Python featureArray示例

示例#1

文件： decisionTreeClassifier.py 项目： olivierh59500/Malware-Classification

def decisionTreeClassifier():
    trainData, trainLabel = featureArray(conf['train']['feature_vector'])
    testData, testLabel = featureArray(conf['test']['feature_vector'])

    clf = tree.DecisionTreeClassifier(criterion='gini')
    clf.fit(trainData, trainLabel)
    print(clf.score(testData,testLabel))

示例#2

文件： regressionClassification.py 项目： manikamittal/Malware-Classification

def regression():
    trainData, trainLabel = featureArray(conf["train"]["feature_vector"])
    testData, testLabel = featureArray(conf["test"]["feature_vector"])

    print "RIDGE REGRESSION"
    clf = linear_model.Ridge(alpha=0.5)
    clf = clf.fit(trainData, trainLabel)
    print str(clf.score(testData, testLabel))

    print ("")
    print ("LOGISTIC REGRESSION")
    clf = linear_model.LogisticRegression(
        penalty="l2",
        dual=False,
        tol=0.0001,
        C=1.0,
        fit_intercept=True,
        intercept_scaling=1,
        class_weight=None,
        random_state=None,
        solver="newton-cg",
        max_iter=100,
        multi_class="ovr",
        verbose=0,
        warm_start=False,
        n_jobs=2,
    )
    clf = clf.fit(trainData, trainLabel)
    print str(clf.score(testData, testLabel))

示例#3

文件： linearSVMClassifier.py 项目： RonakSumbaly/CS260-Machine-Learning-Algorithms

def linearSVCClass():
    trainData, trainLabel = featureArray(conf['train']['feature_vector'])
    testData, testLabel = featureArray(conf['test']['feature_vector'])

    print "Linear SVC"
    clf = LinearSVC(penalty='l2', loss='hinge', dual=True, tol=0.0001, C=1.0, multi_class='crammer_singer', fit_intercept=True, intercept_scaling=1, class_weight=None, verbose=0, random_state=None, max_iter=1000)
    clf = clf.fit(trainData,trainLabel)
    print str(clf.score(testData,testLabel))

示例#4

文件： knnClassifier.py 项目： RonakSumbaly/CS260-Machine-Learning-Algorithms

def knnClassifier():
    trainData, trainLabel = featureArray(conf['train']['feature_vector'])
    testData, testLabel = featureArray(conf['test']['feature_vector'])

    neigh = KNeighborsClassifier(n_neighbors=1, algorithm='auto', p=2)
    neigh.fit(trainData, trainLabel)
    print(neigh.score(testData,testLabel))


    neighRadius = RadiusNeighborsClassifier(radius=500, weights='distance',algorithm='auto', p=2,metric='minkowski')
    neighRadius.fit(trainData, trainLabel)
    print(neighRadius.score(testData, testLabel))

示例#5

文件： randomForestClassification.py 项目： RonakSumbaly/CS260-Machine-Learning-Algorithms

def randomForestClassify():
    trainData, trainLabel = featureArray(conf['train']['feature_vector'])
    testData, testLabel = featureArray(conf['test']['feature_vector'])

    print "RANDOM FOREST"
    for value in xrange(1,50):
        clf = RandomForestClassifier(n_estimators = value,criterion='entropy')
        clf = clf.fit(trainData,trainLabel)
        print str(value) + " " + str(clf.score(testData,testLabel))

    print ""
    print "GRADIENT BOOSTING"
    clf = GradientBoostingClassifier(n_estimators=100, learning_rate=1.0, max_depth=1, random_state=0).fit(trainData, trainLabel)
    print str(clf.score(testData,testLabel))

示例#6

文件： regressionClassification.py 项目： olivierh59500/Malware-Classification

def regression():
    trainData, trainLabel = featureArray(conf['train']['feature_vector'])
    testData, testLabel = featureArray(conf['test']['feature_vector'])

    print "RIDGE REGRESSION"
    clf = linear_model.Ridge (alpha = .5)
    clf = clf.fit(trainData,trainLabel)
    print str(clf.score(testData,testLabel))

    print("")
    print("LOGISTIC REGRESSION")
    clf = linear_model.LogisticRegression(penalty='l2', dual=False, tol=0.0001, C=1.0, fit_intercept=True, intercept_scaling=1, class_weight=None, random_state=None, solver='newton-cg', max_iter=100, multi_class='ovr', verbose=0, warm_start=False, n_jobs=2)
    clf = clf.fit(trainData,trainLabel)
    print str(clf.score(testData,testLabel))

示例#7

def knnClassifier():
    trainData, trainLabel = featureArray(conf['train']['feature_vector'])
    testData, testLabel = featureArray(conf['test']['feature_vector'])

    neigh = KNeighborsClassifier(n_neighbors=1, algorithm='auto', p=2)
    neigh.fit(trainData, trainLabel)
    print(neigh.score(testData, testLabel))

    neighRadius = RadiusNeighborsClassifier(radius=500,
                                            weights='distance',
                                            algorithm='auto',
                                            p=2,
                                            metric='minkowski')
    neighRadius.fit(trainData, trainLabel)
    print(neighRadius.score(testData, testLabel))

