Skip to content

Commit 31fd245

Browse files
rasbtrasbt
committed
find copy
1 parent cf64608 commit 31fd245

2 files changed

Lines changed: 288 additions & 18 deletions

File tree

‎.ipynb_checkpoints/timeit_tests-checkpoint.ipynb‎

Lines changed: 153 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
{
22
"metadata": {
33
"name": "",
4-
"signature": "sha256:faa7cde23cd1ec6598ad386b44eabe2d06ad86d6bdd84c7d999dd174c7df48a6"
4+
"signature": "sha256:c5925e90d7a8c3e6fb36f4e3ca876248f4ba69529367d87b73ef3da2b5415766"
55
},
66
"nbformat": 3,
77
"nbformat_minor": 0,
@@ -64,7 +64,8 @@
6464
" - [Creating lists using conditional statements](#create_cond_list)\n",
6565
"- [Dictionary operations](#dict_ops) \n",
6666
" - [Adding elements to a dictionary](#adding_dict_elements)\n",
67-
"- [Comprehensions vs. for-loops](#comprehensions)"
67+
"- [Comprehensions vs. for-loops](#comprehensions)\n",
68+
"- [Copying files by searching directory trees](#find_copy)"
6869
]
6970
},
7071
{
@@ -1023,6 +1024,14 @@
10231024
"# Comprehesions vs. for-loops"
10241025
]
10251026
},
1027+
{
1028+
"cell_type": "markdown",
1029+
"metadata": {},
1030+
"source": [
1031+
"Comprehensions are not only shorter and prettier than ye goode olde for-loop, \n",
1032+
"but they are also up to ~1.2x faster."
1033+
]
1034+
},
10261035
{
10271036
"cell_type": "code",
10281037
"collapsed": false,
@@ -1126,7 +1135,7 @@
11261135
"language": "python",
11271136
"metadata": {},
11281137
"outputs": [],
1129-
"prompt_number": 11
1138+
"prompt_number": 23
11301139
},
11311140
{
11321141
"cell_type": "code",
@@ -1138,7 +1147,7 @@
11381147
"language": "python",
11391148
"metadata": {},
11401149
"outputs": [],
1141-
"prompt_number": 12
1150+
"prompt_number": 24
11421151
},
11431152
{
11441153
"cell_type": "code",
@@ -1154,8 +1163,8 @@
11541163
"output_type": "stream",
11551164
"stream": "stdout",
11561165
"text": [
1157-
"10000 loops, best of 3: 130 \u00b5s per loop\n",
1158-
"10000 loops, best of 3: 114 \u00b5s per loop"
1166+
"10000 loops, best of 3: 129 \u00b5s per loop\n",
1167+
"10000 loops, best of 3: 111 \u00b5s per loop"
11591168
]
11601169
},
11611170
{
@@ -1166,7 +1175,7 @@
11661175
]
11671176
}
11681177
],
1169-
"prompt_number": 14
1178+
"prompt_number": 25
11701179
},
11711180
{
11721181
"cell_type": "markdown",
@@ -1189,7 +1198,7 @@
11891198
"language": "python",
11901199
"metadata": {},
11911200
"outputs": [],
1192-
"prompt_number": 15
1201+
"prompt_number": 26
11931202
},
11941203
{
11951204
"cell_type": "code",
@@ -1201,7 +1210,7 @@
12011210
"language": "python",
12021211
"metadata": {},
12031212
"outputs": [],
1204-
"prompt_number": 17
1213+
"prompt_number": 27
12051214
},
12061215
{
12071216
"cell_type": "code",
@@ -1217,8 +1226,8 @@
12171226
"output_type": "stream",
12181227
"stream": "stdout",
12191228
"text": [
1220-
"10000 loops, best of 3: 120 \u00b5s per loop\n",
1221-
"10000 loops, best of 3: 118 \u00b5s per loop"
1229+
"10000 loops, best of 3: 121 \u00b5s per loop\n",
1230+
"10000 loops, best of 3: 127 \u00b5s per loop"
12221231
]
12231232
},
12241233
{
@@ -1229,15 +1238,145 @@
12291238
]
12301239
}
12311240
],
1232-
"prompt_number": 18
1241+
"prompt_number": 28
1242+
},
1243+
{
1244+
"cell_type": "markdown",
1245+
"metadata": {},
1246+
"source": [
1247+
"<a name=\"find_copy\"></a>\n",
1248+
"<br>\n",
1249+
"<br>"
1250+
]
1251+
},
1252+
{
1253+
"cell_type": "markdown",
