Machine Learning Pipelines in Scikit-learn
[markdown] content available only on the platform
[markdown] content available only on the platform
Flashcards · Machine Learning Pipelines in Scikit-learn
Pipeline — scikit-learn object that chains preprocessing steps and a final model so they are fitted and applied in the correct order.
Pipeline([("scaler", StandardScaler()), ("model", RandomForestClassifier())])
pipe.fit() — Fits every preprocessing step on the training data, transforms it, then trains the final model.
pipe.fit(x_train, y_train)
pipe.predict() — Transforms new data with the already-fitted steps, then makes predictions; nothing is refitted.
y_pred = pipe.predict(x_test)
cross_val_score() — Evaluates a model on several train/validation folds and returns one score per fold.
cross_val_score(pipe, x_train, y_train, cv=5)
ColumnTransformer — Applies different transformers to different groups of columns and joins the results.
("num", StandardScaler(), ["age", "income"])
handle_unknown="ignore" — OneHotEncoder option that outputs all zeros for unseen categories instead of raising an error.
OneHotEncoder(handle_unknown="ignore")
Silent data leakage — Test or validation information influencing preprocessing with no error shown, so scores look better than reality.
Scaling the whole training set before cross-validation.
Fold — One of the parts the training data is split into during cross-validation.
cv=5 creates five folds.
