From 0b51b1770f9f2584ced7b523ac7eab26ca0d54cb Mon Sep 17 00:00:00 2001
From: Bert Palm <bert.palm@ufz.de>
Date: Sat, 21 Mar 2020 02:28:34 +0100
Subject: [PATCH] some fixes, that came across during integrating dios in saqc
---
__init__.py | 3 ++
dios/indexer.py | 114 +++++++++++++++++++++---------------------------
2 files changed, 52 insertions(+), 65 deletions(-)
create mode 100644 __init__.py
diff --git a/__init__.py b/__init__.py
new file mode 100644
index 0000000..944c1c9
--- /dev/null
+++ b/__init__.py
@@ -0,0 +1,3 @@
+#!/usr/bin/env python
+
+from .dios import *
diff --git a/dios/indexer.py b/dios/indexer.py
index 983a1e1..f1a4c43 100644
--- a/dios/indexer.py
+++ b/dios/indexer.py
@@ -90,12 +90,9 @@ class _Indexer:
set_(data, value, iter=True)
else:
- if _is_list_like(value):
- if _is_hashable(colkey) or _is_hashable(rowkey):
- pass
- else:
- raise ValueError("broadcast array-like to multiple columns "
- "is not allowed, use '.aloc' for that.")
+ if _is_list_like(value) and len(data) > 1:
+ raise ValueError("broadcast array-like to multiple columns "
+ "is not allowed, use '.aloc' for that.")
set_(data, value)
@@ -223,14 +220,6 @@ class _iLocIndexer(_Indexer):
if _is_dios_like(rowkey) or _is_dios_like(colkey):
raise ValueError("Cannot index with multidimensional key")
- def set_(data, value, iter=False):
- c = "?"
- try:
- for i, c in enumerate(data.index):
- data.at[c].iloc[rowkey] = value[i] if iter else value
- except Exception as e:
- raise type(e)(f"failed for column {c}: " + str(e)) from e
-
# .iloc[any, int] = Any
if _is_integer(colkey):
if _is_dios_like(value) or _is_nested_list_like(value):
@@ -259,6 +248,13 @@ class _aLocIndexer(_Indexer):
self._usebool = True
def __call__(self, usebool=True):
+ """ We are called if the user want to set `usebool=False', which make
+ boolean alignable indexer treat as non-boolean alignable indexer.
+
+ Explanation: A boolean dios indexer align its indices with the indices
+ of the receiving dios like a non-boolean dios indexer also would do.
+ Additionally all rows with False values are kicked too. To disable
+ that `usebool=False` can be given."""
self._usebool = usebool
return self
@@ -338,8 +334,7 @@ class _aLocIndexer(_Indexer):
def keys_from_bool_dios_like(key):
if not _is_bool_dios_like(key):
- raise ValueError("Must pass dios-like key with boolean "
- "values only if passed as single indexer")
+ raise ValueError("Must pass dios-like key with boolean values only.")
colkey = self.obj.columns.intersection(key.columns)
rowkey = []
for c in colkey:
@@ -352,56 +347,30 @@ class _aLocIndexer(_Indexer):
rowkey = [self._data.at[c].index.intersection(key[c].index) for c in colkey]
return rowkey, colkey, lowdim
- def keys_from_nested_list(key):
- key = key.values if isinstance(key, pd.Series) else key
- if len(key) != len(self.obj.columns):
- raise ValueError("nested arrays outer length must have same langth than columns.")
- colkey = self.obj.columns
- rowkey = []
- for i, k in colkey:
- rowkey.append(self._data.at[k].index.intersection(key[i]))
- return rowkey, colkey, lowdim
+ rowkey, colkey = self._unpack_key(key)
- # handle multi-dim keys
- if isinstance(key, tuple):
- rowkey, colkey = self._unpack_key(key)
- # .aloc[any, ...]
