BudiBaduQuiziBadu

Python Scikit-Learn Models Quiz

Python
0 Passed
0% acceptance

A 50-question quiz covering the Scikit-Learn machine learning library, from estimator basics and pipelines to model selection and evaluation metrics.

50 Questions
~100 minutes
1

Question 1

What is the core method used to train a model in Scikit-Learn?

A
train()
B
fit()
C
learn()
D
execute()
2

Question 2

Which method is used to generate predictions from a trained model?

A
score()
B
forecast()
C
predict()
D
infer()
3

Question 3

What does `estimator.score(X, y)` typically return for a classifier?

A
The mean squared error.
B
The accuracy of the predictions.
C
The predicted class labels.
D
The confusion matrix.
4

Question 4

What is a 'Transformer' in Scikit-Learn?

A
A deep learning model.
B
An estimator that modifies the data (e.g., scaling, encoding).
C
A visualization tool.
D
A metric calculator.
5

Question 5

Which method combines `fit()` and `transform()` into one step?

javascript

scaler = StandardScaler()
X_scaled = scaler.____(X_train)
A
fit_transform()
B
transform_fit()
C
apply()
D
run()
6

Question 6

What is the shape of the input feature matrix `X` typically expected by `fit()`?

A
(n_features, n_samples)
B
(n_samples, n_features)
C
(n_samples,)
D
A list of lists.
7

Question 7

What happens if you call `fit()` on an estimator that has already been trained?

A
It throws an error.
B
It incrementally updates the model.
C
It re-initializes the model and trains from scratch (forgetting previous training).
D
It does nothing.
8

Question 8

Which attribute usually stores the learned parameters after training (e.g., coefficients)?

A
model.weights
B
model.params
C
model.coef_
D
model.learned
9

Question 9

How do you instantiate a Linear Regression model?

javascript

from sklearn.linear_model import LinearRegression
model = ____
A
LinearRegression.new()
B
LinearRegression()
C
create_model('linear')
D
fit(LinearRegression)
10

Question 10

What is the target vector `y` usually expected to be?

A
A 2D array (n_samples, 1).
B
A 1D array (n_samples,).
C
A dictionary.
D
A string.
11

Question 11

For a classifier, what does `predict_proba(X)` return?

A
The predicted class labels.
B
The probability estimates for each class.
C
The confidence score.
D
The log probabilities.
12

Question 12

If `predict_proba` returns `[0.2, 0.8]` for a binary classifier, what will `predict` return?

A
0
B
1
C
0.8
D
True
13

Question 13

What input does `predict()` require?

A
The target labels `y`.
B
The feature matrix `X` with the same number of features as training data.
C
A single sample only.
D
The training data.
14

Question 14

Which method is used for unsupervised clustering models to assign labels?

A
cluster()
B
group()
C
predict()
D
assign()
15

Question 15

Can you use `predict()` on a model before calling `fit()`?

A
Yes, it returns random predictions.
B
No, it raises a `NotFittedError`.
C
Yes, it uses default weights.
D
It depends on the model.
16

Question 16

Which class handles missing values by replacing them with the mean or median?

A
SimpleImputer
B
MissingValueHandler
C
FillNA
D
ImputeScaler
17

Question 17

How do you convert categorical string variables (e.g., 'red', 'blue') into integers?

A
OneHotEncoder
B
LabelEncoder
C
StringIndexer
D
CategoryEncoder
18

Question 18

What does `OneHotEncoder` do?

A
Converts text to numbers.
B
Creates a binary column for each category value.
C
Scales data to 0-1.
D
Removes duplicates.
19

Question 19

Why should you fit a scaler ONLY on the training set?

A
To save time.
B
To prevent data leakage.
C
Because the test set is too small.
D
It doesn't matter.
20

Question 20

Which preprocessing step is often required for Support Vector Machines (SVM) and KNN?

A
Feature Scaling
B
Imputation
C
Polynomial Features
D
Binning
21

Question 21

What is the main purpose of `sklearn.pipeline.Pipeline`?

A
To visualize data.
B
To chain multiple processing steps and an estimator into a single object.
C
To download data.
D
To parallelize training.
22

Question 22

How do you create a pipeline with a scaler and a classifier?

javascript

from sklearn.pipeline import make_pipeline
pipe = ____(StandardScaler(), LogisticRegression())
A
Pipeline
B
make_pipeline
C
create_pipeline
D
chain
23

Question 23

When you call `pipe.fit(X, y)`, what happens to the intermediate steps?

A
They are skipped.
B
They call `fit_transform()` sequentially, passing output to the next step.
C
They only call `fit()`.
D
They only call `transform()`.
24

Question 24

When you call `pipe.predict(X)`, what happens?

A
It predicts using the first step.
B
It transforms X using all intermediate steps, then calls `predict` on the final estimator.
C
It errors.
D
It refits the model.
25

Question 25

What is `ColumnTransformer` used for?

A
Transforming the target column.
B
Applying different transformations to different columns (e.g., scaling numeric, encoding categorical).
C
Removing columns.
D
Renaming columns.
26

Question 26

What does `StandardScaler` do?

