rsokl

jupyter
kernelspec display_name language name Python 3 python python3

Part one - various cells

rsokl

Useful Links Regarding Probabilistic Programming

Tutorials

• Bayesian Statistics Made Simple (Allen Downey)
  • repo
  • SciPy 2019 Tutorial
• Bayesian Data Science: Probabilistic Programming (Eric Ma)
  • repo
  • SciPy 2019 Tutorial
• Introduction to Bayesian Model Evaluation, Visualization, and Comparison Using Arviz

rsokl

import numpy as np

def ecdf(data):
    """Returns (x) the sorted data and (y) the empirical cumulative-proportion
    of each datum.
    
    Parameters
    ----------
    data : numpy.ndarray, size-N
    

rsokl

def get_fourier_components(
    func, num_samples, domain_length, sort_by_descending_magnitude=False
):
    """
    Returns the N // 2 + 1 amplitude-phase terms of the inverse D series 
    of func(t), where funct t is evaluated on [0, T) in N evenly-spaced points.
    I.e each component
    
                     A[k] cos(2*pi * f[k] * t + phi[k])
    

rsokl

def plot_jobs(*jobs, fn):
    import numpy as np
    import matplotlib.pyplot as plt
    
    (jobs,) = jobs
    x, y = np.arange(-2, 2, 0.1), np.arange(-2, 2, 0.1)
    X, Y = np.meshgrid(x, y)
    V = parabaloid(X, Y)
    fig, ax = plt.subplots()

rsokl

A Crude Prototype of Using MyGrad w/ xarray

import xarray as xr
import mygrad as mg

x = xr.DataArray(mg.arange(3.))
y = xr.DataArray(mg.arange(9.).reshape(3, 3))
z = x * y

rsokl

OBS for live lectures

Download OBS: https://obsproject.com/

OBS VirtualCam (for use with Zoom): https://obsproject.com/forum/resources/obs-virtualcam.539/

Using OBS, we can do lectures live on Zoom with a face + document cam, as well as record the lectures without recording the entire Zoom meeting and everyone in it.

Installation

rsokl

def local_peaks(
    log_spectrogram: np.ndarray, amp_min: float, p_nn: int
) -> List[Tuple[int, int]]:
    """
    Defines a local neighborhood and finds the local peaks
    in the spectrogram, which must be larger than the
    specified `amp_min`.

    Parameters
    ----------