nannyml.datasets.datasets module

Utility module offering curated datasets for quick experimentation.

nannyml.datasets.datasets.load_csv_file_to_df(local_file: str) DataFrame[source]

Loads a data file from within the NannyML package.

Parameters

local_file (str, required) – string with the name of the data file to be loaded.

Returns

df – A DataFrame containing the requested data

Return type

pd.DataFrame

nannyml.datasets.datasets.load_modified_california_housing_dataset()[source]

Loads the modified california housing dataset provided for testing the NannyML package.

This dataset has been altered to represent a binary classification problem over time. More information about the dataset can be found at: California Housing Dataset

Returns

  • reference (pd.DataFrame) – A DataFrame containing reference partition of modified california housing dataset

  • analysis (pd.DataFrame) – A DataFrame containing analysis partition of modified california housing dataset

  • analysis_tgt (pd.DataFrame) – A DataFrame containing target values for the analysis partition of modified california housing dataset

Examples

>>> from nannyml.datasets import load_modified_california_housing_dataset
>>> reference_df, analysis_df, analysis_targets_df = load_modified_california_housing_dataset()
nannyml.datasets.datasets.load_synthetic_binary_classification_dataset()[source]

Loads the synthetic binary classification dataset provided for testing the NannyML package.

Returns

  • reference (pd.DataFrame) – A DataFrame containing reference partition of synthetic binary classification dataset

  • analysis (pd.DataFrame) – A DataFrame containing analysis partition of synthetic binary classification dataset

  • analysis_tgt (pd.DataFrame) – A DataFrame containing target values for the analysis partition of synthetic binary classification dataset

Examples

>>> from nannyml.datasets import load_synthetic_binary_classification_dataset
>>> reference_df, analysis_df, analysis_targets_df = load_synthetic_binary_classification_dataset()
nannyml.datasets.datasets.load_synthetic_multiclass_classification_dataset()[source]

Loads the synthetic multiclass classification dataset provided for testing the NannyML package.

Returns

  • reference (pd.DataFrame) – A DataFrame containing reference partition of synthetic multiclass classification dataset

  • analysis (pd.DataFrame) – A DataFrame containing analysis partition of synthetic multiclass classification dataset

  • analysis_tgt (pd.DataFrame) – A DataFrame containing target values for the analysis partition of synthetic multiclass classification dataset

Examples

>>> from nannyml.datasets import load_synthetic_multiclass_classification_dataset
>>> reference_df, analysis_df, analysis_targets_df = load_synthetic_multiclass_classification_dataset()