automatically download nonzero datatype metadata

README.md

@@ -39,6 +39,12 @@ This makes use of a [fork of the `ssgetpy`](github.com/cwpearson/ssgetpy) packag
 ssgetpy does not discriminate "real" datatype from "integer" datatype, as shown on the suitesparse collection website.
 Therefore, `lists.py` maintains a manually-curated list of `integer` datatype matrices to facilitate discrimination.
 
+## Transfer data to a different filesystem
+
+```
+rsync -rzvh --links pearson@cori.nersc.gov:$SS_DIR/ .
+```
+
 ## how this was done
 
 ```
@@ -48,4 +54,4 @@ poetry add ssgetpy
 
 ```
 poetry install
-```
+```

lib/config.py

@@ -2,8 +2,15 @@ import os
 import sys
 from pathlib import Path
 
+from lib import matrix
+
 try:
     DIR = Path(os.environ["SS_DIR"])
 except KeyError as e:
     print("ERROR: $SS_DIR not set")
     sys.exit(1)
+
+SS_ROOT_URL = "https://sparse.tamu.edu"
+
+
+

lib/datasets.py

@@ -3,7 +3,7 @@ import sys
 
 import ssgetpy
 
-from lib import lists
+from lib import dtypes
 
 Dataset = collections.namedtuple("Dataset", ["name", "mats"])
 
@@ -15,18 +15,19 @@ def safe_dir_name(s):
     t = t.lower()
     return t
 
-def mat_is_integer(mat):
+def mat_is_real(mat):
-    return mat.name in lists.INTEGER_MATS
+    val = dtypes.DTYPES[(mat.group, mat.name)] == "real"
+    return val
 
-def filter_reject_integer(mats):
+def filter_keep_real(mats):
-    return [mat for mat in mats if not mat_is_integer(mat)]
+    return [mat for mat in mats if mat_is_real(mat)]
 
 def mat_is_small(mat):
     return (mat.rows < 1_000 and mat.cols < 1_000) \
         or mat.nnz < 20_000
 
 def mat_is_large(mat):
-    return (mat.rows > 1_000_000 and mat.cols < 1_000_000) \
+    return (mat.rows > 1_000_000 and mat.cols > 1_000_000) \
         or mat.nnz > 20_000_000
 
 def filter_reject_large(mats):
@@ -38,7 +39,7 @@ def filter_reject_small(mats):
 ## all real-valued matrices
 REAL_MATS = Dataset(
     name = "reals",
-    mats = filter_reject_integer(ssgetpy.search(
+    mats = filter_keep_real(ssgetpy.search(
         dtype='real',
         limit=1_000_000
     ))
@@ -66,7 +67,7 @@ for kind in kinds:
     )
 REGULAR_REAL_MATS = Dataset(
     name="regular_reals",
-    mats = filter_reject_integer(mats)
+    mats = filter_keep_real(mats)
 )
 
 ## keep "small" matrices
@@ -91,7 +92,7 @@ REAL_MED_MATS = Dataset (
 
 ## export all datasets
 DATASETS  = [
-    REAL_MATS,
+    # REAL_MATS,
     REAL_SMALL_MATS,
     REAL_MED_MATS,
     REGULAR_REAL_MATS,
@@ -114,7 +115,7 @@ for kind in get_kinds():
             name = "kind_"+safe_dir_name(kind),
             mats = filter_reject_large( \
             filter_reject_small( \
-            filter_reject_integer(ssgetpy.search(
+            filter_keep_real(ssgetpy.search(
                 kind=kind,
                 dtype='real',
                 limit=1_000_000

lib/dtypes.py

@@ -0,0 +1,54 @@
+"""export a map that is (group, name) -> dtype for all mats"""
+
+import requests
+import datetime
+import os
+
+import scipy.io
+
+from lib import config
+
+def download_ss_index(path):
+    with open(path, "wb") as f:
+        req = requests.get(config.SS_ROOT_URL + "/files/ss_index.mat")
+        f.write(req.content)
+
+def ensure_ss_index(path):
+    if not os.path.exists(path):
+        download_ss_index(path)
+    mtime = datetime.datetime.utcfromtimestamp(os.path.getmtime(config.DIR / ".ss_index.mat"))
+    if datetime.datetime.utcnow() - mtime > datetime.timedelta(days=90):
+        download_ss_index(path)
+
+# download metadata file if missing
+local = config.DIR / ".ss_index.mat"
+ensure_ss_index(local)
+
+
+# load metadata and convert to a database
+mat = scipy.io.loadmat(config.DIR / ".ss_index.mat", squeeze_me=True)
+
+s = mat["ss_index"].item()
+for i,x in enumerate(s):
+    print(i, x)
+groups = s[1]
+names = s[2]
+# 3 letters, first letter:
+# r=real, p=binary, c=complex, i=integer
+rbtype = s[19] 
+
+def dtype_from_rbtype(rbtype):
+    if rbtype[0] == "r":
+        return "real"
+    elif rbtype[0] == "p":
+        return "binary"
+    elif rbtype[0] == "c":
+        return "complex"
+    elif rbtype[0] == "i":
+        return "integer"
+    else:
+        raise LookupError
+
+DTYPES = {}
+for i in range(len(names)):
+    DTYPES[(groups[i], names[i])] = dtype_from_rbtype(rbtype[i])

