Cleaned code into functions and modified ARIMA

code/wilshire_5000/nn.py

@@ -15,112 +15,107 @@ def sinus_cosinus(x):
 def swish(x):
     return(x*tf.math.sigmoid(x))
 
-def arima_pred(y_train,y_test,order=[2,1,1]):
-    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[test])
-    return((np.square(np.array(preds) - np.array(y_test))).mean(),preds)
+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]
-models = []
-errors_train,errors_test = [],[]
-mean_y_train,mean_y_test,std_y_test=[],[],[]
 
-df_train,df_test,index = wilshire.preprocess('WILL5000INDFC2.csv')
-x_train = np.arange(df_train.shape[0])
 
-
-maximum = np.max(x_train)
-x_train = x_train / maximum
-
-
-y_train=df_train["WILL5000INDFC"]
-y_train.to_numpy()
-
-x_test = np.arange(df_train.shape[0]+1,df_train.shape[0]+df_test.shape[0]+1)
-y_test = df_test["WILL5000INDFC"]
-y_test.to_numpy()
-print("----")
-print(y_test)
-x_test=x_test / maximum
-
-print(arima_pred(list(y_train),list(y_test)))
-
-
-for activation in activations :
-    y_train_5=[]
-    y_test_5=[]
-    errors_train_5=[]
-    errors_test_5=[]
-    for k in range(1):
-
-        model =  tf.keras.Sequential()
-
-        model.add(tf.keras.layers.Dense(1,input_shape=[1,],activation=activation))
-        model.add(tf.keras.layers.Dense(64,activation=activation))
-        model.add(tf.keras.layers.Dense(64,activation=activation))
-        model.add(tf.keras.layers.Dense(1))
-        opt = tf.keras.optimizers.SGD(learning_rate=0.01,momentum=0.9)
-        model.compile(optimizer=opt, loss='mse')
-        model.build()
-        model.summary()
-        model.fit(x_train,y_train, batch_size=1, epochs=1)
-
-        y_pred_test = model.predict(x_test)
-        y_pred_train = model.predict(x_train)
-        y_train_5.append(y_pred_train)
-        y_test_5.append(y_pred_test)
-        errors_test_5.append(model.evaluate(x_test,y_test))
-        errors_train_5.append(model.evaluate(x_train,y_train))
-
-
-    mean_y_train.append(np.mean(y_train_5,axis=0))
-    mean_y_test.append(np.mean(y_test_5,axis=0))
-    std_y_test.append(np.std(y_test_5,axis=0))
-    errors_train.append([np.mean(errors_train_5),np.std(errors_train_5)])
-    errors_test.append([np.mean(errors_test_5),np.std(errors_test_5)])
-    # y_preds_train.append(y_pred_train)
-    # y_preds_test.append(y_pred_test)
-
-
-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
-
-
-def plot_total(x_train,y_train,y_pred_train,x_test,y_test,y_pred_test):
-    x = np.concatenate((x_train,x_test))
+def prepare_data(filename="WILL5000INDFC2.csv"):
+    df_train,df_test,index = wilshire.preprocess(filename)
+    x_train = np.arange(df_train.shape[0])
+    maximum = np.max(x_train)
+    x_train = x_train / maximum
+    y_train=df_train["WILL5000INDFC"]
+    y_train.to_numpy()
+
+    x_test = np.arange(df_train.shape[0]+1,df_train.shape[0]+df_test.shape[0]+1)
+    y_test = df_test["WILL5000INDFC"]
+    y_test.to_numpy()
+    x_test=x_test / maximum
+    return x_train,x_test,y_train,y_test
+
+
+
+
+def create_model(activation):
+    model =  tf.keras.Sequential()
+
+    model.add(tf.keras.layers.Dense(1,input_shape=[1,],activation=activation))
+    model.add(tf.keras.layers.Dense(64,activation=activation))
+    model.add(tf.keras.layers.Dense(64,activation=activation))
+    model.add(tf.keras.layers.Dense(1))
+
+    opt = tf.keras.optimizers.SGD(learning_rate=0.01,momentum=0.9)
+    model.compile(optimizer=opt, loss='mse')
+    model.build()
+    model.summary()
+    return model
+
+def training_testing(n,activations):
+    models = []
+    errors_train,errors_test = [],[]
+    mean_y_train,mean_y_test,std_y_test=[],[],[]
+    for activation in activations :
+        y_train_5=[]
+        y_test_5=[]
+        errors_train_5=[]
+        errors_test_5=[]
+        for k in range(n):
+
+            model = create_model(activations)
+            model.fit(x_train,y_train, batch_size=1, epochs=1)
+
+            y_pred_test = model.predict(x_test)
+            y_pred_train = model.predict(x_train)
+            y_train_5.append(y_pred_train)
+            y_test_5.append(y_pred_test)
+            errors_test_5.append(model.evaluate(x_test,y_test))
+            errors_train_5.append(model.evaluate(x_train,y_train))
+
+        models.append(model)
+        mean_y_train.append(np.mean(y_train_5,axis=0))
+        mean_y_test.append(np.mean(y_test_5,axis=0))
+        std_y_test.append(np.std(y_test_5,axis=0))
+        errors_train.append([np.mean(errors_train_5),np.std(errors_train_5)])
+        errors_test.append([np.mean(errors_test_5),np.std(errors_test_5)])
+        # y_preds_train.append(y_pred_train)
+        # y_preds_test.append(y_pred_test)
+        return models,errors_train,errors_test
+
+
+def final_plot():
+    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
+
+    #x=np.arange(df_train.shape[0]+df_test.shape[0]+908)
     y_true = np.concatenate((y_train,y_test))
-    y_pred = np.concatenate((y_pred_train,y_pred_test))
+    x_cut = np.arange(df_train.shape[0]+df_test.shape[0])
     plt.figure()
-    plt.plot(x,y_true,label="True data")
-    plt.plot(x,y_pred,label="Predictions")
-    plt.vlines([index,index+85])
+    plt.plot(x_cut,y_true,label="True data")
+    plt.plot(x,future_preds,label="Predictions")
+    plt.xticks(range(0, 9000, 250), range(1995, 2031, 1))
+    plt.xlabel("Années")
+    plt.ylabel("Index Willshire5000 normalisé")
+    plt.vlines([index,index+85],ymin=0,ymax=1,colors="r",label="Test Samples")
     plt.legend()
     plt.show()
 
-#plot_total(x_train,y_train,y_pred_train,x_test,y_test,y_pred_test)
-
-print(errors_test)
-
-#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])
-plt.figure()
-plt.plot(x_cut,y_true,label="True data")
-plt.plot(x,future_preds,label="Predictions")
-plt.xticks(range(0, 9000, 250), range(1995, 2031, 1))
-plt.xlabel("Années")
-plt.ylabel("Index Willshire5000 normalisé")
-plt.vlines([index,index+85],ymin=0,ymax=1,colors="r",label="Test Samples")
-plt.legend()
-plt.show()
-