Q1. Scenario: You need to build a machine learning model to predict house prices based on features like area, bedrooms. Which Python library would you use? What submodule contains regression models?
Scikit-learn (sklearn) is the go-to library. For regression: from sklearn.linear_model import LinearRegression. It provides consistent API: .fit(), .predict(), .score(). Also includes preprocessing, cross-validation, metrics.
Q2. Scenario: Load the iris dataset from sklearn.datasets. Print its feature names and target names. Convert to DataFrame for easier viewing.
from sklearn.datasets import load_iris; iris = load_iris(); print(iris.feature_names); print(iris.target_names); import pandas as pd; df = pd.DataFrame(iris.data, columns=iris.feature_names); df[''target''] = iris.target. This loads built-in datasets for practice.
Q3. Scenario: Why is scikit-learn preferred for classical machine learning over implementing algorithms from scratch?
Scikit-learn provides optimized, well-tested implementations, consistent API, extensive documentation, and integration with other scientific Python libraries. It includes tools for model selection, preprocessing, and pipelines, saving development time and reducing errors.
Q4. Scenario: You have a classification problem. Which scikit-learn models would you try first? Name three.
LogisticRegression, DecisionTreeClassifier, RandomForestClassifier, KNeighborsClassifier, SVC (support vector classifier). Start with simple models (logistic regression) then ensemble methods.
Q5. Scenario: The scikit-learn API follows fit/predict pattern. Write a simple linear regression fitting X (2D) and y (1D) then predicting on new data.
from sklearn.linear_model import LinearRegression; model = LinearRegression(); model.fit(X_train, y_train); predictions = model.predict(X_test). This is standard across all models.