Merge pull request #10443 from bashtage/read-hdf-singleton

ENH: Simplify using read_hdf for HDF files with one dataset

Author: jreback

doc/source/whatsnew/v0.17.0.txt

@@ -32,6 +32,7 @@ New features
 
 Other enhancements
 ^^^^^^^^^^^^^^^^^^
+- Enable `read_hdf` to be used without specifying a key when the HDF file contains a single dataset (:issue:`10443`)
 
 - ``.as_blocks`` will now take a ``copy`` optional argument to return a copy of the data, default is to copy (no change in behavior from prior versions), (:issue:`9607`)
 

pandas/io/pytables.py

@@ -271,7 +271,7 @@ def to_hdf(path_or_buf, key, value, mode=None, complevel=None, complib=None,
         f(path_or_buf)
 
 
-def read_hdf(path_or_buf, key, **kwargs):
+def read_hdf(path_or_buf, key=None, **kwargs):
     """ read from the store, close it if we opened it
 
         Retrieve pandas object stored in file, optionally based on where
@@ -280,7 +280,8 @@ def read_hdf(path_or_buf, key, **kwargs):
         Parameters
         ----------
         path_or_buf : path (string), or buffer to read from
-        key : group identifier in the store
+        key : group identifier in the store. Can be omitted a HDF file contains
+            a single pandas object.
         where : list of Term (or convertable) objects, optional
         start : optional, integer (defaults to None), row number to start
             selection
@@ -329,6 +330,12 @@ def read_hdf(path_or_buf, key, **kwargs):
                                   'implemented.')
 
     try:
+        if key is None:
+            keys = store.keys()
+            if len(keys) != 1:
+                raise ValueError('key must be provided when HDF file contains '
+                                 'multiple datasets.')
+            key = keys[0]
         return store.select(key, auto_close=auto_close, **kwargs)
     except:
         # if there is an error, close the store

pandas/io/tests/test_pytables.py

@@ -4731,6 +4731,17 @@ def test_invalid_complib(self):
                        columns=list('ABCDE'))
         with ensure_clean_path(self.path) as path:
             self.assertRaises(ValueError, df.to_hdf, path, 'df', complib='blosc:zlib')
+    # GH10443
+    def test_read_nokey(self):
+        df = DataFrame(np.random.rand(4, 5),
+                       index=list('abcd'),
+                       columns=list('ABCDE'))
+        with ensure_clean_path(self.path) as path:
+            df.to_hdf(path, 'df', mode='a')
+            reread = read_hdf(path)
+            assert_frame_equal(df, reread)
+            df.to_hdf(path, 'df2', mode='a')
+            self.assertRaises(ValueError, read_hdf, path)
 
 def _test_sort(obj):
     if isinstance(obj, DataFrame):