from sklearn.metrics import f1_score
from sklearn.preprocessing import LabelEncoder
col_names = pd.read_csv('data/names.csv') # 'data/names.csv'
data = pd.read_csv('data/breast-cancer-wisconsin.data', names=col_names.columns)
data = data[data["bare_nuclei"] != '?']
data.set_index('id', inplace=True) #stop the model from using id as a node
train, test = train_test_split(data, test_size=0.2, random_state=0)
Y_test = test['class']
test = test.drop(['class'], axis=1)
#fit model
model = NaiveBayes()
model.fit(train, 'class')
print("Naive Bayes edges: ", model.edges())
#make predictions
Y_pred = model.predict(test)
#Convert Labels so we can use sklearn function to evaluate our model
labelencoder = LabelEncoder()
Y_test = labelencoder.fit_transform(Y_test.values.ravel())
Y_pred = labelencoder.fit_transform(Y_pred.values.ravel())
# Output results
accuracy = accuracy_score(Y_test, Y_pred)
precision = precision_score(Y_test, Y_pred)
f1 = f1_score(Y_test, Y_pred)
print({"Accuracy": accuracy, "Precision": precision, "F1 Score": f1})
# Print the CPDs learned
print("\n\n............Overview of our CPDs from the fit...........:")
for cpd in model.get_cpds():
print("CPD of {variable}:".format(variable=cpd.variable))
print(cpd)
#################################################################################
##### Using the model to query
#################################################################################
# Doing exact inference using Variable Elimination
model_infer = VariableElimination(model)
# Computing the probability of class given sex
# print("\n\n............Here are some queries...............")
# q1 = model_infer.query(variables=['class'], evidence={'sex':0})
# print(q1['class'])
#################################################################################
##### Evalutating the model by predicting
#################################################################################
y_true = data_test['class'].copy()
data_test.drop('class', axis=1, inplace=True)
y_pred = model.predict(data_test)
#print(y_pred)
accuracy = accuracy_score(y_pred, y_true)
print("\n\n\n\n\n\nAccuracy = ", accuracy)
print("\nEnd of code \n...o0o.... F**k you Julien ...o0o...")
print("\nRuntime: ")
end = time.time()
print(round(end - start),"seconds")