import numpy as np
import matplotlib.pyplot as plt
from thinkbayes2 import Pmf, Suite, CredibleInterval, Beta
# PMF for 6-sided die
pmf = Pmf()
for x in [1, 2, 3, 4, 5, 6]:
pmf.Set(x, 1 / 6)
print(pmf)
# How to build up a pmf from a list of strings
pmf2 = Pmf()
for word in ['a', 'in', 'or', 'to', 'a', 'me', 'in']:
pmf2.Incr(word, 1)
pmf2.Normalize()
print(pmf2)
print("Probability of letter a:", pmf2.Prob(
'a')) # Typo p12 print pmf.Prob('the') should read print(pmf.Prob('the'))
# PMF for the Cookie problem
pmf = Pmf()
# Prior:
pmf.Set("Bowl 1", 0.5)
pmf.Set("Bowl 2", 0.5)
# Posterior:
# First multiply prior by likelihood
pmf.Mult("Bowl 1", 0.75)
pmf.Mult("Bowl 2", 0.5)
# Then normalise (we can do this because the hypotheses are mutually exclusive and collectively exhaustive,
from thinkbayes2 import Suite, Pmf, SampleSum, MakeMixture
import thinkplot
from simulationDD02 import Die
pmf_dice = Pmf()
pmf_dice.Set(Die(4), 2)
pmf_dice.Set(Die(6), 3)
pmf_dice.Set(Die(8), 2)
pmf_dice.Set(Die(12), 1)
pmf_dice.Set(Die(20), 1)
pmf_dice.Normalize()
print(pmf_dice)
print("#################################################")
mix = Pmf()
for die, weight in pmf_dice.Items():
for outcome, prob in die.Items():
mix.Incr(outcome, weight * prob)
#Shorthand for above
#mix = MakeMixture(pmf_dice)
print(mix)
thinkplot.Hist(mix)
thinkplot.Save(root='bar',
xlabel='Mixture over a set of dice',
ylabel='Probability',
formats=['pdf'])
print("Program Finished")
class InfulsContribution(Pmf):
def __init__(self, dist_dir):
Pmf.__init__(self)
self.dist_dir = dist_dir
self.pmf = None
self.infs_data = {}
self.json_data = {}
self.dist_file = ''
def prior(self, json_data):
self.pmf = Pmf()
self.posterior(json_data)
return self
def posterior(self, json_data):
self.set_json_data(json_data)
self.update_infs_data()
self.update()
self.set_dist_file(json_data, self.dist_dir)
self.output()
return self
def output(self):
pmf = self.pmf
pmf.Normalize()
dist_data = self.make_result(pmf)
self.save_file(dist_data)
return self
# main nethods
# set jsondata as dict to self.jsondata
def set_json_data(self, json_data):
with open(json_data, 'rb') as f:
data = json.load(f)
self.json_data = data
# update self.infs_data
def update_infs_data(self):
# print('sel', self.json_data)
datas = self.json_data['analythics_data']
click_sum = self.json_data['meta_data']['click_sum']
# infs_data = 0
# for d in datas:
# infs_data += int(datas[d]['prof_clicks'])
for d in datas:
if not self.infs_data.get(d):
self.infs_data[d] = {'click_sum': 0, 'prof_clicks': 0}
self.infs_data[d]['click_sum'] += click_sum
self.infs_data[d]['prof_clicks'] += datas[d]['prof_clicks']
# set self dist_file
def set_dist_file(self, src_file, dist_dir):
dist_file = ''
a = re.search(r'\d{4}-\d{2}-\d{2}', src_file)
b = re.search(r'\d{8}', src_file)
if a: dist_file = a.group()
if b: dist_file = b.group()
dist_file = os.path.join(dist_dir, f'result{dist_file}.json')
self.dist_file = dist_file
# LiKelihood methods
def liKelihood(self, infl):
return (self.infs_data[infl]['prof_clicks'] /
self.infs_data[infl]['click_sum'])
# update datas
def update(self):
data = self.json_data['analythics_data']
click_sum = self.json_data['meta_data']['click_sum']
print('d', data)
# data = {'@yoshiki_ruby': data['@yoshiki_ruby']}
[self.pmf.Incr(infl, self.liKelihood(infl)) for infl in data]
# create result json
def make_result(self, pmf):
d = pmf.Values()
res_d = {k: pmf.Prob(k) for k in d}
res_d = sorted(res_d.items(), key=lambda x: x[1], reverse=True)
# print(res_d)
return {
v[0]: {
"rating": v[1],
"prof_clicks": self.infs_data[v[0]]['prof_clicks'],
"click_sum": self.infs_data[v[0]]['click_sum'],
}
for v in res_d
}
# output json
def save_file(self, json_file):
with open(self.dist_file, 'w') as f:
json.dump(json_file, f, indent=2)
from thinkbayes2 import Pmf
if __name__ == '__main__':
txt = []
with open('/Users/glenn/math/stats/ThinkBayes2/data/ch02_02_text_data.txt'
) as f:
txt = f.read().split()
print "txt = ", txt
pmf = Pmf()
for word in txt:
pmf.Incr(word, 1)
pmf.Normalize()
pmf.Print()
#!/usr/env python
import sys
sys.path.append("../lib/ThinkBayes2/code/")
from thinkbayes2 import Pmf
pmf = Pmf()
for x in [1, 2, 3, 4, 5, 6]:
pmf.Set(x, 1 / 6.0)
print(pmf)
words = Pmf()
f = open('alice.txt', 'r')
for line in f:
for word in line.split():
words.Incr(word.strip(), 1)
#print(words)
words.Normalize()
print(words)
print("Finished")
