def mim(data):
rank = []
for i in range(6):
X = data[i][:, :-1]
Y = data[i][:, -1]
F, _, _ = MIM.mim(X, Y)
idx = samp(F[:-1].tolist())
rank.append(idx)
R = rankaggregate(rank)
return R
def feature_mutual_info_maximisation(x_data, y_data):
features_scores = MIM.mim(x_data.values, y_data.values, n_selected_features=20)
features_index = [int(index[0]) for index in features_scores]
feat_list = x_data.columns.values[features_index]
feat_list_with_imp = [(feat_list[i], features_scores[i][1]) for i in range(len(features_scores))]
# dfscores = pd.DataFrame(features_scores)
# dfcolumns = pd.DataFrame(x_data.columns)
# featureScores = pd.concat([dfcolumns, dfscores], axis=1)
featureScores = pd.DataFrame(feat_list_with_imp)
featureScores.columns = ['Specs', 'Score'] # naming the dataframe columns
top_20_features = featureScores.nlargest(20, 'Score')
return top_20_features
def run_feature_selection(X, Y, n_selected_features):
lst = []
if PARALLEL:
# with multiprocessing.Pool(processes=4) as pool:
# lst.append(pool.apply(JMI.jmi, args=(X, Y), kwds={'n_selected_features': n_selected_features}))
# lst.append(pool.apply(MIM.mim, args=(X, Y), kwds={'n_selected_features': n_selected_features}))
# lst.append(pool.apply(MRMR.mrmr, args=(X, Y), kwds={'n_selected_features': n_selected_features}))
# lst.append(pool.apply(MIFS.mifs, args=(X, Y), kwds={'n_selected_features': n_selected_features}))
# lst = [l[FEAT_IDX] for l in lst]
with ProcessPoolExecutor(max_workers=4) as executor:
lst.append(
executor.submit(JMI.jmi,
X,
Y,
n_selected_features=n_selected_features))
lst.append(
executor.submit(MIM.mim,
X,
Y,
n_selected_features=n_selected_features))
lst.append(
executor.submit(MRMR.mrmr,
X,
Y,
n_selected_features=n_selected_features))
lst.append(
executor.submit(MIFS.mifs,
X,
Y,
n_selected_features=n_selected_features))
lst = [l.result()[FEAT_IDX] for l in lst]
else:
lst.append(
JMI.jmi(X, Y, n_selected_features=n_selected_features)[FEAT_IDX])
lst.append(
MIM.mim(X, Y, n_selected_features=n_selected_features)[FEAT_IDX])
lst.append(
MRMR.mrmr(X, Y, n_selected_features=n_selected_features)[FEAT_IDX])
lst.append(
MIFS.mifs(X, Y, n_selected_features=n_selected_features)[FEAT_IDX])
return lst
def run_fold(trial,P,X,y,method,dataset,parttype):
print 'Obtaining features for %s %s %s fold: %2d' % (parttype,method,dataset,trial)
n_samples, n_features = X.shape
train = P[:,trial] == 1
trnX = X[train]
trnY = y[train]
start_time = time.time()
if method == 'fisher':
score = fisher_score.fisher_score(trnX,trnY)
features = fisher_score.feature_ranking(score)
elif method == 'chi2':
score = chi_square.chi_square(trnX,trnY)
features = chi_square.feature_ranking(score)
elif method == 'relieff':
score = reliefF.reliefF(trnX,trnY)
features = reliefF.feature_ranking(score)
elif method == 'jmi':
features = JMI.jmi(trnX,trnY, n_selected_features=n_features)
elif method == 'mrmr':
features = MRMR.mrmr(trnX,trnY,n_selected_features=n_features)
elif method == 'infogain':
features = MIM.mim(trnX,trnY,n_selected_features=n_features)
elif method == 'svmrfe':
features = svmrfe(trnX,trnY)
elif method == 'hdmr':
sobol_set_all = scipy.io.loadmat('sobol_set.mat')
sobol_set = sobol_set_all['sobol_set']
sobol_set = sobol_set.astype(float)
params = {'sobol_set':sobol_set,'k':1,'p':3,'M':1000,'b':'L'}
models = hdmrlearn(trnX,trnY,params)
features,w = hdmrselect(X,models)
elif method == 'hdmrhaar':
sobol_set_all = scipy.io.loadmat('sobol_set.mat')
sobol_set = sobol_set_all['sobol_set']
sobol_set = sobol_set.astype(float)
params = {'sobol_set':sobol_set,'k':1,'p':255,'M':1000,'b':'H'}
models = hdmrlearn(trnX,trnY,params)
features,w = hdmrselect(X,models)
else:
print(method + 'does no exist')
cputime = time.time() - start_time
print features
print 'cputime %f' % cputime
return {'features': features, 'cputime': cputime}
