tansey

import numpy as np
import numpy.ma as ma


def cap_outliers(points, thresh=3.5, data=None, median=None, med_abs_deviation=None):
    '''
    Cap outliers to be within a certain number of median deviations.
    '''
    if type(points) is np.float64:
        points = np.array([points])

tansey

import numpy as np

def pav(y):
    """
    PAV uses the pair adjacent violators method to produce a monotonic
    smoothing of y

    translated from matlab by Sean Collins (2006) as part of the EMAP toolbox
    Author : Alexandre Gramfort
    license : BSD

tansey

import matplotlib.pyplot as plt
import numpy as np
import statsmodels.api as sm


def generalized_liang_sim_xy(N=500, P=500, S=100):
    '''Generates data from a simple linear model'''
    X = (np.random.normal(size=(N,1)) + np.random.normal(size=(N,P))) / 2.
    w0 = np.random.normal(1, size=S//4)
    w1 = np.random.normal(2, size=S//4)

tansey

import numpy as np
from functools import partial
from scipy.optimize import fmin_l_bfgs_b
from sklearn.linear_model import LogisticRegression


def binary_mf(Y, nembeds, lam=None, lams=30, cv=5, max_steps=30, tol=1e-4, verbose=False):
    # Convert to a log-space grid
    if lam is None and isinstance(lams, int):
        lams = np.exp(np.linspace(np.log(1e-2), np.log(1), lams))

tansey

'''
A O(nlogn) time implementation of the knockoff filter.

Author: Wesley Tansey
Date: 3/27/2020
'''
import numpy as np

def knockoff_filter(knockoff_stats, alpha, offset=1.0, is_sorted=False):
    '''Perform the knockoffs selection procedure at the target FDR threshold.

tansey

'''
Heterogeneous factor modeling.

This model fits a heterogeneous factor model where columns may be:
1) Binary
2) Categorical
3) Gaussian

Everything is fit via alternating minimization and stochastic gradient descent.
The code relies on pytorch for SGD and a demo is included.

tansey

'''Pool adjacent violators algorithm for (column-)monotone matrix factorization.

Applies the PAV algorithm to column factors of a matrix factorization:
Given: M = W.V'
Returns: V_proj, a projected version of V such that M[i] is monotone decreasing
for all i.

Author: Wesley Tansey
Date: May 2019
'''

tansey

'''Fast sampling from a multivariate normal with covariance or precision
    parameterization. Supports sparse arrays. Params:
        - mu: If provided, assumes the model is N(mu, Q)
        - mu_part: If provided, assumes the model is N(Q mu_part, Q).
                    This is common in many conjugate Gibbs steps.
        - sparse: If true, assumes we are working with a sparse Q
        - precision: If true, assumes Q is a precision matrix (inverse covariance)
        - chol_factor: If true, assumes Q is a (lower triangular) Cholesky
                        decomposition of the covariance matrix
                        (or of the precision matrix if precision=True).

tansey

'''
    Program to generate valid time allocations of a mental ward staff.


    Given:

    Two staff lists. Each list applies for a specific window of time. Lists may
    contain non-empty intersections of employees.

    Each employee has a designation as RMN or HCA.

tansey

# Fit using a simple EM algorithm
# observations are x
# weights are w (must be same length as x)
# returns (r, p)
# r - dispersion parameter
# p - probability of success
weightedNegBinomFit <- function(x, w, maxsteps=30)
{
    sum.wx = sum(x*w)
    sum.w = sum(w)