def main(dataset_name, testset_name, new_emails=False):
'''Runs the knn classifier for a training set dataset_name and test set testset_name'''
current_path = os.path.dirname(os.path.abspath(__file__)) + "\\"
trainingset_path = current_path + dataset_name + "\\"
testset_path = current_path + testset_name + "\\"
results_path = testset_path + "results\\"
if not os.path.exists(results_path):
os.mkdir(results_path)
folder_names = next(os.walk(testset_path + "."))[1]
if 'results' in folder_names:
folder_names.remove('results')
if new_emails:
folder_names = [""]
workfilename = 'mergedworkfile.csv'
wordfilename = 'wordfile.csv'
# klist = [1, 3, 7, 15, 24, 33, 42, 50]
klist = [1, 3]
acc = []
ks = []
trainingSet = []
print("Loading Training Set...")
wordsd, subd, digramsd, trigramsd = ex.loadTrainingset(
trainingset_path, workfilename, wordfilename, trainingSet)
print("Training Set loaded.")
print('Collecting ' + 'New' * new_emails + 'Test' * (not new_emails) +
' Emails...')
testSet, all_files = ex.loadTestset(testset_path, folder_names, wordsd,
subd, digramsd, trigramsd)
print('New' * new_emails + 'Test' * (not new_emails) +
' Emails Collected.')
assert (len(trainingSet[0]) == len(testSet[0]))
list_of_predictions = knn.classify(klist, trainingSet, testSet,
results_path)
if not new_emails:
#Finds the predictions and accuracy for new test mails given the predictions for these mails
for i in range(len(klist)):
predictions = []
for x in range(len(testSet)):
predictions.append(list_of_predictions[x][i])
accuracy = knn.getAccuracy(testSet, predictions)
acc.append(accuracy)
ks.append(klist[i])
print('K: ' + repr(klist[i]))
print('Accuracy: ' + repr(accuracy) + '%')
print('Overall Accuracy: ' + str(sum(acc) / len(acc)) + "%")
plt.plot(ks, acc)
plt.xlabel('K')
plt.ylabel('Accuracy')
plt.show()
print('Find the results at: ' + results_path)
def main(dataset_name, testset_name, new_emails = False):
'''Runs the knn classifier for a training set dataset_name and test set testset_name'''
current_path = os.path.dirname(os.path.abspath(__file__)) + "\\"
trainingset_path = current_path + dataset_name + "\\"
testset_path = current_path + testset_name + "\\"
results_path = testset_path + "results\\"
if not os.path.exists(results_path):
os.mkdir(results_path)
folder_names = next(os.walk(testset_path + "."))[1]
if 'results' in folder_names:
folder_names.remove('results')
if new_emails:
folder_names = [""]
workfilename = 'mergedworkfile.csv'
wordfilename = 'wordfile.csv'
# klist = [1, 3, 7, 15, 24, 33, 42, 50]
klist = [1, 3]
acc = []
ks = []
trainingSet=[]
print("Loading Training Set...")
wordsd, subd, digramsd, trigramsd = ex.loadTrainingset(trainingset_path, workfilename, wordfilename, trainingSet)
print("Training Set loaded.")
print('Collecting ' + 'New'*new_emails + 'Test'*(not new_emails) + ' Emails...')
testSet, all_files = ex.loadTestset(testset_path, folder_names, wordsd, subd, digramsd, trigramsd)
print('New'*new_emails + 'Test'*(not new_emails) + ' Emails Collected.')
assert(len(trainingSet[0]) == len(testSet[0]))
list_of_predictions = knn.classify(klist, trainingSet, testSet, results_path)
if not new_emails:
#Finds the predictions and accuracy for new test mails given the predictions for these mails
for i in range(len(klist)):
predictions = []
for x in range(len(testSet)):
predictions.append(list_of_predictions[x][i])
accuracy = knn.getAccuracy(testSet, predictions)
acc.append(accuracy)
ks.append(klist[i])
print('K: ' + repr(klist[i]))
print('Accuracy: ' + repr(accuracy) + '%')
print('Overall Accuracy: '+ str(sum(acc)/len(acc)) + "%")
plt.plot(ks, acc)
plt.xlabel('K')
plt.ylabel('Accuracy')
plt.show()
print('Find the results at: ' + results_path)
preds=[[0,0,0,0,0],[0,0,0,0,0],[0,0,0,0,0],[0,0,0,0,0],[0,0,0,0,0]]
dictClasses={'carettacaretta': 0, 'cheloniamydas': 1,'dermochelyscoriacea':2,'eretmochelysimbricata':3,'lepidochelysolivacea':4}
numeroImagensPorClasse=30.00;
for x in range(len(testSet)):
neighbors = knn.getNeighbors(trainingSet, testSet[x], k)
result = knn.getResponse(neighbors)
predictions.append(result)
indiceClassePred=dictClasses[result]
indiceClasseActual=dictClasses[testSet[x][-1]]
preds[indiceClasseActual][indiceClassePred]=preds[indiceClasseActual][indiceClassePred]+1
print('> predicted=' + repr(result) + ', actual=' + repr(testSet[x][-1]))
accuracy = knn.getAccuracy(testSet, predictions)
print('Accuracy: ' + repr(accuracy) + '%')
conf_arr = preds
norm_conf = []
for i in conf_arr:
a = 0
tmp_arr = []
# -*- coding: utf-8 -*- import numpy as np import cv2 as cv import Dataset import knn path = "ordo_2.csv" DS = Dataset.Dataset(path) df = DS.getDF() print(df.head()) X, Y = DS.getXY() print(X) k = 7 #gnb = GNB.GNB(X, Y) knn = knn.kNN(k, X, Y) accuracy = knn.getAccuracy() print(accuracy)
prototypes_lvq1 = train_prototypes_lvq1(lvq_training_set, n_prototypes,
lrate, epochs)
prototypes_lvq2 = train_prototypes_lvq2(prototypes_lvq1,
lvq_training_set, lrate,
epochs)
prototypes_lvq3 = train_prototypes_lvq3(prototypes_lvq2,
lvq_training_set, lrate,
epochs)
for k in kn:
predictions = []
for row in range(len(knn_test_set)):
neighbors = getNeighbors(prototypes_lvq1, knn_test_set[row], k)
results = getResponse(neighbors)
predictions.append(results)
accuracy = getAccuracy(knn_test_set, predictions)
if k == 1:
accuracy_lvq1_k1.append(accuracy)
else:
accuracy_lvq1_k3.append(accuracy)
print('With LVQ1 for ' + str(n_prototypes) +
' and for dataset -> ' + str(filename) +
' accuracy for k= ' + str(k) + ': ' + repr(accuracy) + '%')
for k in kn:
predictions = []
for row in range(len(knn_test_set)):
neighbors = getNeighbors(prototypes_lvq2, knn_test_set[row], k)
results = getResponse(neighbors)
predictions.append(results)
accuracy = getAccuracy(knn_test_set, predictions)
