ENH: ``__repr__`` for NpzFile object (#23357)

Improves the repr to include information about the arrays contained, e.g.:

   >>> npzfile = np.load('arr.npz')
   >>> npzfile
   NpzFile 'arr.npz' with keys arr_0, arr_1, arr_2, arr_3, arr_4...

closes #23319

Co-authored-by: Ross Barnowski <rossbar@berkeley.edu>

1 files changed, 16 insertions, 0 deletions

diff --git a/numpy/lib/npyio.py b/numpy/lib/npyio.py
index bfda6804a..f8f2ab7a2 100644
--- a/numpy/lib/npyio.py
+++ b/numpy/lib/npyio.py
@@ -167,6 +167,8 @@ class NpzFile(Mapping):
     >>> npz = np.load(outfile)
     >>> isinstance(npz, np.lib.npyio.NpzFile)
     True
+    >>> npz
+    NpzFile 'object' with keys x, y
     >>> sorted(npz.files)
     ['x', 'y']
     >>> npz['x']  # getitem access
@@ -178,6 +180,7 @@ class NpzFile(Mapping):
     # Make __exit__ safe if zipfile_factory raises an exception
     zip = None
     fid = None
+    _MAX_REPR_ARRAY_COUNT = 5
 
     def __init__(self, fid, own_fid=False, allow_pickle=False,
                  pickle_kwargs=None, *,
@@ -259,6 +262,19 @@ class NpzFile(Mapping):
         else:
             raise KeyError("%s is not a file in the archive" % key)
 
+    def __repr__(self):
+        # Get filename or default to `object`
+        if isinstance(self.fid, str):
+            filename = self.fid
+        else:
+            filename = getattr(self.fid, "name", "object")
+
+        # Get the name of arrays
+        array_names = ', '.join(self.files[:self._MAX_REPR_ARRAY_COUNT])
+        if len(self.files) > self._MAX_REPR_ARRAY_COUNT:
+            array_names += "..."
+        return f"NpzFile {filename!r} with keys: {array_names}"
+
 
 @set_module('numpy')
 def load(file, mmap_mode=None, allow_pickle=False, fix_imports=True,