Commit des fichiers traitement données préprocess et réseau de neurones, plus nouvelles data

code/wilshire_5000/nn.py

@@ -0,0 +1,104 @@
+import numpy as np
+import tensorflow as tf
+import pandas as pd
+import matplotlib.pyplot as plt
+import wilshire
+import tensorflow_addons as tfa
+
+def snake(x):
+    return(x+(tf.math.sin(50*x)**2)/50)
+def sinus(x):
+    return(tf.math.sin(x))
+def sinus_cosinus(x):
+    return(tf.math.sin(x)+tf.math.cos(x))
+def swish(x):
+    return(x*tf.math.sigmoid(x))
+
+#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 = 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()
+
+x_test=x_test / maximum
+
+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=2, epochs=20)
+
+        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(df_train.shape[0]+df_test.shape[0]+908)
+x = x / maximum
+future_preds = model.predict(x)  ## 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))
+    y_true = np.concatenate((y_train,y_test))
+    y_pred = np.concatenate((y_pred_train,y_pred_test))
+    plt.figure()
+    plt.plot(x,y_true,label="True data")
+    plt.plot(x,y_pred,label="Predictions")
+    plt.vlines([5240,5326])
+    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.vlines([5240,5326],ymin=0,ymax=1)
+plt.legend()
+plt.show()

code/wilshire_5000/wilshire.py

@@ -0,0 +1,32 @@
+import numpy as np
+import tensorflow as tf
+import pandas as pd
+import matplotlib.pyplot as plt
+
+
+def parser(path):
+    df = pd.read_csv(path,na_values='.')
+    print(df.shape)
+    df = df.interpolate()
+    #df = df.dropna()
+    print(df.shape)
+    #df = df.drop(labels=np.arange(1825)) ### To obtain the same graph than in the article
+    print(df.shape)
+    return(df)
+
+def preprocess(path):
+    df = parser(path)
+    print(df)
+    df_normalized = df[:]
+    df_normalized["WILL5000INDFC"]=df_normalized["WILL5000INDFC"]/np.max(df_normalized["WILL5000INDFC"])
+
+    # df.plot()
+    # plt.show()
+    df_train = df_normalized[:6544]
+    df_test = df_normalized[6545:6629]
+
+    # df_train.plot()
+    # df_test.plot()
+    # plt.show()
+    return(df_train,df_test)
+