Adding files for 2022 workshop (#16)

* adding new files to index for 2022 workshop
* windows compat, fix md5sum

set line endings explicitly to CRLF

CHANGELOG.md

@@ -27,6 +27,9 @@
 -   major refactoring to have an offline catalogue available
 -   allow to download/extract .tar.gz containers
 
+## 0.4.1
+-  updated file catalogue
+
 ### upcoming
 -   removed obsolete/unsused imports/variables/...
 -   replaced assert statements

mdshare/data/mdshare-catalogue.md5

@@ -1 +1 @@
-0cc785f647102bd3a036f9e64b1867fe
+3465007cf4a866ac4316b4e8afba4673

mdshare/data/mdshare-catalogue.yaml

@@ -1,53 +1,150 @@
-containers:
-  mdshare-test.tar.gz: {hash: dee112e2523653c7cf2ed3eec98e41e8, size: 193}
-  pyemma-tutorial-livecoms.tar.gz: {hash: 4e6a9ba2aa7c5f1a15aa34c7d5ccaa32, size: 123937176}
-index:
-  alanine-dipeptide-0-250ns-nowater.xtc: {hash: e82ba584d8e64491f30bd1d9dd019687,
-    size: 42909936}
-  alanine-dipeptide-1-250ns-nowater.xtc: {hash: 96b7686aa28a459d51a0d77c2dd0316e,
-    size: 42911308}
-  alanine-dipeptide-2-250ns-nowater.xtc: {hash: 6d3a8d9aecb3aa0e0a1ea9b195b7dfe0,
-    size: 42907500}
-  alanine-dipeptide-3x250ns-backbone-dihedrals.npz: {hash: 3fa7c72ba512213a3860f9691602cdc7,
-    size: 6000544}
-  alanine-dipeptide-3x250ns-heavy-atom-distances.npz: {hash: c8d108087fdce3ccb0f8e30e76858925,
-    size: 135000544}
-  alanine-dipeptide-3x250ns-heavy-atom-positions.npz: {hash: 55bd66fe4ee49849dead7faf6bf8b71e,
-    size: 90000544}
-  alanine-dipeptide-nowater.pdb: {hash: 728635667ed4937cf4a0e5b7c801d9ea, size: 1813}
-  doublewell_disconnected.npy: {hash: 26717c09a92cf96cda412a8ab0119360, size: 160096}
-  doublewell_oneway.npy: {hash: 2843dc5108ffc5f2adf9d3d1c8cce804, size: 160096}
-  hmm-doublewell-2d-100k.npz: {hash: aaf37fb708a0f8f82f70d3aa06da205f, size: 2000638}
-  mdshare-test-00.txt: {hash: 5cbb04531c2e9fa7cc1e5d83195a2f81, size: 33}
-  methane-dimer-umbrella-sampling.npz: {hash: e494f8bf0da3283c2d6a6ce9ce10c989, size: 193346}
-  pentapeptide-00-500ns-impl-solv.xtc: {hash: 16967d0bb09d24dc66de4d4885f953a4, size: 2221296}
-  pentapeptide-01-500ns-impl-solv.xtc: {hash: 9db9b87ecafb2d5eb0085adc01b97680, size: 2221268}
-  pentapeptide-02-500ns-impl-solv.xtc: {hash: 5ec89b72fa1e48c3a5e1b1ec707f66fb, size: 2221392}
-  pentapeptide-03-500ns-impl-solv.xtc: {hash: 726208c33f9c9ce0eb2688e5788b8d57, size: 2221596}
-  pentapeptide-04-500ns-impl-solv.xtc: {hash: 934d06ed03744c8cada2123a2cfd6fbf, size: 2221604}
-  pentapeptide-05-500ns-impl-solv.xtc: {hash: 395f614244f3d484db8d4a50f35252fd, size: 2221020}
-  pentapeptide-06-500ns-impl-solv.xtc: {hash: 3a94a06657b5bd7cadf6c3767fc4ca18, size: 2221088}
-  pentapeptide-07-500ns-impl-solv.xtc: {hash: 82c633ed92112bf62bb7070f4393ac2a, size: 2221376}
