From be3451dc932089be9ca72cfe1632af36666bd21f Mon Sep 17 00:00:00 2001
From: mlefter <m.lefter@lumc.nl>
Date: Tue, 19 Sep 2017 08:12:13 +0200
Subject: [PATCH] More python small changes
---
more_python/03_more_python_goodness_1.ipynb | 260 ++++++++++----------
more_python/03_more_python_goodness_2.ipynb | 114 ++++++---
2 files changed, 218 insertions(+), 156 deletions(-)
diff --git a/more_python/03_more_python_goodness_1.ipynb b/more_python/03_more_python_goodness_1.ipynb
index fed127b..48d1949 100644
--- a/more_python/03_more_python_goodness_1.ipynb
+++ b/more_python/03_more_python_goodness_1.ipynb
@@ -140,7 +140,9 @@
{
"cell_type": "code",
"execution_count": 1,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"import sys"
@@ -156,7 +158,9 @@
{
"cell_type": "code",
"execution_count": 2,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"sys?"
@@ -228,22 +232,22 @@
"To use `sys.argv` in our script, open a text editor and edit the script by adding an import statement, capturing the `sys.argv` value, and editing our last `print` line:\n",
"\n",
"```python\n",
- " #!/usr/bin/env python\n",
- " import sys\n",
- "\n",
- " def calc_gc_percent(seq):\n",
- " at_count, gc_count = 0, 0\n",
- " for char in seq:\n",
- " if char in ('A', 'T'):\n",
- " at_count += 1\n",
- " elif char in ('G', 'C'):\n",
- " gc_count += 1\n",
- "\n",
- " return gc_count * 100.0 / (gc_count + at_count) \n",
- "\n",
- " input_seq = sys.argv[1]\n",
- " print \"The sequence '{}' has a %GC of {:.2f}\".format(\n",
- " input_seq, calc_gc_percent(input_seq))\n",
+ "#!/usr/bin/env python\n",
+ "import sys\n",
+ "\n",
+ "def calc_gc_percent(seq):\n",
+ " at_count, gc_count = 0, 0\n",
+ " for char in seq:\n",
+ " if char in ('A', 'T'):\n",
+ " at_count += 1\n",
+ " elif char in ('G', 'C'):\n",
+ " gc_count += 1\n",
+ "\n",
+ " return gc_count * 100.0 / (gc_count + at_count) \n",
+ "\n",
+ "input_seq = sys.argv[1]\n",
+ "print \"The sequence '{}' has a %GC of {:.2f}\".format(\n",
+ " input_seq, calc_gc_percent(input_seq))\n",
"```\n",
"To test it, you can run the following command in your shell:\n",
"\n",
@@ -267,7 +271,9 @@
{
"cell_type": "code",
"execution_count": 5,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"my_str = 'Hello again, ipython!'"
@@ -441,15 +447,15 @@
"\n",
"Let's use `upper()` to fortify our function. It should now look something like this:\n",
"```python\n",
- " def calc_gc_percent(seq):\n",
- " at_count, gc_count = 0, 0\n",
- " for char in seq.upper():\n",
- " if char in ('A', 'T'):\n",
- " at_count += 1\n",
- " elif char in ('G', 'C'):\n",
- " gc_count += 1\n",
- "\n",
- " return gc_count * 100.0 / (gc_count + at_count) \n",
+ "def calc_gc_percent(seq):\n",
+ " at_count, gc_count = 0, 0\n",
+ " for char in seq.upper():\n",
+ " if char in ('A', 'T'):\n",
+ " at_count += 1\n",
+ " elif char in ('G', 'C'):\n",
+ " gc_count += 1\n",
+ "\n",
+ " return gc_count * 100.0 / (gc_count + at_count) \n",
"```\n",
"And run it (in whichever way you prefer). Do you get the expected output?"
]
@@ -484,35 +490,35 @@
"\n",
"Open your script again in a text editor, and add the following comments and docstrings: \n",
"```python\n",
- " #!/usr/bin/env python\n",
- " import sys\n",
- "\n",
- " def calc_gc_percent(seq):\n",
- " \"\"\"\n",
- " Calculates the GC percentage of the given sequence.\n",
- "\n",
- " Arguments:\n",
- " - seq - the input sequence (string).\n",
- "\n",
- " Returns:\n",
- " - GC percentage (float).\n",
- "\n",
- " The returned value is always <= 100.0\n",
- " \"\"\"\n",
- " at_count, gc_count = 0, 0\n",
- " # Change input to all caps to allow for non-capital\n",
- " # input sequence.\n",
- " for char in seq.upper():\n",
- " if char in ('A', 'T'):\n",
- " at_count += 1\n",
- " elif char in ('G', 'C'):\n",
- " gc_count += 1\n",
- "\n",
- " return gc_count * 100.0 / (gc_count + at_count) \n",
- "\n",
- " input_seq = sys.argv[1]\n",
- " print \"The sequence '{}' has a %GC of {:.2f}\".format(\n",
- " input_seq, calc_gc_percent(input_seq))\n",
+ "#!/usr/bin/env python\n",
+ "import sys\n",
+ "\n",
+ "def calc_gc_percent(seq):\n",
+ " \"\"\"\n",
+ " Calculates the GC percentage of the given sequence.\n",
+ "\n",
+ " Arguments:\n",
+ " - seq - the input sequence (string).\n",
+ "\n",
+ " Returns:\n",
+ " - GC percentage (float).\n",
+ "\n",
+ " The returned value is always <= 100.0\n",
+ " \"\"\"\n",
+ " at_count, gc_count = 0, 0\n",
+ " # Change input to all caps to allow for non-capital\n",
+ " # input sequence.\n",
+ " for char in seq.upper():\n",
+ " if char in ('A', 'T'):\n",
+ " at_count += 1\n",
+ " elif char in ('G', 'C'):\n",
+ " gc_count += 1\n",
+ "\n",
+ " return gc_count * 100.0 / (gc_count + at_count) \n",
+ "\n",
+ "input_seq = sys.argv[1]\n",
+ "print \"The sequence '{}' has a %GC of {:.2f}\".format(\n",
+ " input_seq, calc_gc_percent(input_seq))\n",
"```"
]
},
@@ -633,13 +639,14 @@
"We don't always want to let exceptions stop program flow, sometimes we want to provide alternative flow. The `try ... except` block allows you to do this.\n",
"\n",
"The syntax is:\n",
- "\n",
- " try:\n",
- " # Statements that may raise exceptions.\n",
- " # [...]\n",
- " except {exception type}:\n",
- " # What to do when the exceptionis raised.\n",
- " # [...]"
+ "```python\n",
+ "try:\n",
+ " # Statements that may raise exceptions.\n",
+ " # [...]\n",
+ "except {exception type}:\n",
+ " # What to do when the exceptionis raised.\n",
+ " # [...]\n",
+ "```"
]
},
{
@@ -651,36 +658,36 @@
"Let's change our script by adding a `try ... except` block:\n",
"\n",
"```python\n",
- " def calc_gc_percent(seq):\n",
- " \"\"\"\n",
- " Calculates the GC percentage of the given sequence.\n",
- "\n",
- " Arguments:\n",
- " - seq - the input sequence (string).\n",
- "\n",
- " Returns:\n",
- " - GC percentage (float).\n",
- "\n",
- " The returned value is always <= 100.0\n",
- " \"\"\"\n",
- " at_count, gc_count = 0, 0\n",
- " # Change input to all caps to allow for non-capital\n",
- " # input sequence.\n",
- " for char in seq.upper():\n",
- " if char in ('A', 'T'):\n",
- " at_count += 1\n",
- " elif char in ('G', 'C'):\n",
- " gc_count += 1\n",
- " else:\n",
- " raise ValueError(\n",
- " \"Unexpeced character found: {}. Only \"\n",
- " \"ACTGs are allowed.\".format(char))\n",
- "\n",
- " # Corner case handling: empty input sequence.\n",
- " try:\n",
- " return gc_count * 100.0 / (gc_count + at_count)\n",
- " except ZeroDivisionError:\n",
- " return 0.0\n",
+ "def calc_gc_percent(seq):\n",
+ " \"\"\"\n",
+ " Calculates the GC percentage of the given sequence.\n",
+ "\n",
+ " Arguments:\n",
+ " - seq - the input sequence (string).\n",
+ "\n",
+ " Returns:\n",
+ " - GC percentage (float).\n",
+ "\n",
+ " The returned value is always <= 100.0\n",
+ " \"\"\"\n",
