In [1]:

    

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


    

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


    

In [3]:

    

dates = np.array(projects.date_posted)
train_idx = np.where(dates < '2014-01-01')[0]
test_idx = np.where(dates >= '2014-01-01')[0]


    

In [4]:

    

projects = projects.fillna(method='pad')


    

In [5]:

    

outcomes = np.array(outcomes.is_exciting)


    

In [6]:

    

projectCatogorialColumns = ['school_city', 'school_state', 'school_zip', 'school_metro', 'school_district', 'school_county', 'school_charter', 'school_magnet',
 'school_year_round', 'school_nlns', 'school_kipp', 'school_charter_ready_promise', 'teacher_prefix', 'teacher_teach_for_america', 'teacher_ny_teaching_fellow', 'primary_focus_subject','primary_focus_area', 
'secondary_focus_subject', 'secondary_focus_area', 'resource_type', 'poverty_level', 'grade_level',
'students_reached', 'eligible_double_your_impact_match', 'eligible_almost_home_match' ]


    

In [7]:

    

datePosted = projects['date_posted']
projects = np.array(projects[projectCatogorialColumns])


    

In [9]:

    

projects = np.column_stack((projects,datePosted))


    

In [10]:

    

for i in range(0, projects.shape[1]):
    le = LabelEncoder()
    projects[:,i] = le.fit_transform(projects[:,i])
projects = projects.astype(float)


    

In [11]:

    

ohe = OneHotEncoder()
projects = ohe.fit_transform(projects)


    

In [12]:

    

projects = projects[train_idx]


    

In [13]:

    

train, crossval, outcomeTrain, outcomeCrossVal = cross_validation.train_test_split(projects, outcomes, test_size=0.4, random_state=1)


    

In [14]:

    

model = LogisticRegression(C = .1)
model.fit(train, outcomeTrain=='t')


    

    
Out[14]:





LogisticRegression(C=0.1, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, penalty='l2', random_state=None, tol=0.0001)

In [15]:

    

preds = model.predict_proba(crossval)[:,1]


    

In [16]:

    

value = roc_auc_score(outcomeCrossVal=='t', preds)


    

In [17]:

    

value


    

    
Out[17]:





0.75522913931681535

In [ ]: