change sparse.bim

bed_reader/_open_bed.py

@@ -1245,19 +1245,29 @@ def read_sparse(
         Examples
         --------
 
-        To read all data in a .bed file, set ``index`` to ``None``. This is the default.
-        cmk continue updating the docs here.
+        Read all data in a .bed file into a `scipy.sparse.csc_matrix`.
+        The file has 10 individuals (samples) by 20 SNPs (variants).
+        All but eight values are 0.
 
         .. doctest::
 
+            >>> # pip install bed-reader[samples,sparse]  # if needed
             >>> from bed_reader import open_bed, sample_file
             >>>
-            >>> file_name = sample_file("small.bed")
+            >>> file_name = sample_file("sparse.bed")
             >>> with open_bed(file_name) as bed:
-            ...     print(bed.read())
-            [[ 1.  0. nan  0.]
-             [ 2.  0. nan  2.]
-             [ 0.  1.  2.  0.]]
+            ...     print(bed.shape())
+            ...     val_sparse = bed.read_sparse(dtype="int8")
+            ...     print(val_sparse)
+            (10, 20)
+                (8, 4)	1
+                (8, 5)	2
+                (0, 8)	2
+                (4, 9)	1
+                (7, 9)	1
+                (5, 11)	1
+                (2, 12)	1
+                (3, 12)	1
 
         To read selected individuals (samples) and/or SNPs (variants), set each part of
         a :class:`numpy.s_` to an `int`, a list of `int`, a slice expression, or

bed_reader/_sample_data.py

@@ -14,7 +14,7 @@
         path=pooch.os_cache("bed_reader"),
         # The remote data is on Github
         base_url="https://raw.githubusercontent.com/"
-        + "fastlmm/bed-reader/rustybed/bed_reader/tests/data/",
+        + "fastlmm/bed-reader/Oct2023/bed_reader/tests/data/",
         # If this is a development version, get the data from the master branch
         version_dev="master",
         # The registry specifies the files that can be fetched

bed_reader/tests/data/sparse.bim

@@ -1,20 +1,20 @@
-1.0	sid_0	0.0	126131822	A1	A2
-2.0	sid_1	0.0	70468033	A1	A2
-2.0	sid_2	0.0	223618033	A1	A2
-3.0	sid_3	0.0	67771248	A1	A2
-4.0	sid_4	0.0	146322476	A1	A2
-4.0	sid_5	0.0	299472476	A1	A2
-5.0	sid_6	0.0	51277007	A1	A2
-6.0	sid_7	0.0	89797274	A1	A2
-7.0	sid_8	0.0	2175616	A1	A2
-8.0	sid_9	0.0	128673782	A1	A2
-9.0	sid_10	0.0	144360723	A1	A2
-10.0	sid_11	0.0	113744049	A1	A2
-11.0	sid_12	0.0	58449190	A1	A2
-12.0	sid_13	0.0	85742409	A1	A2
-13.0	sid_14	0.0	29012823	A1	A2
-15.0	sid_15	0.0	16244046	A1	A2
-16.0	sid_16	0.0	22451361	A1	A2
-18.0	sid_17	0.0	109302574	A1	A2
-20.0	sid_18	0.0	71272297	A1	A2
-22.0	sid_19	0.0	92855895	A1	A2
+1	sid_0	0.0	126131822	A1	A2
+1	sid_1	0.0	70468033	A1	A2
+1	sid_2	0.0	223618033	A1	A2
+1	sid_3	0.0	67771248	A1	A2
+5	sid_4	0.0	146322476	A1	A2
+5	sid_5	0.0	299472476	A1	A2
+5	sid_6	0.0	51277007	A1	A2
+5	sid_7	0.0	89797274	A1	A2
+5	sid_8	0.0	2175616	A1	A2
+5	sid_9	0.0	128673782	A1	A2
+5	sid_10	0.0	144360723	A1	A2
+5	sid_11	0.0	113744049	A1	A2
+5	sid_12	0.0	58449190	A1	A2
+Y	sid_13	0.0	85742409	A1	A2
+Y	sid_14	0.0	29012823	A1	A2
+Y	sid_15	0.0	16244046	A1	A2
+Y	sid_16	0.0	22451361	A1	A2
+Y	sid_17	0.0	109302574	A1	A2
+Y	sid_18	0.0	71272297	A1	A2
+Y	sid_19	0.0	92855895	A1	A2

bed_reader/tests/registry.txt

@@ -34,3 +34,6 @@ some_missing.val.npy 316ad46abcf30b15d3140a893b207b90ae63b00aa1d76443f6113a66c3e
 toydata.5chrom.bed bc1cedaf4c296749dd49cc0dcb95d2a8f4c792433b37ebb9f847dba53c2fc4cf
 toydata.5chrom.bim 131f4beba07b56a604fafb03a9f536dbdfbf6a67a094ddb7714db9609a3a89a3
 toydata.5chrom.fam 9551c70290580c9b23cb83c98ccc7791f380169bdaddfbc2edb905ff78879cc4
+sparse.bed 70f76a3920b4c8498ecfae9c8837c3ea841a874f88f60c082141905a24d63114
+sparse.fam 729bb46dab41082c6b5937f7f9e3a68d0c0f27d2ad795f1fa1fd146354fb6aa7
+sparse.bim 0d08176c438aa1aed8c4d9c64faffc4ba6560688f2c708cfbd0ca87d273c3754