mtramba

from random import randint, choice
import numpy as np

class Passenger():
    
  def __init__(self, desired_floor = 0, current_floor = 0):
    self.desired_floor = desired_floor #floor passenger wants to go to
    self.current_floor = current_floor #current floor the elevator is at
    self.waittime = 0 #total waittime for the passenger

mtramba

from math import sqrt

class Car():
    #define a car and its attributes
    
    def __init__(self, mileage = 0, make = "Tesla", model = "Model X", x = 0, y = 0):
        self.mileage = mileage
        self.make = make
        self.model = model
        self.x = x

mtramba

TASK 1:
def bad_proposal_rvs(size):
    return {
        'mu': sts.norm.rvs(loc=1, scale=3, size=num_samples),
        'sigma': sts.norm.rvs(loc=1, scale=3, size=num_samples)}


def good_proposal_rvs(size):
    return {
        'mu': np.concatenate((sts.norm.rvs(loc=-4.5, scale=1, size=1000), sts.norm.rvs(loc=3, scale=1, size=4000))),

mtramba

def norminvgamma_rvs(mu, nu, alpha, beta, size=1):
    '''
    Generate n samples from the normal-inverse-gamma distribution. This function
    returns a (size x 2) matrix where each row contains a sample, (x, sigma2).
    '''
    sigma2 = stats.invgamma.rvs(a=alpha, scale=beta, size=size)  # Sample sigma^2 from the inverse-gamma
    x = stats.norm.rvs(loc=mu, scale=np.sqrt(sigma2 / nu), size=size)  # Sample x from the normal
    return np.vstack((x, sigma2)).transpose()
    
samples = norminvgamma_rvs(mu_1, nu_1, alpha_1,beta_1, size = 1000)

mtramba

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

# Field goal rate data. Each tuple contains (field goals made, field goals attempted).
player_field_goal_data = {
    # http://www.espn.com/nba/player/gamelog/_/id/2594922/year/2018/otto-porter-jr
    'Otto Porter Jr': [(0, 0), (4, 9), (4, 8), (3, 7), (5, 10), (4, 7), (0, 0), (5, 8), (4, 9)],
    # http://www.espn.com/nba/player/gamelog/_/id/3024/year/2018/jj-redick

mtramba

#Task 1

from scipy.special import betaln
import numpy as np

def multiply(numbers):  
    total = 1
    for x in numbers:
        total *= x  
    return total

mtramba

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


electoral_votes = {
    'Alabama': 9,
    'Alaska': 3,
    'Arizona': 11,

mtramba

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from scipy import stats

plt.figure(1, figsize=(12, 10))
n=1000
p = .1
    

mtramba

import numpy as np
from scipy import stats
import matplotlib.pyplot as plt
import pandas as pd
%matplotlib inline

social_data = pd.read_csv('socialmobility.csv')
print (social_data)

#establish alphas_0 and prior

mtramba

##Task 1

stan_results_c = stan_model.sampling(data=eczema_data['control'])
print(stan_results_c.stansummary(pars=['p'], probs=[0.025, 0.5, 0.975]))
posterior_samples_c = stan_results_c.extract()
print(
    "Posterior 95% confidence interval for p:",
    np.percentile(posterior_samples_c['p'], [2.5, 97.5]))

plt.hist(posterior_samples['p'], bins=50, density=True)