import numpy as np
import tensorflow
from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation
from tensorflow.keras.layers import Conv2D, MaxPooling2D
from tensorflow.keras.preprocessing.text import Tokenizer

# words
pizza = [1,0,0,0,0,0]
taco  = [0,1,0,0,0,0]
sushi = [0,0,1,0,0,0]

car   = [0,0,0,1,0,0]
bike  = [0,0,0,0,1,0]
truck = [0,0,0,0,0,1]

#Training data
sentence1 = "I like pizza, taco and sushi"
classonevalues = [pizza,taco,sushi]

sentence2 = "I have a car, bike and a truck"
classtwovalues = [car,bike,truck]

x_train = np.array(classonevalues+classtwovalues)
y_train = np.array([[1,0],[1,0],[1,0],[0,1],[0,1],[0,1]])
print(x_train)
print(y_train)

max_words = 6
num_classes = 2
batch_size = 1
epochs = 5

#Model

model = Sequential()
model.add(Dense(256, input_shape=(max_words,)))
model.add(Activation('relu'))
model.add(Dense(2))
model.add(Activation('softmax'))

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

model.fit(x_train, y_train,
                    batch_size=batch_size,
                    epochs=epochs,
                    verbose=1,
                    validation_split=0)


sentence_test1 = "I like pizza, taco and sushi"
sentence_test1_vector = [1,1,1,0,0,0]
sentence_test2 = "I have a car, bike and a truck"
sentence_test2_vector = [0,0,0,1,1,1]


def classify(vector):
    aindex = np.argmax(model.predict(np.array([vector])))
    if(aindex==0):
        print("Food")
    else:
        print("Cars")


classify(sentence_test1_vector)
classify(sentence_test2_vector)