fa3 + logistic reg to gradient boosting

Question 1

We can visualize the tree using the export_graph function from the tree module.

Group of answer choices:
True
False

Answer 1

False

Question 2

In the decision tree, the region can be found by traversing the tree from the root and going left or right.

Group of answer choices
True
False

Answer 2

True

Question 3

Decision tree is a model that learns a hierarchy of if/else questions, leading to a decision.

Group of answer choices
True
False

Answer 3

True

Question 4

The .dot file format is a _____ file format for storing graphs.

Answer 4

TEXT

Question 5

In the decision tree, the ______ represents the whole dataset.

Group of answer choices
Terminal Nodes
Edges
Root
Conditions

Answer 5

Root

Question 6

The .dot file format is an image file format for storing graphs.
Group of answer choices
True
False

Answer 6

True

Question 7

Decision trees in scikit learn are implemented in ________ and DecisionTreeClassifier classes.

Group of answer choices: DecisionRegressorTree
TreeDecisionRegressor
RegressorDecisionTree
DecisionTreeRegressor

Answer 7

DecisionTreeRegressor

Question 8

Which is not true about Random Forest?

Group of answer choices
Not in the options
Less memory usage.
Less burden or parameter tuning.
As many trees are created, detailed analysis is difficult.
Poor performance for large and sparse data.

Answer 8

Less memory usage.

Question 9

To build a random forest model, you need to decide on the __________ to build.

Group of answer choices
Depth of the tree Height of tree
Number of trees
Root
Node of the tree

Answer 9

Number of trees

Question 10

The _______ are methods that combine multiple machine learning models to create more powerful models.

Answer 10

ENSEMBLES

Question 11

In the decision tree, the terminal nodes represent the whole dataset.

Group of answer choices
True
False

Answer 11

False

Question 12

In the decision tree, the sequence of if/else questions are called qualifiers.

Group of answer choices
True
False

Answer 12

False

Question 13

Which is not true about Random Forest?

Group of answer choices
Reduces underfitting by averaging trees that predict well.
Reduces overfitting by averaging trees that predict well.
Selects candidate features at random when splitting nodes.
Randomly selects some of the data when creating a tree.

Answer 13

Reduces underfitting by averaging trees that predict well.

Question 14

What are the parameters for Gradient Boosting?

a. n_estimators, learning rate
b. n_estimators, max_features
c. n_estimators, learning rate, max_depth
d. n_estimators, max_features, max_depth

Answer 14

c

Question 15

Gradient boosting is used when you need to take more performance in random forests.

Group of answer choices
True
False

Answer 15

True

Question 16

In the decision tree, the sequence of if/else questions are called ______.

Group of answer choices
Qualifiers
Condition
Tests
Nodes

Answer 16

Tests

Question 17

Decision trees in scikit learn are implemented in DecisionTreeRegressor and _______ classes.

Group of answer choices
DecisionClassifier
TreeDecisionClassifier
DecisionTreeClassifier
DecisionClassifierTree

Answer 17

DecisionTreeClassifier

Question 18

We can visualize the tree using the ______ function from the tree module.

Answer 18

export_graphviz

Question 19

Two most common linear classification algorithms:

Answer 19

Logistic Regression
Linear Support Vector Machines

Question 20

Logistic Regression, implemented in where

Answer 20

linear_model.LogisticRegression

Question 21

Linear Support Vector Machines (Linear SVMs), implemented in where

Answer 21

svm.LinearSVC

Question 22

SVC stands for?

Answer 22

support vector classifier

Question 23

______ is a classification algorithm and not a regression algorithm, and it should not be confused with LinearRegression

Answer 23

LogisticRegression

Question 24

the trade-off parameter detemrins the strength of the regularizaiton, called _____

Answer 24

C

Question 25

Higher values of C correspond to _____

Answer 25

LESS REGULARIZATION

Question 26

When you use a high value of the parameter C, LogisticRegression and LinearSVC will _______

Answer 26

try to fit the training set as best as possible

Question 27

low values of the parameter C, the models put more emphasis on _______

Answer 27

finding a coefficient vector (w) that is close to zero

Question 28

Using low values of C will cause the algorithms to try to adjust to the _____ of data points

Answer 28

“majority”

Question 29

using a higher value of C stresses the importance that each ______ be classified correctly

