Splitting Data into Train and Test Sets

Once the data has been explored, it needs to be split into two parts: one for training the model and one for testing how well it performs on unseen data.

from sklearn.model_selection import train_test_split

X = df.drop("species", axis=1)
y = df["species"]

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

Code Explanation

• X = df.drop("species", axis=1) separates the feature columns from the target column, keeping only the measurements.
• y = df["species"] stores just the species labels separately, since this is what the model needs to predict.
• test_size=0.2 reserves 20% of the data for testing, keeping the remaining 80%  for training.
• random_state=42 ensures the same split happens every time the code runs, keeping results consistent.

After this step is done, you will have four separate variables, X_train and y_train for training the model, and X_test and y_test for evaluating it later. Once this split is ready, the next lesson moves on to actually building the model.