def decisionTree(trainx, trainy,testx,testy):
treeLearn = mlpy.ClassTree(minsize=2)
treeLearn.learn(trainx, trainy)
treeVals = treeLearn.pred(testx)
treeVals = correctVals(treeVals)
print("The decision tree accuracy on the test set is: " + str(mlpy.accuracy(treeVals, testy)))
trainVals = treeLearn.pred(trainx)
treeVals = correctVals(trainVals)
print("The decision tree accuracy on the training set is: " + str(mlpy.accuracy(trainVals, trainy)))
def test_gamma_C(x_arr, y_arr, itraining, K_chk, y_chk,
get_ml, get_kernel=None):
shp = (len(y_arr), len(x_arr))
pnl = pd.Panel(data=[np.zeros(shp), np.zeros(shp)],
items=['error', 'accuracy'],
major_axis=y_arr, minor_axis=x_arr)
for g in x_arr:
for c in y_arr:
print "computing g=%r, c=%r" % (g, c)
ml = get_ml(g, c, get_kernel)
y_all = cls(ml, itraining, K_chk, y_chk)
pnl['error'][g][c] = mlpy.error(y_chk, y_all[y_chk.index])
pnl['accuracy'][g][c] = mlpy.accuracy(y_chk, y_all[y_chk.index])
return pnl
#ACCURACY measure CLASSIFICATION import mlpy t = [3,2,3,3,3,1,1,1] p = [3,2,1,3,3,2,1,1] mlpy.error(t, p) mlpy.accuracy(t, p) #Sensitivity, Specitivity, AUC import mlpy t = [1, 1, 1,-1, 1,-1,-1,-1] p = [1,-1, 1, 1, 1,-1, 1,-1] mlpy.error_p(t, p) mlpy.error_n(t, p) mlpy.sensitivity(t, p) mlpy.specificity(t, p) mlpy.ppv(t, p) mlpy.npv(t, p) mlpy.mcc(t, p) p = [2.3,-0.4, 1.6, 0.6, 3.2,-4.9, 1.3,-0.3] mlpy.auc_wmw(t, p) p = [2.3,0.4, 1.6, -0.6, 3.2,-4.9, -1.3,-0.3] mlpy.auc_wmw(t, p) #Mean Squared Error REGRESSION import mlpy t = [2.4,0.4,1.2,-0.2,3.3,-4.9,-1.1,-0.1] p = [2.3,0.4,1.6,-0.6,3.2,-4.9,-1.3,-0.3] mlpy.mse(t, p)
test_y = train_y[:split_index]
train_X = train_X[split_index:]
train_y = train_y[split_index:]
print strftime("%Y-%m-%d %H:%M:%S", gmtime()), ": Parsing complete!\n"
else:
print strftime("%Y-%m-%d %H:%M:%S", gmtime()), ": Parsing test data..."
# Parsing test input data
data_reader = csv.reader(open(input_test_file, 'rb'), delimiter = ",")
data_reader.next() # Skip the first line, since it contains the labels
test_X = []
for row in data_reader:
line_x = [1]
for i in range(len(row)):
line_x.append(float(row[i]))
test_X.append(line_x)
print strftime("%Y-%m-%d %H:%M:%S", gmtime()), ": Finished parsing test data!"
predicted_labels = Predict_svm(train_X, train_y, test_X)
print strftime("%Y-%m-%d %H:%M:%S", gmtime()), ": Finished predicting!"
if crossval == True:
# Only useful for cross-validation, otherwise test_y is unknown and we get error=1/accuracy=0
print "Error: ", mlpy.error(test_y, predicted_labels)
print "Accuracy: ", mlpy.accuracy(test_y, predicted_labels)
else:
print strftime("%Y-%m-%d %H:%M:%S", gmtime()), ": Writing predicted labels to file..."
