For example,
>>> import pandas as pd >>> df1 = pd.DataFrame(data=[[1, None], [2, None]], columns=['a', 'b']) >>> df2 = pd.DataFrame(data=[[3, None], [4, None]], columns=['a', 'b']) >>> df1 a b 0 1 None 1 2 None >>> df1.dtypes a int64 b object dtype: object >>> df2 a b 0 3 None 1 4 None >>> df2.dtypes a int64 b object dtype: object >>> pd.concat([df1, df2]) a b 0 1 NaN 1 2 NaN 0 3 NaN 1 4 NaN >>> pd.concat([df1, df2]).dtypes a int64 b object dtype: object
I have found that this is a direct result of line 4102-4103 in core/internals.py
4101 # create the result
4102 if 'object' in upcast_classes:
4103 return np.dtype(np.object_), np.nan
4104 elif 'bool' in upcast_classes:
4105 if has_none_blocks:
4106 return np.dtype(np.object_), np.nan
4107 else:
4108 return np.dtype(np.bool_), None
4109 elif 'category' in upcast_classes:
4110 return com.CategoricalDtype(), np.nan
4111 elif 'float' in upcast_classes:
4112 return np.dtype(np.float64), np.nan
4113 elif 'datetime' in upcast_classes:
4114 return np.dtype('M8[ns]'), tslib.iNaT
4115 elif 'timedelta' in upcast_classes:
4116 return np.dtype('m8[ns]'), tslib.iNaT
4117 else: # pragma
4118 raise AssertionError("invalid dtype determination in get_concat_dtype")
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4