Skip to content

Instantly share code, notes, and snippets.

@kantale

kantale/aaa.ipynb

Created March 30, 2022 15:20
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save kantale/6a6308b326dd9782b609d30e53b78051 to your computer and use it in GitHub Desktop.
Save kantale/6a6308b326dd9782b609d30e53b78051 to your computer and use it in GitHub Desktop.
Download ZIP
test
Display the source blob
Display the rendered blob
Raw
aaa.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "9a9cd5f6",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"C:\\Users\\user\n"
]
}
],
"source": [
"!cd"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2e3c5b3e",
"metadata": {},
"outputs": [],
"source": [
"f = open('mitsos.txt')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "5add9f33",
"metadata": {},
"outputs": [],
"source": [
"f = open('C:/Users/user/Downloads/gwas_catalog_v1.0-associations_e105_r2022-03-23.tsv')"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "855464ef",
"metadata": {},
"outputs": [],
"source": [
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "49c835b0",
"metadata": {
"scrolled": true
},
"outputs": [
{
"ename": "SyntaxError",
"evalue": "EOL while scanning string literal (1419483448.py, line 1)",
"output_type": "error",
"traceback": [
"\u001b[1;36m Input \u001b[1;32mIn [6]\u001b[1;36m\u001b[0m\n\u001b[1;33m f = open(r'C:\\Users\\user\\Downloads\\')\u001b[0m\n\u001b[1;37m ^\u001b[0m\n\u001b[1;31mSyntaxError\u001b[0m\u001b[1;31m:\u001b[0m EOL while scanning string literal\n"
]
}
],
"source": [
"f = open(r'C:\\Users\\user\\Downloads\\')"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "cb74cab6",
"metadata": {},
"outputs": [],
"source": [
"f = open('C:/Users/user/results.txt')"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "c54e245c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<_io.TextIOWrapper name='C:/Users/user/results.txt' mode='r' encoding='cp1253'>"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"f"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "675037ff",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"_io.TextIOWrapper"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type(f)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "91509d59",
"metadata": {},
"outputs": [],
"source": [
"s = f.read()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "ae481e3b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'this is a fantastic file\\nvery precious data\\nmuch science\\nnobel\\n'"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "44aa220c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"this is a fantastic file\n",
"very precious data\n",
"much science\n",
"nobel\n",
"\n"
]
}
],
"source": [
"print (s)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "e2a7a3d9",
"metadata": {},
"outputs": [],
"source": [
"g = f.read()"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "d6b24664",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"print (g)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "9d04f1b0",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(g)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "63623e7d",
"metadata": {},
"outputs": [],
"source": [
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "18ebe4db",
"metadata": {},
"outputs": [],
"source": [
"f = open('C:/Users/user/results.txt')"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "3c274b33",
"metadata": {},
"outputs": [],
"source": [
"g = f.read()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "2180acec",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'this is a fantastic file\\nvery precious data\\nmuch science\\nnobel\\n'"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"g"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "638275eb",
