Our goal is to predict whether or not a person gave a 5- or 1-star review based on the words they used in the review. Let’s set a baseline with logistic regression and see how well we can predict this binary category:from sklearn.linear_model import LogisticRegression lr = LogisticRegression()X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=100) […]
Put another way, the COD states that as we increase the number of feature columns, we need exponentially more data to maintain the same level of model performance. This is because, in high-dimensional spaces, even the nearest neighbors can be very far away from a given data point, making it difficult to create good predictions. […]
Feature extraction and PCA A common problem when working with data, particularly when it comes to ML, is having an overwhelming number of columns and not enough rows to handle such a quantity of columns. A great example of this is when we were looking at the send cash now example in our naïve Bayes […]
