sdia-zz

#!/usr/bin/env python3
#-*- coding:utf-8 -*-

import os
import numpy as np

MDE = .01
POWER = .8
BOOT_SIZE = 1000
BOOT_RUNS = 256

sdia-zz

#!/usr/bin/env python3
#-*- coding:utf-8 -*-




import random
import os
import binascii

sdia-zz

{
    "accountId": "12345",
    "projectId": "23456",
    "revision": "6",
    "version": "2",
    "experiments": [
        {
            "key": "my_experiment",
            "id": "45678",
            "layerId": "34567",

sdia-zz

# list all containers
docker ps -aq

# stop running containers
docker stop $(docker ps -aq)

# remove all containers
docker rm $(docker ps -aq)

# remove all images

sdia-zz

import boto3



S3 = boto3.resource('s3', region_name='us-west-2')



fpath = '/path/to/local/file/to/upload.txt'
s3_path = '/path/to/file/in/s3.txt'

sdia-zz

belief = Beta(2,2) # belief is instance of Beta
data = None

while True:
    data = get_new_data()
    belief =  belief * likelihood(data)
    assert IsInstance(belief, Beta) == True   # belief remains an instance of Beta

sdia-zz

%matplotlib inline
import numpy as np
import scipy.stats as stats
from IPython.core.pylabtools import figsize
import matplotlib.pyplot as plt


figsize(12.5, 5)

params = [(2, 5), (1, 1), (0.5, 0.5), (5, 5), (20, 4), (5, 1)]

sdia-zz

def prob_b_winning(a_success, a_fail, b_success, b_fail):
    predict = 0
    for i in range(b_success):
        predict += math.exp(beta_l(a_success + i, b_fail + a_fail)
                            - math.log(b_fail + i)
                            - beta_l(1 + i, b_fail)
                            - beta_l(a_success, a_fail))
    return predict

sdia-zz

from scipy.stats import beta
import matplotlib.pyplot as plt
import numpy as np

a = 2
b = 12

x = np.arange(0.001, 1, 0.01)
y = beta.pdf(x, a, b)

sdia-zz

def beta_1(a, b):
    return math.gamma(a) * math.gamma(b) / math.gamma(a + b)