def main():
# load data
mat = scipy.io.loadmat('../data/colon.mat')
X = mat['X'] # data
X = X.astype(float)
y = mat['Y'] # label
y = y[:, 0]
n_samples, n_features = X.shape # number of samples and number of features
# split data into 10 folds
ss = cross_validation.KFold(n_samples, n_folds=10, shuffle=True)
# perform evaluation on classification task
num_fea = 10 # number of selected features
clf = svm.LinearSVC() # linear SVM
correct = 0
for train, test in ss:
# obtain the index of each feature on the training set
idx,_,_ = MIM.mim(X[train], y[train], n_selected_features=num_fea)
# obtain the dataset on the selected features
features = X[:, idx[0:num_fea]]
# train a classification model with the selected features on the training dataset
clf.fit(features[train], y[train])
# predict the class labels of test data
y_predict = clf.predict(features[test])
# obtain the classification accuracy on the test data
acc = accuracy_score(y[test], y_predict)
correct = correct + acc
# output the average classification accuracy over all 10 folds
print 'Accuracy:', float(correct)/10
def main():
# load data
mat = scipy.io.loadmat('../data/colon.mat')
X = mat['X'] # data
X = X.astype(float)
y = mat['Y'] # label
y = y[:, 0]
n_samples, n_features = X.shape # number of samples and number of features
# split data into 10 folds
ss = cross_validation.KFold(n_samples, n_folds=10, shuffle=True)
# perform evaluation on classification task
num_fea = 10 # number of selected features
clf = svm.LinearSVC() # linear SVM
correct = 0
for train, test in ss:
# obtain the index of each feature on the training set
idx = MIM.mim(X[train], y[train], n_selected_features=num_fea)
# obtain the dataset on the selected features
features = X[:, idx[0:num_fea]]
# train a classification model with the selected features on the training dataset
clf.fit(features[train], y[train])
# predict the class labels of test data
y_predict = clf.predict(features[test])
# obtain the classification accuracy on the test data
acc = accuracy_score(y[test], y_predict)
correct = correct + acc
# output the average classification accuracy over all 10 folds
print('Accuracy:', old_div(float(correct), 10))
def experiment(data, box, cv, output):
"""
Write the results of an experiment.
This function will run an experiment for a specific dataset for a bounding box.
There will be CV runs of randomized experiments run and the outputs will be
written to a file.
Parameters
----------
data : string
Dataset name.
box : string
Bounding box on the file name.
cv : int
Number of cross validation runs.
output : string
If float or tuple, the projection will be the same for all features,
otherwise if a list, the projection will be described feature by feature.
Returns
-------
None
Raises
------
ValueError
If the percent poison exceeds the number of samples in the requested data.
"""
#data, box, cv, output = 'conn-bench-sonar-mines-rocks', '1', 5, 'results/test.npz'
# load normal and adversarial data
path_adversarial_data = 'data/attacks/' + data + '_[xiao][' + box + '].csv'
df_normal = pd.read_csv('data/clean/' + data + '.csv', header=None).values
df_adversarial = pd.read_csv(path_adversarial_data, header=None).values
# separate out the normal and adversarial data
Xn, yn = df_normal[:,:-1], df_normal[:,-1]
Xa, ya = df_adversarial[:,:-1], df_adversarial[:,-1]
# change the labels from +/-1 to [0,1]
ya[ya==-1], yn[yn==-1] = 0, 0
# calculate the rattios of data that would be used for training and hold out
p0, p1 = 1./cv, (1. - 1./cv)
N = len(Xn)
# calculate the total number of training and testing samples and set the number of
# features that are going to be selected
Ntr, Nte = int(p1*N), int(p0*N) ##### [OBS]: Losing one feature in the process
n_selected_features = int(Xn.shape[1]*SEL_PERCENT)+1
# zero the results out
acc_KNN = np.zeros((NPR,6))
