In [1]:

    

import pandas as pd
import numpy as np
from sklearn.linear_model import SGDClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
from sklearn.grid_search import GridSearchCV


    

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') & (dates > '2010-01-01'))[0]
test_idx = np.where(dates >= '2014-01-01')[0]


    

In [4]:

    

outcomes = outcomes.merge(projects[projects.date_posted > '2010-01-01'], how ='inner')


    

In [5]:

    

outcomes.shape, train_idx.shape


    

    
Out[5]:





((439478, 46), (439478,))

In [6]:

    

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


    

In [7]:

    

outcomes = np.array(outcomes.is_exciting)


    

In [8]:

    

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 [9]:

    

projects = np.array(projects[projectCatogorialColumns])


    

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]:

    

train = projects[train_idx]
test = projects[test_idx]


    

In [13]:

    

lr = SGDClassifier()
parameters = {'alpha':[0.001],'loss':['log'],
'penalty' : ['l2'], 'n_iter':[100,1000],'n_jobs':[-1]}
clf = GridSearchCV(lr, parameters, scoring = 'roc_auc', n_jobs = -1)


    

In [14]:

    

clf.fit(train, outcomes=='t')


    

    
Out[14]:





GridSearchCV(cv=None,
       estimator=SGDClassifier(alpha=0.0001, class_weight=None, epsilon=0.1, eta0=0.0,
       fit_intercept=True, l1_ratio=0.15, learning_rate='optimal',
       loss='hinge', n_iter=5, n_jobs=1, penalty='l2', power_t=0.5,
       random_state=None, rho=None, shuffle=False, verbose=0,
       warm_start=False),
       fit_params={}, iid=True, loss_func=None, n_jobs=-1,
       param_grid={'penalty': ['l2'], 'alpha': [0.001], 'n_iter': [100, 1000], 'n_jobs': [-1], 'loss': ['log']},
       pre_dispatch='2*n_jobs', refit=True, score_func=None,
       scoring='roc_auc', verbose=0)

In [15]:

    

clf.grid_scores_


    

    
Out[15]:





[mean: 0.63304, std: 0.00048, params: {'penalty': 'l2', 'alpha': 0.001, 'n_iter': 100, 'n_jobs': -1, 'loss': 'log'},
 mean: 0.63304, std: 0.00051, params: {'penalty': 'l2', 'alpha': 0.001, 'n_iter': 1000, 'n_jobs': -1, 'loss': 'log'}]

In [16]:

    

clf.best_estimator_


    

    
Out[16]:





SGDClassifier(alpha=0.001, class_weight=None, epsilon=0.1, eta0=0.0,
       fit_intercept=True, l1_ratio=0.15, learning_rate='optimal',
       loss='log', n_iter=1000, n_jobs=-1, penalty='l2', power_t=0.5,
       random_state=None, rho=None, shuffle=False, verbose=0,
       warm_start=False)

In [17]:

    

clf.best_score_


    

    
Out[17]:





0.6330430843742525

In [18]:

    

clf.best_params_


    

    
Out[18]:





{'alpha': 0.001, 'loss': 'log', 'n_iter': 1000, 'n_jobs': -1, 'penalty': 'l2'}

In [18]: