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 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 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 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)
