top of page
Search
Writer's picturethe unknown designer

Natural Language Processing NLP tutorials/take aways

Below is an overview of the 5 steps in the neural network model life-cycle in Keras:

1. Define Network.

2. Compile Network.

3. Fit Network. 4. Evaluate Network.

5. Make Predictions.

The most common optimization algorithm is stochastic gradient descent, but Keras also supports a suite of other state-of-the-art optimization algorithms that work well with little or no configuration. Perhaps the most commonly used optimization algorithms because of their generally better performance are:􏰀 Stochastic Gradient Descent, or sgd, that requires the tuning of a learning rate and momentum.􏰀 Adam, or adam, that requires the tuning of learning rate.􏰀 RMSprop, or rmsprop, that requires the tuning of learning rate.


Cleaning TEXT


You cannot go straight from raw text to fitting a machine learning or deep learning model. You must clean your text first, which means splitting it into words and handling punctuation and case.

Some kaftka cleaned.


['One', 'morning,', 'when', 'Gregor', 'Samsa', 'woke', 'from', 'troubled', 'dreams,', 'he', 'found', 'himself', 'transformed', 'in', 'his', 'bed', 'into', 'a', 'horrible', 'vermin.', 'He', 'lay', 'on', 'his', 'armour-like', 'back,', 'and', 'if', 'he', 'lifted', 'his', 'head', 'a', 'little', 'he', 'could', 'see', 'his', 'brown', 'belly,', 'slightly', 'domed', 'and', 'divided', 'by', 'arches', 'into', 'stiff', 'sections.', 'The', 'bedding', 'was', 'hardly', 'able', 'to', 'cover', 'it', 'and', 'seemed', 'ready', 'to', 'slide', 'off', 'any', 'moment.', 'His', 'many', 'legs,', 'pitifully', 'thin', 'compared', 'with', 'the', 'size', 'of', 'the', 'rest', 'of', 'him,', 'waved', 'about', 'helplessly', 'as', 'he', 'looked.', '"What\'s', 'happened', 'to', 'me?"', 'he', 'thought.', 'It', "wasn't", 'a', 'dream.', 'His', 'room,', 'a', 'proper', 'human']


now all lowercase


['one', 'morning,', 'when', 'gregor', 'samsa', 'woke', 'from', 'troubled', 'dreams,', 'he', 'found', 'himself', 'transformed', 'in', 'his', 'bed', 'into', 'a', 'horrible', 'vermin.', 'he', 'lay', 'on', 'his', 'armour-like', 'back,', 'and', 'if', 'he', 'lifted', 'his', 'head', 'a', 'little', 'he', 'could', 'see', 'his', 'brown', 'belly,', 'slightly', 'domed', 'and', 'divided', 'by', 'arches', 'into', 'stiff', 'sections.', 'the', 'bedding', 'was', 'hardly', 'able', 'to', 'cover', 'it', 'and', 'seemed', 'ready', 'to', 'slide', 'off', 'any', 'moment.', 'his', 'many', 'legs,', 'pitifully', 'thin', 'compared', 'with', 'the', 'size', 'of', 'the', 'rest', 'of', 'him,', 'waved', 'about', 'helplessly', 'as', 'he', 'looked.', '"what\'s', 'happened', 'to', 'me?"', 'he', 'thought.', 'it', "wasn't", 'a', 'dream.', 'his', 'room,', 'a', 'proper', 'human']


The Natural Language Toolkit, or NLTK for short, is a Python library written for working and modeling text-up next

3 views0 comments

Recent Posts

See All

troubles

Comments


bottom of page