-  pentapeptide-08-500ns-impl-solv.xtc: {hash: c2f49e03f4c8ef6c8315d844d5d1be0e, size: 2220668}
-  pentapeptide-09-500ns-impl-solv.xtc: {hash: ea74fa65dcb80a086a15c34a907495f3, size: 2221668}
-  pentapeptide-10-500ns-impl-solv.xtc: {hash: 7b374e2402a37f139817be3137e6509e, size: 2221300}
-  pentapeptide-11-500ns-impl-solv.xtc: {hash: 0fe84f969978a492fe26dbb3bd39c6ee, size: 2221672}
-  pentapeptide-12-500ns-impl-solv.xtc: {hash: 8ddaaf213a4b4d34e92cbfbf6f3daad5, size: 2221012}
-  pentapeptide-13-500ns-impl-solv.xtc: {hash: 21ced9d0791a4330c2714a408c6b7b63, size: 2222168}
-  pentapeptide-14-500ns-impl-solv.xtc: {hash: ecd2213ac5de68ef0fc37e9723269d34, size: 2221316}
-  pentapeptide-15-500ns-impl-solv.xtc: {hash: f41d2a6e283d3b43fdf14aa3e95eff03, size: 2221780}
-  pentapeptide-16-500ns-impl-solv.xtc: {hash: 30c8f0805bfa248934714bfb663c4196, size: 2221404}
-  pentapeptide-17-500ns-impl-solv.xtc: {hash: 82c52922cb585962a0b1cab70cc32645, size: 2221296}
-  pentapeptide-18-500ns-impl-solv.xtc: {hash: 6906793b17978370a59025b6c2080ae1, size: 2220924}
-  pentapeptide-19-500ns-impl-solv.xtc: {hash: 4f7948b2f6a5515666b495a1054326c4, size: 2220900}
-  pentapeptide-20-500ns-impl-solv.xtc: {hash: f4f3c376e90826d3dd43bcdf08910863, size: 2221344}
-  pentapeptide-21-500ns-impl-solv.xtc: {hash: e5d2467545d04778d6005c2c904e6df3, size: 2221000}
-  pentapeptide-22-500ns-impl-solv.xtc: {hash: b2cdf3759057ef1a9ccbf9ab41044efa, size: 2220708}
-  pentapeptide-23-500ns-impl-solv.xtc: {hash: 1169c0f9efd028155519fa9bf2a85971, size: 2221592}
-  pentapeptide-24-500ns-impl-solv.xtc: {hash: 8d016a9ea6a5b63843fca58b82b4573c, size: 2220908}
-  pentapeptide-impl-solv.pdb: {hash: c52f482024e0ec7dcd64f2b925b53c2b, size: 7501}
-  pyemma-tutorial-mt-data.npz: {hash: 02f7b91ea2cac71b762f85bdbc4086e9, size: 4763982}
-  pyemma-tutorial-tpt-data.npz: {hash: e3d95283e915cc7992aaefd30cea5462, size: 512952}
-  pyemma-tutorial-us-data.npz: {hash: eb36cfe14a61a5d9a7d5b57ef7f829e8, size: 1622382}
-  pyemma-tutorial-us-nacl.npz: {hash: fca286bd0ffb8f30315e27bff2c1a772, size: 241062}
-url: http://ftp.imp.fu-berlin.de/pub/cmb-data/
+containers:
+  mdshare-test.tar.gz:
+    hash: 8eda06f1af3760ee788101ecb59dba69
+    size: 232
+  pyemma-tutorial-livecoms.tar.gz:
+    hash: 71eebc44c37825fbedb87b35d3b76587
+    size: 123939712
+index:
+  alanine-dipeptide-0-250ns-nowater.xtc:
+    hash: e82ba584d8e64491f30bd1d9dd019687
+    size: 42909936
+  alanine-dipeptide-1-250ns-nowater.xtc:
+    hash: 96b7686aa28a459d51a0d77c2dd0316e
+    size: 42911308
+  alanine-dipeptide-1Mx1ps-with-force.npz:
+    hash: c35a55fb5e5cec0d49e4275d62493ab9
+    size: 463525559
+  alanine-dipeptide-2-250ns-nowater.xtc:
+    hash: 6d3a8d9aecb3aa0e0a1ea9b195b7dfe0
+    size: 42907500
+  alanine-dipeptide-3x250ns-backbone-dihedrals.npz:
+    hash: 3fa7c72ba512213a3860f9691602cdc7
+    size: 6000544
+  alanine-dipeptide-3x250ns-heavy-atom-distances.npz:
+    hash: c8d108087fdce3ccb0f8e30e76858925
+    size: 135000544
+  alanine-dipeptide-3x250ns-heavy-atom-positions.npz:
+    hash: 55bd66fe4ee49849dead7faf6bf8b71e
+    size: 90000544
+  alanine-dipeptide-nowater.pdb:
+    hash: 728635667ed4937cf4a0e5b7c801d9ea
+    size: 1813
+  alanine_dipeptide_parallel_tempering_dihedrals.npz:
+    hash: db21a645b6aa39db4095fa0a5a61c8cc
+    size: 3365062
+  alanine_dipeptide_parallel_tempering_energies.npz:
+    hash: b7b58af1dbd92168d63fac2376edf9cb
+    size: 1685062
+  doublewell_disconnected.npy:
+    hash: 26717c09a92cf96cda412a8ab0119360
+    size: 160096
+  doublewell_oneway.npy:
+    hash: 2843dc5108ffc5f2adf9d3d1c8cce804
+    size: 160096
+  hmm-doublewell-2d-100k.npz:
+    hash: aaf37fb708a0f8f82f70d3aa06da205f
+    size: 2000638
+  imd_channel_transitionmatrix.npy:
+    hash: fdbbd2376541e4be13c503cfa13e789c
+    size: 8320
+  imd_full_system_trajectory.npy:
+    hash: 1d77481bc2d6527016e4791a01349347
+    size: 8000128
+  mdshare-test-00.txt:
+    hash: 5cbb04531c2e9fa7cc1e5d83195a2f81
+    size: 33
+  methane-dimer-umbrella-sampling.npz:
+    hash: e494f8bf0da3283c2d6a6ce9ce10c989
+    size: 193346
+  pentapeptide-00-500ns-impl-solv.xtc:
+    hash: 16967d0bb09d24dc66de4d4885f953a4
+    size: 2221296
+  pentapeptide-01-500ns-impl-solv.xtc:
+    hash: 9db9b87ecafb2d5eb0085adc01b97680
+    size: 2221268
+  pentapeptide-02-500ns-impl-solv.xtc:
+    hash: 5ec89b72fa1e48c3a5e1b1ec707f66fb
+    size: 2221392
+  pentapeptide-03-500ns-impl-solv.xtc:
+    hash: 726208c33f9c9ce0eb2688e5788b8d57
+    size: 2221596
+  pentapeptide-04-500ns-impl-solv.xtc:
+    hash: 934d06ed03744c8cada2123a2cfd6fbf
+    size: 2221604
+  pentapeptide-05-500ns-impl-solv.xtc:
+    hash: 395f614244f3d484db8d4a50f35252fd
+    size: 2221020
+  pentapeptide-06-500ns-impl-solv.xtc:
+    hash: 3a94a06657b5bd7cadf6c3767fc4ca18
+    size: 2221088
+  pentapeptide-07-500ns-impl-solv.xtc:
+    hash: 82c633ed92112bf62bb7070f4393ac2a
+    size: 2221376
+  pentapeptide-08-500ns-impl-solv.xtc:
+    hash: c2f49e03f4c8ef6c8315d844d5d1be0e
+    size: 2220668
+  pentapeptide-09-500ns-impl-solv.xtc:
+    hash: ea74fa65dcb80a086a15c34a907495f3
+    size: 2221668
+  pentapeptide-10-500ns-impl-solv.xtc:
+    hash: 7b374e2402a37f139817be3137e6509e
+    size: 2221300
+  pentapeptide-11-500ns-impl-solv.xtc:
+    hash: 0fe84f969978a492fe26dbb3bd39c6ee
+    size: 2221672
+  pentapeptide-12-500ns-impl-solv.xtc:
+    hash: 8ddaaf213a4b4d34e92cbfbf6f3daad5
+    size: 2221012
+  pentapeptide-13-500ns-impl-solv.xtc:
