def _preprocess_data(self, data):
X = self._feature_matrix(data)
n = X.count()
self.__means, var = column_statistics(X)
var = var * (n - 1) / n
X = RowMatrix(center(X, means=self.__means))
return X, self.__means, var
def _precision(data):
logger.info("Computing precision")
X = as_rdd_of_array(data.select("features"))
X = RowMatrix(center(X))
pres = precision(X)
return pres
def transform(self, data):
X = self._feature_matrix(data)
X = RowMatrix(center(X, self.__means))
return FactorAnalysisTransform(self._transform(data, X), self.model)
def _preprocess_data(self, data):
X = self._feature_matrix(data)
self.__means = column_means(X)
return RowMatrix(center(X, means=self.__means))