Yellowbrick Alpha Testing Questionnaire

Thank you for helping us work through the alpha testing phase of the Yellowbrick library!

Before responding to this form, please review the notebook "Getting Started with Yellowbrick", which includes a tutorial, explanation of use cases, and Alpha testing instructions.

Note that our survey collects email addresses so that we can follow up with you on any questions based on your feedback. We will NEVER share your email address with anyone, or add it to a list of ANY kind. You will receive at most a few one-on-one emails from the core contributors of the Yellowbrick project (especially if you provide particularly valuable feedback!).

Email address *

Link to notebook fork *

Link to your notebook fork (should be a link to your notebook in GitHub). Check the notebook requirements section in the documentation.

Was your dataset used for regression or classification?

Regression

Classification

Both

Other:

How did you load your data?

In a Numpy array

As a Pandas dataframe

Other:

How many features were in your data set?

< 10

10-20

30-50

50-100

100-500

500-1000

> 1000

Other:

How many instances were in your data set?

< 1,000

1,000-5,000

5,000-50,000

50,000-500,000

> 500,000

Which Scikit-Learn estimator(s) did you use?

LogisticRegression

GaussianNB

MultinomialNB

SVC

KNeighborsClassifier

RandomForestClassifier

LinearRegression

Lasso

Ridge

ElasticNet

Other:

What Scikit-Learn tools and utilities did you use?

Cross Validation

Imputation

Normalization

Standardization

Metrics

Feature Selection

Grid Search

Other:

Which Yellowbrick visualizer(s) did you use?

ParallelCoordinates

RadViz

Rank2D

ClassificationReport

ROCAUC

ClassBalance

PredictionError

ResidualsPlot

Custom Visualizer

Other:

How comfortable did you feel with interpreting the visualizations? *

Not at all comfortable

Very comfortable

What type of difficulties with your loaded data did you encounter?

When following the examples was it clear what format, shape or data types were necessary to be used in the example yellowbrick class?

How did Yellowbrick visualizers aid your feature analysis and modeling processes?

They gave me more insight into the dataset.

They sped up my feature analysis/exploration process.

They facilitated my feature engineering process.

They sped up the modeling process.

They helped me make a better (more performant/higher scoring) model.

What types of exceptions (if any) did you encounter?

Please check all that apply!

No errors or exceptions

YellowbrickError

VisualError

ModelError

YellowbrickTypeError

YellowbrickValueError

TypeError

ValueError

AttributeError

KeyError

ImportError

matplotlib Error

scipy Error

sklearn Error

numpy Error

Other:

Error Tracebacks *

Please ensure that you have left any errors that you encountered while using the yellowbrick package with your example notebook data.

Yes - I have included all errors that I encountered.

No - I did not encounter any errors.

What types of Yellowbrick visualizers or utilities would you like to see added?

What were the challenges of working with Yellowbrick?

What would make Yellowbrick better?

Would you be interested in participating in a user study? *

Yes

How likely would you be to use Yellowbrick in your future projects? *

Very unlikely

Very likely

Any final comments?

Send me a copy of my responses.

Submit

Never submit passwords through Google Forms.

reCAPTCHA

Privacy Terms

This form was created inside of Bengfort.com. - Terms of Service

Forms