iris.py

import keras
import sklearn
import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
from sklearn.metrics import f1_score
from keras.utils import to_categorical
from keras.layers import Dense,  Activation
from keras.models import Sequential, Model

iris_X, iris_y = datasets.load_iris(return_X_y=True)
iris_X = preprocessing.scale(iris_X)
iris_y = to_categorical(iris_y)

train_X, test_X, train_y, test_y = train_test_split(iris_X, iris_y, test_size=0.25)
train_X, valid_X, train_y, valid_y = train_test_split(iris_X, iris_y, test_size=0.2)

model = Sequential()
model.add(Dense(10, input_dim=4, activation='relu'))
model.add(Dense(3, activation='softmax'))

model.compile(loss="binary_crossentropy", optimizer="adam", metrics=['accuracy'])

model.fit(train_X, train_y, epochs=30, batch_size=1, validation_data=(valid_X, valid_y))
pred_y = model.predict(test_X)
print(f1_score(np.argmax(test_y, 1), np.argmax(pred_y, 1), average='macro'))