some extras

Author: kyclark

.gitignore

@@ -9,3 +9,4 @@ tex2pdf*
 .mypy_cache
 .log
 .coverage
+.idea

01_hello/hello04_argparse.py

@@ -0,0 +1,10 @@
+#!/usr/bin/env python3
+# Purpose: Say hello
+
+import argparse
+
+parser = argparse.ArgumentParser(description='Say hello')
+parser.add_argument('name', help='Whom to greet')
+args = parser.parse_args()
+name = args.name
+print('Hello, ' + name + '!')

02_crowsnest/crowsnest.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+"""
+Author : Me <[email protected]>
+Date   : today
+Purpose: Rock the Casbah
+"""
+
+import argparse
+import os
+import sys
+
+
+# --------------------------------------------------
+def get_args():
+    """Get command-line arguments"""
+
+    parser = argparse.ArgumentParser(
+        description='Rock the Casbah',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+
+    parser.add_argument('positional',
+                        metavar='str',
+                        help='A positional argument')
+
+    parser.add_argument('-a',
+                        '--arg',
+                        help='A named string argument',
+                        metavar='str',
+                        type=str,
+                        default='')
+
+    parser.add_argument('-i',
+                        '--int',
+                        help='A named integer argument',
+                        metavar='int',
+                        type=int,
+                        default=0)
+
+    parser.add_argument('-f',
+                        '--file',
+                        help='A readable file',
+                        metavar='FILE',
+                        type=argparse.FileType('r'),
+                        default=None)
+
+    parser.add_argument('-o',
+                        '--on',
+                        help='A boolean flag',
+                        action='store_true')
+
+    return parser.parse_args()
+
+
+# --------------------------------------------------
+def main():
+    """Make a jazz noise here"""
+
+    args = get_args()
+    str_arg = args.arg
+    int_arg = args.int
+    file_arg = args.file
+    flag_arg = args.on
+    pos_arg = args.positional
+
+    print('str_arg = "{}"'.format(str_arg))
+    print('int_arg = "{}"'.format(int_arg))
+    print('file_arg = "{}"'.format(file_arg.name))
+    print('flag_arg = "{}"'.format(flag_arg))
+    print('positional = "{}"'.format(pos_arg))
+
+
+# --------------------------------------------------
+if __name__ == '__main__':
+    main()

extra/03_dna/Makefile extra/02_dna/Makefile

@@ -0,0 +1,10 @@
+.PHONY: test pdf clean
+
+pdf:
+	asciidoctor-pdf README.adoc
+
+test:
+	pytest -xv test.py
+
+clean:
+	rm -rf __pycache__

extra/03_dna/README.adoc extra/02_dna/README.adoc

@@ -0,0 +1,150 @@
+= Python Dictionaries: Translate DNA/RNA to AA
+
+Write a Python program called `translate.py` that translates a given DNA/RNA sequence to amino acids.
+The input sequence is expected to be a positional argument.
+The codon table is expected for the `-c` or `--codons` option and should be a valid, readable file.
+The `-o` or `--output` option (default `'out.txt'`) will name a file to write the output. 
+
+When run with no inputs, the program should print a brief usage:
+
+----
+$ ./translate.py
+usage: translate.py [-h] -c FILE [-o FILE] str
+translate.py: error: the following arguments are required: str, -c/--codons
+----
+
+Or a longer usage for the `-h` or `--help` flags:
+
+----
+$ ./translate.py -h
+usage: translate.py [-h] -c FILE [-o FILE] str
+
+Translate DNA/RNA to proteins
+
+positional arguments:
+  str                   DNA/RNA sequence
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -c FILE, --codons FILE
+                        A file with codon translations (default: None)
+  -o FILE, --outfile FILE
+                        Output filename (default: out.txt)
+----
+
+The program should reject a `--codons` argument that fails to name a file:
+
+----
+$ ./translate.py -c lkdflk ACTG
+usage: translate.py [-h] -c FILE [-o FILE] str
+translate.py: error: argument -c/--codons: can't open 'lkdflk': \
+[Errno 2] No such file or directory: 'lkdflk'
+----
+
+If given good input, write the results to the proper output file.
+Note here that the input string is lowercase:
+
+----
+$ ./translate.py -c codons.dna gaactacaccgttctcctggt
+Output written to "out.txt".
+----
+
+And now the `out.txt` file should contain the following:
+
+----
+$ cat out.txt
+ELHRSPG
+----
+
+Note that the `-o` flag should make the program write the output to a different file.
+Note here that the input sequence is uppercase:
+
+----
+$ ./translate.py UGGCCAUGGCGCCCAGAACUG --codons codons.rna -o foo.txt
+Output written to "foo.txt".
+----
+
+Your program will be given the wrong codon table for a given sequence type, e.g., a DNA table for an RNA sequence:
+
+----
+$ ./translate.py UGGCCAUGGCGCCCAGAACUG --codons codons.dna
+Output written to "out.txt".
+----
+
+This means that your program will be unable to find some of the codons in which case it should print a `-` for a missing codon:
+
+----
+$ cat out.txt
+-P-RPE-
+----
+
+If you are creating a dictionary from the codon table, e.g.:
+
+----
+$ head -3 codons.rna
+AAA	K
+AAC	N
+AAG	K
+----
+
+Such that you have something like this:
+
+----
+>>> codons = dict(AAA='K', AAC='N', AAG='K')
+----
+
+Everything is fine as long as you ask for codons that are defined but will fail at runtime if you ask for a codon that does not exist:
+
+----
+>>> codons['AAC']
+'N'
+>>> codons['AAT']
+Traceback (most recent call last):
+  File "<stdin>", line 1, in <module>
+KeyError: 'AAT'
+----
+
+What dictionary access method will prevent you from creating an exception if you ask for a key that doesn't exist and will also allow you to set a default value?
+
+== Extracting k-mers
+
+A k-mer is a `k`-length sequence of contigous characters in a string (a "mer" like "polymer").
+Here is a piece of code that you can use to extract all the 3-mers from the sequence `seq`:
+
+----
+>>> seq = 'actga'
+>>> k = 3
+>>> for codon in [seq[i:i + k] for i in range(0, len(seq) - k + 1)]:
+...     print(codon)
+...
+act
+ctg
+tga
+----
+
+You will then use the `codon` as a key to lookup the amino acid translation from the `codons` dictionary you build using the input file.
+
+== Tests
+
+A passing test suite looks like this:
+
+----
+$ make test
+pytest -xv test.py
+============================= test session starts ==============================
+...
+collected 10 items
+
+test.py::test_exists PASSED                                              [ 10%]
+test.py::test_usage PASSED                                               [ 20%]
+test.py::test_no_args PASSED                                             [ 30%]
+test.py::test_missing_input PASSED                                       [ 40%]
+test.py::test_missing_codons PASSED                                      [ 50%]
+test.py::test_bad_codon_file PASSED                                      [ 60%]
+test.py::test_good_input1 PASSED                                         [ 70%]
+test.py::test_good_input2 PASSED                                         [ 80%]
+test.py::test_good_input3 PASSED                                         [ 90%]
+test.py::test_good_input4 PASSED                                         [100%]
+
+============================== 10 passed in 0.50s ==============================
+----