lib/matrix.py

@@ -0,0 +1,17 @@
+class Matrix:
+    def __init__(self, group, name, dtype, nrows, ncols, nnz):
+        self.group = group
+        self.name = name
+        self.dtype = dtype
+        self.nrows = int(nrows)
+        self.ncols = int(ncols)
+        self.nnz = int(nnz)
+
+    def to_tuple(self):
+        return (self.group, self.name, self.dtype, self.nrows, self.ncols, self.nnz)
+
+    def __repr__(self):
+        return repr(self.to_tuple())
+
+    def url(self):
+        return "/".join(("https://sparse.tamu.edu", "MM", self.group, self.name + ".tar.gz"))

poetry.lock

@@ -33,6 +33,14 @@ category = "main"
 optional = false
 python-versions = ">=3.5"
 
+[[package]]
+name = "numpy"
+version = "1.21.4"
+description = "NumPy is the fundamental package for array computing with Python."
+category = "main"
+optional = false
+python-versions = ">=3.7,<3.11"
+
 [[package]]
 name = "requests"
 version = "2.26.0"
@@ -51,6 +59,17 @@ urllib3 = ">=1.21.1,<1.27"
 socks = ["PySocks (>=1.5.6,!=1.5.7)", "win-inet-pton"]
 use_chardet_on_py3 = ["chardet (>=3.0.2,<5)"]
 
+[[package]]
+name = "scipy"
+version = "1.7.3"
+description = "SciPy: Scientific Library for Python"
+category = "main"
+optional = false
+python-versions = ">=3.7,<3.11"
+
+[package.dependencies]
+numpy = ">=1.16.5,<1.23.0"
+
 [[package]]
 name = "ssgetpy"
 version = "1.0-pre2"
@@ -101,8 +120,8 @@ socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 
 [metadata]
 lock-version = "1.1"
-python-versions = "^3.7"
+python-versions = ">=3.7,<3.11"
-content-hash = "4a624c76d5d28333a13081a3fe5fba3eadcdfc09ac0963d1f1ecd89eb03451aa"
+content-hash = "5a1bf7fe65d1fe23f7c34d44076cc157e3343699790a742492686d6198fb88eb"
 
