Screen Link:
My Code:
top_employer_by_country = {}
countries = f500["country"].unique()
for c in countries:
row_top_employer = f500[f500["country"] == c].sort_values("employees", ascending=False).head(1)
top_employer = row_top_employer.loc[0, "company"]
top_employer_by_country[c] = top_employer
What I expected to happen:
The top_employer_by_country should be populated.
What actually happened:
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
/dataquest/system/env/python3/lib/python3.8/site-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
2645 try:
-> 2646 return self._engine.get_loc(key)
2647 except KeyError:
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
KeyError: 0
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
<ipython-input-1-d42274fd524b> in <module>
12 for c in countries:
13 row_top_employer = f500[f500["country"] == c].sort_values("employees", ascending=False).head(1)
---> 14 top_employer = row_top_employer.loc[0, "company"]
15 top_employer_by_country[c] = top_employer
/dataquest/system/env/python3/lib/python3.8/site-packages/pandas/core/indexing.py in __getitem__(self, key)
1760 except (KeyError, IndexError, AttributeError):
1761 pass
-> 1762 return self._getitem_tuple(key)
1763 else:
1764 # we by definition only have the 0th axis
/dataquest/system/env/python3/lib/python3.8/site-packages/pandas/core/indexing.py in _getitem_tuple(self, tup)
1270 def _getitem_tuple(self, tup: Tuple):
1271 try:
-> 1272 return self._getitem_lowerdim(tup)
1273 except IndexingError:
1274 pass
/dataquest/system/env/python3/lib/python3.8/site-packages/pandas/core/indexing.py in _getitem_lowerdim(self, tup)
1387 for i, key in enumerate(tup):
1388 if is_label_like(key) or isinstance(key, tuple):
-> 1389 section = self._getitem_axis(key, axis=i)
1390
1391 # we have yielded a scalar ?
/dataquest/system/env/python3/lib/python3.8/site-packages/pandas/core/indexing.py in _getitem_axis(self, key, axis)
1963 # fall thru to straight lookup
1964 self._validate_key(key, axis)
-> 1965 return self._get_label(key, axis=axis)
1966
1967
/dataquest/system/env/python3/lib/python3.8/site-packages/pandas/core/indexing.py in _get_label(self, label, axis)
623 raise IndexingError("no slices here, handle elsewhere")
624
--> 625 return self.obj._xs(label, axis=axis)
626
627 def _get_loc(self, key: int, axis: int):
/dataquest/system/env/python3/lib/python3.8/site-packages/pandas/core/generic.py in xs(self, key, axis, level, drop_level)
3535 loc, new_index = self.index.get_loc_level(key, drop_level=drop_level)
3536 else:
-> 3537 loc = self.index.get_loc(key)
3538
3539 if isinstance(loc, np.ndarray):
/dataquest/system/env/python3/lib/python3.8/site-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
2646 return self._engine.get_loc(key)
2647 except KeyError:
-> 2648 return self._engine.get_loc(self._maybe_cast_indexer(key))
2649 indexer = self.get_indexer([key], method=method, tolerance=tolerance)
2650 if indexer.ndim > 1 or indexer.size > 1:
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
KeyError: 0
If I run the code as follows:
top_employer_by_country = {}
countries = f500["country"].unique()
for c in countries:
row_top_employer = f500[f500["country"] == c].sort_values("employees", ascending=False).head(1)
top_employer = row_top_employer.loc[0, "company"]
top_employer_by_country[c] = top_employer
**break**
We can see that the top_employer_by_country is populated with one data:
“USA”: “Walmart.”
Why is this happening?
