- raise an error instead of printing a warning in from_frame()

- updated documentation of from_frame(), df_aslarray() and read_hdf()

Author: alixdamman

larray/inout/hdf.py

@@ -31,9 +31,12 @@ def read_hdf(filepath_or_buffer, key, fill_value=nan, na=nan, sort_rows=False, s
         Value used to fill cells corresponding to label combinations which are not present in the input.
         Defaults to NaN.
     sort_rows : bool, optional
-        Whether or not to sort the rows alphabetically (sorting is more efficient than not sorting). Defaults to False.
+        Whether or not to sort the rows alphabetically.
+        Must be False if the read array has been dumped with an larray version >= 0.30.
+        Defaults to False.
     sort_columns : bool, optional
-        Whether or not to sort the columns alphabetically (sorting is more efficient than not sorting).
+        Whether or not to sort the columns alphabetically.
+        Must be False if the read array has been dumped with an larray version >= 0.30.
         Defaults to False.
     name : str, optional
         Name of the axis or group to return. If None, name is set to passed key.

larray/inout/pandas.py

@@ -152,10 +152,12 @@ def from_frame(df, sort_rows=False, sort_columns=False, parse_header=False, unfo
         columns Index of the dataframe unless argument unfold_last_axis_name is set to True.
     sort_rows : bool, optional
         Whether or not to sort the rows alphabetically (sorting is more efficient than not sorting).
-        Not used if `cartesian_prod` is False. Defaults to False.
+        Must be False if `cartesian_prod` is set to True.
+        Defaults to False.
     sort_columns : bool, optional
         Whether or not to sort the columns alphabetically (sorting is more efficient than not sorting).
-        Not used if `cartesian_prod` is False. Defaults to False.
+        Must be False if `cartesian_prod` is set to True.
+        Defaults to False.
     parse_header : bool, optional
         Whether or not to parse columns labels. Pandas treats column labels as strings.
         If True, column labels are converted into int, float or boolean when possible. Defaults to False.
@@ -171,7 +173,8 @@ def from_frame(df, sort_rows=False, sort_columns=False, parse_header=False, unfo
     cartesian_prod : bool, optional
         Whether or not to expand the dataframe to a cartesian product dataframe as needed by LArray.
         This is an expensive operation but is absolutely required if you cannot guarantee your dataframe is already
-        well formed. Defaults to True.
+        well formed. If True, arguments `sort_rows` and `sort_columns` must be set to False.
+        Defaults to True.
 
     Returns
     -------
@@ -233,8 +236,8 @@ def from_frame(df, sort_rows=False, sort_columns=False, parse_header=False, unfo
                                                fill_value=fill_value, **kwargs)
     else:
         if sort_rows or sort_columns:
-            import warnings
-            warnings.warn('sort_rows and sort_columns are not used when cartesian_prod is set to False', stacklevel=2)
+            raise ValueError('sort_rows and sort_columns cannot not be used when cartesian_prod is set to False. '
+                             'Please call the method sort_axes on the returned array to sort rows or columns')
         axes_labels = index_to_labels(df.index, sort=False)
 
     # Pandas treats column labels as column names (strings) so we need to convert them to values
@@ -258,9 +261,12 @@ def df_aslarray(df, sort_rows=False, sort_columns=False, raw=False, parse_header
     df : Pandas DataFrame
         Input dataframe.
     sort_rows : bool, optional
-        Whether or not to sort the rows alphabetically (sorting is more efficient than not sorting). Defaults to False.
+        Whether or not to sort the rows alphabetically (sorting is more efficient than not sorting).
+        Must be False if `cartesian_prod` is set to True.
+        Defaults to False.
     sort_columns : bool, optional
         Whether or not to sort the columns alphabetically (sorting is more efficient than not sorting).
+        Must be False if `cartesian_prod` is set to True.
         Defaults to False.
     raw : bool, optional
         Whether or not to consider the input dataframe as a raw dataframe, i.e. read without index at all.
@@ -275,7 +281,8 @@ def df_aslarray(df, sort_rows=False, sort_columns=False, raw=False, parse_header
     cartesian_prod : bool, optional
         Whether or not to expand the dataframe to a cartesian product dataframe as needed by LArray.
         This is an expensive operation but is absolutely required if you cannot guarantee your dataframe is already
-        well formed. Defaults to True.
+        well formed. If True, arguments `sort_rows` and `sort_columns` must be set to False.
+        Defaults to True.
 
     Returns
     -------