CausalEGM.util.Base_sampler

class CausalEGM.util.Base_sampler(x, y, v, batch_size=32, normalize=False, random_seed=123)[source]

Base data sampler.

Parameters:

  • x – List or Numpy.ndarray bject denoting the treatment with length N or shape (N, 1) or (N, ).

  • y – List or Numpy.ndarray bject denoting the outcome with length N or shape (N, 1) or (N, ).

  • v – List or Numpy.ndarray bject denoting the covariates with length N or shape (N, v_dim).

  • batch_size – Int object denoting the batch size for mini-batch training. Default: 32.

Examples

>>> from CausalEGM import Base_sampler
>>> import numpy as np
>>> x = np.random.normal(size=(2000,))
>>> y = np.random.normal(size=(2000,))
>>> v = np.random.normal(size=(2000,100))
>>> ds = Base_sampler(x=x,y=y,v=v)
>>> batch = ds.next_batch() # get a batch of data
>>> data = ds.load_all() # get all data as a triplet
__init__(x, y, v, batch_size=32, normalize=False, random_seed=123)[source]

Methods

__init__(x, y, v[, batch_size, normalize, ...])

create_idx_generator(sample_size[, random_seed])

load_all()

next_batch()