Merge remote-tracking branch 'upstream/master' into multi-index-join

pandas-dev · TomAugspurger · Nov 15, 2018 · Sep 19, 2018 · Sep 19, 2018 · Oct 7, 2018
commit 4d4acc5c20a68906cf458793adb4b94d89b1534b
diff --git a/pandas/core/indexes/base.py b/pandas/core/indexes/base.py
@@ -3124,8 +3124,8 @@ def get_value(self, series, key):
                 iloc = self.get_loc(key)
                 return s[iloc]
             except KeyError:
-                if (len(self) > 0
-                        and (self.holds_integer() or self.is_boolean())):
+                if (len(self) > 0 and
+                        (self.holds_integer() or self.is_boolean())):
                     raise
                 elif is_integer(key):
                     return s[key]

diff --git a/pandas/core/reshape/merge.py b/pandas/core/reshape/merge.py
@@ -813,8 +813,11 @@ def _get_merge_keys(self):
 
         left, right = self.left, self.right
 
-        is_lkey = lambda x: is_array_like(x) and len(x) == len(left)
-        is_rkey = lambda x: is_array_like(x) and len(x) == len(right)
+        def is_lkey(x):
+            return is_array_like(x) and len(x) == len(left)
+
+        def is_rkey(x):
+            return is_array_like(x) and len(x) == len(right)
 
         # Note that pd.merge_asof() has separate 'on' and 'by' parameters. A
         # user could, for example, request 'left_index' and 'left_by'. In a
@@ -968,11 +971,11 @@ def _maybe_coerce_merge_keys(self):
 
             # boolean values are considered as numeric, but are still allowed
             # to be merged on object boolean values
-            elif ((is_numeric_dtype(lk) and not is_bool_dtype(lk))
-                    and not is_numeric_dtype(rk)):
+            elif ((is_numeric_dtype(lk) and not is_bool_dtype(lk)) and not
+                    is_numeric_dtype(rk)):
                 raise ValueError(msg)
-            elif (not is_numeric_dtype(lk)
-                    and (is_numeric_dtype(rk) and not is_bool_dtype(rk))):
+            elif (not is_numeric_dtype(lk) and
+                  (is_numeric_dtype(rk) and not is_bool_dtype(rk))):
                 raise ValueError(msg)
             elif is_datetimelike(lk) and not is_datetimelike(rk):
                 raise ValueError(msg)
@@ -1526,6 +1529,9 @@ def flip(xs):
 def _get_multiindex_indexer(join_keys, index, sort):
     from functools import partial
 
+    def i8copy(a):
+        return a.astype('i8', subok=False, copy=True)
+
     # bind `sort` argument
     fkeys = partial(_factorize_keys, sort=sort)
 
@@ -1534,7 +1540,6 @@ def _get_multiindex_indexer(join_keys, index, sort):
     if sort:
         rlab = list(map(np.take, rlab, index.labels))
     else:
-        i8copy = lambda a: a.astype('i8', subok=False, copy=True)
         rlab = list(map(i8copy, index.labels))
 
     # fix right labels if there were any nulls
@@ -1680,8 +1685,11 @@ def _sort_labels(uniques, left, right):
 
 def _get_join_keys(llab, rlab, shape, sort):
 
+    def pred(i):
+        return not is_int64_overflow_possible(shape[:i])
+
     # how many levels can be done without overflow
-    pred = lambda i: not is_int64_overflow_possible(shape[:i])
+
     nlev = next(filter(pred, range(len(shape), 0, -1)))
 
     # get keys for the first `nlev` levels

diff --git a/pandas/tests/reshape/merge/test_multi.py b/pandas/tests/reshape/merge/test_multi.py
@@ -59,8 +59,12 @@ def test_left_join_multi_index(self):
         icols = ['1st', '2nd', '3rd']
 
         def bind_cols(df):
-            iord = lambda a: 0 if a != a else ord(a)
-            f = lambda ts: ts.map(iord) - ord('a')
+            def iord(a):
+                return 0 if a != a else ord(a)
+
+            def f(ts):
+                return ts.map(iord) - ord('a')
+
             return (f(df['1st']) + f(df['3rd']) * 1e2 +
                     df['2nd'].fillna(0) * 1e4)