** 2,
+		        axis=0)[1]
+	print("The mean squared error of stock {} is ".format(label_name), loss)
 
 	# label_X = range(origin_data.data_num - origin_data.train_num - origin_data.start_num_in_test)
 	# predict_X = [x + config.predict_day for x in label_X]
 
-	label_datas = label_norm_data * std_yqy + mean_yqy
+	print("2")
 
-	predict_datas = predict_norm_data * std_yqy + mean_yqy
+	label_data = label_norm_data[:, 1] * std_yqy[1] + mean_yqy[1]
 
-	print(label_datas)
-	print(predict_datas)
+	predict_data = predict_norm_data * std_yqy[1] + mean_yqy[1]
 
-	print(label_datas[-1])
-	print(predict_datas[-1])
+	print(label_data)
+	print(predict_data)
+
+	print(label_data[-1])
+	print(predict_data[-1])
 
 
 PORT_NUMBER = 8080