"metadata": {},
"outputs": [],
"source": [
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "5eeb7b1c",
"metadata": {},
"outputs": [],
"source": [
"f = open('C:/Users/user/results.txt')"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "1aec6ac5",
"metadata": {},
"outputs": [],
"source": [
"line = f.readline()"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "6cf41a73",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"this is a fantastic file\n",
"\n"
]
}
],
"source": [
"print (line)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "72fa5759",
"metadata": {},
"outputs": [],
"source": [
"g = f.read()"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "4bc07fa0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"very precious data\n",
"much science\n",
"nobel\n",
"\n"
]
}
],
"source": [
"print (g)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "807e280c",
"metadata": {},
"outputs": [],
"source": [
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "68f4c41b",
"metadata": {},
"outputs": [],
"source": [
"f = open('C:/Users/user/results.txt')"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "b7f017ae",
"metadata": {},
"outputs": [],
"source": [
"a = f.readline()"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "b833a5d0",
"metadata": {},
"outputs": [],
"source": [
"b = f.readline()"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "7cad2af7",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"very precious data\n",
"\n"
]
}
],
"source": [
"print (b)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "28233975",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"much science\n",
"nobel\n",
"\n"
]
}
],
"source": [
"print (f.read())"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "34832a8e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"10"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"f.seek(10)"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "74c46fc6",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'fantastic file\\n'"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"f.readline()"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "146bfadb",
"metadata": {},
"outputs": [],
"source": [
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "89dfc799",
"metadata": {},
"outputs": [],
"source": [
"f = open('C:/Users/user/results.txt')"
]
},
{
"cell_type": "code",
"execution_count": 44,
"id": "918bf6b4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"this is a fantastic file\n",
"\n",
"very precious data\n",
"\n",
"much science\n",
"\n",
"nobel\n",
"\n",
"\n"
]
}
],
"source": [
"f = open('C:/Users/user/results.txt')\n",
"while True:\n",
" line = f.readline()\n",
" print (line)\n",
" if not line:\n",
" break\n",
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "ca1b40be",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"this is a fantastic file\n",
"\n",
"very precious data\n",
"\n",
"much science\n",
"\n",
"nobel\n",
"\n",
"\n"
]
}
],
"source": [
"f = open('C:/Users/user/results.txt')\n",
"while True:\n",
" line = f.readline()\n",
" print (line)\n",
" if len(line) == 0:\n",
" break\n",
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "2e323488",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"this is a fantastic file\n",
"\n",
"very precious data\n",
"\n",
"much science\n",
"\n",
"nobel\n",
"\n",
"\n"
]
}
],
"source": [
"f = open('C:/Users/user/results.txt')\n",
"while True:\n",
" line = f.readline()\n",
" print (line)\n",
" if line == '':\n",
" break\n",
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "ed3d5adf",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"S\n",
"D\n",
"A\n",
"F\n",
"G\n",
"F\n",
"D\n",
"S\n"
]
}
],
"source": [
"for x in 'SDAFGFDS':\n",
" print (x)"
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "1a6abddf",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"5\n",
"6\n",
"7\n"
]
}
],
"source": [
"for x in [5,6,7,]:\n",
" print (x)"
]
},
{
"cell_type": "code",
"execution_count": 70,
"id": "4cf8358b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"this is a fantastic file\n",
"\n",
"very precious data\n",
"\n",
"much science\n",
"\n",
"nobel\n",
"\n"
]
}
],
"source": [
"f = open('C:/Users/user/results.txt')\n",
"for line in f:\n",
" print (line)\n",
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": 71,
"id": "71008beb",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"this is a fantastic file\n",
"\n",
"very precious data\n",
"\n",
"much science\n",
"\n",
"nobel\n",
"\n"
]
}
],
"source": [
"with open('C:/Users/user/results.txt') as f:\n",
" for l in f:\n",
" print (l)"
]
},
{
"cell_type": "code",
"execution_count": 72,
"id": "267081b8",
"metadata": {},
"outputs": [],
"source": [
"l = []"
]
},
{
"cell_type": "code",
"execution_count": 73,
"id": "853f918b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"much science\n",
"\n"
]
}
],
"source": [
"with open('C:/Users/user/results.txt') as f:\n",
" lc = 0\n",
" for l in f:\n",
" lc += 1\n",
" if lc<3:\n",
" continue\n",
" print (l)\n",
" break"
]
},
{
"cell_type": "code",
"execution_count": 91,
"id": "18fcfe24",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"dyjfjfghjfkhjthjhkhkhjfgfgmgdd.fgjdalkgjshdlfkgjhsdlkfjghsldkfjghsldkjghskldfjghlsdkfjhglskdfjghlskdfjghskldjfghsldkfjghsldkjgh sljgsldkj ghskldjgh sldkgjh skldfjgh skldfjghsldkjghsldkfjgh skldjg hsldfkjghsldkjg hsldfkjgh sldkjgh sldkgjh sldkjg hsdlfkjgh sdfkjg hsldkfjg hsldkfjg hsldkfjg hsldkfjg hsldkfjgh sldkfjg sldkfjgh sldkjgh sldfjgh sldkfjgh sldkfjgh sldkfjg hsldkfjg hsldkfjgh sldkfjgh sldkfjgh fjkldh\n",
"\n"
]
}
],
"source": [
"with open('C:/Users/user/results.txt') as f:\n",
"\n",
" for lc, l in enumerate(f):\n",
" if lc < 6:\n",
" continue\n",
" print (l)\n",
" break"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0ea53c41",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 79,
"id": "fc41c82e",
"metadata": {},
"outputs": [],
"source": [
"my_list = [] \n",
"with open('C:/Users/user/results.txt') as f:\n",
"\n",
" for lc, l in enumerate(f):\n",
" if lc in {1,2}:\n",
" my_list.append(l)\n",
" \n",
" "
]
},
{
"cell_type": "code",
"execution_count": 78,
"id": "486fa248",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['very precious data\\n', 'much science. bravo!\\n']"
]
},
"execution_count": 78,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"my_list"
]
},
{
"cell_type": "code",
"execution_count": 80,
"id": "a711106b",
"metadata": {},
"outputs": [],
"source": [
"with open('C:/Users/user/results.txt') as f:\n",
"\n",
" my_list = [l for lc, l in enumerate(f) if lc in {1,2}]\n"
]
},
{
"cell_type": "code",
"execution_count": 81,
"id": "6be9a275",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['very precious data\\n', 'much science. bravo!\\n']"
]
},
"execution_count": 81,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"my_list"
]
},
{
"cell_type": "code",
"execution_count": 82,
"id": "d39cab02",
"metadata": {},
"outputs": [],
"source": [
" my_list = [l for lc, l in enumerate(open('C:/Users/user/results.txt')) if lc in {1,2}]"
]
},
{
"cell_type": "code",
"execution_count": 83,
"id": "53e6f47c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['very precious data\\n', 'much science. bravo!\\n']"
]
},
"execution_count": 83,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"my_list"
]
},
{
"cell_type": "code",
"execution_count": 84,
"id": "73dcc947",
"metadata": {},
"outputs": [],
"source": [
"a = 'ghjkgfghj\\n'"
]
},
{
"cell_type": "code",
"execution_count": 85,
"id": "6ee824de",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'ghjkgfghj\\n'"
]
},
"execution_count": 85,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a"
]
},
{
"cell_type": "code",
"execution_count": 86,
"id": "667eae1f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'ghjkgfghj'"
]
},
"execution_count": 86,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a.strip()"
]
},
{
"cell_type": "code",
"execution_count": 87,
"id": "213abd5c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'sfdagsagszdfg'"
]
},
"execution_count": 87,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"' sfdagsagszdfg '.strip()"
]
},
{
"cell_type": "code",
"execution_count": 88,
"id": "a3c4f62b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'sadfasdfasdf'"
]
},
"execution_count": 88,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"'sadfasdfasdf\\n'[:-1]"
]
},
{
"cell_type": "code",
"execution_count": 89,
"id": "58c1e766",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'sadfasdfasdf'"
]
},
"execution_count": 89,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"'sadfasdfasdf\\n'.replace('\\n', '')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "64d13d07",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "036de9a6",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "dc0c76a9",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 41,
"id": "12c94bfc",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"mitsos - alex\n"
]
}
],
"source": [
"print ('mitsos', end=' - ')\n",
"print ('alex')"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "30416060",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bool('sdfsdfg')"
]
},
{
"cell_type": "code",
"execution_count": 43,
"id": "4d55acd0",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"False"
]
},
"execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bool('')"
]
},
{
"cell_type": "code",
"execution_count": 92,
"id": "55ebe918",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"488\n"
]
}
],
"source": [
"my_list = [] \n",
"with open('C:/Users/user/results.txt') as f:\n",
"\n",
" data = f.read()\n",
"print (len(data))"
]
},
{
"cell_type": "code",
"execution_count": 93,
"id": "8b524632",
"metadata": {},
"outputs": [
{
"ename": "UnicodeDecodeError",
"evalue": "'charmap' codec can't decode byte 0xd2 in position 16: character maps to <undefined>",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mUnicodeDecodeError\u001b[0m Traceback (most recent call last)",
"Input \u001b[1;32mIn [93]\u001b[0m, in \u001b[0;36m<cell line: 2>\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m my_list \u001b[38;5;241m=\u001b[39m [] \n\u001b[0;32m 2\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mopen\u001b[39m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mC:/Users/user/alex.docx\u001b[39m\u001b[38;5;124m'\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m f:\n\u001b[1;32m----> 4\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[43mf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 5\u001b[0m \u001b[38;5;28mprint\u001b[39m (\u001b[38;5;28mlen\u001b[39m(data))\n",
"File \u001b[1;32m~\\miniconda3\\lib\\encodings\\cp1253.py:23\u001b[0m, in \u001b[0;36mIncrementalDecoder.decode\u001b[1;34m(self, input, final)\u001b[0m\n\u001b[0;32m 22\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecode\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m, final\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[1;32m---> 23\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mcodecs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcharmap_decode\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\u001b[43mdecoding_table\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;241m0\u001b[39m]\n",
"\u001b[1;31mUnicodeDecodeError\u001b[0m: 'charmap' codec can't decode byte 0xd2 in position 16: character maps to <undefined>"
]
}
],
"source": [
"my_list = [] \n",
"with open('C:/Users/user/alex.docx') as f:\n",
"\n",
" data = f.read()\n",
"print (len(data))"
]
},
{
"cell_type": "code",
"execution_count": 107,
"id": "c9197a9f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"379\n"
]
}
],
"source": [
"my_list = [] \n",
"with open('C:/Users/user/alex2.txt') as f:\n",
"\n",
" data = f.read()\n",
"print (len(data))"
]
},
{
"cell_type": "code",
"execution_count": 108,
"id": "717bbc56",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Xf/lgk jh;flsgkhjsfkj ghsfkldghsldkjghsldkfjg hldakfjgh sldfkj ghsldkfjgh skldfjgh skldfjgh skldfjgh ldskfj ghsldkfj ghsldkfjg sldkfjgh sdljgh sldjgh sldkfjgh sldkjgh sldkjgh sldkfjg sldkfjg hsldkjgh sldkfjg hsldfjkg hsldkjgh ldfjgh sldkfjgh \n",
"1. Xghfg\n",
"2. Hfd\n",
"3. Hfd\n",
"4. Ghfd\n",
"5. Ghd\n",
"6. Fghfg\n",
"7. h\n",
"sldkfjg sldkfjgh slkdfjg sdfklgh skldfgh sdlkjg hsldfjgh sldkfjgh sldj ghlsdkf h\n",
"\n",
"\n",
"\n",
"\n"
]
}
],
"source": [
"print (data)"
]
},
{
"cell_type": "code",
"execution_count": 94,
"id": "acea5310",
"metadata": {},
"outputs": [],
"source": [
"def f(l):\n",
" return sum(l)"
]
},
{
"cell_type": "code",
"execution_count": 95,
"id": "fc6cf55f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"60"
]
},
"execution_count": 95,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"f([10, 20, 30])"
]
},
{
"cell_type": "code",
"execution_count": 99,
"id": "8f1e4ff2",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"60"
]
},
"execution_count": 99,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def f(l):\n",
" if not len(l):\n",
" return 0\n",
" return l[0] + f(l[1:])\n",
"\n",
"f([10, 20, 30])"
]
},
{
"cell_type": "code",
"execution_count": 105,
"id": "38860d07",
"metadata": {},
"outputs": [],
"source": [
"l = [['Helen', 23, 8], ['Kostas', 25, 9], ['Alex', 22, 9], ['Maria', 24, 7]]"
]
},
{
"cell_type": "code",
"execution_count": 106,
"id": "1bbbfd73",
"metadata": {},
"outputs": [],
"source": [
"s = 'a σρετςερτςρε σδφγ zfdgsdfg'"
]
},
{
"cell_type": "code",
"execution_count": 101,
"id": "b0da2ea6",
"metadata": {},
"outputs": [],
"source": [
"l = [4,5,4,3,4,5,6,7,6,1,5,4]"
]
},
{
"cell_type": "code",
"execution_count": 102,
"id": "e62a9c2f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1"
]
},
"execution_count": 102,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"min(l)"
]
},
{
"cell_type": "code",
"execution_count": 104,
"id": "4f8da98f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1"
]
},
"execution_count": 104,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def f(l):\n",
" if len(l) ==2:\n",
" if l[0] < l[1]:\n",
" return l[0]\n",
" return l[1]\n",
" \n",
" if l[0] < l[1]:\n",
" return f( [l[0]] + l[2:] )\n",
" \n",
" return f([l[1]] + l[2:])\n",
" \n",
" \n",
"f(l)"
]
},
{
"cell_type": "code",
"execution_count": 110,
"id": "ad7334b4",
"metadata": {},
"outputs": [],
"source": [
"my_list = [] \n",
"with open('C:/Users/user/findings.txt', 'w') as f:\n",
"\n",
