def desicion_tree(k, lenData, pctTest, params, threshold):
clear_csv()
samples = []
if (params[0] == "PAIS"):
samples = generar_muestra_pais(lenData)
else:
samples = generar_muestra_provincia(lenData, params[1])
quantity_for_testing = int(lenData * pctTest)
normalizer = Normalizer()
data = normalizer.separate_data_2(samples, quantity_for_testing)
decisionTree = DecisionTree(threshold)
firstRound = cross_validation(k, decisionTree, data, lenData,
"trainingFeaturesFirst",
"testingFeaturesFirst", "First")
secondRound = cross_validation(k, decisionTree, data, lenData,
"trainingFeaturesSecond",
"testingFeaturesSecond", "Second")
secondWithFirst = cross_validation(k, decisionTree, data, lenData,
"trainingFeaturesFirstInclude",
"testingFeaturesFirstInclude", "Second")
normalData = normalizer.get_normal_data()
predictions = [firstRound, secondRound, secondWithFirst]
show_accuracy("DT", predictions)
make_csv(k, normalData, lenData, pctTest, predictions)
def lr_classification(k, lenData, pctTest, l_regulizer=1):
clear_csv()
samples = generar_muestra_pais(lenData)
quantity_for_testing = int(lenData * pctTest)
normalizer = Normalizer()
data = normalizer.prepare_data_tensor(samples, quantity_for_testing)
lrClassifier = LogisticRegression(1, l_regulizer)
firstRound = cross_validation(k, lrClassifier, data, lenData,
"trainingFeatures", "testingFeatures",
"First")
lrClassifier = LogisticRegression(2, l_regulizer)
print("Paso primero")
secondRound = cross_validation(k, lrClassifier, data, lenData,
"trainingFeatures", "testingFeatures",
"Second")
print("Paso segundo")
secondWithFirst = cross_validation(k, lrClassifier, data, lenData,
"trainingFeaturesFirstInclude",
"testingFeaturesFirstInclude", "Second")
print("Paso tercero")
normalData = normalizer.get_normal_data()
# predictions = [firstRound, secondRound, secondWithFirst]
predictions = [secondRound]
show_accuracy("LR", predictions)
make_csv(k, normalData, lenData, pctTest, predictions)
def main(argv):
poblacion = 0
porcentaje = 0
prueba = 0
try:
opts, args = getopt.getopt(argv, "hi:o:",
["poblacion=", "porcentaje-pruebas="])
except getopt.GetoptError:
print(
'main.py --poblacion <cantidad> --porcentaje-prueba <porcentaje, prueba>'
)
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print(
'main.py --poblacion <cantidad> --porcentaje-prueba <porcentaje, prueba>'
)
sys.exit()
elif opt in ("--poblacion"):
poblacion = arg
elif opt in ("--porcentaje-pruebas"):
porcentaje = arg
print('Poblacion', poblacion)
print('Porcentaje', porcentaje)
print(generar_muestra_pais(5))
def kd_tree_classification(k, lenData, pctTest, params, neightboards):
clear_csv()
samples = []
if (params[0] == "PAIS"):
samples = generar_muestra_pais(lenData)
else:
samples = generar_muestra_provincia(lenData, params[1])
quantity_for_testing = int(lenData * pctTest)
normalizer = Normalizer()
data = normalizer.prepare_data(samples, quantity_for_testing)
kdTree = Kd_Tree(neightboards)
firstRound = cross_validation(k, kdTree, data, lenData, "trainingFeatures",
"testingFeatures", "First")
secondRound = cross_validation(k, kdTree, data, lenData,
"trainingFeatures", "testingFeatures",
"Second")
secondWithFirst = cross_validation(k, kdTree, data, lenData,
"trainingFeaturesFirstInclude",
"testingFeaturesFirstInclude", "Second")
normalData = normalizer.get_normal_data()