 [metadata.files]
 certifi = [
@@ -121,10 +140,73 @@ idna = [
     {file = "idna-3.3-py3-none-any.whl", hash = "sha256:84d9dd047ffa80596e0f246e2eab0b391788b0503584e8945f2368256d2735ff"},
     {file = "idna-3.3.tar.gz", hash = "sha256:9d643ff0a55b762d5cdb124b8eaa99c66322e2157b69160bc32796e824360e6d"},
 ]
+numpy = [
+    {file = "numpy-1.21.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:8890b3360f345e8360133bc078d2dacc2843b6ee6059b568781b15b97acbe39f"},
+    {file = "numpy-1.21.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:69077388c5a4b997442b843dbdc3a85b420fb693ec8e33020bb24d647c164fa5"},
+    {file = "numpy-1.21.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e89717274b41ebd568cd7943fc9418eeb49b1785b66031bc8a7f6300463c5898"},
+    {file = "numpy-1.21.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0b78ecfa070460104934e2caf51694ccd00f37d5e5dbe76f021b1b0b0d221823"},
+    {file = "numpy-1.21.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:615d4e328af7204c13ae3d4df7615a13ff60a49cb0d9106fde07f541207883ca"},
+    {file = "numpy-1.21.4-cp310-cp310-win_amd64.whl", hash = "sha256:1403b4e2181fc72664737d848b60e65150f272fe5a1c1cbc16145ed43884065a"},
+    {file = "numpy-1.21.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:74b85a17528ca60cf98381a5e779fc0264b4a88b46025e6bcbe9621f46bb3e63"},
+    {file = "numpy-1.21.4-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:92aafa03da8658609f59f18722b88f0a73a249101169e28415b4fa148caf7e41"},
+    {file = "numpy-1.21.4-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:5d95668e727c75b3f5088ec7700e260f90ec83f488e4c0aaccb941148b2cd377"},
+    {file = "numpy-1.21.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f5162ec777ba7138906c9c274353ece5603646c6965570d82905546579573f73"},
+    {file = "numpy-1.21.4-cp37-cp37m-win32.whl", hash = "sha256:81225e58ef5fce7f1d80399575576fc5febec79a8a2742e8ef86d7b03beef49f"},
+    {file = "numpy-1.21.4-cp37-cp37m-win_amd64.whl", hash = "sha256:32fe5b12061f6446adcbb32cf4060a14741f9c21e15aaee59a207b6ce6423469"},
+    {file = "numpy-1.21.4-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:c449eb870616a7b62e097982c622d2577b3dbc800aaf8689254ec6e0197cbf1e"},
+    {file = "numpy-1.21.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2e4ed57f45f0aa38beca2a03b6532e70e548faf2debbeb3291cfc9b315d9be8f"},
+    {file = "numpy-1.21.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:1247ef28387b7bb7f21caf2dbe4767f4f4175df44d30604d42ad9bd701ebb31f"},
+    {file = "numpy-1.21.4-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:34f3456f530ae8b44231c63082c8899fe9c983fd9b108c997c4b1c8c2d435333"},
+    {file = "numpy-1.21.4-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:4c9c23158b87ed0e70d9a50c67e5c0b3f75bcf2581a8e34668d4e9d7474d76c6"},
+    {file = "numpy-1.21.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e4799be6a2d7d3c33699a6f77201836ac975b2e1b98c2a07f66a38f499cb50ce"},
+    {file = "numpy-1.21.4-cp38-cp38-win32.whl", hash = "sha256:bc988afcea53e6156546e5b2885b7efab089570783d9d82caf1cfd323b0bb3dd"},
+    {file = "numpy-1.21.4-cp38-cp38-win_amd64.whl", hash = "sha256:170b2a0805c6891ca78c1d96ee72e4c3ed1ae0a992c75444b6ab20ff038ba2cd"},
+    {file = "numpy-1.21.4-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:fde96af889262e85aa033f8ee1d3241e32bf36228318a61f1ace579df4e8170d"},
+    {file = "numpy-1.21.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c885bfc07f77e8fee3dc879152ba993732601f1f11de248d4f357f0ffea6a6d4"},
+    {file = "numpy-1.21.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9e6f5f50d1eff2f2f752b3089a118aee1ea0da63d56c44f3865681009b0af162"},
+    {file = "numpy-1.21.4-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:ad010846cdffe7ec27e3f933397f8a8d6c801a48634f419e3d075db27acf5880"},
+    {file = "numpy-1.21.4-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:c74c699b122918a6c4611285cc2cad4a3aafdb135c22a16ec483340ef97d573c"},
+    {file = "numpy-1.21.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9864424631775b0c052f3bd98bc2712d131b3e2cd95d1c0c68b91709170890b0"},
+    {file = "numpy-1.21.4-cp39-cp39-win32.whl", hash = "sha256:b1e2312f5b8843a3e4e8224b2b48fe16119617b8fc0a54df8f50098721b5bed2"},
+    {file = "numpy-1.21.4-cp39-cp39-win_amd64.whl", hash = "sha256:e3c3e990274444031482a31280bf48674441e0a5b55ddb168f3a6db3e0c38ec8"},
+    {file = "numpy-1.21.4-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:a3deb31bc84f2b42584b8c4001c85d1934dbfb4030827110bc36bfd11509b7bf"},
+    {file = "numpy-1.21.4.zip", hash = "sha256:e6c76a87633aa3fa16614b61ccedfae45b91df2767cf097aa9c933932a7ed1e0"},
+]
 requests = [
     {file = "requests-2.26.0-py2.py3-none-any.whl", hash = "sha256:6c1246513ecd5ecd4528a0906f910e8f0f9c6b8ec72030dc9fd154dc1a6efd24"},
