def main():
preparedDataset = readFile('carData')
#Para toda execucao da main, randomiza os dados
random.shuffle(preparedDataset)
dataset = []
#Features
dataset.append([])
#Label
dataset.append([])
#Separa para dataset[0] como um vetor de vetores, onde cada elemento eh uma linha de features
#Para dataset[1] eh o vetor com as labels (classes)
for t in preparedDataset:
dataset[0].append(t[:-1])
dataset[1].append(t[-1])
#Conjunto de features
dataSet_x = dataset[0]
#Conjunto de classes
dataSet_y = dataset[1]
#Repare acima, dataSet_x[0] representa as features da linha 1 do conjunto, bem como dataSet_y[0] eh a classe da linha 1
nTuples = len(dataSet_x)
nToTrain = int(math.floor(nTuples * 0.7))
dataSet_x_train = dataSet_x[:nToTrain]
dataSet_y_train = dataSet_y[:nToTrain]
dataSet_x_test = dataSet_x[nToTrain:]
dataSet_y_test = dataSet_y[nToTrain:]
#Instancia o NaiveBayes
naive = NaiveBayes()
#Passa os dados para treino
#naive.train(features, class)
naive.train(dataSet_x_train, dataSet_y_train)
accuracy = 0.0
#Faz a predicao
#naive.predict(dados_para_classificar -> apenas features)
results = naive.predict(dataSet_x_test)
#Faz apenas o "score" do modelos, calculando quantos foram preditos corretamente
for index, r in enumerate(results):
yPredicted = max(r, key=r.get)
y = dataSet_y_test[index]
if(y == yPredicted):
accuracy += 1.0
print accuracy / len(dataSet_y_test)
def trainTest(self,
folds=6,
classifier=3,
model1="Logistic Regression",
model2="Logisitc Regression"):
classifierObject = NaiveBayes(model1, model2)
# classifierObject.gatherData()
print model1, model2
classifierObject.initializeModels(model1, model2)
classifierObject.kfold(folds, classifier)
classifierObject.createModel()
def run_naive_bayes(df, num_features):
"""
This function runs naive on the data frame and outputs statistics from five experiments
:param df: The data set to run the algorithm on=
:param num_features: The number of features in this dataset
"""
# Split dataset 5-fold stratified
print(f"Size of total dataset = {len(df)}")
train1, train2, train3, train4, train5 = split_into_random_stratified_groups(
df)
datasets = [train1, train2, train3, train4, train5]
nb_scores = []
for i, d in enumerate(datasets):
print("-------------")
print(f"Experiment #{i + 1}")
print("-------------")
# Use one subset as a test set
df_test = datasets[i]
print(f"Test set size = {len(df_test)}")
training_sets = datasets.copy()
# Create a training set from remaining subsets
del training_sets[i]
df_train = pd.concat(training_sets)
print(f"Training set size = {len(df_train)}")
# Create Naive Bayes
nb = NaiveBayes(df_train.iloc[:, 0:num_features],
df_train.iloc[:, num_features],
df_test.iloc[:, 0:num_features],
df_test.iloc[:, num_features])
# Train with naive bayes
nb.learn()
# Test the accuracy of naive bayes
nb_accuracy = nb.validate()
print('Naive Bayes Percent accurate: ' + repr(nb_accuracy) + '%')
nb_scores.append(nb_accuracy)
return statistics.mean(nb_scores)
def main():
data = loadData()
print("\n############### PROPROCESS DATA ##################")
preprocessor = Precessor(missing_value_method="remove")
cleanDataset = preprocessor.preprocess(data)
print("\n###### DATA INFORMATION AFTER PREPROCESSING ######")
print(cleanDataset.info())
naiveBayesModel = NaiveBayes()
naiveBayesModel.setRomovedCol(["race", "native_country"])
naiveBayesModel.Kfold_cross_validation(cleanDataset, 10)
naiveBayesModel.plotConfusionMatrix()
np.random.seed(13)
np.random.shuffle(idx)
X = X[idx]
y = y[idx]
# split the data
Xtrain = X[:nTrain, :]
ytrain = y[:nTrain]
Xtest = X[nTrain:, :]
ytest = y[nTrain:]
# train the online naive Bayes
modelONB = OnlineNaiveBayes(useLaplaceSmoothing=True)
for i in range(nTrain):
modelONB.fit(Xtrain[i:i+2, :], ytrain[i:i+2]) # train two instances at a time
# train the boosted ONB
modelNB = NaiveBayes(useLaplaceSmoothing=True)
modelNB.fit(Xtrain, ytrain)
# output predictions on the remaining data
ypred_ONB = modelONB.predict(Xtest)
ypred_NB = modelNB.predict(Xtest)
# compute the training accuracy of the model
accuracyONB = accuracy_score(ytest, ypred_ONB)
accuracyNB = accuracy_score(ytest, ypred_NB)
print "Online Naive Bayes Accuracy = "+str(accuracyONB)
print "Batch Naive Bayes Accuracy = "+str(accuracyNB)
docId, wordId, count = map(int, row)
X_train.append([docId, wordId, count])
X_train = np.array(X_train)
trainDataFile.close()
testDataFile = open('Data/test.data', 'r')
testReader = csv.reader(testDataFile, delimiter=' ')
for row in testReader:
docId, wordId, count = map(int, row)
X_test.append([docId, wordId, count])
X_test = np.array(X_test)
testDataFile.close()
alpha = 1.0 / V
print 'Initializing Naive Bayes classifier...'
