def MLP(data, batch_size):
#data = load_iris()
# list1 = list(data.iloc[0,:-2])
# print(list1)
# target = list(data.iloc[0,4:])
# print(target)
mlp = MultiLayerPerceptron(_layers=1,
_bias=1,
_inputs=4,
_outputs=2,
_learningRate=0.01,
_maxIter=200)
for i in range(mlp.maxIter):
mlp.totalError = 0
data = shuffle(data)
#print(data.data[0])
for j in range(len(data)):
row = list(data.iloc[j, :-mlp.outputs])
target = list(data.iloc[j, mlp.inputs:])
mlp.estimate(row)
#mlp.estimate(data.data[j])
mlp.updateDeltaWeight(target)
if j % batch_size == 0:
mlp.updateWeight()
mlp.updateTotalError(target)
# print("at iteration ", i, " error = " + str(mlp.totalError))
if j % batch_size != 0:
mlp.updateWeight()
mlp.updateTotalError(target)
# print("at iteration ", i, " error = " + str(mlp.totalError))
if (mlp.totalError < 0.01):
break
return mlp
