final4_swahili.py

# -*- coding: utf-8 -*-
"""final4_swahili.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1qN1KWrh24ZCv-v5j3fMaPrB00if-O7BY

Referred from https://keras.io/examples/generative/lstm_character_level_text_generation/
"""

import tensorflow
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.layers import Embedding, LSTM, Dense
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.callbacks import EarlyStopping
from tensorflow.keras.models import Sequential
import tensorflow.keras.utils as ku 
import numpy as np

path = "/content/sw-train.txt"
file_content = open(path, "r")
Content = file_content.read()
data = Content[0:4000000]

text= data
len(text)

characters = sorted(list(set(text)))
print("Total characters:", len(characters))

char_indices = dict((c, i) for i, c in enumerate(characters))
indices_char = dict((i, c) for i, c in enumerate(characters))

# cut the text in semi-redundant sequences of maxlen characters
maxlen = 40
step = 3
sentences = []
next_chars = []
for i in range(0, len(text) - maxlen, step):
    sentences.append(text[i : i + maxlen])
    next_chars.append(text[i + maxlen])
print("Number of sequences:", len(sentences))

x = np.zeros((len(sentences), maxlen, len(characters)), dtype=np.bool)
y = np.zeros((len(sentences), len(characters)), dtype=np.bool)
for i, sentence in enumerate(sentences):
    for t, char in enumerate(sentence):
        x[i, t, char_indices[char]] = 1
    y[i, char_indices[next_chars[i]]] = 1

model = tensorflow.keras.Sequential(
    [
        tensorflow.keras.Input(shape=(maxlen, len(characters))),
        tensorflow.keras.layers.LSTM(128,return_sequences=True),
        tensorflow.keras.layers.Dropout(0.3),
        tensorflow.keras.layers.LSTM(128,return_sequences=True),
        tensorflow.keras.layers.Dropout(0.3),
        tensorflow.keras.layers.LSTM(128),
        tensorflow.keras.layers.Dense(len(characters), activation="softmax"),
    ]
)
model.compile(loss="categorical_crossentropy", optimizer='adam')

model.summary()

import random
def sample(preds, temperature=1.0):
    # helper function to sample an index from a probability array
    preds = np.asarray(preds).astype("float64")
    preds = np.log(preds) / temperature
    exp_preds = np.exp(preds)
    preds = exp_preds / np.sum(exp_preds)
    probas = np.random.multinomial(1, preds, 1)
    return np.argmax(probas)

epochs = 40
batch_size = 4096

for epoch in range(epochs):
    model.fit(x, y, batch_size=batch_size, epochs=1)
    print()
    print("Generating text after epoch: %d" % epoch)
    import random

    start_index = random.randint(0, len(text) - maxlen - 1)
    for diversity in [0.2, 0.5]:
        print("...Diversity:", diversity)

        generated = ""
        sentence = text[start_index : start_index + maxlen]
        print('...Generating with seed: "' + sentence + '"')

        for i in range(400):
            x_pred = np.zeros((1, maxlen, len(characters)))
            for t, char in enumerate(sentence):
                x_pred[0, t, char_indices[char]] = 1.0
            preds = model.predict(x_pred, verbose=0)[0]
            next_index = sample(preds, diversity)
            next_char = indices_char[next_index]
            sentence = sentence[1:] + next_char
            generated += next_char

        print("...Generated: ", generated)
        print()

from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.1, random_state = 42)

y_pred = model.predict(X_test)

for y in y_pred:
  for ind, val in enumerate(y):
    if val == max(y):
      y[ind] = 1
    else:
      y[ind] = 0

print(accuracy_score(y_test,y_pred))