Using LSTMs Is Easy
Make your model understand text just as you would read it -- by learning the sequence of words
We build a Fake News Detection model using Spacy and Keras LSTM.
classification
Text Classification Using Keras LSTM, CNN and embeddings
A no-fuss pipeline for binary or multiclass text classification
Exploiting the temporal and spatial aspects of text for classification is easy.
Regressor as Classifier
... it works better than you think.
A classifier predicts a categorical target variable while a regressor predicts a continuous response variable. Can we fit a regressor as a classifier? Let’s find out.
Are Outliers Always a Problem?
no...sometimes we need to treat them with respect
Outliers are mostly seen as not needed. We will see an example where this is not true.
Calibrate Your Classifier
you might wonder how you were doing without it all along
Would you buy oranges weighed on an uncalibrated weighing scale? Then why would you trust an uncalibrated classifier?
Roc Curve Step by Step
...with precision-recall curve thrown in
The ROC curve is an important metric to compare classifiers. Learn how to draw one step-by-step.
Learning Curve
Imagine you have four classifiers with similar accuracies. Are they really similar? Plotting a learning curve might reveal a hidden side to these classifiers.
Understand the Confusion Matrix
Blow away the confusion
You’ve created a classification model and come across a new concept called confusion matrix. However tough it may seem, a classification model evaluation is not complete unless you add in your confusion matrix.
The Validation Curve
Tells you where to get off
Sometimes, you need to know when to stop training your model; this curve helps you decide. Let us see the validation curve applied to an Adaboost classifier use case.
Likelihood ratio: keeping your classifier honest
Is a respectable accuracy score enough?
Imagine training a classifier on a dataset only to find your friend is almost as good guessing at the target label, that too without looking at the data. Is your classifier any good then?