3993008

linear/train_jqxx2.py

@@ -38,28 +38,27 @@ def read_data(path):
 
 def demo(file, model_file):
     X_train,y_train=read_data(file)
-    # X_test,y_test=read_data(config.get('application', 'test_data_path'))
-    Xtrain, Xtest, Ytrain, Ytest = train_test_split(X_train, y_train, test_size=0.3)
+    # Xtrain, Xtest, Ytrain, Ytest = train_test_split(X_train, y_train, test_size=0.3)
     # 一个对象，它代表的线性回归模型，它的成员变量，就已经有了w，b. 刚生成w和b的时候 是随机的
     model = LogisticRegression()
     # 一调用这个函数，就会不停地找合适的w和b 直到误差最小
-    model.fit(Xtrain, Ytrain)
+    model.fit(X_train, y_train)
     # 打印W
     # print(model.coef_)
     # 打印b
     print(model.intercept_)
     # 模型已经训练完毕,用模型看下在训练集的表现
-    y_pred_train = model.predict(Xtrain)
-    # sklearn 求解训练集的mse
-    # y_train 在训练集上 真实的y值
-    # y_pred_train 通过模型预测出来的y值
-    # 计算  (y_train-y_pred_train)^2/n
-    train_mse = metrics.mean_squared_error(Ytrain, y_pred_train)
-    print("train准确率:", accuracy_score(y_pred_train, Ytrain))
-
-    # 看下在测试集上的效果
-    y_pred_test = model.predict(Xtest)
-    print("test准确率:", accuracy_score(y_pred_test, Ytest))
+    # y_pred_train = model.predict(Xtrain)
+    # # sklearn 求解训练集的mse
+    # # y_train 在训练集上 真实的y值
+    # # y_pred_train 通过模型预测出来的y值
+    # # 计算  (y_train-y_pred_train)^2/n
+    # train_mse = metrics.mean_squared_error(Ytrain, y_pred_train)
+    # print("train准确率:", accuracy_score(y_pred_train, Ytrain))
+    #
+    # # 看下在测试集上的效果
+    # y_pred_test = model.predict(Xtest)
+    # print("test准确率:", accuracy_score(y_pred_test, Ytest))
     # 保存模型
     joblib.dump(model,  model_file)
 
@@ -127,6 +126,6 @@ def demo_3(file, model_file):
 if __name__ == '__main__':
     root_dir = 'D:\\data\\quantization\\jqxx2\\'
     model_dir = 'D:\\data\\quantization\\jqxx2_svm_model\\'
-    m = '399306.SZ.log'
-    demo(root_dir + m, model_dir + str(m)[:6] + '.pkl')
+    m = '399308.SZ.log'
+    demo_1(root_dir + m, model_dir + str(m)[:6] + '.pkl')