Answer 29

individual data point

Question 30

_______ are a family of classifiers that are quite similar to the linear models

Answer 30

Naive Bayes classifiers

Question 31

In Naive Bayes, ____is faster than linear classifier

Answer 31

Training Speeds

Question 32

In Naive Bayes, _____ performance is slightly lower

Answer 32

Generalization

Question 33

The reason that Naive Bayes models are so efficient is that they______ and collect simple per-class statistics from each feature

Answer 33

learn parameters by looking at each feature individually

Question 34

The reason that Naive Bayes models are so efficient is that they learn parameters by looking at each feature individually and _______

Answer 34

collect simple per-class statistics from each feature

Question 35

3 Kinds of Naive Bayes Classifier in Scikit-learn:

Answer 35

GaussianNB BernoulliNB MultinomialNB

Question 36

GuassianNB -> ____ data

Answer 36

Continuous

Question 37

BernoulliNB -> ____ data, ___ data

Answer 37

Binary data, Text data

Question 38

MultinomialNB -> ____ data, ___ data

Answer 38

Integer count data, text data

Question 39

In Naive Bayes, it controls _____

Answer 39

model complexity with alpha parameter

Question 40

In Naives Bayes, _____ by adding virtually positive data as much as alpha

Answer 40

Smooth statistics

Question 41

In Naive Bayes, ____ decreases the complexity of the model but does not change the performance

Answer 41

Large alpha

Question 42

_____ is a high-dimensional dataset

Answer 42

GaussianNB

Question 43

_____ and ______ are a text-like used to count sparse data

Answer 43

BernioulliNB and MultinomialNB

Question 44

In Naive Bayes, _____ are fast and easy to understand and process

Answer 44

Training and testing

Question 45

Naives Bayes works well with _____ and is not _____

Answer 45

sparse high-dimensional datasets, parameter sensitive

Question 46

______ are widely used models for classification and regression tasks

Answer 46

Decision trees

Question 47

In Decision Trees, they learn a hierarchy of ____, leading to a decision

Answer 47

if/else questions

Question 48

Learning a _____ means learning the sequence of if/else questions that gets us to the true answer most quickly

Answer 48

decision tree

Question 49

In the machine learning setting, if/else questions are called ___

Answer 49

tests

Question 50

To build a tree, the algorithm searches over all possible tests and finds the one that is ____ about the target variable

Answer 50

most informative

Question 51

The top node is called the ___, representing the whole dataset.

Answer 51

root

Question 52

Parts of a decision tree:

Answer 52

Root Node Node Edge (Connects tests to other nodes) Terminal Node (Nodes with no futher edges) Characteristics (inside nodes)

Question 53

A prediction on a new data is made by checking which region of the ____ the point lies in, and then predicting the majority target (or the single target in the case of pure leaves) in that region

Answer 53

partition of the feature space

Question 54

The ____ can be found by traversing the tree from the root and going left or right, depending on whether the test is fulfilled or not

Answer 54

region

Question 55

Decision trees in scikit learn are implemented in ____ and ____ classes

Answer 55

DecisionTreeRegressor, DecisionTreeClassifier

Question 56

We can visualize the tree using the ___ function from the tree module

Answer 56

export_graphviz

Question 57

export_graphviz writes a file in the ____, which is a text file format for storing graphs

Answer 57

.dot file format

Question 58

export_graphviz writes a file in the .dot file format, which is a ____for storing graphs

Answer 58

text file format

Question 59

We can visualize the _____ in a way that is similar to the way we visualize the coefficients in the linear model

Answer 59

feature importances

Question 60

______ is impossible for extrapolation predicting outside the range of training data

Answer 60

Extrapolation 0

Question 61

____ is not affected by scale

Answer 61

Decision Tree Regression

Question 62

_____ are methods that combine multiple machine learning models to create more powerful models

Answer 62

Ensembles

Question 63

Two ensemble models that have proven to be effective on a wide range of datasets, for classification and regression, both of which use decision trees as their building blocks:

Answer 63

Random Forests Gradient Boosted Decision Trees

Question 64

It is one of the ensemble methods that can avoid overfitting by combining multiple decision trees

Answer 64

Random Forests

Question 65

Random Forests Reduces overfitting by ______

Answer 65

averaging trees that predict well

Question 66

In Random Forests, Regression is:

Answer 66

average of predicted values

Question 67

In Random Forests, Classification is:

