Ctrl+K

mightypy.make package

mightypy.make package#

Module contents#

mightypy.make#

rotation_matrix_2d(theta: float) → ndarray[source]#

Create 2D data rotation matrix.

Reference article#

https://en.wikipedia.org/wiki/Rotation_matrix

param theta:

angle for rotation.

type theta:

float

returns:

rotation matrix.

rtype:

np.ndarray

sine_wave_from_sample(n_samples: int, signal_freq: float, n_cycles: int = 10, amplitude: int = 1, amp_shift: int = 0, phase_shift: int = 0) → Tuple[ndarray, ndarray, ndarray][source]#

Sine wave generation with number of samples and signal frequency

Reference:

https://machinelearningexploration.readthedocs.io/en/latest/MathExploration/Fourier.html#Sine-wave

Parameters:

  • n_samples (int) – number of samples.

  • signal_freq (float) – signal frequency.

  • n_cycles (int, optional) – number of cycles. Defaults to 10.

  • amplitude (int, optional) – signal amplitude. Defaults to 1.

  • amp_shift (int, optional) – amplitude shift. Defaults to 0.

  • phase_shift (int, optional) – phase shift. Defaults to 0.

Returns:

signal wave, time, freq.

Return type:

Tuple[np.ndarray, np.ndarray, np.ndarray]

sine_wave_from_timesteps(signal_freq: float, time_step: float, amplitude: int = 1, amp_shift: int = 0, phase_shift: int = 0) → Tuple[ndarray, ndarray, ndarray][source]#

Sine wave generation with time steps and signal frequency

Parameters:

  • signal_freq (float) – singal frequency.

  • time_step (float) – time step.

  • amplitude (int, optional) – amplitude. Defaults to 1.

  • amp_shift (int, optional) – amplitude shift. Defaults to 0.

  • phase_shift (int, optional) – phase shift. Defaults to 0.

Returns:

signal wave, time, freq.

Return type:

Tuple[np.ndarray, np.ndarray, np.ndarray]

spiral_data(data_limit: int = 30, n_classes: int = 2, n_samples_per_class=300) → Tuple[ndarray, ndarray][source]#

Generate spiral data for classification problem.

Parameters:

  • data_limit (int, optional) – range of data. Defaults to 30.

  • n_classes (int, optional) – number of classes for classification. Defaults to 2.

  • n_samples_per_class (int, optional) – number of samples per classes. Defaults to 300.

Returns:

X,y.

Return type:

Tuple[np.ndarray, np.ndarray]

Contents