In [1]:

    

#import pandas as pd


    

    




/Users/kelty/Desktop/Amazon-Review-Project/venv/lib/python2.7/site-packages/pandas/io/excel.py:626: UserWarning: Installed openpyxl is not supported at this time. Use >=1.6.1 and <2.0.0.
  .format(openpyxl_compat.start_ver, openpyxl_compat.stop_ver))

In [1]:

    

import numpy as np


    

In [29]:

    

import datetime as dt


    

In [3]:

    

import matplotlib.pyplot as plt


    

In [4]:

    

import MySQLdb


    

In [5]:

    

%matplotlib inline


    

In [6]:

    

def time_data_clean(time_data):
    rating = [0.0]*len(time_data)
    time = [0]*len(time_data)
    rating = [x[0] for x in time_data]
    time = [x[1] for x in time_data]
    return rating, time


    

In [7]:

    

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


    

In [8]:

    

cursor = db.cursor()


    

In [9]:

    

tablename = 'electronics'


    

In [10]:

    

prod_id = ' B000KO0GY6'


    

In [11]:

    

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


    

In [12]:

    

print sql


    

    




Select RTime, RScore From electronics Where PID = " B000KO0GY6";

In [13]:

    

cursor.execute(sql)


    

    
Out[13]:





427L

In [14]:

    

time_data = cursor.fetchall()


    

In [15]:

    

time_data = sorted(time_data)


    

In [74]:

    

#print time_data


    

In [75]:

    

#rating, time = time_data_clean(time_data)


    

In [76]:

    

#print rating


    

In [77]:

    

#print time


    

In [16]:

    

rating = zip(*time_data)[1]


    

In [17]:

    

time = zip(*time_data)[0]


    

In [30]:

    

dates=[dt.datetime.fromtimestamp(ts) for ts in time]


    

In [18]:

    

#print time


    

In [32]:

    

plt.scatter(dates, rating)


    

    
Out[32]:





<matplotlib.collections.PathCollection at 0x1061d8910>






    

In [20]:

    

avg = [0]*len(time)


    

In [21]:

    

limited_avg = [0]*len(time)


    

In [22]:

    

avg[0] = rating[0]


    

In [23]:

    

limited_avg[0] = rating[0]


    

In [24]:

    

for k in range(1, len(time)):
    avg[k]= np.mean(rating[:k])


    

In [25]:

    

for k in range(1, len(time)):
    if k<100:
        limited_avg[k]= np.mean(rating[:k])
    else:
        limited_avg[k]=np.mean(rating[k-100:k])


    

In [26]:

    

#print avg


    

In [33]:

    

plt.scatter(dates, avg)


    

    
Out[33]:





<matplotlib.collections.PathCollection at 0x106265350>






    

In [34]:

    

plt.scatter(dates, limited_avg)


    

    
Out[34]:





<matplotlib.collections.PathCollection at 0x1062ef390>






    

In [28]:

    

timemin = time[0]


    

In [29]:

    

mink = 0


    

In [30]:

    

for k in range(len(time)):
    if time[k]<timemin:
        timemin = time[k]
        mink = k


    

In [31]:

    

print mink


    

    




29

In [32]:

    

print rating[29]


    

    




5.0

In [33]:

    

print timemin


    

    




957225600

In [35]:

    

limited_avg_50 = limited_avg[50:]


    

In [ ]: