While working on modeling, should you split the data? If yes, in how many splits and in what proportions?

When working on modeling, it is generally recommended to split the data into training and testing sets. This allows you to evaluate the performance of your model on unseen data and helps to prevent overfitting.

The most common approach is to split the data into two sets: a training set and a testing set. The training set is used to train the model, while the testing set is used to evaluate its performance.

The proportion in which you split the data depends on the size of your dataset. A common practice is to use a 70-30 or 80-20 split, where 70% or 80% of the data is used for training and the remaining 30% or 20% is used for testing.

However, in some cases, especially when dealing with limited data, a more advanced technique called cross-validation can be used. Cross-validation involves splitting the data into multiple subsets, or folds, and training and testing the model on different combinations of these folds. This helps to provide a more robust evaluation of the model's performance.

The choice of the number of splits in cross-validation depends on the size of your dataset and the computational resources available. Common choices include 5-fold or 10-fold cross-validation, where the data is split into 5 or 10 equal-sized folds, respectively.

In summary, it is generally recommended to split the data into training and testing sets when working on modeling. The proportion of the split can be determined based on the size of your dataset, and in some cases, cross-validation can be used for a more robust evaluation.