Building Pipelines with scikit-learn
When you build machine learning solutions, you often repeat the same steps: data preprocessing, feature engineering, model training, and evaluation. Writing these steps separately can lead to code duplication and make it hard to reproduce results. scikit-learn provides the Pipeline class, which lets you chain preprocessing and modeling steps together into a single, streamlined workflow. This approach makes your code cleaner, more maintainable, and easier to reproduce.
A pipeline standardizes the ML workflow and reduces code duplication.
12345678910111213141516171819202122232425262728import pandas as pd from sklearn.datasets import load_iris from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.linear_model import LogisticRegression from sklearn.pipeline import Pipeline # Load sample data iris = load_iris() X = pd.DataFrame(iris.data, columns=iris.feature_names) y = iris.target # Split data X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42) # Create a pipeline with preprocessing and modeling steps pipeline = Pipeline([ ("scaler", StandardScaler()), # Step 1: Standardize features ("classifier", LogisticRegression()) # Step 2: Train classifier ]) # Fit the pipeline on training data pipeline.fit(X_train, y_train) # Predict on test data predictions = pipeline.predict(X_test) print("Pipeline accuracy:", pipeline.score(X_test, y_test))
Thanks for your feedback!
Ask AI
Ask AI
Ask anything or try one of the suggested questions to begin our chat
Awesome!
Completion rate improved to 6.67Building Pipelines with scikit-learn
Swipe to show menu
When you build machine learning solutions, you often repeat the same steps: data preprocessing, feature engineering, model training, and evaluation. Writing these steps separately can lead to code duplication and make it hard to reproduce results. scikit-learn provides the Pipeline class, which lets you chain preprocessing and modeling steps together into a single, streamlined workflow. This approach makes your code cleaner, more maintainable, and easier to reproduce.
A pipeline standardizes the ML workflow and reduces code duplication.
12345678910111213141516171819202122232425262728import pandas as pd from sklearn.datasets import load_iris from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.linear_model import LogisticRegression from sklearn.pipeline import Pipeline # Load sample data iris = load_iris() X = pd.DataFrame(iris.data, columns=iris.feature_names) y = iris.target # Split data X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42) # Create a pipeline with preprocessing and modeling steps pipeline = Pipeline([ ("scaler", StandardScaler()), # Step 1: Standardize features ("classifier", LogisticRegression()) # Step 2: Train classifier ]) # Fit the pipeline on training data pipeline.fit(X_train, y_train) # Predict on test data predictions = pipeline.predict(X_test) print("Pipeline accuracy:", pipeline.score(X_test, y_test))
Thanks for your feedback!
