def predictResult(x_train, y_train, y_test, x_test):
data2 = pd.read_csv("/tmp/predict_result.csv", header=0)
# vamos percorrer o arquivo com o valor a ser testado, onde vamos pegar as colunas e jogar os valores numa array
cols2 = data2.columns[(data2.columns != columnResultName)]
fts2 = data2[cols2]
fts2 = Normalizer().fit_transform(fts2)
randomForest.fit(x_train, y_train)
dump(randomForest, 'randomForest.model')
randomForestLoaded = load('randomForest.model')
prFit = randomForestLoaded.predict(x_test)
print("predicao:", prFit)
print("Matriz de Confusao LR:")
print(cfm(y_test, prFit))
print("F1 score LR:")
print(f1s(y_test, prFit))
print("Precision score LR:")
print(ps(y_test, prFit))
print("Recall score LR:")
print(rs(y_test, prFit))
print("Classification Report")
print(cr(y_test, prFit))
pr1 = randomForestLoaded.predict(fts2)
print("predico unica", pr1)
return pr1
def predictResult(betterN, x_train, y_train, y_test, x_test):
data2 = pd.read_csv("/tmp/predict_result.csv", header=0)
# vamos percorrer o arquivo com o valor a ser testado, onde vamos pegar as colunas e jogar os valores numa array
cols2 = data2.columns[(data2.columns != columnResultName)]
fts2 = np.array(data2[cols2])
#quando nao mandar um vaor de betterN, significa que demos o load do modelo
if betterN > 0:
knn.n_neighbors = betterN
knn.fit(x_train, y_train)
# dump(knn, 'models/knn_teste.joblib')
prFit = knn.predict(x_test)
print("predicao: a", prFit)
print("Matriz de Confusao NB:")
print(cfm(y_test, prFit))
print("F1 score NB:")
print(f1s(y_test, prFit))
print("Precision score NB:")
print(ps(y_test, prFit))
print("Recall score NB:")
print(rs(y_test, prFit))
print("Classification Report")
print(cr(y_test, prFit))
pr1 = knn.predict(fts2)
print("predico unica", int(pr1[0]))
print("predicao unica score")
print(pr1)
return pr1
def predictResult(x_train, y_train, y_test, x_test):
data2 = pd.read_csv("/tmp/predict_result.csv", header=0)
# vamos percorrer o arquivo com o valor a ser testado, onde vamos pegar as colunas e jogar os valores numa array
cols2 = data2.columns[(data2.columns != columnResultName)]
fts2 = data2[cols2]
fts2 = Normalizer().fit_transform(fts2)
scores = cross_val_score(logisticR, x_train, y_train, n_jobs=30)
print("scores cross val")
print(scores)
logisticR.fit(x_train, y_train)
dump(logisticR, 'logistic.model')
logisticLoaded = load('logistic.model')
prFit = logisticLoaded.predict(x_test)
print("predicao:", prFit)
print("Matriz de Confusao LR:")
print(cfm(y_test, prFit))
print("F1 score LR:")
print(f1s(y_test, prFit))
print("Precision score LR:")
print(ps(y_test, prFit))
print("Recall score LR:")
print(rs(y_test, prFit))
print("Classification Report")
print(cr(y_test, prFit))
print("Accuracy score")
print(asc(y_test, prFit))
class_names = [0, 1] # name of classes
fig, ax = plt.subplots()
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
# create heatmap
sns.heatmap(pd.DataFrame(cfm(y_test, prFit)),
annot=True,
cmap="YlGnBu",
fmt='g')
ax.xaxis.set_label_position("top")
plt.tight_layout()
plt.title('Confusion matrix', y=1.1)
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
plt.show()
y_pred_proba = logisticLoaded.predict_proba(x_test)[::, 1]
fpr, tpr, _ = metrics.roc_curve(y_test, y_pred_proba)
auc = metrics.roc_auc_score(y_test, y_pred_proba)
plt.plot(fpr, tpr, label="data 1, auc=" + str(auc))
plt.legend(loc=4)
plt.show()
pr1 = logisticLoaded.predict(fts2)
print("predico unica", pr1)
return pr1
def f1_score(gt, pred, F1_Thresh=0.5, files=None, median=False):
from sklearn.metrics import precision_score, recall_score
from sklearn.metrics import f1_score as f1s
if type(gt)==list: gt = np.array(gt)
if type(pred)==list: pred = np.array(pred)
# F1_Thresh = 0.5
output = (pred>F1_Thresh)*1.0
F1 = f1s(gt, output)
F1_MAX=F1
if median:
output_median3, output_median5, output_median7 = get_median(output, files)
F1_median3 = f1s(gt, output_median3)
F1_median5 = f1s(gt, output_median5)
F1_median7 = f1s(gt, output_median7)
return [F1], F1_MAX, F1_Thresh, F1_median3, F1_median5, F1_median7
else:
return [F1], F1_MAX, F1_Thresh
for n in range(0, 5):
print "Quantidade Vizinhos:", neighbors[n]
knn3 = KNeighborsClassifier(n_neighbors=neighbors[n])
knn3.fit(x_train, y_train)
print "Accuracy Training KNN:", knn3.score(x_train, y_train)
predictions = knn3.predict(x_test)
accuracy = metrics.accuracy_score(y_test, predictions)
print "Accuracy Test KNN:", accuracy
print "Matriz de Confusao KNN:"
print cfm(y_test, predictions)
print "F1 score KNN:"
print f1s(y_test, predictions)
print "Precision score KNN:"
print ps(y_test, predictions)
print "Recall score KNN:"
print rs(y_test, predictions)
#svm kernel linear
svm = svm.SVC(kernel='linear', C=1.0)
svm.fit(x_train, y_train)
predictionsSvm = svm.predict(x_test)
accuracySvm = metrics.accuracy_score(predictionsSvm, y_test)
print "SVM LINEAR Accuracy Test:", accuracySvm