Python DataSet.standardize示例

示例#1

# 	'nonViolPerPop',
# ])
crime = crime.take_columns([
    'racePctHisp',
    'racePctWhite',
    #'racepctblack',
    #'racePctAsian',
    'medIncome',
    'NumStreet',
    'NumImmig',
    'PctEmploy',
    'PctPopUnderPov',
    'pctUrban'
])
crime = crime.fix_missing(fill_mean=True)
crime = crime.standardize()
#crime = crime.normalize()
#crime = crime.drop_nominals()

crime = crime.take_first_n_rows(200)

crime = crime.discretize('racePctWhite', 2)
crime = crime.set_class_column('racePctWhite')
#crime = DataSet(dataframe=crime.df[:200])
#print(crime.df.assaults)
print(crime.y)
#col = crime.one_of_k('pctUrban', 2)
#print(col)
#dataset = crime.discretize('pctUrban', 2)
#dataset = crime.set_class_column('pctUrban')
#print(dataset.y)

示例#2

##	'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)



outer_n = 5
inner_n = 3
for outer_i in range(outer_n):
	
	
	X = dataset.X
	M = dataset.M
	N = dataset.N
	
	

示例#3

文件： clustering.py 项目： maddymanu/machinelearning-project

# 	'larcenies', 'larcPerPop',
# 	'autoTheft', 'autoTheftPerPop',
# 	'arsons', 'arsonsPerPop',
# 	'ViolentCrimesPerPop',
# 	'nonViolPerPop',
# ])
crime = crime.take_columns([
	'racePctHisp', 
	'racePctWhite',
	#'racepctblack',
	#'racePctAsian',
	'medIncome', 'NumStreet', 'NumImmig',
	'PctEmploy', 'PctPopUnderPov', 'pctUrban'
	])
crime = crime.fix_missing(fill_mean=True)
crime = crime.standardize()
#crime = crime.normalize()
#crime = crime.drop_nominals()

crime = crime.take_first_n_rows(200)

crime = crime.discretize('racePctWhite', 2)
crime = crime.set_class_column('racePctWhite')
#crime = DataSet(dataframe=crime.df[:200])
#print(crime.df.assaults)
print(crime.y)
#col = crime.one_of_k('pctUrban', 2)
#print(col)
#dataset = crime.discretize('pctUrban', 2)
#dataset = crime.set_class_column('pctUrban')
#print(dataset.y)