optuna wilshire

code/RNN_wilshire_5000/training.py

@@ -2,74 +2,96 @@ import tensorflow as tf
 from matplotlib import pyplot as plt
 import numpy as np
 from Model import MyModel
-
-
-LEN_SEQ = 64
-PRED = 0.027
-HIDDEN = 128
-
-model = MyModel(HIDDEN)
-
-dataset = np.load('dataset.npy')
-scale = (np.max(dataset) - np.min(dataset))
-data = dataset/scale
-shift = np.min(data)
-data = data - shift
-
-annee = np.array(list(range(len(data))))/365
-annee = annee - annee[-1]
-start_pred = int(len(data)*(1-PRED))
-print(len(data))
-print(start_pred)
-plt.figure(1)
-plt.plot(annee[:start_pred],data[:start_pred], label="apprentissage")
-plt.plot(annee[start_pred:],data[start_pred:], label="validation")
-plt.legend()
-plt.show()
-
-X_train_tot = [data[0:start_pred-1]]
-Y_train_tot = [data[1:start_pred]]
-
-X_train_tot = np.expand_dims(np.array(X_train_tot),2)
-Y_train_tot = np.expand_dims(np.array(Y_train_tot),2)
-
-X_train = X_train_tot[:,:LEN_SEQ,:]
-Y_train = Y_train_tot[:,:LEN_SEQ,:]
-
-for i in range(len(X_train_tot[0]) - LEN_SEQ) :
-	X_train = np.concatenate((X_train, X_train_tot[:,i:i+LEN_SEQ,:]),0)
-	Y_train = np.concatenate((Y_train, Y_train_tot[:,i:i+LEN_SEQ,:]),0)
-print(X_train_tot.shape)
-print(X_train.shape)
-
-
-model.compile(optimizer='adam',
-			  loss='binary_crossentropy',
-			  metrics=['binary_crossentropy'])
-import os 
-os.system("rm -rf log_dir")
-
-model.fit(x=X_train, y=Y_train, batch_size=16, epochs=5, shuffle=True)
-
-Pred = X_train_tot.copy()
-while len(Pred[0]) < len(data) :
-	print(len(data) - len(Pred[0]))
-	Pred = np.concatenate((Pred, np.array([[model.predict(Pred)[0][-1]]])),1)
-Pred = Pred + shift
-Pred = Pred * scale
-
-data_Pred = np.squeeze(Pred)
-
-plt.figure(2)
-plt.plot(annee[:start_pred],dataset[:start_pred], label="apprentissage")
-plt.plot(annee[start_pred:],dataset[start_pred:], label="validation")
-plt.plot(annee, data_Pred, label="prediction")
-plt.legend()
-
-fig, axs = plt.subplots(2)
-axs[0].plot(annee[:start_pred],dataset[:start_pred], label="données")
-axs[0].plot(annee[start_pred:],dataset[start_pred:], label="validation")
-axs[1].plot(annee[:start_pred],dataset[:start_pred], label="données")
-axs[1].plot(annee[start_pred:], data_Pred[start_pred:], label="prediction")
-plt.legend()
-plt.show()
+import optuna
+
+def objectif(trial) :
+	LEN_SEQ = trial.suggest_int('len_seq', 64,256)
+	PRED = 0.1
+	HIDDEN = trial.suggest_int('hidden',32,256)
+
+	model = MyModel(HIDDEN)
+
+	dataset = np.load('dataset.npy')
+	scale = (np.max(dataset) - np.min(dataset))
+	data = dataset/scale
+	shift = np.min(data)
+	data = data - shift
+
+	annee = np.array(list(range(len(data))))/365
+	annee = annee - annee[-1]
+	start_pred = int(len(data)*(1-PRED))
+	#print(len(data))
+	#print(start_pred)
+	plt.figure(1)
+	plt.plot(annee[:start_pred],data[:start_pred], label="apprentissage")
+	plt.plot(annee[start_pred:],data[start_pred:], label="validation")
+	plt.legend()
+	#plt.show()
+
+	X_train_tot = [data[0:start_pred-1]]
+	Y_train_tot = [data[1:start_pred]]
+
+	X_train_tot = np.expand_dims(np.array(X_train_tot),2)
+	Y_train_tot = np.expand_dims(np.array(Y_train_tot),2)
+
+	X_train = X_train_tot[:,:LEN_SEQ,:]
+	Y_train = Y_train_tot[:,:LEN_SEQ,:]
+
+	for i in range(len(X_train_tot[0]) - LEN_SEQ) :
+		X_train = np.concatenate((X_train, X_train_tot[:,i:i+LEN_SEQ,:]),0)
+		Y_train = np.concatenate((Y_train, Y_train_tot[:,i:i+LEN_SEQ,:]),0)
+	#print(X_train_tot.shape)
+	#print(X_train.shape)
+
+
+	model.compile(optimizer='adam',
+				  loss='binary_crossentropy',
+				  metrics=['binary_crossentropy','mse'])
+	import os 
+	os.system("rm -rf log_dir")
+
+	model.fit(x=X_train, y=Y_train, batch_size=16, epochs=5, shuffle=True)
+
+	Pred = X_train_tot.copy()
+	while len(Pred[0]) < len(data)+500 :
+		print(len(data) - len(Pred[0]))
+		Pred = np.concatenate((Pred, np.array([[model.predict(Pred)[0][-1]]])),1)
+	Pred = Pred + shift
+	Pred = Pred * scale
+
+	data_Pred = np.squeeze(Pred)
+
+	plt.figure(2)
+	plt.clf()
+	plt.plot(annee[:start_pred],dataset[:start_pred], label="apprentissage")
+	plt.plot(annee[start_pred:],dataset[start_pred:], label="validation")
+	plt.plot(annee[start_pred:], data_Pred[start_pred:len(annee)], label="prediction")
+	plt.legend()
+	plt.savefig(f"images/{LEN_SEQ}_{HIDDEN}_fig2.png")
+
+	plt.figure(3)
+	plt.clf()
+	fig, axs = plt.subplots(2)
+	axs[0].plot(annee[:start_pred],dataset[:start_pred], label="apprentissage")
+	axs[0].plot(annee[start_pred:],dataset[start_pred:], label="validation")
+	axs[1].plot(annee[:start_pred],dataset[:start_pred], label="données")
+	axs[1].plot(annee[start_pred:], data_Pred[start_pred:len(annee)], label="prediction")
+	plt.legend()
+	plt.savefig(f"images/{LEN_SEQ}_{HIDDEN}_fig3.png")
+
+	annee_ex = np.array(list(range(len(data_Pred))))/365
+	annee_ex = annee_ex + annee[0]
+	plt.figure(4)
+	plt.clf()
+	plt.plot(annee[:start_pred],dataset[:start_pred], label="données")
+	plt.plot(annee_ex[start_pred:], data_Pred[start_pred:], label="prediction")
+	plt.legend()
+	plt.savefig(f"images/{LEN_SEQ}_{HIDDEN}_fig4.png")
+
+	loss = np.linalg.norm(dataset[start_pred:] - data_Pred[start_pred:len(dataset)])/(np.max(data_Pred[start_pred:]) - np.min(data_Pred[start_pred:]))
+	print(loss*100)
+	return loss
+	#plt.show()
+
+study = optuna.create_study()
+study.optimize(objectif, n_trials=10)