+ " at_count, gc_count = 0, 0\n",
+ " # Change input to all caps to allow for non-capital\n",
+ " # input sequence.\n",
+ " for char in seq.upper():\n",
+ " if char in ('A', 'T'):\n",
+ " at_count += 1\n",
+ " elif char in ('G', 'C'):\n",
+ " gc_count += 1\n",
+ " else:\n",
+ " raise ValueError(\n",
+ " \"Unexpeced character found: {}. Only \"\n",
+ " \"ACTGs are allowed.\".format(char))\n",
+ "\n",
+ " # Corner case handling: empty input sequence.\n",
+ " try:\n",
+ " return gc_count * 100.0 / (gc_count + at_count)\n",
+ " except ZeroDivisionError:\n",
+ " return 0.0\n",
"```"
]
},
@@ -696,19 +703,20 @@
"\n",
"Example of code that violates this principle:\n",
"```python\n",
- " try:\n",
- " my_function()\n",
- " my_other_function()\n",
- " except ValueError:\n",
- " my_fallback_function()\n",
+ "try:\n",
+ " my_function()\n",
+ " my_other_function()\n",
+ "except ValueError:\n",
+ " my_fallback_function()\n",
"```\n",
"A better way would be:\n",
"```python\n",
- " try:\n",
- " my_function()\n",
- " except ValueError:\n",
- " my_fallback_function()\n",
- " my_other_function()"
+ "try:\n",
+ " my_function()\n",
+ "except ValueError:\n",
+ " my_fallback_function()\n",
+ "my_other_function()\n",
+ "```"
]
},
{
@@ -719,21 +727,21 @@
"\n",
"The following code is syntactically valid, but *never* use it in your real scripts / programs:\n",
"```python\n",
- " try:\n",
- " my_function()\n",
- " except:\n",
- " my_fallback_function()\n",
+ "try:\n",
+ " my_function()\n",
+ "except:\n",
+ " my_fallback_function()\n",
"```\n",
"*Always* use the full exception name when handling exceptions, to make for a much cleaner code:\n",
"```python\n",
- " try:\n",
- " my_function()\n",
- " except ValueError:\n",
- " my_fallback_function()\n",
- " except TypeError:\n",
- " my_other_fallback_function()\n",
- " except IndexError:\n",
- " my_final_function()\n",
+ "try:\n",
+ " my_function()\n",
+ "except ValueError:\n",
+ " my_fallback_function()\n",
+ "except TypeError:\n",
+ " my_other_fallback_function()\n",
+ "except IndexError:\n",
+ " my_final_function()\n",
"```"
]
},
@@ -745,9 +753,9 @@
" \n",
"We could have written our last exception block like so:\n",
"```python\n",
- " if gc_count + at_count == 0:\n",
- " return 0.0\n",
- " return gc_count * 100.0 / (gc_count + at_count)\n",
+ "if gc_count + at_count == 0:\n",
+ " return 0.0\n",
+ "return gc_count * 100.0 / (gc_count + at_count)\n",
"```\n",
"Both approaches are correct and have their own plus and minuses in general. However in this case, I would argue that EAFP is better since it makes the code more readable."
]
@@ -766,7 +774,9 @@
{
"cell_type": "code",
"execution_count": 15,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"from IPython.core.display import HTML\n",
@@ -919,21 +929,21 @@
"metadata": {
"celltoolbar": "Slideshow",
"kernelspec": {
- "display_name": "Python 2",
+ "display_name": "Python 3",
"language": "python",
- "name": "python2"
+ "name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
- "version": 2
+ "version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
- "pygments_lexer": "ipython2",
- "version": "2.7.12"
+ "pygments_lexer": "ipython3",
+ "version": "3.5.2"
}
},
"nbformat": 4,
diff --git a/more_python/03_more_python_goodness_2.ipynb b/more_python/03_more_python_goodness_2.ipynb
index 0cf23e7..4c45b26 100644
--- a/more_python/03_more_python_goodness_2.ipynb
+++ b/more_python/03_more_python_goodness_2.ipynb
@@ -130,7 +130,9 @@
{
"cell_type": "code",
"execution_count": 1,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"import seq_toolbox"
@@ -166,7 +168,9 @@
{
"cell_type": "code",
"execution_count": 3,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"seq_toolbox.calc_gc_percent?"
