simple_neural_network_mlp_sklearn_class_iris

import os
import ipdb
import numpy as np
import matplotlib.pyplot as plt
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import OneHotEncoder, MinMaxScaler, StandardScaler
from sklearn import datasets
from sklearn.model_selection import train_test_split

data = datasets.load_iris()

X = data['data']
Y = data['target']

# use and the scaled input the encoded output
enc = OneHotEncoder()
Y_enc = enc.fit_transform(Y[:, np.newaxis]).toarray()

Y = Y_enc

scaler = MinMaxScaler()
X_scaled = scaler.fit_transform(X)

X = X_scaled


X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.3, random_state=0)


clf = MLPClassifier(solver='sgd', hidden_layer_sizes=(13,10),
                    activation='tanh',
                    learning_rate='constant',
                    learning_rate_init=0.2,
                    momentum=0,
                    random_state=0)

clf.fit(X_train, Y_train)
predictedY_train = clf.predict(X_train)
accuracy_train = accuracy_score(Y_train, predictedY_train)
#similar a clf.score(X,Y)

predictedY_test = clf.predict(X_test)
accuracy_test = accuracy_score(Y_test, predictedY_test)

print("Accuracy for train set is: %f" %accuracy_train)
print("Accuracy for test set is: %f" %accuracy_test)

# visualizar os pesos
#print("Coefficients: %s" %clf.coefs_)
#  Cada elemento i da lista representa a matriz de coeficientes da camada correspondente
#  em cada elemento, cada linha é referente a uma entrada,
#                    cada coluna é referente a um neurônio da camada

# visualizar o número de iterações rodadas
print("Number of iterations: %d" %clf.n_iter_)

#for i,x in enumerate(X):
#    print("Input: %s \t Output: %s" %(x,clf.predict([x])[0]))