NBClassifier = NaiveBayes(V, numY)
print 'Training the model...'
NBClassifier.train(X_train, y_train, alpha)
print 'Making predictions on test data...'
y_predicted = NBClassifier.predict(X_test)
# Solution for question 3.2
print 'Accuracy of Naive Bayes classifier: ' + str(
getAccuracy(y_test, y_predicted))
print
#print 'Confusion Matrix:'
#print
#printConfusionMatrix(y_test, y_predicted, range(1,21))
#print
# Solution for question 3.4
def test(self, summarizer="LexRank"):
classifierObject = NaiveBayes()
classifierObject.test(summarizer)
trainIndex = []
for (label, i) in trainlabels:
trainX.append(data[i])
trainY.append(label)
trainIndex.append(i)
testX = []
testIndex = [i for i in range(len(data)) if i not in trainIndex]
for i in testIndex:
testX.append(data[i])
################# USING NAIVE BAYES TO PREDICT SCORE #################
clf = NaiveBayes()
clf.train(trainX, trainY)
pred = clf.prediction(testX)
if '-save' in sys.argv:
writeFile = open(resultFile, 'w')
for (idx, p) in zip(testIndex, pred):
print(p, idx)
writeFile.writelines('{} {}\n'.format(p, idx))
writeFile.close()
else:
for (idx, p) in zip(testIndex, pred):
print(p, idx)
randItemIterator3 = 4
print()
print(
"############################################################################"
)
print(
"-------------------------Problem 2 question 1a/2----------------------------"
)
print(
"---Testing the prediction on the test data along with scatter plot and ROC--"
)
print(
"############################################################################"
)
NaiveBayes(set1, randItemIterator1, 1, 1, m1, m2, stdDev1, stdDev2)
# print()
# print("############################################################################")
# print("-------------------------Problem 2 question 1b------------------------------")
# print("---------Changing number of samples [10, 20, 50, 100, 300, 500]-------------")
# print("############################################################################")
# NaiveBayes(set2, randItemIterator2, 0, 0, m1, m2, stdDev1, stdDev2)
#
print()
print(
"############################################################################"
)
print(
"-------------------------Problem 2 question 1c/2----------------------------"
)
def predict(model, dataset, vari, deli, day):
X,Y = dataset.bootstrap(vari, deli, day, n=10**4)
model.fit(X, Y)
x = dataset.get_x(vari, deli, day)
return model.predict(x)
if __name__=='__main__':
vari,deli,m = 'cu','1712',7
db = DB()
days = db.execute("select date from contract_daily where vari=%s and deli=%s order by date asc",
(vari, deli))[30:]
data = DataSet(m, 'direction')
model = NaiveBayes(m)
y_real = []
y_pred = []
for day in days:
model.fit(*data.bootstrap(vari, deli, day, 300))
r = model.predict(data.get_x(vari, deli, day))
if r[0]>=r[1] and r[0]>=r[2]:
r = 0
elif r[1]>=r[0] and r[1]>=r[2]:
r = 1
else:
r = 2
y_pred.append(r)
y_real.append(data.get_y(vari, deli, day))
y = y[idx] # split the data Xtrain = X[:nTrain, :] ytrain = y[:nTrain] Xtest = X[nTrain:, :] ytest = y[nTrain:] # for i in range(len(Xtest)): # for j in range(len(Xtest[0])): # if(Xtest[i][j]>16): # print "out" # train the decision tree modelDT = DecisionTreeClassifier() modelDT.fit(Xtrain, ytrain) # train the naive Bayes modelNB = NaiveBayes(useLaplaceSmoothing=True) modelNB.fit(Xtrain, ytrain) # output predictions on the remaining data ypred_DT = modelDT.predict(Xtest) ypred_NB = modelNB.predict(Xtest) # compute the training accuracy of the model accuracyDT = accuracy_score(ytest, ypred_DT) accuracyNB = accuracy_score(ytest, ypred_NB) print "Decision Tree Accuracy = " + str(accuracyDT) print "Naive Bayes Accuracy = " + str(accuracyNB)
def __init__(self): # Janela Inicial
self.window = Tk()
variavel_controlo = BooleanVar(self.window)
nb=NaiveBayes()
self.window.title('Filtro de Spam')
self.window.resizable(False, False)
