def _update(self): res = h2o.frame(self._id)["frames"][0] # TODO: exclude here? self._nrows = res["rows"] self._ncols = len(res["columns"]) self._col_names = [c["label"] for c in res["columns"]] self._computed=True self._ast=None
def _update(self): # get ncols,nrows,names and exclude everything else # frames_ex = ["row_offset", "row_count", "checksum", "default_percentiles", "compatible_models", # "vec_ids","chunk_summary","distribution_summary"] # columns_ex = ["missing_count", "zero_count", "positive_infinity_count", "negative_infinity_count", # "mins", "maxs", "mean", "sigma", "type", "domain", "data", "string_data", # "precision", "histogram_bins", "histogram_base", "histogram_stride", "percentiles"] # # frames_ex = "frames/" + ",frames/".join(frames_ex) # columns_ex = "frames/columns/" + ",frames/columns/".join(columns_ex) # exclude="?_exclude_fields={},{}".format(frames_ex,columns_ex) res = h2o.frame(self._id)["frames"][0] # TODO: exclude here? self._nrows = res["rows"] self._ncols = len(res["columns"]) self._col_names = [c["label"] for c in res["columns"]] self._computed=True self._ast=None
def describe(self): """ Generate an in-depth description of this H2OFrame. The description is a tabular print of the type, min, max, sigma, number of zeros, and number of missing elements for each H2OVec in this H2OFrame. :return: None (print to stdout) """ self._eager() thousands_sep = h2o.H2ODisplay.THOUSANDS print "Rows:", thousands_sep.format(self._nrows), "Cols:", thousands_sep.format(self._ncols) chunk_dist_sum = h2o.frame(self._id)["frames"][0] dist_summary = chunk_dist_sum["distribution_summary"] chunk_summary = chunk_dist_sum["chunk_summary"] chunk_summary.show() dist_summary.show() self.summary()