def cv_evaluate_model(model, dframe):
X = get_featues(dframe)
y = get_label(dframe)
kfold = StratifiedKFold(n_splits=10, shuffle=True)
accuracy = np.empty(10)
precision = np.empty(10)
recall = np.empty(10)
for i, (train_idx, test_idx) in tqdm(enumerate(kfold.split(X, y))):
model.train(dframe.iloc[train_idx])
predictions = model.predict(X.iloc[test_idx])
accuracy[i] = accuracy_score(y[test_idx], predictions)
precision[i] = precision_score(y[test_idx],
predictions,
average='macro')
recall[i] = recall_score(y[test_idx], predictions, average='macro')
results = {
'params': model.get_params(),
'model': model.name,
'accuracy_std': np.std(accuracy),
'accuracy_mean': np.mean(accuracy),
'precision_std': np.std(precision),
'precision_mean': np.mean(precision),
'recall_std': np.std(recall),
'recall_mean': np.mean(recall)
}
return results
def train(self, dframe):
# from preprocess.py
X = get_featues(dframe)
y = get_label(dframe)
self.clf.fit(X, y)
def train(self, dframe):
X = get_featues(dframe)
y = get_label(dframe)
self.clf.fit(X, y)
def plot_learning_curve(self, dframe):
X = get_featues(dframe)
y = get_label(dframe)
return skplt.plot_learning_curve(self.clf, X, y)