Htydjtk

I'm trying to do task for system calls classification. The code bellow is inspired from a text classification project. My system calls are represented as sequences of integers between 1 and 340. The error I got is:

valueError: input arrays should have the same number of samples as target arrays. Find 1 input samples and 0 target samples. I don't know what to do as it's my first time Thank you in advance

`

   df = pd.read_csv("data.txt") 

   df_test = pd.read_csv("validation.txt")

   #split arrays into train and test data (cross validation)

    train_text, test_text, train_y, test_y = 

   train_test_split(df,df,test_size = 0.2)

   MAX_NB_WORDS = 5700



   # get the raw text data

   texts_train = train_text.astype(str)

   texts_test = test_text.astype(str)

   # finally, vectorize the text samples into a 2D integer tensor

   tokenizer = Tokenizer(nb_words=MAX_NB_WORDS, char_level=False)

   tokenizer.fit_on_texts(texts_train)

   sequences = tokenizer.texts_to_sequences(texts_train)

   sequences_test = tokenizer.texts_to_sequences(texts_test)



   word_index = tokenizer.word_index

   type(tokenizer.word_index), len(tokenizer.word_index)

   index_to_word = dict((i, w) for w, i in tokenizer.word_index.items()) 

    " ".join([index_to_word[i] for i in sequences[0]])

    seq_lens = [len(s) for s in sequences]



    MAX_SEQUENCE_LENGTH = 100

    # pad sequences with 0s

    x_train = pad_sequences(sequences, maxlen=MAX_SEQUENCE_LENGTH) 

    x_test = pad_sequences(sequences_test, maxlen=MAX_SEQUENCE_LENGTH)

    #print('Shape of data train:', x_train.shape)  #cela a donnée (1,100)

    #print('Shape of data test tensor:', x_test.shape)

    y_train = train_y

    y_test = test_y

    print('Shape of label tensor:', y_train.shape)

    EMBEDDING_DIM = 32

    N_CLASSES = 2



    y_train = keras.utils.to_categorical( y_train , N_CLASSES )

    sequence_input = Input(shape=(MAX_SEQUENCE_LENGTH,), dtype='float32')



    embedding_layer = Embedding(MAX_NB_WORDS, EMBEDDING_DIM,

                    input_length=MAX_SEQUENCE_LENGTH,

                    trainable=True)

    embedded_sequences = embedding_layer(sequence_input)



    average = GlobalAveragePooling1D()(embedded_sequences)

    predictions = Dense(N_CLASSES, activation='softmax')(average)



    model = Model(sequence_input, predictions)

    model.compile(loss='categorical_crossentropy',

      optimizer='adam', metrics=['acc'])

    model.fit(x_train, y_train, validation_split=0.1,

    nb_epoch=10, batch_size=1)

    output_test = model.predict(x_test)

    print("test auc:", roc_auc_score(y_test,output_test[:,1]))

`