meal_price_outlier_classifier.py 文件源码

def fit(self, X):
        _X = X[self.__applicable_rows(X)]
        companies = _X.groupby('recipient_id').apply(self.__company_stats) \
            .reset_index()
        companies = companies[self.__applicable_company_rows(companies)]

        self.cluster_model = KMeans(n_clusters=3)
        self.cluster_model.fit(companies[self.CLUSTER_KEYS])
        companies['cluster'] = self.cluster_model.predict(companies[self.CLUSTER_KEYS])
        self.clusters = companies.groupby('cluster') \
            .apply(self.__cluster_stats) \
            .reset_index()
        self.clusters['threshold'] = \
            self.clusters['mean'] + 4 * self.clusters['std']
        return self