predictions = [firstRound, secondRound, secondWithFirst]
show_accuracy("KD-TREE", predictions)
make_csv(k, normalData, lenData, pctTest, predictions)
def svm_classification(
k, lenData, pctTest, params, C=1, gamma=1, kernel="rbf"):
clear_csv()
samples = []
print(params)
if (params[0] == "PAIS"):
samples = generar_muestra_pais(lenData)
else:
samples = generar_muestra_provincia(lenData, params[1])
quantity_for_testing = int(lenData * pctTest)
normalizer = Normalizer()
data = normalizer.prepare_data(samples, quantity_for_testing)
svmClassifier = SVMClassifier(kernel, C, gamma)
firstRound = cross_validation(
k,
svmClassifier,
data,
lenData,
"trainingFeatures",
"testingFeatures",
"First"
)
secondRound = cross_validation(
k,
svmClassifier,
data,
lenData,
"trainingFeatures",
"testingFeatures",
"Second"
)
secondWithFirst = cross_validation(
k,
svmClassifier,
data,
lenData,
"trainingFeaturesFirstInclude",
"testingFeaturesFirstInclude",
"Second"
)
normalData = normalizer.get_normal_data()
predictions = [firstRound, secondRound, secondWithFirst]
show_accuracy("SVM", predictions)
make_csv(k, normalData, lenData, pctTest, predictions)
def lr_classification(k, lenData, pctTest, l_regulizer=1):
clear_csv()
samples = generar_muestra_pais(lenData)
quantity_for_testing = int(lenData * pctTest)
normalizer = Normalizer()
data = normalizer.prepare_data_tensor(samples, quantity_for_testing)
lrClassifier = LogisticRegression(1, l_regulizer)
firstRound = cross_validation(
k,
lrClassifier,
data,
lenData,
"trainingFeatures",
"testingFeatures",
"First"
)
lrClassifier = LogisticRegression(2, l_regulizer)
print("Paso primero")
secondRound = cross_validation(
k,
lrClassifier,
data,
lenData,
"trainingFeatures",
"testingFeatures",
"Second"
)
print("Paso segundo")
secondWithFirst = cross_validation(
k,
lrClassifier,
data,
lenData,
"trainingFeaturesFirstInclude",
"testingFeaturesFirstInclude",
"Second"
)
print("Paso tercero")
normalData = normalizer.get_normal_data()
# predictions = [firstRound, secondRound, secondWithFirst]
predictions = [secondRound]
show_accuracy("LR", predictions)
make_csv(k, normalData, lenData, pctTest, predictions)
def kd_tree_classification(k, lenData, pctTest, params, neightboards):
clear_csv()
samples = []
if (params[0] == "PAIS"):
samples = generar_muestra_pais(lenData)
else:
samples = generar_muestra_provincia(lenData, params[1])
quantity_for_testing = int(lenData * pctTest)
normalizer = Normalizer()
data = normalizer.prepare_data(samples, quantity_for_testing)
kdTree = Kd_Tree(neightboards)
firstRound = cross_validation(
k,
kdTree,
data,
lenData,
"trainingFeatures",
"testingFeatures",
"First"
)
secondRound = cross_validation(
k,
kdTree,
data,
lenData,
"trainingFeatures",
"testingFeatures",
"Second"
)
secondWithFirst = cross_validation(
k,
kdTree,
data,
lenData,
"trainingFeaturesFirstInclude",
"testingFeaturesFirstInclude",
"Second"
)
normalData = normalizer.get_normal_data()
predictions = [firstRound, secondRound, secondWithFirst]
show_accuracy("KD-TREE", predictions)
make_csv(k, normalData, lenData, pctTest, predictions)
def desicion_tree(k, lenData, pctTest, params, threshold):
clear_csv()
samples = []
if (params[0] == "PAIS"):
samples = generar_muestra_pais(lenData)
else:
samples = generar_muestra_provincia(lenData, params[1])
quantity_for_testing = int(lenData * pctTest)