prediction_filename = "test_" + strftime("%Y-%m-%d_%H-%M-%S", gmtime()) + ".csv"
prediction_writer = csv.writer(open(prediction_filename, 'wb'))
for row in predicted_labels:
list_row = [row]
prediction_writer.writerow(list_row)
def mlpyKNN(k,trainx,trainy,testx,testy,typist):
mlknn = mlpy.KNN(k)
mlknn.learn(trainx, trainy)
knnVals = mlknn.pred(testx)
print("The mlpy KNN accuracy on the " + typist + " set for k = "+ str(k) +" is: " + str(mlpy.accuracy(knnVals, testy)))
testy = []
indx = i.pop()
for c in indx[0]:
trainx.append(x[c].split(","))
trainy.append(y[c])
for c in indx[1]:
testx.append(x[c].split(","))
testy.append(y[c])
mlknn = mlpy.KNN(5)
mlknn.learn(trainx, trainy)
knnVals = mlknn.pred(testx)
print("The mlpy KNN accuracy on fold " + str(m) + " set for k = 5 is: " + str(mlpy.accuracy(knnVals, testy)))
KNNRESULTS.append(mlpy.accuracy(knnVals, testy))
treeLearn = mlpy.ClassTree(minsize=2)
treeLearn.learn(trainx, trainy)
treeVals = treeLearn.pred(testx)
treeVals = correctVals(treeVals)
print("The Decision Tree accuracy on on fold " + str(m) + " is: "+ str(mlpy.accuracy(treeVals, testy)))
DTRESULTS.append(mlpy.accuracy(treeVals, testy))
svm = mlpy.LibLinear(solver_type="l2r_lr")
svm.learn(trainx,trainy)
svmVals = svm.pred(testx)
print("The mlpy Logistic Regression accuracy on fold " + str(m) + " is: " + str(mlpy.accuracy(svmVals, testy)))
LRRESULTS.append(mlpy.accuracy(svmVals, testy))
def make_model(self):
if self.model_type not in [
"Combined", "comb", "Comb", "overall", "Overall", "o", "O"
]:
training_fet = np.array([
select_fet2(i[0], i[1], self.model_type)
for i in self.datasets.training()
])
testing_fet = np.array([
select_fet2(i[0], i[1], self.model_type)
for i in self.datasets.testing()
])
self.logit1.learn(training_fet[:, :-1], training_fet[:, -1])
test_pred = [self.logit1.pred(i[:-1]) for i in testing_fet]
test_vals = [i[-1] for i in testing_fet]
cds_test_pred = [
self.logit1.pred(i[:-1]) for i in testing_fet if i[-1] == '1'
]
cds_test_vals = [i[-1] for i in testing_fet if i[-1] == '1']
ncds_test_pred = [
self.logit1.pred(i[:-1]) for i in testing_fet if i[-1] == '0'
]
ncds_test_vals = [i[-1] for i in testing_fet if i[-1] == '0']
print "=-" * 5 + "Accuracies" + "=-" * 5
print "Overall accuracy of predictor : %s" % mlpy.accuracy(
test_vals, test_pred)
print "Accuracy of predicting CDS correctly : %s" % mlpy.accuracy(
cds_test_vals, cds_test_pred)
print "Accuracy of predicting NCDS correctly : %s" % mlpy.accuracy(
ncds_test_vals, ncds_test_pred)
else:
training_fet_1 = np.array([
select_fet2(i[0], i[1], "u") for i in self.datasets.training()
])
testing_fet_1 = np.array([
select_fet2(i[0], i[1], "u") for i in self.datasets.testing()
])
self.logit1.learn(training_fet_1[:, :-1], training_fet_1[:, -1])
training_fet_2 = np.array([
select_fet2(i[0], i[1], "c") for i in self.datasets.training()
])
testing_fet_2 = np.array([
select_fet2(i[0], i[1], "c") for i in self.datasets.testing()
])
self.logit2.learn(training_fet_2[:, :-1], training_fet_2[:, -1])
k = len(training_fet_1)
j = len(testing_fet_1)
comb_training = [[
self.logit1.pred_probability(training_fet_1[i][:-1])[1],
self.logit2.pred_probability(training_fet_2[i][:-1])[1],
training_fet_1[i][-1]
] for i in range(k)] # training file
comb_training = np.array(comb_training, dtype=float)
self.logit3.learn(comb_training[:, :-1], comb_training[:, -1])
comb_testing = [[
self.logit1.pred_probability(testing_fet_1[i][:-1])[1],
self.logit2.pred_probability(testing_fet_2[i][:-1])[1],
testing_fet_1[i][-1]
] for i in range(j)] # testing file
comb_testing = np.array(comb_testing, dtype=float)
test_pred = [self.logit3.pred(i[:-1]) for i in comb_testing]
test_vals = [i[-1] for i in comb_testing]
cds_test_pred = [
self.logit3.pred(i[:-1]) for i in comb_testing if i[-1] == 1
]
cds_test_vals = [i[-1] for i in comb_testing if i[-1] == 1]
ncds_test_pred = [
self.logit3.pred(i[:-1]) for i in comb_testing if i[-1] == 0
]
ncds_test_vals = [i[-1] for i in comb_testing if i[-1] == 0]
print "=-" * 5 + "Accuracies" + "=-" * 5
print "Overall accuracy of predictor : %s" % mlpy.accuracy(
test_vals, test_pred)
print "Accuracy of predicting CDS correctly : %s" % mlpy.accuracy(
cds_test_vals, cds_test_pred)
print "Accuracy of predicting NCDS correctly : %s" % mlpy.accuracy(
ncds_test_vals, ncds_test_pred)
