def CostList(parameters):
costList = []
averageErrorList = []
for i in range(0 + predictionData.p, 136 - predictionData.p):
X, Y, Y_List = predictionData.DataSet(predictionData.postMile[i])
pred_test, cost = functions.predict(X[:, 4000:4600], Y[:, 4000:4600],
parameters)
averageError = functions.averageError(pred_test, Y[:, 4000:4600])
costList.append(cost)
averageErrorList.append(averageError)
outList.append(costList)
outList.append(averageErrorList)
parameters)
test_x = np.concatenate((test_x[1:6, :], pred_test, test_x[6:, :]), 0)
costList.append(cost)
averageError = functions.averageError(pred_test,
test_y_List[j][:, 4000:4600])
averageErrorList.append(averageError)
outList.append(costList)
outList.append(averageErrorList)
listPostMile = [51.72, 42.18, 31.83, 6.62]
listPostMile_1 = [53.57, 43.46, 34.36, 4.48]
for i in range(0, 4):
inputData, outputData, outputList = predictionData.DataSet(listPostMile[i])
Algorithm(inputData, outputData, outputList, None, True)
inputData, outputData, outputList = predictionData.DataSet(40.68)
train_x = inputData[:, 0:4000]
train_y = outputData[:, 0:4000]
test_x = inputData[:, 4000:4600]
test_y = outputData[:, 4000:4600]
test_y_List = outputList
parameters = L_layer_model(train_x,
train_y,
layers_dims,
num_iterations=10000,
print_cost=True)
for i in range(0, 4):
predictions = function.forward_propagation(X, parameters)
rmse_error, average_error = function.compute_error(predictions, Y)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
rmse_error = rmse_error.eval({X: X_train, Y: Y_train})
average_error = average_error.eval({X: X_train, Y: Y_train})
return rmse_error, average_error
inputData, outputData, outputList = predictionData.DataSet(40.68)
X_train = inputData[:, 0:4000]
Y_train = outputData[:, 0:4000]
X_test = inputData[:, 4000:4600]
Y_test = outputData[:, 4000:4600]
Y_test_List = outputList
layers_dims = [30, 25, 25, 1]
#print(np.shape(inputData))
#print(np.shape(outputData))
#print(np.shape(inputData))
#X_test[:, 0:5] = random.uniform(0, 1)