normalizer = Normalizer()
data = normalizer.separate_data_2(samples, quantity_for_testing)
decisionTree = DecisionTree(threshold)
firstRound = cross_validation(
k,
decisionTree,
data,
lenData,
"trainingFeaturesFirst",
"testingFeaturesFirst",
"First"
)
secondRound = cross_validation(
k,
decisionTree,
data,
lenData,
"trainingFeaturesSecond",
"testingFeaturesSecond",
"Second"
)
secondWithFirst = cross_validation(
k,
decisionTree,
data,
lenData,
"trainingFeaturesFirstInclude",
"testingFeaturesFirstInclude",
"Second"
)
normalData = normalizer.get_normal_data()
predictions = [firstRound, secondRound, secondWithFirst]
show_accuracy("DT", predictions)
make_csv(k, normalData, lenData, pctTest, predictions)
def pruebas():
# svm_classification(1000, 0.2, C=10, gamma=0.00833333333, kernel="rbf")
lenData = 2500
print(lenData)
print("kernel: ", "sigmoid", " C: ", 1, " G: ", 0.000000001)
pctTest = 0.2
# samples = generar_muestra_provincia(lenData, "SAN JOSE")
# quantity_for_testing = int(lenData*pctTest)
# normalizer = Normalizer()
# data = normalizer.prepare_data(samples, quantity_for_testing)
# svm_classification(10, lenData, pctTest, C=1, gamma=1, kernel="rbf")
time1 = time.time()
for i in range(0, 30):
samples = generar_muestra_pais(lenData)
quantity_for_testing = int(lenData * pctTest)
normalizer = Normalizer()
data = normalizer.prepare_data(samples, quantity_for_testing)
svm_classification(10,
lenData,
pctTest,
C=1,
gamma=0.000000001,
kernel="sigmoid")
time2 = time.time()
print("ms: ", ((time2 - time1) * 1000.0))
totalacc = 0.0
for i in range(0, len(accList), 3):
totalacc += accList[i][1]
print("ER: ", 1 - (totalacc / 30.0))
totalacc = 0.0
for i in range(1, len(accList), 3):
totalacc += accList[i][1]
print("ER: ", 1 - (totalacc / 30.0))
totalacc = 0.0
for i in range(2, len(accList), 3):
totalacc += accList[i][1]
print("ER: ", 1 - (totalacc / 30.0))
def pruebas():
# svm_classification(1000, 0.2, C=10, gamma=0.00833333333, kernel="rbf")
lenData = 2500
print(lenData)
print("kernel: ", "sigmoid", " C: ", 1, " G: ", 0.000000001)
pctTest = 0.2
# samples = generar_muestra_provincia(lenData, "SAN JOSE")
# quantity_for_testing = int(lenData*pctTest)
# normalizer = Normalizer()
# data = normalizer.prepare_data(samples, quantity_for_testing)
# svm_classification(10, lenData, pctTest, C=1, gamma=1, kernel="rbf")
time1 = time.time()
for i in range(0, 30):
samples = generar_muestra_pais(lenData)
quantity_for_testing = int(lenData*pctTest)
normalizer = Normalizer()
data = normalizer.prepare_data(samples, quantity_for_testing)
svm_classification(
10, lenData, pctTest, C=1, gamma=0.000000001, kernel="sigmoid")
time2 = time.time()
print("ms: ", ((time2-time1)*1000.0))
totalacc = 0.0
for i in range(0, len(accList), 3):
totalacc += accList[i][1]
print("ER: ", 1-(totalacc/30.0))
totalacc = 0.0
for i in range(1, len(accList), 3):
totalacc += accList[i][1]
print("ER: ", 1-(totalacc/30.0))
totalacc = 0.0
for i in range(2, len(accList), 3):
totalacc += accList[i][1]
print("ER: ", 1-(totalacc/30.0))
def svm_classification(k,
lenData,
pctTest,
params,
C=1,
gamma=1,
kernel="rbf"):
clear_csv()
samples = []
print(params)
if (params[0] == "PAIS"):
samples = generar_muestra_pais(lenData)
else:
samples = generar_muestra_provincia(lenData, params[1])
quantity_for_testing = int(lenData * pctTest)
normalizer = Normalizer()
