gistfile1.txt

import pickle
import seaborn as sns
import pandas as pd
import numpy as np
from collections import Counter
import matplotlib.pyplot as plt
import pymc as pm

review = pickle.load(open('pickles/review.pkl'))
review['date'] = pd.to_datetime(review['date'])
biz = pickle.load(open('pickles/business.pkl'))
biz = biz.sort(column="review_count", ascending=False)

businessids = [ i for i in biz['business_id'][:500]]


influencers=[]
allreviews=[]
start = 0
n=50
finish = start+n

for idx, bizid in enumerate(businessids[start:finish]):
    temp = review[review['business_id'] == bizid]
    temp = temp.sort(column='date')
    asdf = temp.groupby(by='date').count()
    timetemp = pd.Series(asdf.stars.values, index=asdf.index)

#     timetemp.plot()
    

    count_data = timetemp.values # count data keeps track of the number of reviews per day
    n_count_data = len(timetemp.values) # n_count_date is just a limit of how many days to keep track of
    
    alpha = 1.0 / count_data.mean()  # Recall count_data is the
                                   # variable that holds our txt counts
    lambda_1 = pm.Exponential("lambda_1", alpha)
    lambda_2 = pm.Exponential("lambda_2", alpha)
    
    tau = pm.DiscreteUniform("tau", lower=0, upper=n_count_data)
    @pm.deterministic
    def lambda_(tau=tau, lambda_1=lambda_1, lambda_2=lambda_2):
        out = np.zeros(n_count_data)
        out[:tau] = lambda_1  # lambda before tau is lambda1
        out[tau:] = lambda_2  # lambda after (and including) tau is lambda2
        return out
    observation = pm.Poisson("obs", lambda_, value=count_data, observed=True)
    model = pm.Model([observation, lambda_1, lambda_2, tau])
    
    mcmc = pm.MCMC(model)
    mcmc.sample(40000, 10000, 3)
    lambda_1_samples = mcmc.trace('lambda_1')[:]
    lambda_2_samples = mcmc.trace('lambda_2')[:]
    tau_samples = mcmc.trace('tau')[15:] # cut off point for tau
    
    tempidx = Counter(tau_samples).most_common(1)[0][0]
    print " ", temp.iloc[tempidx]['date'], tempidx
    try:
        a = temp[temp['date'] <= timetemp.index[tempidx]]
        for i in a['user_id'][:10]:
            influencers.append(i)
    
    except Exception:
        influencers.append("not enough samples for business % s" % (bizid))
    
    try:
        b = temp[temp['date'] > timetemp.index[tempidx]]
        for i in b['user_id'][-5:]:
            influencers.append(i)
    
    except Exception:
        influencers.append("not enough samples for business % s" % (bizid))