1254+
"metadata": {},
1255+
"source": [
1256+
"# Copying files by searching directory trees"
1257+
]
1258+
},
1259+
{
1260+
"cell_type": "markdown",
1261+
"metadata": {},
1262+
"source": [
1263+
"Executing `Unix`/`Linux` shell commands:"
1264+
]
12331265
},
12341266
{
12351267
"cell_type": "code",
12361268
"collapsed": false,
1237-
"input": [],
1269+
"input": [
1270+
"import subprocess\n",
1271+
"\n",
1272+
"def subprocess_findcopy(path, search_str, dest): \n",
1273+
" query = 'find %s -name \"%s\" -exec cp {}\" %s \\;' %(path, search_str, dest)\n",
1274+
" subprocess.call(query, shell=True)\n",
1275+
" return "
1276+
],
12381277
"language": "python",
12391278
"metadata": {},
1240-
"outputs": []
1279+
"outputs": [],
1280+
"prompt_number": 2
1281+
},
1282+
{
1283+
"cell_type": "markdown",
1284+
"metadata": {},
1285+
"source": [
1286+
"Using Python's `os.walk()` to search the directory tree recursively and matching patterns via `fnmatch.filter()`"
1287+
]
1288+
},
1289+
{
1290+
"cell_type": "code",
1291+
"collapsed": false,
1292+
"input": [
1293+
"import shutil\n",
1294+
"import os\n",
1295+
"import fnmatch\n",
1296+
"\n",
1297+
"def walk_findcopy(path, search_str, dest):\n",
1298+
" for path, subdirs, files in os.walk(path):\n",
1299+
" for name in fnmatch.filter(files, search_str):\n",
1300+
" shutil.copy(os.path.join(path,name), dest)"
1301+
],
1302+
"language": "python",
1303+
"metadata": {},
1304+
"outputs": [],
1305+
"prompt_number": 3
1306+
},
1307+
{
1308+
"cell_type": "code",
1309+
"collapsed": false,
1310+
"input": [
1311+
"import timeit\n",
1312+
"\n",
1313+
"print('small tree')\n",
1314+
"inpath = '/Users/sebastian/Desktop/testdir_in'\n",
1315+
"outpath = '/Users/sebastian/Desktop/testdir_out'\n",
1316+
"searchstr = '*.png'\n",
1317+
"%timeit subprocess_findcopy(inpath, searchstr, outpath)\n",
1318+
"%timeit walk_findcopy(inpath, searchstr, outpath)\n",
1319+
"\n",
1320+
"print('\\nlarger tree')\n",
1321+
"inpath = '/Users/sebastian/Dropbox'\n",
1322+
"outpath = '/Users/sebastian/Desktop/testdir_out'\n",
1323+
"searchstr = '*.csv'\n",
1324+
"%timeit subprocess_findcopy(inpath, searchstr, outpath)\n",
1325+
"%timeit walk_findcopy(inpath, searchstr, outpath)"
1326+
],
1327+
"language": "python",
1328+
"metadata": {},
1329+
"outputs": [
1330+
{
1331+
"output_type": "stream",
1332+
"stream": "stdout",
1333+
"text": [
1334+
"small tree\n",
1335+
"100 loops, best of 3: 8.48 ms per loop"
1336+
]
1337+
},
1338+
{
1339+
"output_type": "stream",
1340+
"stream": "stdout",
1341+
"text": [
1342+
"\n",
1343+
"100 loops, best of 3: 22.3 ms per loop"
1344+
]
1345+
},
1346+
{
1347+
"output_type": "stream",
1348+
"stream": "stdout",
1349+
"text": [
1350+
"\n",
1351+
"\n",
1352+
"larger tree\n",
1353+
"10 loops, best of 3: 7.13 ms per loop"
1354+
]
1355+
},
1356+
{
1357+
"output_type": "stream",
1358+
"stream": "stdout",
1359+
"text": [
1360+
"\n",
1361+
"1 loops, best of 3: 413 ms per loop"
1362+
]
1363+
},
1364+
{
1365+
"output_type": "stream",
1366+
"stream": "stdout",
1367+
"text": [
1368+
"\n"
1369+
]
1370+
}
1371+
],
1372+
"prompt_number": 4
1373+
},
1374+
{
1375+
"cell_type": "markdown",
1376+
"metadata": {},
1377+
"source": [
1378+
"I have to say that I am really positvively surprised. The shell's `find` scales even better than expected!"
1379+
]
12411380
}
12421381
],
12431382
"metadata": {}

0 commit comments

Comments
 (0)