from sklearn.naive_bayes import BernoulliNB
from sklearn import svm
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
import time
import numpy as np
from sklearn.preprocessing import LabelBinarizer
from sklearn.externals import joblib
#features = ['DayOfWeekNo', 'PdDistrict_ID', 'Year', 'Month', 'Day', 'Hour', 'X_quan', 'Y_quan', 'Street1_ID', 'Street2_ID']
print 'preparing training data...'
if not os.path.exists('train_clean.csv'):
train_raw = pd.read_csv('train.csv')
train_prepared = munge(train_raw, 'train_clean.csv')
else:
train_prepared = pd.read_csv('train_clean.csv')
neg_fea = [u'X_quan', u'Y_quan', u'X', u'Y', u'Category', u'Descript', u'DayOfWeek', u'PdDistrict', u'Resolution', u'Category_ID',
u'Address', u'PdDistrict_ID', u'DayOfWeekNo', u'Day', u'Month', u'Year', u'Hour', u'Dates']
y = train_prepared['Category_ID']
X = train_prepared.drop(neg_fea, 1)
X = X.drop(X.columns[0], 1)
# free up memory occupied by train_prepared
del train_prepared
train_prepared = None
print 'Fitting...'
for dc in cols_to_drop:
if re.match(dc, col):
data.drop(col, axis=1, inplace=True)
break
def singly_predict(clf, trainX, trainY, testX):
clf.fit(trainX, trainY)
results = clf.predict(testX)
write_results(results)
if os.path.isfile('train_clean.csv'):
train_data = pd.read_csv('train_clean.csv')
else:
train_data = munge('train')
if os.path.isfile('test_clean.csv'):
test_data = pd.read_csv('test_clean.csv')
else:
test_data = munge('test')
y = train_data['Hazard']
X = train_data.drop(['Id', 'Hazard'], axis=1)
Id = test_data['Id']
test_data.drop('Id', axis=1, inplace=True)
# drop cols
Dropcols = ['T2_V10', 'T2_V7', 'T1_V13', 'T1_V10']
