''' Load the data. For this demo, we're using sklearn's digits dataset Digits are 8x8 pixel images. Each row is one image, in a linear format, where columns 65-74 correspond to one hot encoded responses representing digits 0 through 9. 1797 rows 74 columns ''' data = np.loadtxt("transformed.csv", delimiter = ',') m = len(data) # Split the data into training set and test set. train_set = data[:(3*m/4),:] test_set = data[m/4:,:] # Instantiate a new neural network. 64 input, 64 hidden, 10 output nodes. NN = NeuralNetwork(64,HIDDEN_NODES,10,LEARNING_RATE,ITERATIONS) # Train on the training set, test on the test set. The test() function # will print out the percent correctness on the test set. errors = NN.train(train_set) NN.test(test_set) # Plot the error curve if VIEW_PLOT == True: plt.plot(errors) plt.title("Average Error Per Iteration On Training Set") plt.xlabel("Iteration") plt.ylabel("Average Error") pylab.show()