michaelchughes

vals_float32 = np.logspace(0, 5, dtype=np.float32)                                                                           
vals_float64 = np.logspace(0, 5, dtype=np.float64)                                                                           

## Pretty-print output of array so each float takes same num chars
def pprint_arr(arr, n_per_line=6): 
     for s in range(0, arr.size, n_per_line): 
         chunk = arr[s:s+n_per_line] 
         print(" ".join(["%10s" % np.format_float_scientific(x, precision=2, unique=False, exp_digits=3) for x in chunk])) 

print()

michaelchughes

import argparse
import pandas as pd
import os
import subprocess
import psutil

global GPU_UUID_MAP
GPU_UUID_MAP = dict()

def get_current_cpu_mem_usage(field='rss', process=None):

michaelchughes

sacct -j 56012984_1.batch --format=jobid,jobname,partition,maxvmsize,maxrss,state,elapsed,reqmem,reqcpus

michaelchughes

import numpy as np
import scipy.stats

from scipy.special import logsumexp, softmax

np.set_printoptions(precision=3, suppress=1)

## Settings
## --------

michaelchughes

## Using notation from HDP-HMM paper in NeurIPS 2015 (Hughes, Stephenson, Sudderth)

## Start for a single sequence of interest,
## Compute the following as in the tutorial here:
https://bnpy.readthedocs.io/en/latest/examples/08_mocap6/plot-03-demo=interpret_hdphmm_params_and_run_viterbi.html#sphx-glr-examples-08-mocap6-plot-03-demo-interpret-hdphmm-params-and-run-viterbi-py

# start_prob_K : 1D array size K, sums to one
# trans_proba_KK : 2D array, size K x K, rows sum to one
# log_lik_seq_TK : 2D array, size T x K

michaelchughes

S = 10 # num samples throughout

## FIRST, REMEMBER THE COMMON PARAMETERIZATION
# x ~ Normal(m, sigma^2)
# m is a real number
# sigma >= 0 is a standard deviation

m = 2
sigma = 0.1

michaelchughes

michaelchughes

import pandas as pd
import numpy as np
import time

prng = np.random.RandomState(0)

n_subj = 20000
n_rows = 1000000

# Randomly assign to one of 20000 subjects

michaelchughes

import numpy as np
import pandas as pd
import argparse

def convert_ordered_dx_df_to_indicator_df(
        ordered_dx_df,
        list_of_possible_icd_code_values=None,
        list_of_possible_icd_code_names=None):
    ''' Convert rank-ordered diagnosis codes into indicator format

michaelchughes

RECIPE TO TOTALLY REMOVE BAD FILES FROM A GIT REPO WITH MULTIPLE USERS

1) Make sure all local copies of the repo are sync'd on the same commit

We assume that there are two users (A and B). A is gonna delete the bad files. B is gonna receive the changes.

At the start, we need A and B to have the SAME version history.

We'll assume there are no branches other than master.