self.window.geometry('600x450+584+230')
labelwel = Label(self.window)
labelwel.place(relx=0.125, rely=0.325, height=75, width=450)
labelwel.configure(background="#0082ba", foreground="white", relief='ridge', text='''Classificadores Filtro Spam''', font=("Rockwell", 14))
def menuNaiveBayes(): # janela do filtro de spam Naive Bayes
self.window2 = Tk()
variavel_controlo = BooleanVar(self.window2)
nb=NaiveBayes()
self.window2.title('Naïve Bayes')
self.window2.resizable(False, False)
self.window2.geometry('600x450+584+230')
self.window2.configure(background="#91cded")
labelwel = Label(self.window2)
labelwel.place(relx=0.25, rely=0.067, height=35, width=305)
labelwel.configure(background="#0082ba", foreground="white", relief='ridge', text='''Classificador Naïve Bayes''', font=("Rockwell", 14))
frame1 = Frame(self.window2)
frame1.place(relx=0.125, rely=0.225, relheight=0.250, relwidth=0.750)
frame1.configure(relief='groove', borderwidth="2", width=305)
labelframe = LabelFrame(frame1, text="Opções")
labelframe.pack(fill="both", expand="yes")
labelframe.configure(background="#f7f7f7")
frame2 = Frame(self.window2)
frame2.place(relx=0.125, rely=0.500, relheight=0.475, relwidth=0.350)
frame2.configure(relief='groove', borderwidth="2", width=305)
labelframe2 = LabelFrame(frame2, text="Métricas")
labelframe2.pack(fill="both", expand="yes")
frame3 = Frame(self.window2)
frame3.place(relx=0.525, rely=0.500, relheight=0.475, relwidth=0.350)
frame3.configure(relief='groove', borderwidth="2", width=305)
labelframe3 = LabelFrame(frame3, text="Palavras e Matrizes")
labelframe3.pack(fill="both", expand="yes")
def menuLista(): # Janela de frequência de palavras absolutas e relativas do Naive Bayes
if variavel_controlo.get() == False:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
else:
palavras = nb.matrizP
palavrasRel = nb.matrizP_Relativa
window9 = Toplevel()
window9.resizable(False, False)
window9.title('Frequências de Palavras')
window9.geometry("700x450+517+216")
frame1 = Frame(window9)
frame1.place(relx=0.0, rely=0.0, relheight=1.011, relwidth=0.508)
frame1.configure(relief='raised', borderwidth="2", width=700, background="#91cded")
titleA = Label(frame1)
titleA.place(relx=0.325, rely=0.0, height=40, width=125)
titleA.configure(relief="ridge", text="""Absolutas""", fg='white', background="#028f99", font=("Rockwell", 10))
labeltitle = Label(frame1)
labeltitle.place(relx=0.035, rely=0.138, height=31, width=80)
labeltitle.configure(relief="ridge", text="""Palavra:""", fg='white', background="#0082ba", font=("Rockwell", 9))
labeltitle2 = Label(frame1)
labeltitle2.place(relx=0.625, rely=0.138, height=31, width=50)
labeltitle2.configure(relief="ridge", text="""Spam""", fg='white', background="#0082ba", font=("Rockwell", 9))
labeltitle3 = Label(frame1)
labeltitle3.place(relx=0.805, rely=0.138, height=31, width=50)
labeltitle3.configure(relief="ridge", text="""Ham""", fg='white', background="#0082ba", font=("Rockwell", 9))
palAbs = Text(frame1)
for i, j in palavras.items():
lista = "{:22s}".format(str(i)) + "{:3s}".format(str(j[0])) + " " + "{:3s}".format(str(j[1])) + "\n"
palAbs.insert(END, lista)
palAbs.place(relx=0.035, rely=0.225, relheight=0.700, relwidth=0.915)
palAbs.configure(width=174, state='disabled')
frame2 = Frame(window9)
frame2.place(relx=0.5, rely=0.0, relheight=1.011, relwidth=0.508)
frame2.configure(relief='raised', borderwidth="2", width=700, background="#91cded")
title = Label(frame2)
title.place(relx=0.325, rely=0.0, height=40, width=125)
title.configure(relief="ridge", text="""Relativas""", fg='white', background="#028f99", font=("Rockwell", 10))
labeltitle2 = Label(frame2)
labeltitle2.place(relx=0.035, rely=0.138, height=31, width=80)
labeltitle2.configure(relief="ridge", text="""Palavra:""", fg='white', background="#0082ba", font=("Rockwell", 9))
