imputegap.algorithms.stmvl package

The imputegap.algorithms.stmvl package contains various imputation algorithms used for handling missing values in time series data. This package supports multiple imputation techniques like CDRec, MRNN, IIM, and more.

Submodules

Modules

imputegap.algorithms.stmvl.native_stmvl(__py_matrix, __py_window, __py_gamma, __py_alpha)[source]

Perform matrix imputation using the STMVL algorithm with native C++ support.

Parameters

__py_matrixnumpy.ndarray

The input matrix with missing values (NaNs).

__py_windowint

The window size for the temporal component in the STMVL algorithm.

__py_gammafloat

The smoothing parameter for temporal weight (0 < gamma < 1).

__py_alphafloat

The power for the spatial weight.

Returns

numpy.ndarray

The recovered matrix after imputation.

Notes

The STMVL algorithm leverages temporal and spatial relationships to recover missing values in a matrix. The native C++ implementation is invoked for better performance.

Example

>>> recov_data = stmvl(incomp_data=incomp_data, window_size=2, gamma=0.85, alpha=7)
>>> print(recov_data)

References

Yi, X., Zheng, Y., Zhang, J., & Li, T. ST-MVL: Filling Missing Values in Geo-Sensory Time Series Data. School of Information Science and Technology, Southwest Jiaotong University; Microsoft Research; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences.

imputegap.algorithms.stmvl.stmvl(incomp_data, window_size, gamma, alpha, logs=True)[source]

CDREC algorithm for imputation of missing data :author: Quentin Nater

Parameters:

  • incomp_data – time series with contamination

  • window_size – window size for temporal component

  • gamma – smoothing parameter for temporal weight

  • alpha – power for spatial weight

  • logs – print logs of time execution

Returns:

recov_data, metrics : all time series with imputation data and their metrics