Answer 67

average of predicted probabilities

Question 68

It injects randomness when creating trees

Answer 68

Random Forests

Question 69

In Random Forests, it randomly selects _____ when creating a tree

Answer 69

some of the data

Question 70

In Random Features, selects ______ when splitting nodes

Answer 70

candidate features at random

Question 71

To build a random forest model, you need to decide on the _____ to build

Answer 71

number of trees

Question 72

To build a random forest model, you need to decide on the number of trees to build (the ____ parameter of RandomForestRegressor or RandomForestClassifier)

Answer 72

n_estimators

Question 73

To build a tree, we first take what is called a _____ of our data. That is, from our n_samples data points, we repeatedly draw an example randomly with replacement

Answer 73

bootstrap sample

Question 74

A critical parameter in this process is ____. If we set _____ to n features, that means that each split can look at all features in the dataset, and no randomness will be injected in the feature selection

Answer 74

max features

Question 75

The Advantages of Random Forests are:

Answer 75

Mostly widely used algorithm in regression and classification Excellent performance, less burden or parameter tuning, no data scale required Large datasets can be applied

Question 76

In Random Forests, it is the _______ algorithm in regression and classification

Answer 76

Mostly widely used

Question 77

In Random Forests, it has ___ performance, less burden or _____, ____ required

Answer 77

excellent performance, parameter tuning, no data scale required

Question 78

In Random Forests, ____ datasets can be applied

Answer 78

Large

Question 79

The Disadvantages of Random Forests are:

Answer 79

As many trees are created, detailed analysis is difficult, and the trees tend to get deeper Poor performance for large and sparse data More memory usage and slower training and prediction than linear models

Question 80

In Random Forests, as many trees are created, _____ is difficult and the trees tends to get deeper

Answer 80

detailed analysis

Question 81

In Random Forests, it has poor performance for ___ and ____ data

Answer 81

large and sparse data

Question 82

In Random Forests, it has more ____ and slower ___ and ____ than linear models

Answer 82

memory usage slower training and prediction

Question 83

The parameters used in Random Forests are:

Answer 83

n_estimators, max features

Question 84

Another ensemble algorithm based on DecisiontreeRegressor

Answer 84

Gradient Boosted Regression Trees (gradient boosting machines)

Question 85

Gradient Boosted Regression Trees can be used for both ____ and ___

Answer 85

classification and regression

Question 86

In Gradient Boosted Regression Trees, unlike random forest, _____ is strongly applied instead of randomness

Answer 86

pre-pruning

Question 87

Used a lot in machine learning contests (Kaggle)

Answer 87

Gradient Boosted Regression Trees (gradient boosting machines)

Question 88

In Gradient Boosted Regression Trees, it is slightly more _____, slightly ____ than random forest

Answer 88

more parameter sensitive higher performance

Question 89

Create the next tree to compensate for the error of the previous tree using a ______

Answer 89

shallow tree of 5 or less

Question 90

In Gradient Boosted Regression Trees, the regression is:

Answer 90

least squares error loss function

Question 91

In Gradient Boosted Regression Trees, the classification is:

Answer 91

logistic loss function

Question 92

In Gradient Boosted Regression Trees, use _____ method

Answer 92

gradient descent method

Question 93

In Gradient Boosted Regression Trees, use gradient descent method (learning rate parameter is important default = ___)

Answer 93

0.1

Question 94

Gradient Boosting Advantages:

Answer 94

Use when you need to take more performance in random forests (xgboost for larger scales) No need for feature scale adjustment and can be used for binary and continuous features

Question 95

In Gradient Boosting, we can use it when you need to take more _____ in random forests (____ for larger scales)

Answer 95

performance, xgboost

Question 96

In Gradient Boosting, no need for _________ and can be used for binary and continuous features

Answer 96

feature scale adjustment

Question 97

Gradient Boosting Disadvantages:

Answer 97

Doesn't work well for sparse high-dimensional data Sensitive to parameters, takes longer training time

Question 98

In Gradient Boosting, it doesn't work well for sparse ___

Answer 98

high-dimensional data

Question 99

In Gradient Boosting, it is sensitive to _____, takes longer _____

Answer 99

Parameters Longer Training time

Question 100

Gradient Boosting Parameters are:

Answer 100

n_estimators learning rate max_depth (<=5)