labeltitle2_2 = Label(frame2)
labeltitle2_2.place(relx=0.565, rely=0.138, height=31, width=50)
labeltitle2_2.configure(relief="ridge", text="""Spam""", fg='white', background="#0082ba", font=("Rockwell", 9))
labeltitle3_2 = Label(frame2)
labeltitle3_2.place(relx=0.765, rely=0.138, height=31, width=50)
labeltitle3_2.configure(relief="ridge", text="""Ham""", fg='white', background="#0082ba", font=("Rockwell", 9))
palRel = Text(frame2)
for i, j in palavrasRel.items():
lista = "{:18s}".format(str(i)) + "{:0.4f}".format(j[0]) + " " + "{:0.4f}".format(j[1]) + "\n"
palRel.insert(END, lista)
palRel.place(relx=0.035, rely=0.225, relheight=0.700, relwidth=0.915)
palRel.configure(width=174, state='disabled')
window9.mainloop()
def iniciar(): # Funcao para iniciar o algoritmo de Naive Bayes
variavel_controlo.set(True)
nb.algoritmo()
def exatidao(): # Funcao para retornar o valor da exatidao de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="Exatidão", message='''{:0.3f} %'''.format(nb.exatidao))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
def sensibilidade(): # Funcao para retornar o valor da sensibilidade de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="Sensibilidade", message='''{:0.3f} %''' .format(nb.sensibilidade))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
def precisao(): # Funcao para retornar o valor da precisao de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="Precisão", message='''{:0.3f} %''' .format(nb.precisao))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
def fScore(): # Funcao para retornar o valor de fScore de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="fScore", message='''{:0.3f} %''' .format(nb.fScore))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
def MatrizC(): # Funcao para retornar a matriz de confusao de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="Matriz de Confusão", message=str(nb.confMatriz))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
def MatrizRel(): # Funcao para retornar a matriz de confusao relativa de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="Matriz Conf. Relativa", message=str(nb.confMatriz_Relativa))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
buttonlista = Button(frame1, command=lambda: iniciar())
buttonlista.place(relx=0.075, rely=0.400, height=35, width=150)
buttonlista.configure(text='''Iniciar''', pady="0", width=267, background="#9ef702", foreground="black", font=("Rockwell", 11))
buttonclose = Button(frame1, command=self.window2.destroy)
buttonclose.place(relx=0.475, rely=0.400, height=35, width=200)
buttonclose.configure(text='''Fechar Classificador''', pady="0", width=267, background="#f74702", foreground="white", font=("Rockwell", 11))
buttonExat = Button(frame2, command=lambda: exatidao())
buttonExat.place(relx=0.135, rely=0.150, height=30, width=150)
buttonExat.configure(text='''Exatidão''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonSensibilidade = Button(frame2, command=lambda: sensibilidade())
buttonSensibilidade.place(relx=0.135, rely=0.375, height=30, width=150)
buttonSensibilidade.configure(text='''Sensibilidade''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonPrecisao = Button(frame2, command=lambda: precisao())
buttonPrecisao.place(relx=0.135, rely=0.600, height=30, width=150)
buttonPrecisao.configure(text='''Precisão''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonfScore = Button(frame2, command=lambda: fScore())
buttonfScore.place(relx=0.135, rely=0.825, height=30, width=150)
buttonfScore.configure(text='''fScore''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonLista = Button(frame3, command=lambda: menuLista())
buttonLista.place(relx=0.075, rely=0.225, height=30, width=175)
buttonLista.configure(text='''Frequência Palavras''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonMatrizC = Button(frame3, command=lambda: MatrizC())
buttonMatrizC.place(relx=0.075, rely=0.475, height=30, width=175)
buttonMatrizC.configure(text='''Matriz de Confusão''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonMatrizRel = Button(frame3, command=lambda: MatrizRel())
buttonMatrizRel.place(relx=0.075, rely=0.725, height=30, width=175)
buttonMatrizRel.configure(text='''Matriz Conf. Relativa''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
def menuPerceptron(): # Janela do filtro de spam Perceptrao
self.window3 = Tk()
variavel_controlo = BooleanVar(self.window3)
pt = Perceptron()
self.window3.title('Perceptron')
self.window3.resizable(False, False)
self.window3.geometry('600x475+584+230')
self.window3.configure(background="#91cded")
labelwel = Label(self.window3)
labelwel.place(relx=0.25, rely=0.067, height=35, width=305)
labelwel.configure(background="#0082ba", foreground="white", relief='ridge', text='''Classificador Perceptron''', font=("Rockwell", 14))
frame1 = Frame(self.window3)
frame1.place(relx=0.125, rely=0.225, relheight=0.250, relwidth=0.750)
frame1.configure(relief='groove', borderwidth="2", width=305)
labelframe = LabelFrame(frame1, text="Opções")
labelframe.pack(fill="both", expand="yes")
labelframe.configure(background="#f7f7f7")
frame2 = Frame(self.window3)
frame2.place(relx=0.125, rely=0.500, relheight=0.475, relwidth=0.350)
frame2.configure(relief='groove', borderwidth="2", width=305)
labelframe2 = LabelFrame(frame2, text="Métricas")
labelframe2.pack(fill="both", expand="yes")
frame3 = Frame(self.window3)
frame3.place(relx=0.525, rely=0.500, relheight=0.475, relwidth=0.350)
frame3.configure(relief='groove', borderwidth="2", width=305)
labelframe3 = LabelFrame(frame3, text="Palavras e Matrizes")
labelframe3.pack(fill="both", expand="yes")
def menuListaPerc(): # Janela da quantidade de palavras do Perceptron
if variavel_controlo.get() == False:
messagebox.showerror(title="Erro", message="Inicie o Classificador Perceptron.")
else:
palavras = pt.freq_Pal
window10 = Toplevel()
window10.resizable(False, False)
window10.title('Frequências de Palavras')
window10.geometry("350x450+517+216")
frame1 = Frame(window10)
frame1.place(relx=0.0, rely=0.0, relheight=1, relwidth=1)
frame1.configure(relief='raised', borderwidth="2", width=700, background="#91cded")
titleA = Label(frame1)
titleA.place(relx=0.325, rely=0.0, height=40, width=125)
titleA.configure(relief="ridge", text="""Frequência""", fg='white', background="#028f99", font=("Rockwell", 10))
labeltitle = Label(frame1)
labeltitle.place(relx=0.035, rely=0.138, height=31, width=80)
labeltitle.configure(relief="ridge", text="""Palavra:""", fg='white', background="#0082ba", font=("Rockwell", 9))
labeltitle2 = Label(frame1)
labeltitle2.place(relx=0.665, rely=0.138, height=31, width=100)
labeltitle2.configure(relief="ridge", text="""Quantidade""", fg='white', background="#0082ba", font=("Rockwell", 9))
palAbs = Text(frame1)
for chave, valor in palavras.items():
lista = "{:26s}".format(str(chave)) + "{:3s}\n".format(str(valor))
palAbs.insert(END, lista)
palAbs.place(relx=0.035, rely=0.225, relheight=0.700, relwidth=0.915)
palAbs.configure(width=174, state='disabled')
window10.mainloop()
def iniciar(): # Funcao para iniciar o algoritmo de Perceptron
variavel_controlo.set(True)
pt.algoritmo()
def exatidao(): # Funcao para retornar o valor da exatidao de Perceptron
if variavel_controlo.get() == True:
messagebox.showinfo(title="Exatidão", message='''{:0.3f} %'''.format(pt.exatidao))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Perceptron.")
def sensibilidade(): # Funcao para retornar o valor da sensibilidade de Perceptron
if variavel_controlo.get() == True:
messagebox.showinfo(title="Sensibilidade", message='''{:0.3f} %''' .format(pt.sensibilidade))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Perceptron.")
