pip install 'numpy   <hr><h2>         ii - 创建数据集 </h2>  <p>您需要创建一个数据<a style="color:#f60; text-decoration:underline;" href="https://www.php.cn/zt/52359.html" target="_blank">字符串数组</a>来计算一个小数据集，例如我创建：</p>  <pre class="brush:php;toolbar:false">  data = [     "salut comment ca va",     "je suis en train de coder",     "le machine learning est une branche de l'intelligence artificielle",     "le deep learning est une branche du machine learning", ]   

  class llm:      def __init__(self):         self.model = none         self.max_sequence_length = none         self.input_sequences = none         self.total_words = none         self.tokenizer = none         self.tokenize()         self.create_input_sequences()         self.create_model()         self.train()         test_sentence = "pour moi le machine learning est"         print(self.test(test_sentence, 10))      def tokenize(self):         self.tokenizer = tokenizer()         self.tokenizer.fit_on_texts(data)         self.total_words = len(self.tokenizer.word_index) + 1      def create_input_sequences(self):         self.input_sequences = []         for line in data:             token_list = self.tokenizer.texts_to_sequences([line])[0]             for i in range(1, len(token_list)):                 n_gram_sequence = token_list[:i + 1]                 self.input_sequences.append(n_gram_sequence)          self.max_sequence_length = max([len(x) for x in self.input_sequences])         self.input_sequences = pad_sequences(self.input_sequences, maxlen=self.max_sequence_length, padding='pre')      def create_model(self):         self.model = sequential()         self.model.add(embedding(self.total_words, 100, input_length=self.max_sequence_length - 1))         self.model.add(lstm(150, return_sequences=true))         self.model.add(dropout(0.2))         self.model.add(lstm(100))         self.model.add(dense(self.total_words, activation='softmax'))      def train(self):         self.model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])          x, y = self.input_sequences[:, :-1], self.input_sequences[:, -1]         y = tf.keras.utils.to_categorical(y, num_classes=self.total_words)          self.model.fit(x, y, epochs=200, verbose=1)   

      def test(self, sentence: str, nb_word_to_generate: int):         last_word = ""         for _ in range(nb_word_to_generate):              token_list = self.tokenizer.texts_to_sequences([sentence])[0]             token_list = pad_sequences([token_list], maxlen=self.max_sequence_length - 1, padding='pre')             predicted = np.argmax(self.model.predict(token_list), axis=-1)             output_word = ""             for word, index in self.tokenizer.word_index.items():                 if index == predicted:                     output_word = word                     break              if last_word == output_word:                 return sentence              sentence += " " + output_word             last_word = output_word          return sentence