####################################
# CLASSIFICATION
##################################
# run `cv` randomized experiments. note this is not performing cross-validation, rather
# we are going to use randomized splits of the data.
for _ in range(cv):
# shuffle up the data for the experiment then split the data into a training and
# testing dataset
i = np.random.permutation(N)
Xtrk, ytrk, Xtek, ytek = Xn[i][:Ntr], yn[i][:Ntr], Xn[i][-Nte:], yn[i][-Nte:]
####### Classification on Normal Data with no FS #######################
yn_allfeature_KNN = KNN_classification(Xtrk, ytrk, Xtek, ytek)
####### Classification on JMI-based features on Normal data #############
sf_base_jmi = JMI.jmi(Xtrk, ytrk, n_selected_features=n_selected_features)[FEAT_IDX]
#print("\nNOR: JMI features", sf_base_jmi)
Xtr_jmi = Xtrk[:, sf_base_jmi]
Xte_jmi = Xtek[:, sf_base_jmi]
yn_JMI_KNN = KNN_classification(Xtr_jmi, ytrk, Xte_jmi, ytek)
for n in range(NPR):
# calucate the number of poisoned data that we are going to need to make sure
# that the poisoning ratio is correct in the training data. e.g., if you have
# N=100 samples and you want to poison by 20% then the 20% needs to be from
# the training size. hence it is not 20.
Np = int(len(ytrk)*POI_RNG[n]+1)
if Np >= len(ya):
# shouldn't happen but catch the case where we are requesting more poison
# data samples than are available. NEED TO BE CAREFUL WHEN WE ARE CREATING
# THE ADVERSARIAL DATA
ValueError('Number of poison data requested is larger than the available data.')
# find the number of normal samples (i.e., not poisoned) samples in the
# training data. then create the randomized data set that has Nn normal data
# samples and Np adversarial samples in the training data
Nn = len(ytrk) - Np
idx_normal, idx_adversarial = np.random.permutation(len(ytrk))[:Nn], \
np.random.permutation(len(ya))[:Np]
Xtrk_poisoned, ytrk_poisoned = np.concatenate((Xtrk[idx_normal], Xa[idx_adversarial])), \
np.concatenate((ytrk[idx_normal], ya[idx_adversarial]))
ya_allfeature_KNN = KNN_classification(Xtrk_poisoned, ytrk_poisoned, Xtek, ytek)
# run feature selection with the training data that has adversarial samples
sf_adv_jmi = JMI.jmi(Xtrk_poisoned, ytrk_poisoned, n_selected_features=n_selected_features)[FEAT_IDX]
sf_adv_mim = MIM.mim(Xtrk_poisoned, ytrk_poisoned, n_selected_features=n_selected_features)[FEAT_IDX]
sf_adv_mrmr = MRMR.mrmr(Xtrk_poisoned, ytrk_poisoned, n_selected_features=n_selected_features)[FEAT_IDX]
sf_adv_misf = MIFS.mifs(Xtrk_poisoned, ytrk_poisoned, n_selected_features=n_selected_features)[FEAT_IDX]
# KNN Classification on JMI selected features
Xtrk_poisoned_JMI = Xtrk_poisoned[:, sf_adv_jmi]
Xtest_JMI = Xtek[:, sf_adv_jmi]
ya_JMI_KNN = KNN_classification(Xtrk_poisoned_JMI, ytrk_poisoned, Xtest_JMI, ytek)
# KNN Classification on MIM selected features
Xtrk_poisoned_MIM = Xtrk_poisoned[:, sf_adv_mim]
Xtest_MIM = Xtek[:, sf_adv_mim]
ya_MIM_KNN = KNN_classification(Xtrk_poisoned_MIM, ytrk_poisoned, Xtest_MIM, ytek)
# KNN Classification on MRMR selected features
Xtrk_poisoned_MRMR = Xtrk_poisoned[:, sf_adv_mrmr]