def precisao(): # Funcao para retornar o valor da precisao de Perceptron
if variavel_controlo.get() == True:
messagebox.showinfo(title="Precisão", message='''{:0.3f} %''' .format(pt.precisao))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Perceptron.")
def fScore(): # Funcao para retornar o valor de fscore de Perceptron
if variavel_controlo.get() == True:
messagebox.showinfo(title="fScore", message='''{:0.3f} %''' .format(pt.fScore))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Perceptron.")
def MatrizC(): # Funcao para retornar o valor da matriz de confusao de Perceptron
if variavel_controlo.get() == True:
messagebox.showinfo(title="Matriz de Confusão", message=str(pt.matriz_Confusao))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Perceptron.")
def MatrizRel(): # Funcao para retornar o valor da matriz de confusao relativa de Perceptron
if variavel_controlo.get() == True:
messagebox.showinfo(title="Matriz Conf. Relativa", message=str(pt.matriz_Relativa))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Perceptron.")
buttonlista = Button(frame1, command=lambda: iniciar())
buttonlista.place(relx=0.075, rely=0.400, height=35, width=150)
buttonlista.configure(text='''Iniciar''', pady="0", width=267, background="#9ef702", foreground="black", font=("Rockwell", 11))
buttonclose = Button(frame1, command=self.window3.destroy)
buttonclose.place(relx=0.475, rely=0.400, height=35, width=200)
buttonclose.configure(text='''Fechar Classificador''', pady="0", width=267, background="#f74702", foreground="white", font=("Rockwell", 11))
buttonExat = Button(frame2, command=lambda: exatidao())
buttonExat.place(relx=0.135, rely=0.150, height=30, width=150)
buttonExat.configure(text='''Exatidão''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonSensibilidade = Button(frame2, command=lambda: sensibilidade())
buttonSensibilidade.place(relx=0.135, rely=0.375, height=30, width=150)
buttonSensibilidade.configure(text='''Sensibilidade''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonPrecisao = Button(frame2, command=lambda: precisao())
buttonPrecisao.place(relx=0.135, rely=0.600, height=30, width=150)
buttonPrecisao.configure(text='''Precisão''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonfScore = Button(frame2, command=lambda: fScore())
buttonfScore.place(relx=0.135, rely=0.825, height=30, width=150)
buttonfScore.configure(text='''fScore''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonLista = Button(frame3, command=lambda: menuListaPerc())
buttonLista.place(relx=0.075, rely=0.225, height=30, width=175)
buttonLista.configure(text='''Frequência Palavras''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonMatrizC = Button(frame3, command=lambda: MatrizC())
buttonMatrizC.place(relx=0.075, rely=0.475, height=30, width=175)
buttonMatrizC.configure(text='''Matriz de Confusão''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonMatrizRel = Button(frame3, command=lambda: MatrizRel())
buttonMatrizRel.place(relx=0.075, rely=0.725, height=30, width=175)
buttonMatrizRel.configure(text='''Matriz Conf. Relativa''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
def creditos(): # Funcao para mostrar os creditos do trabalho
messagebox.showinfo('Créditos',"""
Elaborado por:
- {:20s} - Nº 30003769
- {:20s} - Nº 30003043
- {:20s} - Nº 30005711
- {:20s} - Nº 30003039
Inteligência Artificial
@UAL - Universidade Autónoma de Lisboa
""".format('Bruno Silva', 'David Monteiro', 'Nuno Barrocas', 'Zacarias Chiena'))
def quit_program(): # Funcao para Sair do programa
self.window.quit()
self.window.destroy()
def on_closing(): # Funcao para terminar/fechar a janela do programa de filtro de spam
if messagebox.askokcancel("Fechar", "De certeza que quer sair?"):
self.window.destroy()
self.window2.destroy()
self.window3.destroy()
self.window.protocol("WM_DELETE_WINDOW", on_closing)
menubar = Menu(self.window)
gamemenu = Menu(menubar, tearoff=0)
gamemenu.add_command(label="Sobre", command=lambda: creditos())
gamemenu.add_command(label="Sair", command=lambda: quit_program())
menubar.add_cascade(label="Opções", menu=gamemenu)
menubar.add_cascade(label="Naïve Bayes", command=lambda: menuNaiveBayes())
