dataset = DataSet(
datafile ='../data/raw.csv',
na_values=['?'],
string_columns=['state'],
)
dataset = dataset.set_class_column('communityname')
dataset = dataset.drop_columns([
# 'communityname',
# 'countyCode',
## 'communityCode',
# 'fold',
# 'murders', 'murdPerPop',
# 'rapes', 'rapesPerPop',
# 'robberies', 'robbbPerPop',
# 'assaults', 'assaultPerPop',
# 'burglaries', 'burglPerPop',
# 'larcenies', 'larcPerPop',
# 'autoTheft', 'autoTheftPerPop',
# 'arsons', 'arsonsPerPop',
# 'ViolentCrimesPerPop',
# 'nonViolPerPop',
])
#dataset = dataset.standardize()
dataset = dataset.standardize();
dataset = dataset.fix_missing(drop_attributes=True)
crime = DataSet(
datafile='../data/raw.csv',
nominals=['state', 'communityname', 'countyCode', 'communityCode'])
#crime = crime.drop(['state', 'communityname']) # Drop strings
#crime = crime.drop(['countyCode','communityCode']) # Drop nominals
crime = crime.drop_columns([
'fold',
'murders',
'murdPerPop',
'rapes',
'rapesPerPop',
'robberies',
'robbbPerPop',
# 'assaults', 'assaultPerPop',
'burglaries',
'burglPerPop',
'larcenies',
'larcPerPop',
'autoTheft',
'autoTheftPerPop',
#'arsons', 'arsonsPerPop',
'ViolentCrimesPerPop',
#'nonViolPerPop',
])
print(type(crime.X))
crime = crime.normalize()
crime = crime.take_columns(['nonViolPerPop', 'arsons'])
#print(crime)
from Framework.DataSet import *
crime = DataSet(
datafile ='../data/raw.csv',
na_values=['?'],
string_columns =['communityname','state'],
class_column = 'state'
)
crime = crime.drop_columns([
'fold',
'murders', 'murdPerPop',
'rapes', 'rapesPerPop',
'robberies', 'robbbPerPop',
'assaults', 'assaultPerPop',
'burglaries', 'burglPerPop',
'larcenies', 'larcPerPop',
'autoTheft', 'autoTheftPerPop',
'arsons', 'arsonsPerPop',
'ViolentCrimesPerPop',
'nonViolPerPop',
])
crime = crime.normalize()
data = crime
data = data.fix_missing(drop_objects=True)
#mat_data = loadmat('../Data/synth1.mat')
#X = np.matrix(mat_data['X'])
X = data.X