stevenobadja

Keybase proof

I hereby claim:

• I am stevenobadja on github.
• I am obadja (https://keybase.io/obadja) on keybase.
• I have a public key ASCPhv4R1upTN17S0-bC-aa9awZdMQrqXe558_eQCNKEcAo

To claim this, I am signing this object:

stevenobadja

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

pop1 = np.random.binomial(10, 0.2, 10000)
pop2 = np.random.binomial(10,0.5, 10000) 

stevenobadja

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

# Generate a bernoulli distribution
bernoulli= np.random.binomial(1, .5, 100)
plt.hist(bernoulli)
plt.axvline(bernoulli.mean(), color='g', linestyle='solid', linewidth=2)
plt.axvline(bernoulli.mean() + bernoulli.std(), color='y', linestyle='dashed', linewidth=2)

stevenobadja

P ( Car in Door 1 | Goat in Door 2 )	
	
P ( A and B ) =  P( A | B ) * P(B)	
P ( B and A ) = P( B | A ) * P(A)	
	
	
P( A | B ) * P(B) = P( B | A ) * P(A)	
	
P( A | B ) = P( B | A ) * P(A) / P(B)	
	

stevenobadja

#Question 1
#Due to the dataset that was used was close to a holiday. 
#Certain locations may not be available. To reframe the 
#question I would ask "What are the popular Amsterdam 
#neighborhoods during Christmas?"

#Question 2
#Due to September 12, 2001 was exactly the day after the 
#911 attack I would say that the data is biased and will 
#show that services will be used more in New York. I 

stevenobadja

#Total Population
suff_pop = .005
nonsuff_pop = .955

#Testing for Sufferer
sufftest_pos = .98
sufftest_neg = .02

#Testing for Non-Sufferer
nonsufftest_pos = .1

stevenobadja

print('Question #1')
print('Probability of either of those pattern is: {:.02%} or .5**4'.format(.5**4))
print('\n')

print('Question #2')
print('Probability of not choosing a man is: {:.02%} or 24/45'.format(24/45))
print('\n')

print('Question #3')
print('Probability that Bernice will be in a plane crash sometime in the next year is: {:%} or .1*.00005'.format(.1*.00005))

stevenobadja

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
df = pd.DataFrame()

df['age'] = [14,12,11,10,8,6,8]

print ('Question #1:')
print ('Mean: {}'.format(np.mean(df['age'])))

stevenobadja

import matplotlib.pyplot as plt
import pandas as pd

df = pd.read_csv("http://bit.ly/2ifPlDC")
df.drop(['Format: Draw Number', ' Draw Date (yyyymmdd)', '6', ' Division 1', '2.1', '3.1', '4.1', '5.1', '6.1', '7', '8'], axis=1, inplace=True)
df_cols = ['first','second','third','fourth','fifth','powerball']
df.columns = df_cols
df['powerball'] = df['powerball'].str.replace('-', '0')
df['powerball'] = df.powerball.astype('int64')
plt.hist(x = (df['first'],df['second'], df['third'],df['fourth'],df['fifth'],df['powerball']), bins = 50, stacked = True, histtype = 'bar', rwidth = .8)