In [1]:

    

import pandas as pd
import numpy as np
from sklearn.preprocessing import LabelEncoder
import pylab as p


    

In [2]:

    

projects = pd.read_csv('../data/projects.csv')
outcome = pd.read_csv('../data/outcomes.csv')


    

In [3]:

    

projects = projects.merge(outcome, how = 'inner')


    

In [4]:

    

projects = projects.sort('date_posted')


    

In [5]:

    

le = LabelEncoder()


    

In [6]:

    

for i in range(0,projects.shape[0]):
    projects.date_posted[i] = projects.date_posted[i][0:7]


    

In [7]:

    

projects['date_posted'] = le.fit_transform(projects.date_posted)


    

In [8]:

    

projects = projects[['date_posted','is_exciting']]


    

In [9]:

    

tot = projects[projects.date_posted == 0]
true = [float(tot[tot.is_exciting == 't'].count()[0])/float(tot.count()[0])]
for i in range(1,projects.date_posted.max()+1):
    tot = projects[projects.date_posted == i]
    true.append(float(tot[tot.is_exciting == 't'].count()[0])/float(tot.count()[0]))


    

In [10]:

    

p.plot(true)


    

    
Out[10]:





[<matplotlib.lines.Line2D at 0xee98350>]

In [11]:

    

p.show()