Update train.py

train.py

@@ -6,6 +6,7 @@ from keras.layers import Embedding, Dense, Dropout, Flatten, PReLU
 from keras.preprocessing.text import Tokenizer
 from keras_self_attention import SeqSelfAttention, SeqWeightedAttention
 
+
 with open("dataset.json", "r") as f: # TODO: move the outputs into a separate file, so it would be "key": 0, "key2": 1 etc
     dset = json.load(f)
 
@@ -28,4 +29,25 @@ model.add(Dense(512, activation="relu"))
 model.add(Dense(256, activation="relu"))
 model.add(Dense(dset_size, activation="linear")) # TBH it doesn't matter that much what activation function to use, just linear does nothing at all to the output, that might be something like softmax but i'll test that later
 
-model.save("chatbot.keras") # It's obvious what it does, saves the model to a file
+X = [] # we're loading the training data into input X
+y = [] # and output y
+
+for line, key in enumerate(dset):
+    tokens = tokenizer.tokenize(key)
+    X.append(numpy.array((list(tokens)+[0,]*inp_len)[:inp_len])) # refusing to use pad_sequences for an unspecified reason and creating the worst line of code
+    output_array = np.zeros(dset_size)
+    output_array[line] = 1 # 0 0 0 1 0 0 0 0 0, the neuron of the each line activates in the correct response
+    y.append(output_array)
+
+X = np.array(X) # normal lists are way slower than numpy arrays (remember, a list and an array is not the same thing, an array is far more limited)
+y = np.array(y) # that's why keras supports only numpy arrays ^
+
+model.compile(optimizer=Adam(), loss="mse", metrics=["accuracy",]) # kind of like settings for the training
+# TODO: change the loss
+
+model.fit(X, y, epochs=10, batch_size=8) # training the model, epochs means how many times does it have to read the data, batch_size is an optimization to train on multiple messages at the same time. Loss and accuracy are the opposite things, loss is how far the output is from a correct one, from 1 to 0, and accuracy how often does the model get the answer right, from 0 to 1.
+# Use   workers=4, use_multiprocessing=True)   if you don't have a GPU
+
+model.summary() # just for you to see info about the model, useful because you can check the parameter count
+
+model.save("chatbot.keras")