Code LSTM Keras

LSTM_redshift

import numpy as np
import matplotlib.pyplot as plt
import collections
from sklearn.model_selection import train_test_split
from keras.layers import Input, Dense, Dropout, Conv1D, MaxPooling1D,Flatten, LSTM
from keras.models import Model, Sequential
from keras import metrics
import keras
import matplotlib.pyplot as plt


def LSTM_redshift(X_train,nb_class):

	if nb_class == 2 :
		loss='binary_crossentropy'
	else:
		loss='categorical_crossentropy'

	print(loss)
	
	dim=(17908,1)
	
	model_LSTM = Sequential()
	model_LSTM.add(LSTM(256,  input_shape=dim))# ,
	model_LSTM.add(Dense(nb_class, activation="sigmoid")) 
	model_LSTM.layers[0].trainable = False

	model_LSTM.compile(loss=loss,
              optimizer=keras.optimizers.Adam(learning_rate=1e-3),
              metrics=['acc'])

	return model_LSTM

main

from dataset_redshift import dataset_redshift
from MLP_redshift import MLP_redshift
from CNN1D_redshift import CNN1D_redshift
from LSTM_redshift import LSTM_redshift

#from visu_data import visu_data
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import collections
from sklearn.model_selection import train_test_split
from keras.layers import Input, Dense, Dropout, Flatten
from keras.models import Model, Sequential
from keras import metrics
import matplotlib.pyplot as plt
from keras.utils import np_utils

from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay

X_train, X_validation ,X_test, target_train, target_validation ,target_test , Y_train , Y_validation, Y_test , nb_class, nom_classes = dataset_redshift('Flag_class',Undersample=True)


X_test=np.reshape(X_test, (X_test.shape[0],X_test.shape[1],1))
X_train=np.reshape(X_train, (X_train.shape[0],X_train.shape[1],1))	
X_validation=np.reshape(X_validation, (X_validation.shape[0],X_validation.shape[1],1))	


model=LSTM_redshift(X_train,nb_class)

h = model.fit(X_train, Y_train,
              epochs=20,
              batch_size=32,
              verbose =1,
              validation_data = (X_validation , Y_validation))



y_pred_test=model.predict(X_test)
y_pred_test=np.argmax(y_pred_test, axis=1)

conf_matrix_test=confusion_matrix(target_test, y_pred_test)
print(conf_matrix_test)



y_pred_train=model.predict(X_train)
y_pred_train=np.argmax(y_pred_train, axis=1)

conf_matrix_train=confusion_matrix(target_train, y_pred_train)
print(conf_matrix_train)