import tensorflow as tf
import numpy as np
from tensorflow.keras.layers import Embedding, LSTM, Dense, Dropout
from tensorflow.keras.models import Sequential
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflowjs import converters

# Load your text data
text_data = "I am a chicken nugget that likes food and I ate a monkey yesterday, it was actually pretty good and I enjoyed it a lot, hey speaking of that, how is your new iPhone 11 going, I hope it is well"

# Tokenization and sequence generation
tokenizer = Tokenizer(char_level=True, lower=True)
tokenizer.fit_on_texts([text_data])
sequences = tokenizer.texts_to_sequences([text_data])[0]

# Prepare input and output sequences
sequence_length = 100
input_sequences = []
output_sequences = []

for i in range(len(sequences) - sequence_length):
  input_sequences.append(sequences[i:i + sequence_length])
  output_sequences.append(sequences[i + sequence_length])

input_sequences = np.array(pad_sequences(input_sequences, maxlen=sequence_length, padding="post"))
output_sequences = np.array(output_sequences)

# Define the model using the Sequential API
vocab_size = len(tokenizer.word_index) + 1

model = Sequential([
  Embedding(vocab_size, 16, input_shape=(sequence_length,), name='embedding_layer'),
  LSTM(128, dropout=0.2, recurrent_dropout=0.2, name='lstm_layer'),
  Dense(vocab_size, activation="softmax", name='dense_layer')
])

model.compile(loss="sparse_categorical_crossentropy", optimizer="adam", metrics=["accuracy"])
model.summary()

# Training the model
epochs = 80
batch_size = 128
model.fit(input_sequences, output_sequences, epochs=epochs, batch_size=batch_size)

# Convert the model to TensorFlow.js format
converters.save_keras_model(model, 'tfjs_model')

# Create a reverse word index
reverse_word_index = dict([(value, key) for (key, value) in tokenizer.word_index.items()])

# Function to generate text
def generate_text(seed_text, model, tokenizer, sequence_length, num_chars_to_generate):
  generated_text = seed_text

  for _ in range(num_chars_to_generate):
    token_list = tokenizer.texts_to_sequences([generated_text])[0]
    token_list = pad_sequences([token_list], maxlen=sequence_length, padding="pre")
    predicted_probs = model.predict(token_list, verbose=0)
    predicted_token = np.argmax(predicted_probs, axis=-1)[0]

    output_char = reverse_word_index.get(predicted_token, '')
    generated_text += output_char

  return generated_text

# Generate text
seed_text = "What is a nugget?"
generated_text = generate_text(seed_text, model, tokenizer, sequence_length, 800)
print(generated_text)

/usr/bin/python /home/meoof2010/interact.py
2024-04-16 02:05:40.812208: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
2024-04-16 02:05:40.818757: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
2024-04-16 02:05:40.893898: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-04-16 02:05:42.141769: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
/usr/local/lib/python3.9/dist-packages/keras/src/layers/core/embedding.py:81: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.
  super().__init__(**kwargs)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
│ embedding_layer (Embedding)          │ (None, 100, 16)             │             400 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ lstm_layer (LSTM)                    │ (None, 128)                 │          74,240 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_layer (Dense)                  │ (None, 25)                  │           3,225 │
└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘
 Total params: 77,865 (304.16 KB)
 Trainable params: 77,865 (304.16 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/10
1/1 ━━━━━━━━━━━━━━━━━━━━ 2s 2s/step - accuracy: 0.0543 - loss: 3.2190
Epoch 2/10
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 239ms/step - accuracy: 0.2174 - loss: 3.2131
Epoch 3/10
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 293ms/step - accuracy: 0.2174 - loss: 3.2067
Epoch 4/10
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 308ms/step - accuracy: 0.2174 - loss: 3.1991
Epoch 5/10
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 303ms/step - accuracy: 0.2174 - loss: 3.1888
Epoch 6/10
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 160ms/step - accuracy: 0.2174 - loss: 3.1726
Epoch 7/10
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 310ms/step - accuracy: 0.2174 - loss: 3.1477
Epoch 8/10
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 304ms/step - accuracy: 0.2174 - loss: 3.0994
Epoch 9/10
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 298ms/step - accuracy: 0.2174 - loss: 3.0179
Epoch 10/10
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 303ms/step - accuracy: 0.2174 - loss: 2.8978
WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. 
failed to lookup keras version from the file,
    this is likely a weight only file
Traceback (most recent call last):
  File "/home/meoof2010/interact.py", line 47, in <module>
    converters.save_keras_model(model, 'tfjs_model')
  File "/usr/local/lib/python3.9/dist-packages/tensorflowjs/converters/keras_h5_conversion.py", line 467, in save_keras_model
    write_artifacts(
  File "/usr/local/lib/python3.9/dist-packages/tensorflowjs/converters/keras_h5_conversion.py", line 418, in write_artifacts
    weights_manifest = write_weights.write_weights(
  File "/usr/local/lib/python3.9/dist-packages/tensorflowjs/write_weights.py", line 118, in write_weights
    _assert_no_duplicate_weight_names(weight_groups)
  File "/usr/local/lib/python3.9/dist-packages/tensorflowjs/write_weights.py", line 346, in _assert_no_duplicate_weight_names
    raise Exception(
Exception: Error dumping weights, duplicate weight name kernel