Xtest_MRMR = Xtek[:, sf_adv_mrmr]
ya_MRMR_KNN = KNN_classification(Xtrk_poisoned_MRMR, ytrk_poisoned, Xtest_MRMR, ytek)
# KNN Classification on MISF selected features
Xtrk_poisoned_MISF = Xtrk_poisoned[:, sf_adv_misf]
Xtest_MISF = Xtek[:, sf_adv_misf]
ya_MISF_KNN = KNN_classification(Xtrk_poisoned_MISF, ytrk_poisoned, Xtest_MISF, ytek)
"""
######### KNN Classification on adversarial data with no FS #################
ya_allfeature_KNN = KNN_classification(Xtrk_poisoned, ytrk_poisoned, Xtek, ytek)
#print("[ADV] KNN: No FS Confusion Matrix for Poisoning Ratio: ", POI_RNG[n], "\n", confusion_matrix(ytek, ya_allfeature_KNN))
#print(classification_report(ytek, ya_allfeature_KNN))
#print("[ADV] KNN: NO FS Accuracy for Poisoning ratio", POI_RNG[n], "\n", accuracy_score(ytek, ya_allfeature_KNN))
######### KNN Classification on adversarial data with JMI FS #################
sf_adv_jmi = JMI.jmi(Xtrk_poisoned, ytrk_poisoned, n_selected_features=n_selected_features)[FEAT_IDX]
Xtrk_poisoned_JMI = Xtrk_poisoned[:, sf_adv_jmi]
Xtest_JMI = Xtek[:, sf_adv_jmi]
ya_JMI_KNN = KNN_classification(Xtrk_poisoned_JMI, ytrk_poisoned, Xtest_JMI, ytek)
#print("\nJMI Features: ", sf_adv_jmi)
#print("[ADV] KNN: JMI FS Confusion Matrix for Poisoning Ratio: ", POI_RNG[n], "\n", confusion_matrix(ytek, ya_JMI_KNN))
#print("[ADV] KNN: JMI Accuracy for Poisoning ratio", POI_RNG[n], "\n", accuracy_score(ytek, ya_JMI_KNN))
######### KNN Classification on adversarial data with MIM FS #################
sf_adv_mim = MIM.mim(Xtrk_poisoned, ytrk_poisoned, n_selected_features=n_selected_features)[FEAT_IDX]
Xtrk_poisoned_MIM = Xtrk_poisoned[:, sf_adv_mim]
Xtest_MIM = Xtek[:, sf_adv_mim]
ya_MIM_KNN = KNN_classification(Xtrk_poisoned_MIM, ytrk_poisoned, Xtest_MIM, ytek)
#print("\nMIM Features: ", sf_adv_mim)
#print("[ADV] KNN: MIM FS Confusion Matrix for Poisoning Ratio: ", POI_RNG[n], "\n", confusion_matrix(ytek, ya_MIM_KNN))
#print("[ADV] KNN: MIM Accuracy for Poisoning ratio", POI_RNG[n], "\n", accuracy_score(ytek, ya_MIM_KNN))
######### KNN Classification on adversarial data with MRMR FS #################
sf_adv_mrmr = MRMR.mrmr(Xtrk_poisoned, ytrk_poisoned, n_selected_features=n_selected_features)[FEAT_IDX]
Xtrk_poisoned_MRMR = Xtrk_poisoned[:, sf_adv_mrmr]
Xtest_MRMR = Xtek[:, sf_adv_mrmr]
ya_MRMR_KNN = KNN_classification(Xtrk_poisoned_MRMR, ytrk_poisoned, Xtest_MRMR, ytek)
#print("\nMRMR Features: ", sf_adv_mrmr)
#print("[ADV] KNN: MRMR FS Confusion Matrix for Poisoning Ratio: ", POI_RNG[n], "\n", confusion_matrix(ytek, ya_MRMR_KNN))
#print("[ADV] KNN: MRMR Accuracy for Poisoning ratio", POI_RNG[n], "\n", accuracy_score(ytek, ya_MRMR_KNN))
######### KNN Classification on adversarial data with MISF FS #################
sf_adv_misf = MIFS.mifs(Xtrk_poisoned, ytrk_poisoned, n_selected_features=n_selected_features)[FEAT_IDX]
Xtrk_poisoned_MISF = Xtrk_poisoned[:, sf_adv_misf]
Xtest_MISF = Xtek[:, sf_adv_misf]
ya_MISF_KNN = KNN_classification(Xtrk_poisoned_MISF, ytrk_poisoned, Xtest_MISF, ytek)
#print("\nMISF Features: ", sf_adv_misf)
