def stackedmodel_p(train, query, train_cols):
#instantiating the model
rf = RandomForestClassifier(n_estimators=150)
hybrid_model_AB = AdaBoostClassifier(DecisionTreeClassifier(max_depth=3), n_estimators=10)
lrd = LogisticRegression(solver='lbfgs', max_iter=300)
clf_stackd = StackingClassifier(classifiers =[rf, hybrid_model_AB], meta_classifier = lra, use_probas = True, use_features_in_secondary = True)
#cleaning data by applying preprocessing
train[train_cols] = preprocessing.scale(train[train_cols])
query[train_cols] = preprocessing.scale(query[train_cols])
#fitting the model
print(clf_stackd.fit(train[train_cols], train['malicious']))
#cross-validating and evaluating the performance of model
scores = cv.cross_val_score(clf_stackd, train[train_cols], train['malicious'], cv=30)
print('Estimated score Random Forest & Gaussian Naive Bayes: %0.5f (+/- %0.5f)' % (scores.mean(), scores.std() / 2))
#predicting the target query from the model
query['result'] = clf_stackd.predict(query[train_cols])
#printing the predicted results
print(query[['URL', 'result']])
return query['result']
def stackedmodel_n(train, query, train_cols):
#instantiating the model
rf = RandomForestClassifier(n_estimators=150)
tree = DecisionTreeClassifier(min_impurity_decrease=0)
lrb = LogisticRegression(solver='lbfgs', max_iter=300)
clf_stackb = StackingClassifier(classifiers =[rf, tree], meta_classifier = lra, use_probas = True, use_features_in_secondary = True)
#cleaning data by applying preprocessing
train[train_cols] = preprocessing.scale(train[train_cols])
query[train_cols] = preprocessing.scale(query[train_cols])
#fitting the model
print(clf_stackb.fit(train[train_cols], train['malicious']))
#cross-validating and evaluating the performance of model
scores = cv.cross_val_score(clf_stackb, train[train_cols], train['malicious'], cv=30)
print('Estimated score Random Forest & Decision Tree: %0.5f (+/- %0.5f)' % (scores.mean(), scores.std() / 2))
#predicting the target query from the model
query['result'] = clf_stackb.predict(query[train_cols])
#printing the predicted results
print(query[['URL', 'result']])
return query['result']
def stackedmodel_e(train, query, train_cols):
#instantiating the model
rf = RandomForestClassifier(n_estimators=150)
gnb = GaussianNB()
tree = DecisionTreeClassifier(min_impurity_decrease=0)
mlp = MLPClassifier(alpha=0.001, hidden_layer_sizes=([100,100,100]),max_iter=900)
hybrid_model_AB = AdaBoostClassifier(DecisionTreeClassifier(max_depth=3), n_estimators=10)
clf = svm.SVC()
lrm = LogisticRegression(solver='lbfgs', max_iter=1000)
clf_stackm = StackingClassifier(classifiers =[clf_stackz, clf], meta_classifier = lrz, use_probas = True, use_features_in_secondary = True)
#cleaning data by applying preprocessing
train[train_cols] = preprocessing.scale(train[train_cols])
query[train_cols] = preprocessing.scale(query[train_cols])
#fitting the model
print(clf_stackm.fit(train[train_cols], train['malicious']))
#cross-validating and evaluating the performance of model
scores = cv.cross_val_score(clf_stackm, train[train_cols], train['malicious'], cv=30)
print('Estimated score Random Forest,Gaussian Naive Bayes,Decision Forest,MLPs,AdaBoost & SVM: %0.5f (+/- %0.5f)' % (scores.mean(), scores.std() / 2))
#predicting the target query from the model
query['result'] = clf_stackm.predict(query[train_cols])
#printing the predicted results
print(query[['URL', 'result']])
return query['result']
def modelfit(alg, dtrain, dtest, predictors, target, IDcol, filename):
# Fit the algorithm on the data
alg.fit(dtrain[predictors], dtrain[target])
# Predict training set:
dtrain_predictions = alg.predict(dtrain[predictors])
# Perform cross-validation:
cv_score = cross_validate.cross_val_score(alg, dtrain[predictors], dtrain[target], cv=20,
scoring='mean_squared_error')
cv_score = np.sqrt(np.abs(cv_score))
# Print model report:
print
"\nModel Report"
print
"RMSE : %.4g" % np.sqrt(metrics.mean_squared_error(dtrain[target].values, dtrain_predictions))
print
"CV Score : Mean - %.4g | Std - %.4g | Min - %.4g | Max - %.4g" % (
np.mean(cv_score), np.std(cv_score), np.min(cv_score), np.max(cv_score))
# Predict on testing data:
dtest[target] = alg.predict(dtest[predictors])
# Export submission file:
IDcol.append(target)
submission = pd.DataFrame({x: dtest[x] for x in IDcol})
submission.to_csv(filename, index=False)
def forest_classifier(train, query, train_cols):
rf = RandomForestClassifier(n_estimators=150)
print rf.fit(train[train_cols], train['firmware_bool'])
scores = cv.cross_val_score(rf,
train[train_cols],
train['firmware_bool'],
cv=30)
print('Estimated score RandomForestClassifier: %0.5f (+/- %0.5f)' %
(scores.mean(), scores.std() / 2))
query['result'] = rf.predict(query[train_cols])
print query[['url', 'result']]
def cross_validation():
dataset = load_data()
print(dataset)
row, col = dataset.shape
X = dataset[:, :col - 1]
y = dataset[:, -1]
clf = SVC(kernel='rbf', C=1000)
clf.fit(X, Y)
scores = cs.cross_val_score(clf, X, y, cv=5, score_func=None)
print("Accuracy: %0.2f (+- %0.2f)" % (scores.mean(), scores.std()))
return clf
def svm_classifier(train, query, train_cols): ###特征数据，带查询的特征数据，去除字符串的特征信息
clf = svm.SVC() ##分类器
train[train_cols] = preprocessing.scale(train[train_cols])
query[train_cols] = preprocessing.scale(query[train_cols])
print clf.fit(train[train_cols], train['firmware_bool'])
scores = cv.cross_val_score(clf,
train[train_cols],
train['firmware_bool'],
cv=30)
print('Estimated score SVM: %0.5f (+/- %0.5f)' %
(scores.mean(), scores.std() / 2))
query['result'] = clf.predict(query[train_cols])
print query[['url', 'result']]
def svm_classifier(train, query, train_cols):
clf = svm.SVC()
train[train_cols] = preprocessing.scale(train[train_cols])
query[train_cols] = preprocessing.scale(query[train_cols])
print(clf.fit(train[train_cols], train['malicious']))
scores = cv.cross_val_score(clf, train[train_cols], train['malicious'], cv=30)
print('Estimated score SVM: %0.5f (+/- %0.5f)' % (scores.mean(), scores.std() / 2))
query['result'] = clf.predict(query[train_cols])
print(query[['URL', 'result']])