A
Scales features to the range [0, 1].
B
Standardizes features by removing the mean and scaling to unit variance.
C
Normalizes samples to unit norm.
D
Takes the logarithm.
27

Question 27

What does `MinMaxScaler` do?

A
Scales features to a given range, usually [0, 1].
B
Centers the data.
C
Divides by the maximum value.
D
Removes outliers.
28

Question 28

Which scaler is robust to outliers?

A
StandardScaler
B
MinMaxScaler
C
RobustScaler
D
Normalizer
29

Question 29

What is the difference between `Normalizer` and `StandardScaler`?

A
They are the same.
B
`Normalizer` scales individual samples (rows) to have unit norm; `StandardScaler` scales features (columns).
C
`Normalizer` is for regression.
D
`StandardScaler` is deprecated.
30

Question 30

If you use `fit_transform` on the test set with `StandardScaler`, what happens?

A
It works perfectly.
B
You introduce data leakage.
C
It errors.
D
It improves accuracy legitimately.
31

Question 31

Which function is used to split data into training and testing sets?

A
train_test_split
B
split_data
C
cross_val_split
D
sample_split
32

Question 32

What is the purpose of the `random_state` parameter?

A
To improve accuracy.
B
To ensure reproducibility of the split.
C
To randomize the model weights.
D
To speed up processing.
33

Question 33

What is 'Stratified Sampling' (via `stratify=y`)?

A
Splitting data based on time.
B
Ensuring the proportion of class labels is the same in train and test sets.
C
Random sampling.
D
Sampling with replacement.
34

Question 34

Which model is a good baseline for classification tasks?

A
Neural Network
B
DummyClassifier
C
XGBoost
D
SVM
35

Question 35

How do you perform K-Fold Cross-Validation?

A
cross_val_score(model, X, y, cv=5)
B
model.cross_validate(5)
C
kfold(model)
D
validate(model)
36

Question 36

What does `GridSearchCV` do?

A
Searches for data on the grid.
B
Exhaustively searches over a specified parameter grid to find the best combination.
C
Randomly samples parameters.
D
Visualizes the grid.
37

Question 37

How do you define the parameter grid for `GridSearchCV`?

javascript

param_grid = {
    'C': [0.1, 1, 10],
    'kernel': ['linear', 'rbf']
}
A
A list of values.
B
A dictionary where keys are parameter names and values are lists of settings.
C
A function.
D
A tuple.
38

Question 38

What is the advantage of `RandomizedSearchCV` over `GridSearchCV`?

A
It is more accurate.
B
It is faster and more efficient for large parameter spaces.
C
It checks every combination.
D
It works without data.
39

Question 39

After fitting `GridSearchCV`, how do you access the best model?

A
grid.best_estimator_
B
grid.model
C
grid.winner
D
grid.top
40

Question 40

Can you tune pipeline parameters with GridSearchCV?

A
No, only single models.
B
Yes, by using the step name followed by double underscore (e.g., `stepname__param`).
C
Yes, but only the last step.
D
Yes, using a special class.
41

Question 41

Why is Cross-Validation preferred over a single Train/Test split?

A
It is faster.
B
It provides a more robust estimate of model performance by using all data for both training and validation.
C
It requires less data.
D
It is easier to code.
42

Question 42

What is `LeaveOneOut` cross-validation?

A
K-Fold where K equals the number of samples.
B
Leaving one feature out.
C
Training on one sample.
D
A deprecated method.
43

Question 43

What does `cross_val_predict` return?

A
The scores.
B
The predictions for each sample when it was in the test set.
C
The trained models.
D
The parameters.
44

Question 44

When should you use `TimeSeriesSplit`?

A
Always.
B
When data is ordered by time (e.g., stock prices).
C
When data is random.
D
For image data.
45

Question 45

Does `cross_val_score` return a fitted model?

A
Yes.
B
No, it returns a list of scores.
C
It returns the best model.
D
It returns the data.
46

Question 46

Which metric is appropriate for a classification problem with imbalanced classes?

A
Accuracy
B
F1-Score or ROC-AUC
C
Mean Squared Error
D
R-Squared
47

Question 47

What does the Confusion Matrix show?

A
The correlation between features.
B
The counts of True Positives, True Negatives, False Positives, and False Negatives.
C
The training time.
D
The probability distribution.
48

Question 48

What is the ROC Curve?

A
A plot of True Positive Rate vs. False Positive Rate at various thresholds.
B
A plot of Precision vs. Recall.
C
A plot of Loss vs. Epochs.
D
A plot of Accuracy vs. Data Size.
49

Question 49

Which function calculates the Mean Squared Error?

A
accuracy_score
B
mean_squared_error
C
r2_score
D
confusion_matrix
50

Question 50

What does an R^2 score of 1.0 indicate?

A
The model explains none of the variance.
B
The model makes perfect predictions.
C
The model is overfitting.
D
The model is random.