extra/03_dna/README.pdf extra/02_dna/README.pdf

@@ -0,0 +1,64 @@
+AAA K
+AAC N
+AAG K
+AAT N
+ACA T
+ACC T
+ACG T
+ACT T
+AGA R
+AGC S
+AGG R
+AGT S
+ATA I
+ATC I
+ATG M
+ATT I
+CAA Q
+CAC H
+CAG Q
+CAT H
+CCA P
+CCC P
+CCG P
+CCT P
+CGA R
+CGC R
+CGG R
+CGT R
+CTA L
+CTC L
+CTG L
+CTT L
+GAA E
+GAC D
+GAG E
+GAT D
+GCA A
+GCC A
+GCG A
+GCT A
+GGA G
+GGC G
+GGG G
+GGT G
+GTA V
+GTC V
+GTG V
+GTT V
+TAA Stop
+TAC Y
+TAG Stop
+TAT Y
+TCA S
+TCC S
+TCG S
+TCT S
+TGA Stop
+TGC C
+TGG W
+TGT C
+TTA L
+TTC F
+TTG L
+TTT F

extra/03_dna/test.py extra/02_dna/test.py

@@ -0,0 +1,64 @@
+AAA	K
+AAC	N
+AAG	K
+AAU	N
+ACA	T
+ACC	T
+ACG	T
+ACU	T
+AGA	R
+AGC	S
+AGG	R
+AGU	S
+AUA	I
+AUC	I
+AUG	M
+AUU	I
+CAA	Q
+CAC	H
+CAG	Q
+CAU	H
+CCA	P
+CCC	P
+CCG	P
+CCU	P
+CGA	R
+CGC	R
+CGG	R
+CGU	R
+CUA	L
+CUC	L
+CUG	L
+CUU	L
+GAA	E
+GAC	D
+GAG	E
+GAU	D
+GCA	A
+GCC	A
+GCG	A
+GCU	A
+GGA	G
+GGC	G
+GGG	G
+GGU	G
+GUA	V
+GUC	V
+GUG	V
+GUU	V
+UAA	Stop
+UAC	Y
+UAG	Stop
+UAU	Y
+UCA	S
+UCC	S
+UCG	S
+UCU	S
+UGA	Stop
+UGC	C
+UGG	W
+UGU	C
+UUA	L
+UUC	F
+UUG	L
+UUU	F

extra/03_spanish/Makefile extra/02_spanish/Makefile

@@ -0,0 +1 @@
+gaactacaccgttctcctggt

extra/03_spanish/README.adoc extra/02_spanish/README.adoc

@@ -0,0 +1 @@
+UGGCCAUGGCGCCCAGAACUGAGAUCAAUAGUACCCGUAUUAACGGGUGAA