In [3]:

    

import numpy as np
import matplotlib.pyplot as plt
import MySQLdb
%matplotlib inline


    

In [4]:

    

db = MySQLdb.connect(host="localhost", user="root", db = "home_kitchen")
cursor = db.cursor()


    

In [5]:

    

tablename = 'all_hk'


    

In [17]:

    

PIDlistquery = 'Select PID from (SELECT PID, RScore, COUNT(*) AS magnitude FROM all_hk GROUP BY PID HAVING magnitude > 500 ORDER BY magnitude ASC LIMIT 200) as a'
cursor.execute(PIDlistquery)
Pidlist = cursor.fetchall()


    

In [42]:

    

pidlist = zip(*Pidlist)[0]


    

In [43]:

    

def running_avg(data):
    avg = [0]*len(data)
    total = 0
    for k in range(len(data)):
        #avg[k] = np.mean(data[:k])
        total += data[k]
        avg[k] = float(total/(k+1))
    return avg


    

In [55]:

    

PID = pidlist[2]
print PID


    

    




 B000P1NYE8

In [56]:

    

sql = "Select RTime, RScore From " +tablename + " Where PID = " + '"' + PID +'";'


    

In [57]:

    

cursor.execute(sql)
data = cursor.fetchall()
data = sorted(data)


    

In [58]:

    

rating = zip(*data)[1]
time = zip(*data)[0]
avg =[]
normal_time = [0]*len(time)


    

In [59]:

    

avg = running_avg(rating)


    

In [60]:

    

nums = np.arange(len(avg))


    

In [61]:

    

diffs = [avg[i] - avg[len(avg)-1] for i in range(len(avg))]


    

In [62]:

    

plt.scatter(nums, diffs)


    

    
Out[62]:





<matplotlib.collections.PathCollection at 0x1135284d0>






    

In [65]:

    

#how long til convergence within .1?
a = 0
for i in range(len(diffs)):
    if -.1<diffs[i]<.1:
        a = i
        
print a, len(diffs)


    

    




509 510

In [64]:

    

print PID


    

    




 B000P1NYE8

In [ ]: