# GRADED FUNCTION: predict

def predict$($sentence$,$ model, sentence$\_$vectorizer, tag$\_$map$)$:

$"""$

Predict NER labels for a given sentence using a trained model.

Parameters:

sentence $($str$)$: Input sentence.

model $($tf$.$keras.Model$)$: Trained NER model.

sentence$\_$vectorizer $($tf$.$keras.layers.TextVectorization$)$: Sentence vectorization layer.

tag$\_$map $($dict$)$: Dictionary mapping tag IDs to labels.

Returns:

predictions $($list$)$: Predicted NER labels for the sentence.

$"""$

### START CODE HERE ###

# Convert the sentence into ids

sentence$\_$vectorized $=$ None

# Expand its dimension to make it appropriate to pass to the model

sentence$\_$vectorized $=$ tf$.$expand$\_$dims$($None$,$ None$)$

# Get the model output

output $=$ None

# Get the predicted labels for each token, using argmax function and specifying the correct axis to perform the argmax

outputs $=$ np$.$argmax$($None$,$ axis $=$ None$)$

# Next line is just to adjust outputs dimension. Since this function expects only one input to get a prediction, outputs will be something like $[[1,2,3]]$

# so to avoid heavy notation below, let's transform it into $[1,2,3]$

outputs $=$ outputs$[0]$

# Get a list of all keys, remember that the tag$\_$map was built in a way that each label id matches its index in a list

labels $=$ list$($tag$\_$map.keys$())$

pred $=[]$

# Iterating over every predicted token in outputs list

for tag$\_$idx in None

pred$\_$label $=$ None

pred.append$($None$)$

### END CODE HERE ###

return pred