Skip to content

Instantly share code, notes, and snippets.

@karlnapf
Created January 20, 2018 18:08
Show Gist options
  • Save karlnapf/b9122a880c9954cf795f20471b12363c to your computer and use it in GitHub Desktop.
Save karlnapf/b9122a880c9954cf795f20471b12363c to your computer and use it in GitHub Desktop.
Bug in Python3 StringFetaures?
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import shogun as sg"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"data = [\"ACGTT\", \"TACGTTAA\"]"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"feats = sg.StringCharFeatures(sg.DNA)\n",
"feats.set_features(data)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"A\n",
"C\n",
"G\n"
]
}
],
"source": [
"print(feats.get_feature(0, 0))\n",
"print(feats.get_feature(0, 1))\n",
"print(feats.get_feature(0, 2))"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"T\n",
"A\n",
"C\n"
]
}
],
"source": [
"print(feats.get_feature(1, 0))\n",
"print(feats.get_feature(1, 1))\n",
"print(feats.get_feature(1, 2))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['ACGTT', 'TACGTTAA']"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"feats.get_features()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"ename": "UnicodeDecodeError",
"evalue": "'utf-32-le' codec can't decode bytes in position 0-3: code point not in range(0x110000)",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mUnicodeDecodeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m/opt/conda/lib/python3.6/site-packages/IPython/core/formatters.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, obj)\u001b[0m\n\u001b[1;32m 700\u001b[0m \u001b[0mtype_pprinters\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtype_printers\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 701\u001b[0m deferred_pprinters=self.deferred_printers)\n\u001b[0;32m--> 702\u001b[0;31m \u001b[0mprinter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpretty\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 703\u001b[0m \u001b[0mprinter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mflush\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 704\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mstream\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetvalue\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/conda/lib/python3.6/site-packages/IPython/lib/pretty.py\u001b[0m in \u001b[0;36mpretty\u001b[0;34m(self, obj)\u001b[0m\n\u001b[1;32m 393\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mcallable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmeth\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 394\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mmeth\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcycle\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 395\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0m_default_pprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcycle\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 396\u001b[0m \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 397\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mend_group\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/conda/lib/python3.6/site-packages/IPython/lib/pretty.py\u001b[0m in \u001b[0;36m_default_pprint\u001b[0;34m(obj, p, cycle)\u001b[0m\n\u001b[1;32m 508\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0m_safe_getattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mklass\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'__repr__'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mobject\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__repr__\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 509\u001b[0m \u001b[0;31m# A user-provided repr. Find newlines and replace them with p.break_()\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 510\u001b[0;31m \u001b[0m_repr_pprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcycle\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 511\u001b[0m \u001b[0;32mreturn\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 512\u001b[0m \u001b[0mp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbegin_group\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[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/conda/lib/python3.6/site-packages/IPython/lib/pretty.py\u001b[0m in \u001b[0;36m_repr_pprint\u001b[0;34m(obj, p, cycle)\u001b[0m\n\u001b[1;32m 699\u001b[0m \u001b[0;34m\"\"\"A pprint that just redirects to the normal repr function.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 700\u001b[0m \u001b[0;31m# Find newlines and replace them with p.break_()\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 701\u001b[0;31m \u001b[0moutput\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrepr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 702\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0midx\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0moutput_line\u001b[0m \u001b[0;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplitlines\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 703\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0midx\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/conda/lib/python3.6/site-packages/numpy/core/numeric.py\u001b[0m in \u001b[0;36marray_repr\u001b[0;34m(arr, max_line_width, precision, suppress_small)\u001b[0m\n\u001b[1;32m 1896\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0marr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m0\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0marr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m0\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 1897\u001b[0m lst = array2string(arr, max_line_width, precision, suppress_small,\n\u001b[0;32m-> 1898\u001b[0;31m ', ', \"array(\")\n\u001b[0m\u001b[1;32m 1899\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;31m# show zero-length shape unless it is (0,)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1900\u001b[0m \u001b[0mlst\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"[], shape=%s\"\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mrepr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0marr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\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/opt/conda/lib/python3.6/site-packages/numpy/core/arrayprint.py\u001b[0m in \u001b[0;36marray2string\u001b[0;34m(a, max_line_width, precision, suppress_small, separator, prefix, style, formatter)\u001b[0m\n\u001b[1;32m 461\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 462\u001b[0m lst = _array2string(a, max_line_width, precision, suppress_small,\n\u001b[0;32m--> 463\u001b[0;31m separator, prefix, formatter=formatter)\n\u001b[0m\u001b[1;32m 464\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mlst\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 465\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/conda/lib/python3.6/site-packages/numpy/core/arrayprint.py\u001b[0m in \u001b[0;36m_array2string\u001b[0;34m(a, max_line_width, precision, suppress_small, separator, prefix, formatter)\u001b[0m\n\u001b[1;32m 334\u001b[0m lst = _formatArray(a, format_function, len(a.shape), max_line_width,\n\u001b[1;32m 335\u001b[0m \u001b[0mnext_line_prefix\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mseparator\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 336\u001b[0;31m _summaryEdgeItems, summary_insert)[:-1]\n\u001b[0m\u001b[1;32m 337\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mlst\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 338\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/conda/lib/python3.6/site-packages/numpy/core/arrayprint.py\u001b[0m in \u001b[0;36m_formatArray\u001b[0;34m(a, format_function, rank, max_line_len, next_line_prefix, separator, edge_items, summary_insert)\u001b[0m\n\u001b[1;32m 505\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 506\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrailing_items\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\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--> 507\u001b[0;31m \u001b[0mword\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mformat_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ma\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mseparator\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 508\u001b[0m \u001b[0ms\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mline\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_extendLine\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ms\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mline\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mword\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_line_len\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnext_line_prefix\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 509\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mUnicodeDecodeError\u001b[0m: 'utf-32-le' codec can't decode bytes in position 0-3: code point not in range(0x110000)"
]
}
],
"source": [
"feats.get_feature_vector(0)"
]
},
{
"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": "3.6.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment