Multi-class Text Classification using Tensorflow - Imbalanced dataset

#datascience #textclassification #nlp

In this video we will create an end to end NLP pipeline starting from cleaning text data, setting NLP pipeline, model selection, model evaluation, handling imbalanced dataset among others

In next set of videos we will use complex models to see how we can improve the performance of this model

[AIEngineeringLife]

If you want to add a LSTM layer instead of regular ANN you can use this as model and change the layer size of info

model = tf.keras.Sequential()
model.add(hub_layer)
target_shape=(128, 1 ) ))
model.add(tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32, return_sequences=True)))

for units in [128, 64 ]:
model.add(tf.keras.layers.Dense(units, activation='relu'))

model.add(tf.keras.layers.Dense(6, activation='softmax'))

model.summary()

[ijeffking]

This is am indebted to you in terms of gratitude. Appreciate your efforts !

[faraza]

Awesome tutorial!! Really appreciate the hard work you put into making this tutorial

[vijaykarthikeyan]

Such a nice video. Very well explained bro!!

[rohansohani]

Hi, Thanks for all your contents and knowledge sharing. very informative.

[madhavimehta]

Indeed the right one for me to work . Thanks a ton for making such vedios

[ajithshenoy]

Thanks a ton . Please conclude this series by industrial deployment demo.

[bigbena]

Hi - great video.
Any chance you can share the Jupyter notebook file?
Also - assuming I'm having a (relatively) small dataset (~17000 samples) can I still use this aproach?

[ashwinideshmukh]

sir your video has been great for me. sir I have one question now that model is trained i want to pass a real data and check for output please can you tell me the code for it. As we have taken tarain_data_f and not just x_train how to write code for model checking. sir plz waiting for a reply.

[Dirkster___]

Can I also pass in a string tensor:
<tf.Tensor: shape=(), dtype=string, numpy=b"The ..."> object when using a GloVe embedding layer or is the ability to consume strings directly (without tokenizer) a special feature of the hub embedding layer?

Is there a reference documentation for this direct way of consuming text without having to tokenize it first?

[ahanchatterjee]

@
AIEngineering

getting this error while running show batch: TypeError: Signature mismatch. Keys must be dtype <dtype: 'string'>, got <dtype: 'int64'>.
Can you pls solve this.

[ariouathanane]

Hello, thank you very much for your video. But i have a question if you can help me. how to do with multiple text features and one output label please?

[iqrayousaf]

Can you share the code how use CNN instead of regular NN, Like you LSTM model code.

[devarshraval]

Where do i find syntax to convert an imported tf dataset from slices into a list of text to tokenize it? In your From Scratch video, you tokenized a tfds in built dataset but how to tokenize custom imported dataset like in this video? I could not find it in the docs.

[madhavimehta]

Can u make vedios for keyword extraction which makes much meaningful 3 grams keyphrases?

[srikanth]

Thanks a lot. Great Explanation. Could you share the notebook and dataset link

[adwaitanand]

Very nice video just a doubt... what should be the code if we want to test a single complaint and get its a function where we pass a single complaint string and it returns the product/label

[Reddie]

I'm missing how to tokenize and embedding since I was doing it in a spanish dataset and I can't use the google reviews dataset...

[ahmedfahmyaee]

I need input_shape to pass to build() function to build this model when using LSTM model what is input_shape?

[dipinpaul]

Excellent!
Can you share the guthub code path?