From f672e760a52613f099c36937ecee5ee68893b316 Mon Sep 17 00:00:00 2001
From: Bert Palm <bert.palm@ufz.de>
Date: Mon, 17 Feb 2020 02:32:45 +0100
Subject: [PATCH] more better
---
dios/dios.py | 92 +++++++++++++++++++++++--------------------------
dios/options.py | 22 ++++++++----
2 files changed, 60 insertions(+), 54 deletions(-)
diff --git a/dios/dios.py b/dios/dios.py
index 07062ed..44aaad4 100644
--- a/dios/dios.py
+++ b/dios/dios.py
@@ -193,16 +193,23 @@ class DictOfSeries:
raise KeyError(key)
# all other cases
else:
- keys, ixs = self._unpack_key(key)
+ keys, ixs, ixstype = self._unpack_key(key)
+ ixs = self._unpack_indexer(keys, ixs, ixstype)
new = self.copy_empty()
for i, _ in enumerate(keys):
key, ix = keys[i], ixs[i]
- new._data[key] = self._get_item(key)[ix]
+ new._data[key] = self._get_item(key, ix, True)
return new
- def _get_item(self, key):
+ def _get_item(self, key, ix=None, insertna=False):
"""Extract a pd.Series from self"""
- return self._data[key]
+ if ix is None:
+ return self._data[key]
+ elif insertna:
+ s = self._data[key]
+ return s[ix].reindex_like(s)
+ else:
+ return self._data[key][ix]
def __setitem__(self, key, value):
"""
@@ -224,11 +231,11 @@ class DictOfSeries:
self._insert(key, value)
return
else:
- k, i = [key], [slice(None)]
+ k, i, it = [key], [slice(None)], None
# all other cases
else:
- k, i = self._unpack_key(key)
-
+ k, i, it = self._unpack_key(key)
+ i = self._unpack_indexer(k, i, it)
gen = self._unpack_value(k, i, value)
for tup in gen:
self._set_item(*tup)
@@ -285,29 +292,22 @@ class DictOfSeries:
Notes:
Which keys we get, may depend on the policy in dios_options
"""
- err_bool = "only boolean values are allowed"
len_err_msg = "length of given column-indexer does not match length of columns"
keys = None
- boolidxer = None
- sliceidxer = None
- haskeys = False
+ indexer, idxtype = None, None
# prevent consuming of a generator
key = list(key) if is_iterator(key) else key
if isinstance(key, slice):
keys = self.columns
- sliceidxer = [key]
+ indexer, idxtype = [key], 'slice'
# list, np.arrays, ... of list, np.arrays..
elif is_nested_list_like(key):
# we only allow bool nlists
keys = self.columns
- boolidxer = key
-
- # todo ..
- # elif is_bool_indexer(key):
- # ...
+ indexer, idxtype = key, 'nlist'
# ser, df, dios
elif is_pandas_like(key):
@@ -328,16 +328,15 @@ class DictOfSeries:
elif is_dataframe_like(key):
# we only allow bool df's
keys = key.columns.to_list()
- boolidxer, haskeys= key, True
+ indexer, idxtype = key, 'df'
elif is_dios_like(key):
# we only allow bool dios's
keys = key.columns
- boolidxer, haskeys= key, True
+ indexer, idxtype = key, 'dios'
# list, np.array, np.ndarray, ...
- # Note: series considered list-like,
- # so we handle lists last
+ # Note: series considered list-like, so we handle lists at last
elif is_list_like(key):
arr = np.array(key)
if is_bool_array(arr):
@@ -347,7 +346,6 @@ class DictOfSeries:
keys = np.array(keys)[arr]
else:
keys = key
-
else:
raise KeyError(f"{key}")
@@ -355,30 +353,28 @@ class DictOfSeries:
method = dios_options[OptsFields.col_indexing_method]
keys = check_keys_by_policy(keys, self.columns, method)
- # check indexers
- idxer = []
- if sliceidxer is not None:
- idxer = sliceidxer * len(keys)
- elif boolidxer is not None:
- if haskeys:
- for k in keys:
- ix = boolidxer[k]
- idxer.append(ix)
- if not is_bool_indexer(ix):
- raise ValueError(err_bool)
- else:
- for i in boolidxer:
- ix = np.array(i)
- idxer.append(ix)
- if not is_bool_array(ix):
- raise ValueError(err_bool)
- else:
- idxer = [slice(None)] * len(keys)
-
- assert len(idxer) == len(keys)
+ return keys, indexer, idxtype
- # now we have a valid indexer (a slice or a bool array) for every key
- return keys, idxer
+ def _unpack_indexer(self, keys, indexer, idxtype):
+ err_bool = "only boolean values are allowed"
+ idxerlist = []
+ if idxtype == 'slice':
+ idxerlist = indexer * len(keys)
+ elif idxtype in ['df', 'dios']:
+ for k in keys:
+ ix = indexer[k]
+ idxerlist.append(ix)
+ if not is_bool_indexer(ix):
+ raise ValueError(err_bool)
+ elif idxtype == 'nlist':
+ for i in indexer:
+ ix = np.array(i)
+ idxerlist.append(ix)
+ if not is_bool_array(ix):
+ raise ValueError(err_bool)
+ else:
+ idxerlist = [slice(None)] * len(keys)
+ return idxerlist
@property
def loc(self):
@@ -606,7 +602,7 @@ class _LocIndexer(_Indexer):
rkey, cols = self._unpack_key(key)
new = self._dios.copy_empty()
for i, _ in enumerate(cols):
- c,r = cols[i], rkey[i]
+ c, r = cols[i], rkey[i]
new[c] = self._data[c].loc[r]
return new
@@ -637,7 +633,7 @@ class _LocIndexer(_Indexer):
else:
try:
# list and bool list like
- cols, _ = self._dios._unpack_key(ckey)
+ cols, *_ = self._dios._unpack_key(ckey)
except Exception:
raise
@@ -669,7 +665,7 @@ class _iLocIndexer(_Indexer):
rkey, cols = self._unpack_key(key)
new = self._dios.copy_empty()
for i, _ in enumerate(cols):
- c,r = cols[i], rkey[i]
+ c, r = cols[i], rkey[i]
new[c] = self._data[c].iloc[r]
return new
diff --git a/dios/options.py b/dios/options.py
index 95a3f98..ae735ea 100644
--- a/dios/options.py
+++ b/dios/options.py
@@ -10,16 +10,25 @@ class OptsFields:
disp_max_vars = "disp_max_vars"
"""
- none_plus: none or more can be given
- at_leat_one: accept if at least one column is present
- all_present: all given columns must be present
- all_plus: (pandas, bool-series style) all must be present but more can be given
+ none_plus: none or more columns, than in self, can be given
+ at_least_one: accept if at least one column is present in self
+ all_present: all given columns must be present in self
"""
- col_indexing_method = "dios_to_dios_method"
+ col_indexing_method = "col_indexing_method"
mixed_itype_warn_policy = "mixed_itype_policy"
+
+ """
+ should nans be droppend during comparision(drop),
+ stay nans (keep), or be compared (nplike).
+ nplike is quite silly as `5 < NaN` will simply evaluate to False"""
comparison_nan_policy = "comparison_nan_policy"
+ """
+ Get item nan policy:
+
+ """
+
class Opts:
none_plus = 'none_plus'
@@ -31,7 +40,8 @@ class Opts:
itype_ignore = 'ignore'
keep_nans = 'keep'
- nplike_nans = 'nplike_nans '
+ nplike_nans = 'nplike'
+ drop_nans = 'drop'
# set default values
--
GitLab