menubar.add_cascade(label="Perceptron", command=lambda: menuPerceptron())
self.window.config(menu=menubar)
self.window.mainloop()
def menuNaiveBayes(): # janela do filtro de spam Naive Bayes
self.window2 = Tk()
variavel_controlo = BooleanVar(self.window2)
nb=NaiveBayes()
self.window2.title('Naïve Bayes')
self.window2.resizable(False, False)
self.window2.geometry('600x450+584+230')
self.window2.configure(background="#91cded")
labelwel = Label(self.window2)
labelwel.place(relx=0.25, rely=0.067, height=35, width=305)
labelwel.configure(background="#0082ba", foreground="white", relief='ridge', text='''Classificador Naïve Bayes''', font=("Rockwell", 14))
frame1 = Frame(self.window2)
frame1.place(relx=0.125, rely=0.225, relheight=0.250, relwidth=0.750)
frame1.configure(relief='groove', borderwidth="2", width=305)
labelframe = LabelFrame(frame1, text="Opções")
labelframe.pack(fill="both", expand="yes")
labelframe.configure(background="#f7f7f7")
frame2 = Frame(self.window2)
frame2.place(relx=0.125, rely=0.500, relheight=0.475, relwidth=0.350)
frame2.configure(relief='groove', borderwidth="2", width=305)
labelframe2 = LabelFrame(frame2, text="Métricas")
labelframe2.pack(fill="both", expand="yes")
frame3 = Frame(self.window2)
frame3.place(relx=0.525, rely=0.500, relheight=0.475, relwidth=0.350)
frame3.configure(relief='groove', borderwidth="2", width=305)
labelframe3 = LabelFrame(frame3, text="Palavras e Matrizes")
labelframe3.pack(fill="both", expand="yes")
def menuLista(): # Janela de frequência de palavras absolutas e relativas do Naive Bayes
if variavel_controlo.get() == False:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
else:
palavras = nb.matrizP
palavrasRel = nb.matrizP_Relativa
window9 = Toplevel()
window9.resizable(False, False)
window9.title('Frequências de Palavras')
window9.geometry("700x450+517+216")
frame1 = Frame(window9)
frame1.place(relx=0.0, rely=0.0, relheight=1.011, relwidth=0.508)
frame1.configure(relief='raised', borderwidth="2", width=700, background="#91cded")
titleA = Label(frame1)
titleA.place(relx=0.325, rely=0.0, height=40, width=125)
titleA.configure(relief="ridge", text="""Absolutas""", fg='white', background="#028f99", font=("Rockwell", 10))
labeltitle = Label(frame1)
labeltitle.place(relx=0.035, rely=0.138, height=31, width=80)
labeltitle.configure(relief="ridge", text="""Palavra:""", fg='white', background="#0082ba", font=("Rockwell", 9))
labeltitle2 = Label(frame1)
labeltitle2.place(relx=0.625, rely=0.138, height=31, width=50)
labeltitle2.configure(relief="ridge", text="""Spam""", fg='white', background="#0082ba", font=("Rockwell", 9))
labeltitle3 = Label(frame1)
labeltitle3.place(relx=0.805, rely=0.138, height=31, width=50)
labeltitle3.configure(relief="ridge", text="""Ham""", fg='white', background="#0082ba", font=("Rockwell", 9))
palAbs = Text(frame1)
for i, j in palavras.items():
lista = "{:22s}".format(str(i)) + "{:3s}".format(str(j[0])) + " " + "{:3s}".format(str(j[1])) + "\n"
palAbs.insert(END, lista)
palAbs.place(relx=0.035, rely=0.225, relheight=0.700, relwidth=0.915)
palAbs.configure(width=174, state='disabled')
frame2 = Frame(window9)
frame2.place(relx=0.5, rely=0.0, relheight=1.011, relwidth=0.508)
frame2.configure(relief='raised', borderwidth="2", width=700, background="#91cded")
title = Label(frame2)
title.place(relx=0.325, rely=0.0, height=40, width=125)
title.configure(relief="ridge", text="""Relativas""", fg='white', background="#028f99", font=("Rockwell", 10))
labeltitle2 = Label(frame2)
labeltitle2.place(relx=0.035, rely=0.138, height=31, width=80)
labeltitle2.configure(relief="ridge", text="""Palavra:""", fg='white', background="#0082ba", font=("Rockwell", 9))
labeltitle2_2 = Label(frame2)
labeltitle2_2.place(relx=0.565, rely=0.138, height=31, width=50)
labeltitle2_2.configure(relief="ridge", text="""Spam""", fg='white', background="#0082ba", font=("Rockwell", 9))
labeltitle3_2 = Label(frame2)
labeltitle3_2.place(relx=0.765, rely=0.138, height=31, width=50)
labeltitle3_2.configure(relief="ridge", text="""Ham""", fg='white', background="#0082ba", font=("Rockwell", 9))
palRel = Text(frame2)
for i, j in palavrasRel.items():
lista = "{:18s}".format(str(i)) + "{:0.4f}".format(j[0]) + " " + "{:0.4f}".format(j[1]) + "\n"
