In [1]:

    

import pandas as pd
import numpy as np
from sklearn.linear_model import LogisticRegression
from sklearn.linear_model import SGDClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
from sklearn import cross_validation
from sklearn.metrics import roc_auc_score
import re


    

In [2]:

    

#donations = pd.read_csv('../data/donations.csv').sort('projectid')
projects = pd.read_csv('../data/projects.csv').sort('projectid')
#outcomes = pd.read_csv('../data/outcomes.csv').sort('projectid')
resources = pd.read_csv('../data/resources.csv')
#sample = pd.read_csv('../data/sampleSubmission.csv').sort('projectid')
#essays = pd.read_csv('../data/essays.csv').sort('projectid')


    

In [3]:

    

s = resources.project_resource_type.unique()


    

In [4]:

    

s.size


    

    
Out[4]:





7

In [5]:

    

arr = np.zeros((projects.shape[0],7))


    

In [6]:

    

arr.shape


    

    
Out[6]:





(664098, 7)

In [7]:

    

le = LabelEncoder()


    

In [8]:

    

le.fit(projects.projectid)


    

    
Out[8]:





LabelEncoder()

In [ ]: