class ModelEmbedder :

    def __init__(self, model, rare_threshold) :
        self.model = model
        self.means = {}
        self.rare_threshold = rare_threshold
        self.train = None
        self.origin_train = None
        self.average = 0


    def fit(self,train,target):
        self.origin_train = train.copy().fillna(-1)
        self.train = train.copy()
        self.train = self.train.fillna(-1)
        self.train['target'] = target
        self.average = target.mean()

        for feat in train.columns:
            if feat != 'target' :
                if self.train[feat].dtype=='object' :
                    self.train.loc[self.train[feat].value_counts()[self.train[feat]].values <  self.rare_threshold, feat] = "RARE"
                    self.origin_train.loc[self.origin_train[feat].value_counts()[self.origin_train[feat]].values <  self.rare_threshold, feat] = "RARE"
                    self.means[feat] = self.train.groupby([feat])['target'].mean()
                    self.means[feat]["RARE"] = self.average

                    self.train[feat] = self.train[feat].replace(self.means[feat], inplace=False)

        del self.train['target']

        self.model.fit(self.train,target)

    def _pre_treat_test(self,test) :
        test = test.copy()
        test = test.fillna(-1)

        for feat in self.origin_train.columns:
            if self.origin_train[feat].dtype=='object' :
                test.loc[self.origin_train[feat].value_counts()[self.origin_train[feat]].values  <  self.rare_threshold, feat] = "RARE"

                criterion = ~test[feat].isin(set(self.origin_train[feat]))

                test.loc[criterion,feat] = self.average


                test[feat]  = test[feat].replace(self.means[feat], inplace=False)

        return test

    def predict_proba(self,test) :
        test = self._pre_treat_test(test)
        return self.model.predict_proba(test)

    def get_params(self, deep = True):
        return self.model.get_params(deep)

rf = ensemble.ExtraTreesClassifier(n_jobs=7,
    n_estimators = n_estimators,
    random_state = 11)

rf_embedded = model_embedder.ModelEmbedder(rf,10)