" f.write('cvghjklcvbnjkfyucvhjkcvhcgh')\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1bd94d08",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "983f66ba",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "68e5239a",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 115,
"id": "136095ee",
"metadata": {},
"outputs": [
{
"ename": "FileExistsError",
"evalue": "[Errno 17] File exists: 'C:/Users/user/findings.txt'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mFileExistsError\u001b[0m Traceback (most recent call last)",
"Input \u001b[1;32mIn [115]\u001b[0m, in \u001b[0;36m<cell line: 2>\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m my_list \u001b[38;5;241m=\u001b[39m [] \n\u001b[1;32m----> 2\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mC:/Users/user/findings.txt\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mx\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m f:\n\u001b[0;32m 4\u001b[0m f\u001b[38;5;241m.\u001b[39mwrite(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mSUCH RESEARCH! WOW!!!!\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
"\u001b[1;31mFileExistsError\u001b[0m: [Errno 17] File exists: 'C:/Users/user/findings.txt'"
]
}
],
"source": [
"my_list = [] \n",
"with open('C:/Users/user/findings.txt', 'x') as f:\n",
"\n",
" f.write('SUCH RESEARCH! WOW!!!!')\n"
]
},
{
"cell_type": "code",
"execution_count": 118,
"id": "36f6bca0",
"metadata": {},
"outputs": [],
"source": [
"my_list = [] \n",
"with open('C:/Users/user/findings.txt', 'w') as f:\n",
"\n",
" f.write('SUCH RESEARCH! WOW!!!!\\n')\n",
" f.write('cannot get better than this!\\n')\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cce3e72b",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 36,
"id": "3b932420",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Progress: 0\n",
"Progress: 10000\n",
"Progress: 20000\n",
"Progress: 30000\n",
"Progress: 40000\n",
"Progress: 50000\n",
"Progress: 60000\n",
"Progress: 70000\n",
"Progress: 80000\n",
"Progress: 90000\n",
"Progress: 100000\n",
"Progress: 110000\n",
"Progress: 120000\n",
"Progress: 130000\n",
"Progress: 140000\n",
"Progress: 150000\n",
"Progress: 160000\n",
"Progress: 170000\n",
" read 175920 lines\n"
]
}
],
"source": [
"data = []\n",
"with open('C:/Users/user/Downloads/gwas_catalog_v1.0-associations_e105_r2022-03-23.tsv', \n",
" encoding='iso-8859-1') as f:\n",
" line = f.readline()\n",
" header = line.strip().split('\\t')\n",
"\n",
" for line_counter, line in enumerate(f):\n",
" l = f.readline()\n",
" \n",
" if line_counter % 10_000 == 0: \n",
" print (f'Progress: {line_counter}')\n",
"\n",
" l_list = l.strip().split('\\t')\n",
" \n",
" data.append(l_list)\n",
" \n",
"print (f' read {line_counter} lines')"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "026f83b9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['2019-02-14',\n",
" '29507422',\n",
" 'Hoffmann TJ',\n",
" '2018-03-05',\n",
" 'Nat Genet',\n",
" 'www.ncbi.nlm.nih.gov/pubmed/29507422',\n",
" 'A large electronic-health-record-based genome-wide study of serum lipids.',\n",
" 'High density lipoprotein cholesterol levels',\n",
" '76,627 European ancestry individuals, 7,795 Hispanic individuals, 6,855 East Asian ancestry individuals, 2,958 African American individuals, 439 South Asian ancestry individuals',\n",
" 'NA',\n",
" '2p24.1',\n",
" '2',\n",
" '21041028',\n",
" 'NR',\n",
" 'APOB',\n",
" '',\n",
" '',\n",
" 'ENSG00000084674',\n",
" '',\n",
" '',\n",
" 'rs1367117-G',\n",
" 'rs1367117',\n",
" '0',\n",
" '1367117',\n",
" 'missense_variant',\n",
" '0',\n",
" 'NR',\n",
" '3E-6',\n",
" '5.522878745280337',\n",
" '',\n",