data = normalizer.prepare_data(samples, quantity_for_testing)
svmClassifier = SVMClassifier(kernel, C, gamma)
firstRound = cross_validation(k, svmClassifier, data, lenData,
"trainingFeatures", "testingFeatures",
"First")
secondRound = cross_validation(k, svmClassifier, data, lenData,
"trainingFeatures", "testingFeatures",
"Second")
secondWithFirst = cross_validation(k, svmClassifier, data, lenData,
"trainingFeaturesFirstInclude",
"testingFeaturesFirstInclude", "Second")
normalData = normalizer.get_normal_data()
predictions = [firstRound, secondRound, secondWithFirst]
show_accuracy("SVM", predictions)
make_csv(k, normalData, lenData, pctTest, predictions)
def main(argv):
poblacion = 0
porcentaje = 0
prueba = 0
try:
opts, args = getopt.getopt(argv,"hi:o:",["poblacion=","porcentaje-pruebas="])
except getopt.GetoptError:
print ('main.py --poblacion <cantidad> --porcentaje-prueba <porcentaje, prueba>')
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print ('main.py --poblacion <cantidad> --porcentaje-prueba <porcentaje, prueba>')
sys.exit()
elif opt in ("--poblacion"):
poblacion = arg
elif opt in ("--porcentaje-pruebas"):
porcentaje =arg
print ('Poblacion', poblacion)
print ('Porcentaje', porcentaje)
print(generar_muestra_pais(5))
# empieza el entrenamiento
_, c = sess.run([optimizer, cost], feed_dict={self.X: train_x,
self.y: train_y})
cost_in_each_epoch += c
## # you can uncomment next two lines of code for printing cost when training
## if (epoch+1) % display_step == 0:
## print("Epoch: {}".format(epoch + 1), "cost={}".format(cost_in_each_epoch))
print("Accuracy Training:", accuracy.eval({X: train_x, y: train_y}))
## sess = tf.Session()
## with sess.as_default():
## return self.toparty(self.y.eval({self.X: test_x, self.y: test_y}).tolist())
##
samples = generar_muestra_pais(100)
quantity_for_testing = int(100*0.2)
normalizer = Normalizer()
data = normalizer.prepare_data(samples, quantity_for_testing)
classes = np.append(
data["trainingClassesFirst"],
data["testingClassesFirst"],
axis=0
)
sample = { "trainingFeatures": data["trainingFeatures"], "trainingClasses": data["trainingClassesFirst"],"testingFeatures": data["testingFeatures"], "testingClasses": data["testingClassesFirst"]}
sample2 = { "testingFeatures": data["testingFeatures"], "testingClasses": data["testingClassesFirst"]}
print(sample2["testingClasses"])
prueba = logistic_regression_classifier(1,classes)
prueba.train(sample)
print(prueba.classify(sample2))
## if (epoch+1) % display_step == 0:
## print("Epoch: {}".format(epoch + 1), "cost={}".format(cost_in_each_epoch))
print("Accuracy Training:",
accuracy.eval({
X: train_x,
y: train_y
}))
## sess = tf.Session()
## with sess.as_default():
## return self.toparty(self.y.eval({self.X: test_x, self.y: test_y}).tolist())
##
samples = generar_muestra_pais(100)
quantity_for_testing = int(100 * 0.2)
normalizer = Normalizer()
data = normalizer.prepare_data(samples, quantity_for_testing)
classes = np.append(data["trainingClassesFirst"],
data["testingClassesFirst"],
axis=0)
sample = {
"trainingFeatures": data["trainingFeatures"],
"trainingClasses": data["trainingClassesFirst"],
"testingFeatures": data["testingFeatures"],
"testingClasses": data["testingClassesFirst"]
}
sample2 = {
"testingFeatures": data["testingFeatures"],
"testingClasses": data["testingClassesFirst"]