def summarize_df(dframe, dataset, groups=[]):
"""Calculate summary statistics."""
return {
col: {SUMMARY: series_to_jsondict(summarize_series(dataset.is_dimension(col), data))}
for col, data in dframe.iteritems()
if summarizable(dframe, col, groups, dataset)
}
def summarize_df(dframe, groups=[], dataset=None):
"""Calculate summary statistics."""
dtypes = dframe.dtypes
return {
col: {SUMMARY: series_to_jsondict(summarize_series(dtypes[col], data))}
for col, data in dframe.iteritems()
if summarizable(dframe, col, groups, dataset)
}
def _check_dframe_is_subset(self, dframe1, dframe2):
dframe2_rows = [self._reduce_precision(row) for row in
BambooFrame(dframe2).to_jsondict()]
for row in dframe1.iterrows():
dframe1_row = self._reduce_precision(series_to_jsondict(row[1]))
self.assertTrue(dframe1_row in dframe2_rows,
'dframe1_row: %s\n\ndframe2_rows: %s' % (
dframe1_row, dframe2_rows))
def summarize_df(dframe, dataset, groups=[]):
"""Calculate summary statistics."""
return {
col: {
SUMMARY:
series_to_jsondict(
summarize_series(dataset.is_dimension(col), data))
}
for col, data in dframe.iteritems()
if summarizable(dframe, col, groups, dataset)
}
def to_jsondict(self):
"""Return DataFrame as a list of dicts for each row."""
return [series_to_jsondict(series) for _, series in self.iterrows()]
def summarize_with_groups(dframe, groups, dataset):
"""Calculate summary statistics for group."""
return series_to_jsondict(dframe.groupby(groups).apply(summarize_df, dataset, groups))
def summarize_with_groups(dframe, groups, dataset):
"""Calculate summary statistics for group."""
return series_to_jsondict(
dframe.groupby(groups).apply(summarize_df, dataset, groups))