" '0.018',\n",
" 'unit increase',\n",
" 'Affymetrix [at least 7091467] (imputed)',\n",
" 'N']"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data[100]"
]
},
{
"cell_type": "code",
"execution_count": 134,
"id": "c3813db4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['']"
]
},
"execution_count": 134,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"''.strip().split('\\t')"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "73b52e01",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'DATE ADDED TO CATALOG': '2019-02-14',\n",
" 'PUBMEDID': '29507422',\n",
" 'FIRST AUTHOR': 'Hoffmann TJ',\n",
" 'DATE': '2018-03-05',\n",
" 'JOURNAL': 'Nat Genet',\n",
" 'LINK': 'www.ncbi.nlm.nih.gov/pubmed/29507422',\n",
" 'STUDY': 'A large electronic-health-record-based genome-wide study of serum lipids.',\n",
" 'DISEASE/TRAIT': 'High density lipoprotein cholesterol levels',\n",
" 'INITIAL SAMPLE SIZE': '76,627 European ancestry individuals, 7,795 Hispanic individuals, 6,855 East Asian ancestry individuals, 2,958 African American individuals, 439 South Asian ancestry individuals',\n",
" 'REPLICATION SAMPLE SIZE': 'NA',\n",
" 'REGION': '2p24.1',\n",
" 'CHR_ID': '2',\n",
" 'CHR_POS': '21041028',\n",
" 'REPORTED GENE(S)': 'NR',\n",
" 'MAPPED_GENE': 'APOB',\n",
" 'UPSTREAM_GENE_ID': '',\n",
" 'DOWNSTREAM_GENE_ID': '',\n",
" 'SNP_GENE_IDS': 'ENSG00000084674',\n",
" 'UPSTREAM_GENE_DISTANCE': '',\n",
" 'DOWNSTREAM_GENE_DISTANCE': '',\n",
" 'STRONGEST SNP-RISK ALLELE': 'rs1367117-G',\n",
" 'SNPS': 'rs1367117',\n",
" 'MERGED': '0',\n",
" 'SNP_ID_CURRENT': '1367117',\n",
" 'CONTEXT': 'missense_variant',\n",
" 'INTERGENIC': '0',\n",
" 'RISK ALLELE FREQUENCY': 'NR',\n",
" 'P-VALUE': '3E-6',\n",
" 'PVALUE_MLOG': '5.522878745280337',\n",
" 'P-VALUE (TEXT)': '',\n",
" 'OR or BETA': '0.018',\n",
" '95% CI (TEXT)': 'unit increase',\n",
" 'PLATFORM [SNPS PASSING QC]': 'Affymetrix [at least 7091467] (imputed)',\n",
" 'CNV': 'N'}"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dict(zip(header, data[100]))"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "ef4efef8",
"metadata": {},
"outputs": [],
"source": [
"d = {}\n",
"\n",
"for item in data:\n",
" for h, v in zip(header, item):\n",
" if not h in d:\n",
" d[h] = []\n",
" \n",
" d[h].append(v)\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "e137b689",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"123"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(set(d['FIRST AUTHOR']))"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "6492bc17",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'Ahmed S',\n",
" 'Allen RJ',\n",
" 'Almgren P',\n",
" 'Almli LM',\n",
" 'Anney RJL',\n",
" 'Arpawong TE',\n",
" 'Astle WJ',\n",
" 'Bei JX',\n",
" 'Benyamin B',\n",
" 'Biernacka JM',\n",
" 'Bonas-Guarch S',\n",
" 'Cha S',\n",
" 'Chan JP',\n",
" 'Chang X',\n",
" 'Chaturvedi S',\n",
" 'Chen H',\n",
" 'Chenoweth MJ',\n",
" 'Christophersen IE',\n",
" 'Clarke TK',\n",
" 'Coleman JRI',\n",
" 'Conti DV',\n",
" 'Cooper JD',\n",
" 'Corre T',\n",
" 'Darlow JM',\n",
" 'Day FR',\n",
" 'Delgado DA',\n",
" 'Dong C',\n",
" 'Dudenkov TM',\n",
" 'Ferreira MA',\n",
" 'Gao B',\n",
" 'Gorski M',\n",
" 'Graff M',\n",
" 'Guo Q',\n",
" 'Hammerschlag AR',\n",
" 'Haryono SJ',\n",
" 'Hinks A',\n",
" 'Hofer P',\n",
" 'Hoffmann TJ',\n",
" 'Hong X',\n",
" 'Hu X',\n",
" 'Ikram MA',\n",
" 'Ilboudo Y',\n",
" 'Jia P',\n",
" 'Jonsson L',\n",
" 'Jun GR',\n",
" 'Justice AE',\n",
" 'Kawaguchi T',\n",
" 'Kerr KF',\n",
" 'Kim KW',\n",
" 'Kim M',\n",
" 'Kimura M',\n",
" 'Konte B',\n",
" 'Kristiansen W',\n",
" 'Kunz M',\n",
" 'Lee MH',\n",
" 'Lee MK',\n",
