Font size
WorksheetsLesson 3 Quiz
Total questions: 15
Worksheet time: 15mins
Data wrangling involves which of the following steps?
Data discovery
Imputation
Validation and publishing
All of the above
_________ helps keep your data secure by keeping connection information internal
Datastores
Datasets
Data Type
Data Warehouse
Datasets allows you to do the following things
No need to create multiple copies each time you need that data available
Access data during model training by specifying connection strings or data paths
Easily share data and collaborate with other users
Bookmark the state of your data
Versioning is used when
You need to go back and retrieve specific versions of your files
Trace backing to the original datasets in storage service
Retraining, data preparation and feature engineering
All of the above
C
A
B
D
Reasons for feature selection include
to eliminate highly irrelevant and redundant features
eliminate highly correlated features by choosing one out of them
encode large number of features into small number of features
All of the above
Which is the correct sequence of data access workflow
Creating datastore, data monitor, and then dataset
Creating dataset, datastore, and then data monitor
Creating datastore, dataset, and then data monitors
Creating dataset, data monitor, and then datastore
Which type of data drift are we talking about when we see that two features that used to be correlated are no longer correlated
Natural Drift in Data
Data Quality issues
Covariate Shift
Upstream Process Change
What is the purpose of a validation set
Train the model
Test the model with unseen data
Tune the hyper parameters
To find model metrics such as RMSE, Precision, etc.
A container that helps you organize the model training process
Experiment
Workspace
Model Registry
Compute Instance
Which of the following measures the Strength and Direction of the relationship b/w each prediction and true values
MAE
RMSE
R-squared
Sperman Correlation
What all is true about boosting
helps in reducing bias for models
helps in reducing overfitting for models that tend to have high variance
The final prediction is an average prediction from individual models
The final predictions are a weighted average from the individual models
Ensemble learning can only be applied to supervised learning methods
True
False
In an election, N candidates are competing against each other and people are voting for either of the candidates. Voters don’t communicate with each other while casting their votes. Which of the following ensemble method works similar to above-discussed election procedure?
Bagging
Boosting
Both
Neither
You had predicted that England would win, but it lost. What is this example signify in terms of a confusion matrix
True Positive
True Negative
False Positive
False Negative
