0

I am using keras model.predict after training my model for a sentence classification task. My code is

import numpy as np model = Sequential() l = ['Hello this is police department', 'hello this is 911 emergency'] tokenizer = Tokenizer() tokenizer.fit_on_texts(l) X = tokenizer.texts_to_sequences(l) X = np.array(X) a = model.predict(X) print(a)

But the output seems to be an array,

[[1. 2. 3. 4. 5.] [1. 2. 3. 6. 7.]]

I am working on a sentence classification task with 2 labels. So I wanted to predict these sentences as 0 or 1. But instead getting a numpy array. How do I code such that it predicts one of these two labels?

Improve this question

1 Answer 1

Reset to default
1

add some layer to your model. to get probabilities in [0,1] use sigmoid as last activation

from sklearn.preprocessing import LabelEncoder maxlen = 10 X_train = ['Hello this is police department', 'hello this is 911 emergency', 'asdsa sadasd', 'asnxas asxkx', 'kas', 'jwxxxx'] y_train = ['positive','negative','positive','negative','positive','negative'] label_enc = LabelEncoder() label_enc.fit(y_train) tokenizer = tf.keras.preprocessing.text.Tokenizer() tokenizer.fit_on_texts(X_train) X_train = tokenizer.texts_to_sequences(X_train) X_train = tf.keras.preprocessing.sequence.pad_sequences(X_train, maxlen=maxlen) y_train = label_enc.transform(y_train) model = Sequential() model.add(Dense(1, activation='sigmoid', input_shape=(maxlen,))) model.compile('adam', 'binary_crossentropy') model.fit(X_train,y_train, epochs=3) ### PREDICT NEW UNSEEN DATA ### X_test = ['hello hSDAS', '911 oaoad'] X_test = tokenizer.texts_to_sequences(X_test) X_test = tf.keras.preprocessing.sequence.pad_sequences(X_test, maxlen=maxlen) a = (model.predict(X_test)>0.5).astype(int).ravel() print(a) reverse_pred = label_enc.inverse_transform(a.ravel()) print(reverse_pred)
Improve this answer
Sign up to request clarification or add additional context in comments.

4 Comments

It is working, But suppose, I have emotion classification task and I want to rate it as 0 for negative and 1 for positive. How should I use the training/testing model so that it predicts according to that. Here in your example, it is just predicting 0 or 1 based on probabilities.
you can map 0 as nevative and 1 as positive. is this what u mean?
No no, see here in our example, we are predicting without any prior training/testing. So this is just plain prediction. What if I want to predict based on my trained sentences. Like in training I have trained my data and now I want to use that to predict newer sentences which are not in the dataset.
after fitting on train u have to use the same fitted model to do predictions. remember to operate the same preprocessing. I edited it with an example. don't forget to upvote and accept as answer ;-)

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.