palRel.insert(END, lista)
palRel.place(relx=0.035, rely=0.225, relheight=0.700, relwidth=0.915)
palRel.configure(width=174, state='disabled')
window9.mainloop()
def iniciar(): # Funcao para iniciar o algoritmo de Naive Bayes
variavel_controlo.set(True)
nb.algoritmo()
def exatidao(): # Funcao para retornar o valor da exatidao de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="Exatidão", message='''{:0.3f} %'''.format(nb.exatidao))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
def sensibilidade(): # Funcao para retornar o valor da sensibilidade de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="Sensibilidade", message='''{:0.3f} %''' .format(nb.sensibilidade))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
def precisao(): # Funcao para retornar o valor da precisao de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="Precisão", message='''{:0.3f} %''' .format(nb.precisao))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
def fScore(): # Funcao para retornar o valor de fScore de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="fScore", message='''{:0.3f} %''' .format(nb.fScore))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
def MatrizC(): # Funcao para retornar a matriz de confusao de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="Matriz de Confusão", message=str(nb.confMatriz))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
def MatrizRel(): # Funcao para retornar a matriz de confusao relativa de Naive Bayes
if variavel_controlo.get() == True:
messagebox.showinfo(title="Matriz Conf. Relativa", message=str(nb.confMatriz_Relativa))
else:
messagebox.showerror(title="Erro", message="Inicie o Classificador Naïve Bayes.")
buttonlista = Button(frame1, command=lambda: iniciar())
buttonlista.place(relx=0.075, rely=0.400, height=35, width=150)
buttonlista.configure(text='''Iniciar''', pady="0", width=267, background="#9ef702", foreground="black", font=("Rockwell", 11))
buttonclose = Button(frame1, command=self.window2.destroy)
buttonclose.place(relx=0.475, rely=0.400, height=35, width=200)
buttonclose.configure(text='''Fechar Classificador''', pady="0", width=267, background="#f74702", foreground="white", font=("Rockwell", 11))
buttonExat = Button(frame2, command=lambda: exatidao())
buttonExat.place(relx=0.135, rely=0.150, height=30, width=150)
buttonExat.configure(text='''Exatidão''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonSensibilidade = Button(frame2, command=lambda: sensibilidade())
buttonSensibilidade.place(relx=0.135, rely=0.375, height=30, width=150)
buttonSensibilidade.configure(text='''Sensibilidade''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonPrecisao = Button(frame2, command=lambda: precisao())
buttonPrecisao.place(relx=0.135, rely=0.600, height=30, width=150)
buttonPrecisao.configure(text='''Precisão''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonfScore = Button(frame2, command=lambda: fScore())
buttonfScore.place(relx=0.135, rely=0.825, height=30, width=150)
buttonfScore.configure(text='''fScore''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonLista = Button(frame3, command=lambda: menuLista())
buttonLista.place(relx=0.075, rely=0.225, height=30, width=175)
buttonLista.configure(text='''Frequência Palavras''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonMatrizC = Button(frame3, command=lambda: MatrizC())
buttonMatrizC.place(relx=0.075, rely=0.475, height=30, width=175)
buttonMatrizC.configure(text='''Matriz de Confusão''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
buttonMatrizRel = Button(frame3, command=lambda: MatrizRel())
buttonMatrizRel.place(relx=0.075, rely=0.725, height=30, width=175)
buttonMatrizRel.configure(text='''Matriz Conf. Relativa''', pady="0", width=267, background="#028f99", foreground="white", font=("Rockwell", 10))
from naiveBayes import NaiveBayes
from glob import glob
r = NaiveBayes('../data/nb/20news-bydate-train/')
r.train()
folders = ['talk.politics.mideast', 'sci.crypt', 'comp.os.ms-windows.misc',
'comp.sys.ibm.pc.hardware', 'rec.sport.baseball']
for folder in folders:
for file in glob('../data/nb/20news-bydate-test/' + folder + "/*"):
print file
r.testFile(file)
break
break