#print("[ADV] KNN: MISF FS Confusion Matrix for Poisoning Ratio: ", POI_RNG[n], "\n", confusion_matrix(ytek, ya_MISF_KNN))
#print("[ADV] KNN: MISF Accuracy for Poisoning ratio", POI_RNG[n], "\n", accuracy_score(ytek, ya_MISF_KNN))
"""
# Calculate accumulated accuracy in a matrix of size 9x6
acc_KNN[n, 0] += accuracy_score(ytek, yn_allfeature_KNN) # Acc score of normal data without Feature Selection
acc_KNN[n, 1] += accuracy_score(ytek, ya_allfeature_KNN) # Acc score of adversarial data without Feature Selection
acc_KNN[n, 2] += accuracy_score(ytek, ya_JMI_KNN) # Acc score of adversarial data with JMI Feature Selection algo
acc_KNN[n, 3] += accuracy_score(ytek, ya_MIM_KNN) # Acc score of adversarial data with MIM Feature Selection algo
acc_KNN[n, 4] += accuracy_score(ytek, ya_MRMR_KNN) # Acc score of adversarial data with MRMR Feature Selection algo
acc_KNN[n, 5] += accuracy_score(ytek, ya_MISF_KNN) # Acc score of adversarial data with MISF Feature Selection algo
#print(acc_KNN)
# scale the accuracy statistics by 1.0/cv then write the output file
acc_KNN = acc_KNN/cv
print("\n Accuracy matrix of KNN")
print("[COL]: Norm_noFS, Adv_noFS, Adv_JMI, Adv_MIM, Adv_MRMR, Adv_MISF")
print("[ROW]: Poisoning ratios: 0.01, 0.025, 0.05, 0.075, 0.1, 0.125, 0.15, 0.175, 0.2")
print("\n", acc_KNN)
np.savez(output, acc_KNN=acc_KNN)
return None
repr(average_precision_score(Y_test, Y_pred)))
print("Kappa: " + repr(cohen_kappa_score(Y_test, Y_pred)))
print("Hamming Loss: " + repr(hamming_loss(Y_test, Y_pred)))
print("AUC" + repr(roc_auc_score(Y_test, Y_pred)))
print("Sensitivity" + repr(recall_score(Y_test, Y_pred)))
tn, fp, fn, tp = confusion_matrix(Y_test, Y_pred).ravel()
print("Specificity" + repr(tn / (tn + fp)))
sheet_test.write(r, c, roc_auc_score(Y_test, Y_pred))
r = r + 1
c = c + 1
r = 0
MV_sel = []
MV_sel.append(('MIM', MIM.mim(X_train, Y_train, n_selected_features=num_fea)))
print('MIM')
MV_sel.append(('MIFS', MIFS.mifs(X_train, Y_train,
n_selected_features=num_fea)))
print('MIFS')
MV_sel.append(('MRMR', MRMR.mrmr(X_train, Y_train,
n_selected_features=num_fea)))
print('MRMR')
MV_sel.append(('CIFE', CIFE.cife(X_train, Y_train,
n_selected_features=num_fea)))
print('CIFE')
MV_sel.append(('JMI', JMI.jmi(X_train, Y_train, n_selected_features=num_fea)))
print('JMI')
MV_sel.append(('CMIM', CMIM.cmim(X_train, Y_train,
n_selected_features=num_fea)))
print('CMIM')
result = pymrmr.mRMR(X, 'MIQ', 10)
print(result)
def import_Data():
Data = pd.read_csv('Disease_Data_BiGram.csv')
# print(Data.shape)
X = Data.iloc[:, 0:Data.shape[1] - 2]
Y = Data['Class']
Y_ = Data['Subject']
return X, Y, Y_
FS = {}
X, Y, Y_ = import_Data()
FS['MRMR'] = X.columns[MRMR.mrmr(np.array(X), Y_, n_selected_features=15)[:15]]
FS['JMI'] = X.columns[JMI.jmi(np.array(X), Y_, n_selected_features=15)[:15]]
FS['MIFS'] = X.columns[MIFS.mifs(np.array(X), Y_, n_selected_features=15)[:15]]
FS['MIM'] = X.columns[MIM.mim(np.array(X), Y_, n_selected_features=15)[:15]]
FS = pd.DataFrame(FS)
print(FS)
FS.to_csv('Selected_Features_MultiVar_BiG.csv')
#print(pd.DataFrame(FS))
#model = apply_Model(X,Y_)