# -*- coding: utf-8 -*-
"""chatgpt-alphabet.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1BFy2tYkYPr7mev8Gg9AMT8ZD_Nj0hH3U
"""

# !pip install tensorflow

import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense, Embedding

alphabet = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"

# Convert alphabet to integers
char_to_int = dict((c, i) for i, c in enumerate(alphabet))
int_to_char = dict((i, c) for i, c in enumerate(alphabet))

# Prepare dataset
seq_length = 1
dataX = []
dataY = []
for i in range(0, len(alphabet) - seq_length, 1):
    seq_in = alphabet[i:i + seq_length]
    seq_out = alphabet[i + seq_length]
    dataX.append([char_to_int[char] for char in seq_in])
    dataY.append(char_to_int[seq_out])

X = np.reshape(dataX, (len(dataX), seq_length, 1))
y = tf.keras.utils.to_categorical(dataY)

model = Sequential()
model.add(LSTM(32, input_shape=(X.shape[1], X.shape[2])))
model.add(Dense(y.shape[1], activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam')

model.fit(X, y, epochs=500, batch_size=1, verbose=2)

for pattern in dataX:
    x = np.reshape(pattern, (1, len(pattern), 1))
    prediction = model.predict(x, verbose=0)
    index = np.argmax(prediction)
    result = int_to_char[index]
    seq_in = [int_to_char[value] for value in pattern]
    print(seq_in, "->", result)

model.save('alphabet_model.h5')
from google.colab import files
files.download('alphabet_model.h5')