climb.tool.impl.data_suite.third_party.uq360.datasets package

Submodules

climb.tool.impl.data_suite.third_party.uq360.datasets.atis_dataset module

class climb.tool.impl.data_suite.third_party.uq360.datasets.atis_dataset.AtisDataset(custom_preprocessing=<function default_preprocessing>, dirpath=None)

Bases: object

The Bank Marketing dataset comes from a phone-based marketing campaign from a Portuguese banking institution. The labels indicate whether an individual contacted in the campaign chose to subscribe to the product (bank term deposit) or not.

See uq360/data/banking_data/README.md for more details on the dataset and instructions on downloading/processing the data. .. rubric:: References

[1]

[Moro et al., 2014] S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014

data()

climb.tool.impl.data_suite.third_party.uq360.datasets.atis_dataset.default_preprocessing(data)

Grab query text (features) and class intent (labels).

climb.tool.impl.data_suite.third_party.uq360.datasets.banking_dataset module

class climb.tool.impl.data_suite.third_party.uq360.datasets.banking_dataset.BankMarketingDataset(custom_preprocessing=<function default_preprocessing>, dirpath=None)

Bases: object

The Bank Marketing dataset comes from a phone-based marketing campaign from a Portuguese banking institution. The labels indicate whether an individual contacted in the campaign chose to subscribe to the product (bank term deposit) or not.

See uq360/data/banking_data/README.md for more details on the dataset and instructions on downloading/processing the data. .. rubric:: References

[2]

[Moro et al., 2014] S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014

data()

climb.tool.impl.data_suite.third_party.uq360.datasets.banking_dataset.default_preprocessing(df)

1. Drop some unnecessary columns and na values.

2. Break off label column from dataframe.

3. Encode categorical columns

4. Return x and y as numpy arrays

climb.tool.impl.data_suite.third_party.uq360.datasets.meps_dataset module

class climb.tool.impl.data_suite.third_party.uq360.datasets.meps_dataset.MEPSDataset(custom_preprocessing=<function default_preprocessing>, dirpath=None)

Bases: object

The Medical Expenditure Panel Survey (MEPS) [1] data consists of large scale surveys of families and individuals, medical providers, and employers, and collects data on health services used, costs & frequency of services, demographics, health status and conditions, etc., of the respondents. This specific dataset contains MEPS survey data for calendar year 2015 obtained in rounds 3, 4, and 5 of Panel 19, and rounds 1, 2, and 3 of Panel 20. See uq360/data/meps_data/README.md for more details on the dataset and instructions on downloading/processing the data. .. rubric:: References

[3]

Medical Expenditure Panel Survey data

data()

climb.tool.impl.data_suite.third_party.uq360.datasets.meps_dataset.default_preprocessing(df)

1.Create a new column, RACE that is ‘White’ if RACEV2X = 1 and HISPANX = 2 i.e. non Hispanic White

and ‘non-White’ otherwise

2. Restrict to Panel 19

3. RENAME all columns that are PANEL/ROUND SPECIFIC

4. Drop rows based on certain values of individual features that correspond to missing/unknown - generally < -1

5. Compute UTILIZATION.

Module contents