- # The ellipsis is meant for dios only to indicate
- # that alignment of dios is requested, instead of
- # using (and checking) it as boolean dios
- if colkey is Ellipsis:
- if _is_dios_like(rowkey):
- return keys_from_dios_like(rowkey)
- if _is_nested_list_like(rowkey):
- return keys_from_nested_list(rowkey)
- colkey = slice(None)
-
- # (I) .aloc[dios] -> defaults to (III)
- # (II) .aloc(booldios=False)[dios] or
- # (III) .aloc(booldios=True)[dios]
- elif _is_dios_like(key):
- if self._usebool:
- return keys_from_bool_dios_like(key)
- else:
- return keys_from_dios_like(key)
+ if _is_dios_like(colkey) or _is_nested_list_like(colkey):
+ raise ValueError("Could not index with multi-dimensional column key.")
- elif _is_nested_list_like(key):
- return keys_from_nested_list(key)
+ # giving the ellipsis as column key, is an alias
+ # for giving `usebool=False`. see self.__call__()
+ if colkey is Ellipsis:
+ self._usebool = False
+ colkey = slice(None)
- # a single row indexer (not multi-dim)
- # or just some random crap was given
- else:
- rowkey, colkey = self._unpack_key(key)
+ # .aloc[dios]
+ if _is_dios_like(rowkey):
- # all multi-dim indexer was already handled
- if _is_dios_like(rowkey) or _is_nested_list_like(rowkey):
- raise ValueError("Could not index with multi-dimensional row key"
- ", if column key is given and is not Ellipsis.")
- elif _is_dios_like(colkey) or _is_nested_list_like(colkey):
- raise ValueError("Could not index with multi-dimensional column key.")
+ if not _is_null_slice(colkey):
+ raise ValueError(f"Could not index with a dios-like indexer as rowkey,"
+ f"and a column key of that type {type(colkey)}")
+ if self._usebool:
+ return keys_from_bool_dios_like(rowkey)
+ else:
+ return keys_from_dios_like(rowkey)
# handle gracefully: scalar
- if _is_hashable(colkey):
+ elif _is_hashable(colkey):
colkey = [colkey] if colkey in self.obj.columns else []
lowdim = True
@@ -422,12 +391,26 @@ class _aLocIndexer(_Indexer):
if len(colkey) == 0: # (!) `if not colkey:` fails for pd.Index
return [], [], lowdim
- # and now... No.1... the larch...
- # and now... filter row key
+ rowkey = self._get_rowkey(rowkey, colkey)
+
+ return rowkey, colkey, lowdim
+
+ def _get_rowkey(self, rowkey, colkey, depth=0):
+
+ if _is_nested_list_like(rowkey) and depth == 0:
+ rowkey = rowkey.values if isinstance(rowkey, pd.Series) else rowkey
+ if len(rowkey) != len(colkey):
+ raise ValueError("Nested arrays indexer must have same (outer) "
+ "length than the number of selected columns.")
+ indexer = []
+ for i, c in enumerate(colkey):
+ # recurse to get the row indexer from inner element
+ indexer += self._get_rowkey(rowkey[i], [c], depth=depth+1)
+ rowkey = indexer
# row-alignable: pd.Series(), align rows to every series in colkey (columns)
- if isinstance(rowkey, pd.Series):
- if _is_bool_indexer(rowkey) and self._usebool:
+ elif isinstance(rowkey, pd.Series):
+ if self._usebool and _is_bool_indexer(rowkey):
rowkey = [self._data.at[c].index.intersection(rowkey[rowkey].index) for c in colkey]
else:
rowkey = [self._data.at[c].index.intersection(rowkey.index) for c in colkey]
@@ -447,7 +430,7 @@ class _aLocIndexer(_Indexer):
else:
rowkey = [rowkey] * len(colkey)
- return rowkey, colkey, lowdim
+ return rowkey
# #############################################################################
@@ -497,3 +480,4 @@ class _iAtIndexer(_Indexer):
if _is_dios_like(value) or _is_nested_list_like(value):
raise TypeError(".iat[] cannot be used to set multi-dimensional values, use .aloc[] instead.")
self._data.iat[key[1]].iat[key[0]] = value
+
--
GitLab