Generate missing data in time series¶

In [1]:

import numpy as np
import matplotlib.pyplot as plt
from badgers.generators.time_series.missingness import MissingAtRandomGenerator

import numpy as np import matplotlib.pyplot as plt from badgers.generators.time_series.missingness import MissingAtRandomGenerator

Setup random generator¶

In [2]:

from numpy.random import default_rng
seed = 0
rng = default_rng(seed)

from numpy.random import default_rng seed = 0 rng = default_rng(seed)

Import data (using sktime)¶

In [3]:

from sktime.datasets import load_airline

from sktime.datasets import load_airline

In [4]:

X = load_airline()
t = X.index.to_timestamp()

X = load_airline() t = X.index.to_timestamp()

In [5]:

plt.plot(t, X.values)

plt.plot(t, X.values)

Out[5]:

[<matplotlib.lines.Line2D at 0x2e7bd6568d0>]

Missing randomly completly at random (1 Dimension)¶

In [6]:

generator = MissingAtRandomGenerator(random_generator=rng)

generator = MissingAtRandomGenerator(random_generator=rng)

In [7]:

Xt, _ = generator.generate(X.copy(), y=None, n_missing=10)

Xt, _ = generator.generate(X.copy(), y=None, n_missing=10)

In [8]:

fig, axes = plt.subplots(2, sharex=True, sharey=True, figsize=(6,6))
axes[0].plot(t, X.values)
axes[0].set_title('Original data')
axes[1].plot(t, Xt)
axes[1].set_title('Transformed data')
plt.tight_layout();

fig, axes = plt.subplots(2, sharex=True, sharey=True, figsize=(6,6)) axes[0].plot(t, X.values) axes[0].set_title('Original data') axes[1].plot(t, Xt) axes[1].set_title('Transformed data') plt.tight_layout();

Missing randomly completly at random (2 Dimensions and more)¶

In [19]:

X = np.random.normal(loc=(2,0), scale=(0.5, 0.1), size=(100,2))

X = np.random.normal(loc=(2,0), scale=(0.5, 0.1), size=(100,2))

In [20]:

Xt, _ = generator.generate(X.copy(), y=None, n_missing=25)

Xt, _ = generator.generate(X.copy(), y=None, n_missing=25)

In [21]:

fig, axes = plt.subplots(2, sharex=True, sharey=True, figsize=(6,6))
axes[0].plot(X)
axes[0].set_title('Original data')
axes[1].plot(Xt)
axes[1].set_title('Transformed data')
plt.tight_layout();

fig, axes = plt.subplots(2, sharex=True, sharey=True, figsize=(6,6)) axes[0].plot(X) axes[0].set_title('Original data') axes[1].plot(Xt) axes[1].set_title('Transformed data') plt.tight_layout();

In [ ]:

In [ ]: