PERF: sparse to_csv

asv_bench/benchmarks/io/csv.py

@@ -172,6 +172,26 @@ def time_head_of_multiindex(self):
         self.df_custom_index_then_head.to_csv(self.fname)
 
 
+class ToCSVSparse(BaseIO):
+
+    fname = "__test__.csv"
+
+    def setup(self):
+        from scipy import sparse as sc
+
+        vals = np.random.randint(0, 10, size=(10000, 1000))
+        keep = vals > 3
+        vals[keep] = 0
+        sparse_mtx = sc.coo_matrix(vals)
+        self.data = DataFrame.sparse.from_spmatrix(sparse_mtx)
+
+    def time_sparse_to_csv(self):
+        self.data.to_csv("sparse_pd.csv")
+
+    def time_sparse_to_dense_to_csv(self):
+        self.data.sparse.to_dense().to_csv("sparse_pd.csv")
+
+
 class StringIORewind:
     def data(self, stringio_object):
         stringio_object.seek(0)

doc/source/whatsnew/v2.0.0.rst

@@ -163,6 +163,7 @@ Performance improvements
 - Performance improvements to :func:`read_sas` (:issue:`47403`, :issue:`47405`, :issue:`47656`, :issue:`48502`)
 - Memory improvement in :meth:`RangeIndex.sort_values` (:issue:`48801`)
 - Performance improvement in :class:`DataFrameGroupBy` and :class:`SeriesGroupBy` when ``by`` is a categorical type and ``sort=False`` (:issue:`48976`)
+- Performance improvement for saving to CSV with :class:`CSVFormatter` when data frame is sparse (:issue:`41023`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_200.bug_fixes:

pandas/io/formats/csvs.py

@@ -69,7 +69,10 @@ def __init__(
     ) -> None:
         self.fmt = formatter
 
-        self.obj = self.fmt.frame
+        if hasattr(self.fmt.frame, "sparse"):
+            self.obj = self.fmt.frame.sparse.to_dense()
+        else:
+            self.obj = self.fmt.frame
 
         self.filepath_or_buffer = path_or_buf
         self.encoding = encoding