Prediction.py 文件源码

def CART(train, test, tunings=None, smoteit=True, duplicate=True):
  "  CART"
  # Apply random forest Classifier to predict the number of bugs.
  if smoteit:
    train = SMOTE(train, atleast=50, atmost=101, resample=duplicate)

  if not tunings:
    clf = DecisionTreeClassifier()
  else:
    clf = DecisionTreeClassifier(max_depth=int(tunings[0]),
                                 min_samples_split=int(tunings[1]),
                                 min_samples_leaf=int(tunings[2]),
                                 max_features=float(tunings[3] / 100),
                                 max_leaf_nodes=int(tunings[4]),
                                 criterion='entropy')
  train_DF = formatData(train)
  test_DF = formatData(test)
  features = train_DF.columns[:-2]
  klass = train_DF[train_DF.columns[-2]]
  # set_trace()
  clf.fit(train_DF[features].astype('float32'), klass.astype('float32'))
  preds = clf.predict(test_DF[test_DF.columns[:-2]].astype('float32')).tolist()
  return preds