+    hash: 21ced9d0791a4330c2714a408c6b7b63
+    size: 2222168
+  pentapeptide-14-500ns-impl-solv.xtc:
+    hash: ecd2213ac5de68ef0fc37e9723269d34
+    size: 2221316
+  pentapeptide-15-500ns-impl-solv.xtc:
+    hash: f41d2a6e283d3b43fdf14aa3e95eff03
+    size: 2221780
+  pentapeptide-16-500ns-impl-solv.xtc:
+    hash: 30c8f0805bfa248934714bfb663c4196
+    size: 2221404
+  pentapeptide-17-500ns-impl-solv.xtc:
+    hash: 82c52922cb585962a0b1cab70cc32645
+    size: 2221296
+  pentapeptide-18-500ns-impl-solv.xtc:
+    hash: 6906793b17978370a59025b6c2080ae1
+    size: 2220924
+  pentapeptide-19-500ns-impl-solv.xtc:
+    hash: 4f7948b2f6a5515666b495a1054326c4
+    size: 2220900
+  pentapeptide-20-500ns-impl-solv.xtc:
+    hash: f4f3c376e90826d3dd43bcdf08910863
+    size: 2221344
+  pentapeptide-21-500ns-impl-solv.xtc:
+    hash: e5d2467545d04778d6005c2c904e6df3
+    size: 2221000
+  pentapeptide-22-500ns-impl-solv.xtc:
+    hash: b2cdf3759057ef1a9ccbf9ab41044efa
+    size: 2220708
+  pentapeptide-23-500ns-impl-solv.xtc:
+    hash: 1169c0f9efd028155519fa9bf2a85971
+    size: 2221592
+  pentapeptide-24-500ns-impl-solv.xtc:
+    hash: 8d016a9ea6a5b63843fca58b82b4573c
+    size: 2220908
+  pentapeptide-impl-solv.pdb:
+    hash: c52f482024e0ec7dcd64f2b925b53c2b
+    size: 7501
+  pyemma-tutorial-mt-data.npz:
+    hash: 02f7b91ea2cac71b762f85bdbc4086e9
+    size: 4763982
+  pyemma-tutorial-tpt-data.npz:
+    hash: e3d95283e915cc7992aaefd30cea5462
+    size: 512952
+  pyemma-tutorial-us-data.npz:
+    hash: eb36cfe14a61a5d9a7d5b57ef7f829e8
+    size: 1622382
+  pyemma-tutorial-us-nacl.npz:
+    hash: fca286bd0ffb8f30315e27bff2c1a772
+    size: 241062
+url: http://ftp.imp.fu-berlin.de/pub/cmb-data/

mdshare/data/template.yaml

@@ -3,7 +3,7 @@
 # This is the template to compile the current catalogue file.
 # Navigate to the directory where the data files are and run
 #
-#   python path/to/mdshare-index-maker.py path/to/template.yaml
+#   python path/to/mdshare-index-maker.py build path/to/template.yaml
 #
 # This will create a yaml file (NAME.yaml) and a corresponding MD5
 # checksum file (NAME.md5) where NAME corresponds to the 'name' entry
@@ -35,6 +35,10 @@ include:
   - doublewell_oneway.npy
   - hmm-doublewell-2d-100k.npz
   - mdshare-test-00.txt
+  - imd_channel_transitionmatrix.npy
+  - imd_full_system_trajectory.npy
+  - alanine_dipeptide_parallel_tempering_energies.npz
+  - alanine_dipeptide_parallel_tempering_dihedrals.npz
 containers:
   pyemma-tutorial-livecoms.tar.gz:
     - alanine-dipeptide-*-nowater.xtc
@@ -45,4 +49,4 @@ containers:
     - doublewell_oneway.npy
     - hmm-doublewell-2d-100k.npz
   mdshare-test.tar.gz:
-    - mdshare-test-00.txt
+    - mdshare-test-00.txt