     {file = "requests-2.26.0.tar.gz", hash = "sha256:b8aa58f8cf793ffd8782d3d8cb19e66ef36f7aba4353eec859e74678b01b07a7"},
 ]
+scipy = [
+    {file = "scipy-1.7.3-1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:c9e04d7e9b03a8a6ac2045f7c5ef741be86727d8f49c45db45f244bdd2bcff17"},
+    {file = "scipy-1.7.3-1-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:b0e0aeb061a1d7dcd2ed59ea57ee56c9b23dd60100825f98238c06ee5cc4467e"},
+    {file = "scipy-1.7.3-1-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:b78a35c5c74d336f42f44106174b9851c783184a85a3fe3e68857259b37b9ffb"},
+    {file = "scipy-1.7.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:173308efba2270dcd61cd45a30dfded6ec0085b4b6eb33b5eb11ab443005e088"},
+    {file = "scipy-1.7.3-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:21b66200cf44b1c3e86495e3a436fc7a26608f92b8d43d344457c54f1c024cbc"},
+    {file = "scipy-1.7.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ceebc3c4f6a109777c0053dfa0282fddb8893eddfb0d598574acfb734a926168"},
+    {file = "scipy-1.7.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f7eaea089345a35130bc9a39b89ec1ff69c208efa97b3f8b25ea5d4c41d88094"},
+    {file = "scipy-1.7.3-cp310-cp310-win_amd64.whl", hash = "sha256:304dfaa7146cffdb75fbf6bb7c190fd7688795389ad060b970269c8576d038e9"},
+    {file = "scipy-1.7.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:033ce76ed4e9f62923e1f8124f7e2b0800db533828c853b402c7eec6e9465d80"},
+    {file = "scipy-1.7.3-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:4d242d13206ca4302d83d8a6388c9dfce49fc48fdd3c20efad89ba12f785bf9e"},
+    {file = "scipy-1.7.3-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:8499d9dd1459dc0d0fe68db0832c3d5fc1361ae8e13d05e6849b358dc3f2c279"},
+    {file = "scipy-1.7.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ca36e7d9430f7481fc7d11e015ae16fbd5575615a8e9060538104778be84addf"},
+    {file = "scipy-1.7.3-cp37-cp37m-win32.whl", hash = "sha256:e2c036492e673aad1b7b0d0ccdc0cb30a968353d2c4bf92ac8e73509e1bf212c"},
+    {file = "scipy-1.7.3-cp37-cp37m-win_amd64.whl", hash = "sha256:866ada14a95b083dd727a845a764cf95dd13ba3dc69a16b99038001b05439709"},
+    {file = "scipy-1.7.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:65bd52bf55f9a1071398557394203d881384d27b9c2cad7df9a027170aeaef93"},
+    {file = "scipy-1.7.3-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:f99d206db1f1ae735a8192ab93bd6028f3a42f6fa08467d37a14eb96c9dd34a3"},
+    {file = "scipy-1.7.3-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:5f2cfc359379c56b3a41b17ebd024109b2049f878badc1e454f31418c3a18436"},
+    {file = "scipy-1.7.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eb7ae2c4dbdb3c9247e07acc532f91077ae6dbc40ad5bd5dca0bb5a176ee9bda"},
+    {file = "scipy-1.7.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95c2d250074cfa76715d58830579c64dff7354484b284c2b8b87e5a38321672c"},
+    {file = "scipy-1.7.3-cp38-cp38-win32.whl", hash = "sha256:87069cf875f0262a6e3187ab0f419f5b4280d3dcf4811ef9613c605f6e4dca95"},
+    {file = "scipy-1.7.3-cp38-cp38-win_amd64.whl", hash = "sha256:7edd9a311299a61e9919ea4192dd477395b50c014cdc1a1ac572d7c27e2207fa"},
+    {file = "scipy-1.7.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:eef93a446114ac0193a7b714ce67659db80caf940f3232bad63f4c7a81bc18df"},
+    {file = "scipy-1.7.3-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:eb326658f9b73c07081300daba90a8746543b5ea177184daed26528273157294"},
+    {file = "scipy-1.7.3-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:93378f3d14fff07572392ce6a6a2ceb3a1f237733bd6dcb9eb6a2b29b0d19085"},
+    {file = "scipy-1.7.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:edad1cf5b2ce1912c4d8ddad20e11d333165552aba262c882e28c78bbc09dbf6"},
+    {file = "scipy-1.7.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d1cc2c19afe3b5a546ede7e6a44ce1ff52e443d12b231823268019f608b9b12"},
+    {file = "scipy-1.7.3-cp39-cp39-win32.whl", hash = "sha256:2c56b820d304dffcadbbb6cbfbc2e2c79ee46ea291db17e288e73cd3c64fefa9"},
+    {file = "scipy-1.7.3-cp39-cp39-win_amd64.whl", hash = "sha256:3f78181a153fa21c018d346f595edd648344751d7f03ab94b398be2ad083ed3e"},
+    {file = "scipy-1.7.3.tar.gz", hash = "sha256:ab5875facfdef77e0a47d5fd39ea178b58e60e454a4c85aa1e52fcb80db7babf"},
+]
 ssgetpy = []
 tqdm = [
     {file = "tqdm-4.62.3-py2.py3-none-any.whl", hash = "sha256:8dd278a422499cd6b727e6ae4061c40b48fce8b76d1ccbf5d34fca9b7f925b0c"},

pyproject.toml

@@ -5,8 +5,9 @@ description = ""
 authors = ["Carl Pearson <cwpears@sandia.gov>"]
 
 [tool.poetry.dependencies]
-python = "^3.7"
+python = ">=3.7,<3.11"
 ssgetpy = {git = "https://github.com/cwpearson/ssgetpy.git", rev = "be00d2a"}
+scipy = "^1.7.3"
 
 [tool.poetry.dev-dependencies]