Other Quiz Categories

JavaScript
47 quizzes
Basics
Variables & Data Types
Operators & Expressions
Rust
30 quizzes
Cargo and Project Setup
Variables and Mutability
Data Types
Golang
29 quizzes
Basics & Syntax
Data Types & Zero Values
Operators & Expressions
C++
26 quizzes
Basics
Variables & Data Types
Operators & Expression
Java
22 quizzes
Java Basics & JVM Fundamentals
Variables, Data Types & Type Casting
Operators & Expressions
Matlab
21 quizzes
Basics & Environment
Variables and Data Type
Arrays and Matric
TypeScript
19 quizzes
Introduction and Overview
Installation and Configuration
Basic Types and Type Annotations
SQL Database
15 quizzes
Foundations and Basics
Basic Query Selection
Filter, Sort, and Alias Essentials
PHP
15 quizzes
Syntax Building Blocks
Variable Naming
Data Types Overview
Linked List
11 quizzes
Introduction
Node Structure and Pointer Fundamentals
Singly Linked List

QUIZZES IN Python

1

Introduction & Core Fundamentals

40

A 40-question quiz covering Python introduction, basic syntax, variables, data types, execution model, indentation rules, and foundational concepts.

2

Data Types Overview

35

A 35-question quiz introducing Python’s core data types, covering numbers, strings, booleans, sequences, mappings, mutability concepts, and how Python treats values at a high level.

3

Type Casting

50

A 50-question quiz covering Python type casting: numeric conversions, string casting, boolean rules, safe casting, error cases, and real-world usage patterns.

4

Operators Overview

50

A 50-question quiz exploring Python’s operator system, including arithmetic, comparison, logical, assignment, membership, identity, and bitwise operators with practical reasoning scenarios.

5

Logic Flow Basics

25

A 25-question quiz exploring Python’s conditional statements, covering if/elif/else logic, nested conditions, truthiness, comparison flow, and real-world decision structures.

6

Iteration Patterns

30

A 30-question quiz exploring Python’s loop structures, including for-loops, while-loops, iteration patterns, break/continue, nested loops, ranges, and real-world loop applications.

7

String Manipulation Fundamentals

35

A 35-question quiz covering Python string manipulation concepts, including slicing, searching, formatting, immutability, transformations, and real-world text-processing patterns.

8

Sequence Collections

30

A 30-question quiz focused on Python lists, covering list creation, indexing, slicing, mutation, iteration, list methods, copying behavior, and practical data-handling scenarios.

9

Python Lists Basics

35

A 35-question quiz covering list creation, indexing, appending, inserting, removing, updating, and length checking.

10

Python Dictionaries

35

A 35-question quiz covering dictionary creation, key-value pairs, accessing data, modifying dictionaries, and checking for keys.

11

Python Tuples & Unpacking

35

A 35-question quiz covering tuple creation, immutability, access, operations, packing/unpacking, and value swapping.

12

Python Sets

35

A 35-question quiz covering set creation, uniqueness, adding/removing items, and mathematical operations like union and intersection.

13

Python Booleans & Truth Values

35

A 35-question quiz covering boolean logic, truthy/falsy values, operators, and conditional expressions.

14

Python Variable Scope Basics

35

A 35-question quiz covering local vs global scope, the global keyword, variable shadowing, and best practices for managing state.

15

File Handling Basics

35

A 35-question quiz covering file opening, reading, writing, modes, and the importance of context managers.

16

Modules and Imports

35

A 35-question quiz covering import syntax, namespace management, standard libraries, and module organization.

17

Random Module

35

A 35-question quiz covering random number generation, selecting elements, shuffling sequences, and managing seeds.

18

Date and Time Basics

35

A 35-question quiz covering datetime objects, current timestamps, formatting, parsing, and calculating time differences.

19

Lambda Functions

35

A 35-question quiz covering anonymous functions, their syntax, usage with map/filter/sort, and their limitations.

20

Exception Handling

35

A 35-question quiz covering try-except blocks, handling multiple errors, using else and finally, and creating custom exceptions.

21

OOP Basics

35

A 35-question quiz covering the fundamentals of Object-Oriented Programming in Python, including classes, objects, attributes, and methods.

22

NumPy Arrays

35

A 35-question quiz covering NumPy array creation, shapes, indexing, slicing, broadcasting, and aggregation.

23

Pandas DataFrames

35

A 35-question quiz covering Pandas DataFrame operations, including column manipulation, row filtering, data import, statistics, missing values, and data types.

24

Matplotlib Visualization

35

A 35-question quiz covering Matplotlib figure structure, axes elements, line charts, labels, legends, and exporting plots.

25

Seaborn Charts

35

A 35-question quiz covering Seaborn's high-level plotting interface, including scatter plots, categorical charts, distributions, themes, and statistical visualizations.

26

Django Framework

60

A comprehensive 60-question quiz covering the Django web framework, from project structure and models to views, templates, and advanced configuration.

27

Flask Framework

60

A 60-question quiz covering the Flask microframework, from app initialization and routing to templates, blueprints, and error handling.

28

Jupyter Notebooks

50

A 50-question quiz covering Jupyter Notebooks, from interface basics and cell types to magic commands, kernel execution, and advanced features.

29

Scikit-Learn Models

50

A 50-question quiz covering the Scikit-Learn machine learning library, from estimator basics and pipelines to model selection and evaluation metrics.