More cleaning in preparation for the notebook

code/wilshire_5000/nn.py

@@ -15,23 +15,6 @@ def sinus_cosinus(x):
 def swish(x):
     return(x*tf.math.sigmoid(x))
 
-def arima_pred(y_train,y_test,orders=[[2,1,1],[2,2,1],[3,1,1],[2,1,2]],n=5):
-    mse=[]
-    for order in orders :
-        mean_err=np.array()
-        for k in range(n):
-            train = y_train
-            preds = []
-            for test in range(len(y_test)):
-                model = ARIMA(train, order=(order[0],order[1],order[2]))
-                model = model.fit()
-                output = model.forecast() 
-                preds.append(output[0])
-                #train.append(y_test[te
-            mean_err.append((np.square(np.array(preds) - np.array(y_test))).mean())
-        mse.append(mean_err.mean())
-    return(mse)
-
 
 #activations = [tf.keras.activations.relu,swish,sinus_cosinus,sinus,snake]
 activations = [snake]
@@ -49,9 +32,24 @@ def prepare_data(filename="WILL5000INDFC2.csv"):
     y_test = df_test["WILL5000INDFC"]
     y_test.to_numpy()
     x_test=x_test / maximum
-    return x_train,x_test,y_train,y_test
-
+    return x_train,x_test,y_train,y_test,maximum,index
 
+def arima_pred(y_train,y_test,orders=[[2,1,1],[2,2,1],[3,1,1],[2,1,2]],n=5):
+    mse=[]
+    for order in orders :
+        mean_err=np.array()
+        for k in range(n):
+            train = y_train
+            preds = []
+            for test in range(len(y_test)):
+                model = ARIMA(train, order=(order[0],order[1],order[2]))
+                model = model.fit()
+                output = model.forecast() 
+                preds.append(output[0])
+                #train.append(y_test[te
+            mean_err.append((np.square(np.array(preds) - np.array(y_test))).mean())
+        mse.append(mean_err.mean())
+    return(mse)
 
 
 def create_model(activation):
@@ -68,7 +66,8 @@ def create_model(activation):
     model.summary()
     return model
 
-def training_testing(n,activations):
+def training_testing(n=5,activations = [tf.keras.activations.relu,swish,sinus_cosinus,sinus,snake]):
+    x_train,x_test,y_train,y_test,maximum,index = prepare_data(filename="WILL5000INDFC2.csv")
     models = []
     errors_train,errors_test = [],[]
     mean_y_train,mean_y_test,std_y_test=[],[],[]
@@ -100,14 +99,19 @@ def training_testing(n,activations):
         return models,errors_train,errors_test
 
 
-def final_plot():
+def final_plot(models,errors_test,arima_err):
+    x_train,x_test,y_train,y_test,maximum,index = prepare_data(filename="WILL5000INDFC2.csv")
     x = np.arange(9000)
     x_n = x / maximum
-    future_preds = model.predict(x_n)  ## Calculated with a website the number of working days between 01-06-2020 and 01-01-2024
+    future_preds = models[-1].predict(x_n)  ## Calculated with a website the number of working days between 01-06-2020 and 01-01-2024
 
     #x=np.arange(df_train.shape[0]+df_test.shape[0]+908)
     y_true = np.concatenate((y_train,y_test))
-    x_cut = np.arange(df_train.shape[0]+df_test.shape[0])
+    x_cut = np.arange(x_train.shape[0]+x_test.shape[0])
+
+    print("----- ARIMA -----")
+    print()
+
     plt.figure()
     plt.plot(x_cut,y_true,label="True data")
     plt.plot(x,future_preds,label="Predictions")
@@ -119,3 +123,4 @@ def final_plot():
     plt.show()
 
 
+