示例#8

def randomForestClassify():
    trainData, trainLabel = featureArray(conf['train']['feature_vector'])
    testData, testLabel = featureArray(conf['test']['feature_vector'])

    print "RANDOM FOREST"
    for value in xrange(1, 50):
        clf = RandomForestClassifier(n_estimators=value, criterion='entropy')
        clf = clf.fit(trainData, trainLabel)
        print str(value) + " " + str(clf.score(testData, testLabel))

    print ""
    print "GRADIENT BOOSTING"
    clf = GradientBoostingClassifier(n_estimators=100,
                                     learning_rate=1.0,
                                     max_depth=1,
                                     random_state=0).fit(
                                         trainData, trainLabel)
    print str(clf.score(testData, testLabel))

示例#9

文件： linearSVMClassifier.py 项目： olivierh59500/Malware-Classification

def linearSVCClass():
    trainData, trainLabel = featureArray(conf['train']['feature_vector'])
    testData, testLabel = featureArray(conf['test']['feature_vector'])

    print "Linear SVC"
    clf = LinearSVC(penalty='l2',
                    loss='hinge',
                    dual=True,
                    tol=0.0001,
                    C=1.0,
                    multi_class='crammer_singer',
                    fit_intercept=True,
                    intercept_scaling=1,
                    class_weight=None,
                    verbose=0,
                    random_state=None,
                    max_iter=1000)
    clf = clf.fit(trainData, trainLabel)
    print str(clf.score(testData, testLabel))

示例#10

文件： classifications.py 项目： RonakSumbaly/Malware-Classification

from sklearn.neighbors import RadiusNeighborsClassifier
from sklearn import tree
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn import linear_model
from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import MultinomialNB
from sklearn.naive_bayes import BernoulliNB
from sklearn.svm import NuSVC
from sklearn.svm import LinearSVC
from plotAccuracy import plotAccuracy
import numpy as np
import warnings

warnings.filterwarnings("ignore")
trainData, trainLabel = featureArray(conf['train']['feature_vector'])
validationData, validationLabel = featureArray(conf['valid']['feature_vector'])
testData, testLabel = featureArray(conf['test']['feature_vector'])

guideToGraph = {}

def knnClassifier():
    # checking for 10 neighbors
    maximumValue = 0
    returnParameters = ['0','0']
    for neighbor in xrange(1,11):
        neighAuto = KNeighborsClassifier(n_neighbors=neighbor, algorithm='auto', p=2)
        neighDistance = KNeighborsClassifier(n_neighbors=neighbor, algorithm='auto', p=2,weights='distance')
        neighAuto.fit(trainData, trainLabel)
        neighDistance.fit(trainData,trainLabel)
        scoreAuto = neighAuto.score(validationData, validationLabel)

示例#11

import sys
sys.path.append("../Scripts")
from config import conf
from csvToArray import featureArray
from sklearn.svm import NuSVC

trainData, trainLabel = featureArray(conf['train']['feature_vector'])
testData, testLabel = featureArray(conf['test']['feature_vector'])

# gamma = [4**(-7),4**(-6),4**(-5),4**(-4),4**(-3),4**(-2),4**(-1),4**(0),4**(1),4**(2),4**(3),4**(4),4**(5),4**(6),4**(7)]

print "Nu- SUPPORT VECTOR CLASSIFICATION"
def svmClassifier():
    for deg in xrange(1,200):
        print deg
        print "RBF Nu-SVC"
        clf = NuSVC(gamma=deg)
        clf.fit(trainData, trainLabel)
        print(clf.score(testData,testLabel))

        print "LINEAR Nu-SVC"
        clf = NuSVC(kernel="linear")
        clf.fit(trainData, trainLabel)
        print(clf.score(testData,testLabel))

        print "POLYNOMIAL Nu-SVC"
        clf = NuSVC(kernel="poly",gamma=deg)
        clf.fit(trainData, trainLabel)
        print(clf.score(testData,testLabel))

        print "SIGMOID Nu-SVC"

示例#12

文件： classifications.py 项目： olivierh59500/Malware-Classification

from sklearn.neighbors import RadiusNeighborsClassifier
from sklearn import tree
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn import linear_model
from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import MultinomialNB
from sklearn.naive_bayes import BernoulliNB
from sklearn.svm import NuSVC
from sklearn.svm import LinearSVC
from plotAccuracy import plotAccuracy
import numpy as np
import warnings

warnings.filterwarnings("ignore")
trainData, trainLabel = featureArray(conf['train']['feature_vector'])
validationData, validationLabel = featureArray(conf['valid']['feature_vector'])
testData, testLabel = featureArray(conf['test']['feature_vector'])

guideToGraph = {}


def knnClassifier():
    # checking for 10 neighbors
    maximumValue = 0
    returnParameters = ['0', '0']
    for neighbor in xrange(1, 11):
        neighAuto = KNeighborsClassifier(n_neighbors=neighbor,
                                         algorithm='auto',
                                         p=2)
        neighDistance = KNeighborsClassifier(n_neighbors=neighbor,