Skip to content

Instantly share code, notes, and snippets.

@gtsambos

gtsambos/load_text-error.ipynb

Created April 1, 2019 06:54
Show Gist options
  • Save gtsambos/d20f85954fd9325b94af548e7eda7051 to your computer and use it in GitHub Desktop.
Save gtsambos/d20f85954fd9325b94af548e7eda7051 to your computer and use it in GitHub Desktop.
Download ZIP
Shows an error I get when I try to use load_text in tskit.
Display the source blob
Display the rendered blob
Raw
load_text-error.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import tskit\n",
"import six"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"small_tree_ex_nodes = \"\"\"\\\n",
"id is_sample population time\n",
"0 1 0 0 0.00000000000000\n",
"1 1 0 0 0.00000000000000\n",
"2 1 0 0 0.00000000000000\n",
"3 1 0 0 0.00000000000000\n",
"4 1 0 0 0.00000000000000\n",
"5 0 0 0 0.14567111023387\n",
"6 0 0 1 0.21385545626353\n",
"7 0 0 2 0.43508024345063\n",
"8 0 0 3 1.60156352971203\n",
"\"\"\"\n",
"small_tree_ex_edges = \"\"\"\\\n",
"id left right parent child\n",
"0 0.00000000 1.00000000 5 0\n",
"1 0.00000000 1.00000000 5 1\n",
"2 0.00000000 1.00000000 6 2\n",
"3 0.00000000 1.00000000 6 3\n",
"4 0.00000000 1.00000000 7 4\n",
"5 0.00000000 1.00000000 7 5\n",
"6 0.00000000 1.00000000 8 6\n",
"7 0.00000000 1.00000000 8 7\n",
"\"\"\"\n",
"small_tree_ex_populations = \"\"\"\\\n",
"id metadata\n",
"0\n",
"1\n",
"2\n",
"3\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"ename": "IndexError",
"evalue": "list index out of range",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mIndexError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-3-d37165d6a2b6>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0medges\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msix\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mStringIO\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msmall_tree_ex_edges\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mpopulations\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msix\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mStringIO\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msmall_tree_ex_populations\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m strict=False)\n\u001b[0m",
"\u001b[0;32m/usr/local/opt/python3/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tskit/trees.py\u001b[0m in \u001b[0;36mload_text\u001b[0;34m(nodes, edges, sites, mutations, individuals, populations, sequence_length, strict, encoding, base64_metadata)\u001b[0m\n\u001b[1;32m 1624\u001b[0m parse_populations(\n\u001b[1;32m 1625\u001b[0m \u001b[0mpopulations\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstrict\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstrict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mencoding\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mencoding\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1626\u001b[0;31m base64_metadata=base64_metadata, table=tc.populations)\n\u001b[0m\u001b[1;32m 1627\u001b[0m \u001b[0mtc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msort\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1628\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mtc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtree_sequence\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/opt/python3/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tskit/trees.py\u001b[0m in \u001b[0;36mparse_populations\u001b[0;34m(source, strict, encoding, base64_metadata, table)\u001b[0m\n\u001b[1;32m 1515\u001b[0m \u001b[0mtokens\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mline\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msep\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1516\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtokens\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>=\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1517\u001b[0;31m \u001b[0mmetadata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtokens\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mmetadata_index\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mencoding\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1518\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mbase64_metadata\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1519\u001b[0m \u001b[0mmetadata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbase64\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mb64decode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmetadata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mIndexError\u001b[0m: list index out of range"
]
}
],
"source": [
"ts0 = tskit.load_text(\n",
" nodes=six.StringIO(small_tree_ex_nodes),\n",
" edges=six.StringIO(small_tree_ex_edges),\n",
" populations=six.StringIO(small_tree_ex_populations),\n",
" strict=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"I'm also getting a (different) error when I don't include the population table."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"ename": "LibraryError",
"evalue": "time[parent] must be greater than time[child]",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mLibraryError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-4-53c0b9e3dcac>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0medges\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msix\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mStringIO\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msmall_tree_ex_edges\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;31m# populations=six.StringIO(small_tree_ex_populations),\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m strict=False)\n\u001b[0m",
"\u001b[0;32m/usr/local/opt/python3/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tskit/trees.py\u001b[0m in \u001b[0;36mload_text\u001b[0;34m(nodes, edges, sites, mutations, individuals, populations, sequence_length, strict, encoding, base64_metadata)\u001b[0m\n\u001b[1;32m 1625\u001b[0m \u001b[0mpopulations\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstrict\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstrict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mencoding\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mencoding\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1626\u001b[0m base64_metadata=base64_metadata, table=tc.populations)\n\u001b[0;32m-> 1627\u001b[0;31m \u001b[0mtc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msort\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1628\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mtc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtree_sequence\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1629\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/opt/python3/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tskit/tables.py\u001b[0m in \u001b[0;36msort\u001b[0;34m(self, edge_start)\u001b[0m\n\u001b[1;32m 1726\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mdefault\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m;\u001b[0m \u001b[0mmust\u001b[0m \u001b[0mbe\u001b[0m \u001b[0;34m<=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0medges\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1727\u001b[0m \"\"\"\n\u001b[0;32m-> 1728\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mll_tables\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msort\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0medge_start\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1729\u001b[0m \u001b[0;31m# TODO add provenance\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1730\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mLibraryError\u001b[0m: time[parent] must be greater than time[child]"
]
}
],
"source": [
"ts0 = tskit.load_text(\n",
" nodes=six.StringIO(small_tree_ex_nodes),\n",
" edges=six.StringIO(small_tree_ex_edges),\n",
"# populations=six.StringIO(small_tree_ex_populations),\n",
" strict=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
@jeromekelleher
Copy link

I think you have an extra column in the node table, in between is_sample and population. Either remove it or give it a heading value. Looks fine to me otherwise.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment