import pylab as pl from Framework.DataSet import * from Tools import writeapriorifile dataset = DataSet( datafile ='../data/normalized.csv', na_values=['?'], string_columns=['state','communityname'], ) dataset = dataset.fix_missing(drop_objects=True) dataset = dataset.binarize() minSup = 40 minConf = 90 maxRule = 4 # BEGIN APRIORI filename = '../tmp/apriori.txt' writeapriorifile.WriteAprioriFile(dataset.X, filename=filename)
# '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 displayN = 10
#'countyCode', 'communityCode',
#'fold',
'murders', 'murdPerPop',
'rapes', 'rapesPerPop',
'robberies', 'robbbPerPop',
'assaults', 'assaultPerPop',
'burglaries', 'burglPerPop',
'larcenies', 'larcPerPop',
'autoTheft', 'autoTheftPerPop',
'arsons', 'arsonsPerPop',
#'ViolentCrimesPerPop',
'nonViolPerPop',
])
crime = crime.normalize()
crime = crime.fix_missing(fill_mean=True)
crime = crime.discretize('ViolentCrimesPerPop',2)
crime = crime.classIn('ViolentCrimesPerPop')
print(type(crime.X))
print(crime.y)
X=crime.X
dataset=crime
y = crime.y
X = dataset.X
y = dataset.y
N = dataset.N
M = dataset.M
import pylab as pl
from Framework.DataSet import *
from Tools import writeapriorifile
dataset = DataSet(
datafile='../data/normalized.csv',
na_values=['?'],
string_columns=['state', 'communityname'],
)
dataset = dataset.fix_missing(drop_objects=True)
dataset = dataset.binarize()
minSup = 40
minConf = 90
maxRule = 4
# BEGIN APRIORI
filename = '../tmp/apriori.txt'
writeapriorifile.WriteAprioriFile(dataset.X, filename=filename)
import numpy as np
import subprocess
from subprocess import call
import re
import os
# Run Apriori Algorithm
print('Mining for frequent itemsets by the Apriori algorithm')
# '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')