@@ -202,7 +206,9 @@
{
"cell_type": "code",
"execution_count": 5,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"from seq_toolbox import calc_gc_percent"
@@ -238,7 +244,9 @@
{
"cell_type": "code",
"execution_count": 7,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"from seq_toolbox import calc_gc_percent as gc_calc"
@@ -305,7 +313,9 @@
{
"cell_type": "code",
"execution_count": 9,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"import os"
@@ -354,7 +364,9 @@
{
"cell_type": "code",
"execution_count": 12,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"my_filename = 'input.fastq'"
@@ -475,7 +487,9 @@
{
"cell_type": "code",
"execution_count": 18,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"import sys"
@@ -595,7 +609,9 @@
{
"cell_type": "code",
"execution_count": 23,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"import math"
@@ -715,7 +731,9 @@
{
"cell_type": "code",
"execution_count": 29,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"import random"
@@ -817,7 +835,9 @@
{
"cell_type": "code",
"execution_count": 34,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"import re"
@@ -826,7 +846,9 @@
{
"cell_type": "code",
"execution_count": 35,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"my_seq = 'CAGTCAGT'"
@@ -835,7 +857,9 @@
{
"cell_type": "code",
"execution_count": 36,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"results1 = re.search(r'CA.+CA', my_seq)"
@@ -864,7 +888,9 @@
{
"cell_type": "code",
"execution_count": 38,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"results2 = re.search(r'CCC..', my_seq)"
@@ -955,7 +981,9 @@
{
"cell_type": "code",
"execution_count": 40,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"open?"
@@ -973,7 +1001,9 @@
{
"cell_type": "code",
"execution_count": 41,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"fh = open('data/short_file.txt')"
@@ -1043,7 +1073,9 @@
{
"cell_type": "code",
"execution_count": 44,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"fh.seek(0)"
@@ -1079,7 +1111,9 @@
{
"cell_type": "code",
"execution_count": 46,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"fh.seek(0)"
@@ -1155,7 +1189,9 @@
{
"cell_type": "code",
"execution_count": 50,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"fh.seek(0)"
@@ -1246,7 +1282,9 @@
{
"cell_type": "code",
"execution_count": 54,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"fh.close()"
@@ -1284,7 +1322,9 @@
{
"cell_type": "code",
"execution_count": 58,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"fw = open('data/my_file.txt', 'w')"
@@ -1327,7 +1367,9 @@
{
"cell_type": "code",
"execution_count": 60,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"fw.write('This is my first line ')"
@@ -1336,7 +1378,9 @@
{
"cell_type": "code",
"execution_count": 61,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"fw.write('Still on my first line\\n')"
@@ -1345,7 +1389,9 @@
{
"cell_type": "code",
"execution_count": 62,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"fw.write('Now on my second line')"
@@ -1361,7 +1407,9 @@
{
"cell_type": "code",
"execution_count": 63,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"fw.close()"
@@ -1399,7 +1447,9 @@
{
"cell_type": "code",
"execution_count": 65,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"os.remove('data/my_file.txt')"
@@ -1676,7 +1726,9 @@
{
"cell_type": "code",
"execution_count": 71,
- "metadata": {},
+ "metadata": {
+ "collapsed": true
+ },
"outputs": [],
"source": [
"from IPython.core.display import HTML\n",
@@ -1824,21 +1876,21 @@
],
"metadata": {
"kernelspec": {
- "display_name": "Python 2",
+ "display_name": "Python 3",
"language": "python",
- "name": "python2"
+ "name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
- "version": 2
+ "version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
- "pygments_lexer": "ipython2",
- "version": "2.7.12"
+ "pygments_lexer": "ipython3",
+ "version": "3.5.2"
}
},
"nbformat": 4,
--
GitLab