" 'Lee TH',\n",
" 'Lencer R',\n",
" 'Lessard CJ',\n",
" 'Li C',\n",
" 'Li D',\n",
" 'Li J',\n",
" 'Li M',\n",
" 'Litchfield K',\n",
" 'Liu JZ',\n",
" 'Liu Y',\n",
" 'Lu AT',\n",
" 'Lutz SM',\n",
" 'Lv H',\n",
" 'Mack S',\n",
" 'Magvanjav O',\n",
" 'Marenholz I',\n",
" 'McKay JD',\n",
" 'Michailidou K',\n",
" 'Milne RL',\n",
" 'Miron J',\n",
" 'Moore CB',\n",
" 'Moore KN',\n",
" 'Morris AP',\n",
" 'Morton LM',\n",
" 'Munz M',\n",
" 'Nakada TA',\n",
" 'Ng E',\n",
" 'Nolte IM',\n",
" 'Persad PJ',\n",
" 'Qian DC',\n",
" 'Randall CL',\n",
" 'Ravenhall M',\n",
" 'Ren HY',\n",
" 'Saccone NL',\n",
" 'Sakamoto Y',\n",
" 'Sanchez-Juan P',\n",
" 'Sanchez-Roige S',\n",
" 'Scelo G',\n",
" 'Seyerle AA',\n",
" 'Shah AA',\n",
" 'Shen X',\n",
" 'Sobota RS',\n",
" 'Sud A',\n",
" 'Sugier PE',\n",
" 'Suh Y',\n",
" 'Suhre K',\n",
" 'Sun Y',\n",
" 'Tachmazidou I',\n",
" 'Tapper W',\n",
" 'Thompson AG',\n",
" 'Tian C',\n",
" 'Tomer Y',\n",
" 'Turley P',\n",
" 'Wang Z',\n",
" 'Ward-Caviness CK',\n",
" 'Wattacheril J',\n",
" 'Winkler TW',\n",
" 'Witt SH',\n",
" 'Xu W',\n",
" 'Yashin AI',\n",
" 'Yeo A',\n",
" 'Yin X',\n",
" 'Yucesoy B',\n",
" 'Zai CC',\n",
" 'Zhang Y',\n",
" 'Zhang YB',\n",
" 'Zhou H'}"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"set(d['FIRST AUTHOR'])"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "f3190b93",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'Michailidou K', 'Tachmazidou I'}"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"set([x for x in d['FIRST AUTHOR'] if 'idou' in x])"
]
},
{
"cell_type": "code",
"execution_count": 120,
"id": "49ac0396",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'DATE ADDED TO CATALOG\\tPUBMEDID\\tFIRST AUTHOR\\tDATE\\tJOURNAL\\tLINK\\tSTUDY\\tDISEASE/TRAIT\\tINITIAL SAMPLE SIZE\\tREPLICATION SAMPLE SIZE\\tREGION\\tCHR_ID\\tCHR_POS\\tREPORTED GENE(S)\\tMAPPED_GENE\\tUPSTREAM_GENE_ID\\tDOWNSTREAM_GENE_ID\\tSNP_GENE_IDS\\tUPSTREAM_GENE_DISTANCE\\tDOWNSTREAM_GENE_DISTANCE\\tSTRONGEST SNP-RISK ALLELE\\tSNPS\\tMERGED\\tSNP_ID_CURRENT\\tCONTEXT\\tINTERGENIC\\tRISK ALLELE FREQUENCY\\tP-VALUE\\tPVALUE_MLOG\\tP-VALUE (TEXT)\\tOR or BETA\\t95% CI (TEXT)\\tPLATFORM [SNPS PASSING QC]\\tCNV\\n'"
]
},
"execution_count": 120,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"line"
]
},
{
"cell_type": "code",
"execution_count": 122,
"id": "908eec77",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['DATE ADDED TO CATALOG',\n",
" 'PUBMEDID',\n",
" 'FIRST AUTHOR',\n",
" 'DATE',\n",
" 'JOURNAL',\n",
" 'LINK',\n",
" 'STUDY',\n",
" 'DISEASE/TRAIT',\n",
" 'INITIAL SAMPLE SIZE',\n",
" 'REPLICATION SAMPLE SIZE',\n",
" 'REGION',\n",
" 'CHR_ID',\n",
" 'CHR_POS',\n",
" 'REPORTED GENE(S)',\n",
" 'MAPPED_GENE',\n",
" 'UPSTREAM_GENE_ID',\n",
" 'DOWNSTREAM_GENE_ID',\n",
" 'SNP_GENE_IDS',\n",
" 'UPSTREAM_GENE_DISTANCE',\n",
" 'DOWNSTREAM_GENE_DISTANCE',\n",
" 'STRONGEST SNP-RISK ALLELE',\n",
" 'SNPS',\n",
" 'MERGED',\n",
" 'SNP_ID_CURRENT',\n",
" 'CONTEXT',\n",
" 'INTERGENIC',\n",
" 'RISK ALLELE FREQUENCY',\n",
" 'P-VALUE',\n",
" 'PVALUE_MLOG',\n",
" 'P-VALUE (TEXT)',\n",
" 'OR or BETA',\n",
" '95% CI (TEXT)',\n",
" 'PLATFORM [SNPS PASSING QC]',\n",
" 'CNV']"
]
},
"execution_count": 122,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"line.strip().split('\\t')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2b60418e",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "400f9e13",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "4efb7a4f",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "5c29077f",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.9.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment