exercise from Lu Yi for comments

README.md

@@ -2,8 +2,8 @@
 
 ## Make these badges green
 
-[![Build Status](https://travis-ci.org/bast/python-tdd-exercises.svg?branch=master)](https://travis-ci.org/bast/python-tdd-exercises/builds)
-[![Coverage Status](https://coveralls.io/repos/bast/python-tdd-exercises/badge.png?branch=master)](https://coveralls.io/r/bast/python-tdd-exercises?branch=master)
+[![Build Status](https://travis-ci.org/luyi0629/python-tdd-exercises.svg?branch=master)](https://travis-ci.org/luyi0629/python-tdd-exercises/builds)
+[![Coverage Status](https://coveralls.io/repos/luyi0629/python-tdd-exercises/badge.png?branch=master)](https://coveralls.io/r/luyi0629/python-tdd-exercises?branch=master)
 
 After you fork, edit this `README.md` and rename "bast" to your GitHub username
 or namespace to make the badges point to your fork.
@@ -22,7 +22,7 @@ or namespace to make the badges point to your fork.
 - Login to [Travis CI](https://travis-ci.org) with your GitHub account and activate this repo for testing.
 - Login to [Coveralls](https://coveralls.io) with your GitHub account and activate this repo for code coverage analysis.
 - Implement missing functions to make the unit tests pass (run tests either locally or let Travis run them for you each time you push changes).
-- Increase the test coverage to 100% by making [all lines](https://coveralls.io/r/bast/python-tdd-exercises?branch=master) green.
+- Increase the test coverage to 100% by making [all lines](https://coveralls.io/r/luyi0629/python-tdd-exercises?branch=master) green.
 
 
 ## How to run tests locally (Linux or Mac OS X)

exercises.py

@@ -3,11 +3,12 @@ def reverse_list(l):
     """
     Reverses order of elements in list l.
     """
-    return None
-
+    reverse = l[::-1]
+    # or l.reverse()
+    return reverse
 
 def test_reverse_list():
-    assert reverse_list([1, 2, 3, 4, 5]) == [5, 4, 3, 2, 1]
+    assert reverse_list([1, 2, 3, 4, 5]) == [5,4,3,2,1]
 
 
 # ------------------------------------------------------------------------------
@@ -16,7 +17,8 @@ def reverse_string(s):
     """
     Reverses order of characters in string s.
     """
-    return None
+    reverse = s[::-1]
+    return reverse
 
 
 def test_reverse_string():
@@ -30,7 +32,12 @@ def is_english_vowel(c):
     Returns True if c is an english vowel
     and False otherwise.
     """
-    return None
+    vowels=['a','e','i','o','u','A','E','I','O','U']
+    if c in vowels:
+       out=True
+    else:
+       out=False
+    return out
 
 
 def test_is_english_vowel():
@@ -39,13 +46,13 @@ def test_is_english_vowel():
     assert is_english_vowel('i')
     assert is_english_vowel('o')
     assert is_english_vowel('u')
-    assert is_english_vowel('y')
+    assert not is_english_vowel('y')
     assert is_english_vowel('A')
     assert is_english_vowel('E')
     assert is_english_vowel('I')
     assert is_english_vowel('O')
     assert is_english_vowel('U')
-    assert is_english_vowel('Y')
+    assert not is_english_vowel('Y')
     assert not is_english_vowel('k')
     assert not is_english_vowel('z')
     assert not is_english_vowel('?')
@@ -57,20 +64,26 @@ def count_num_vowels(s):
     """
     Returns the number of vowels in a string s.
     """
-    return None
+    # use previous function is_english_vowel()
+    l = []
+    for c in s:
+        if is_english_vowel(c): 
+            l.append(True)
+    totnum = l.count(True) # or totnum = sum(l)
+    return totnum
 
 
 def test_count_num_vowels():
     sentence = "hey ho let's go"
-    assert count_num_vowels(sentence) == 5
+    assert count_num_vowels(sentence) == 4
     sentence = "HEY ho let's GO"
-    assert count_num_vowels(sentence) == 5
+    assert count_num_vowels(sentence) == 4
     paragraph = """She told me her name was Billie Jean,
                    as she caused a scene
                    Then every head turned with eyes
                    that dreamed of being the one
                    Who will dance on the floor in the round"""
-    assert count_num_vowels(paragraph) == 54
+    assert count_num_vowels(paragraph) == 52
 
 
 # ------------------------------------------------------------------------------
@@ -79,7 +92,10 @@ def histogram(l):
     """
     Converts a list of integers into a simple string histogram.
     """
-    return None
+    out = []  # initialise!
+    for i in l:
+       out.append('#'*i)
+    return "\n".join(out)  # turn the list into string with format!
 
 
 def test_histogram():
@@ -93,7 +109,10 @@ def get_word_lengths(s):
     Returns a list of integers representing
     the word lengths in string s.
     """
-    return None
+    out = []
+    for i in s.split():  # s.split(): splits the string into list
+        out.append(len(i))
+    return out
 
 
 def test_get_word_lengths():
@@ -108,7 +127,14 @@ def find_longest_word(s):
     Returns the longest word in string s.
     In case there are several, return the first.
     """
-    return None
+    # use previous function get_word_lengths()
+    w_length = get_word_lengths(s)
+    lengthmax = sorted(w_length)[-1]  # sorted(): returns a new sorted list while leaving the source unaltered
+    for i in s.split():
+        if len(i) == lengthmax:  # if the length of current element  equals to the max length, 
+           firstmax = i
+           break      # add 'break' to ensure the first one!
+    return firstmax
 
 
 def test_find_longest_word():
@@ -125,7 +151,20 @@ def validate_dna(s):
     Return True if the DNA string only contains characters
     a, c, t, or g (lower or uppercase). False otherwise.
     """
-    return None
+    # define the dna seq first
+    dna = 'atcgATCG'    
+    # idea: for each character in the string - test whether the character is dna - append the initialised list with T/F - after reading all characters, if sum(list) equals the length of string, then T, else F.
+    l = []
+    for c in s:
+        if c in dna:
+          l.append(True)
+        else:
+          l.append(False)
+    if sum(l) == len(s):
+        out=True
+    else:
+        out=False
+    return out
 
 
 def test_validate_dna():
@@ -141,7 +180,15 @@ def base_pair(c):
     of the base pair. If the base is not recognized,
     return 'unknown'.
     """
-    return None
+    # make a dictionary
+    map = {'a':'t', 't':'a', 'c':'g', 'g':'c', 'A':'t','T':'a', 'C':'g','G':'c'}
+    for k in map:
+       if k == c:
+          out = map[k] # note here out is not a list, so the value is replaced at each iteration. to ensure no replacement after a key is matched, add the next line to break the loop. 
+          break
+       else: 
+          out='unknown'  # loop until the last one, and if no match, the last value will be 'unknown'.
+    return out
 
 
 def test_base_pair():
@@ -164,7 +211,14 @@ def transcribe_dna_to_rna(s):
     Return string s with each letter T replaced by U.
     Result is always uppercase.
     """
-    return None
+    map = {'t':'U', 'T':'U'}
+    out = []
+    for c in s: 
+        if c in ['t', 'T']:
+            out.append(map[c])
+        else:
+            out.append(c.upper())  # list.upper() returns the uppercase
+    return "".join(out)   # again, turn the list into string with format
 
 
 def test_transcribe_dna_to_rna():
@@ -179,8 +233,13 @@ def get_complement(s):
     Return the DNA complement in uppercase
     (A -> T, T-> A, C -> G, G-> C).
     """
-    return None
-
+    # use previous function base_pair()
+    out = []
+    for c in s:
+        out.append(base_pair(c).upper())
+    return "".join(out) # again, turn the list into string with format
+# or in one line, use map function, apply the function to each element in the function.
+#     return ''.join(map(base_pair(s))).upper()
 
 def test_get_complement():
     assert get_complement('CCGGAAGAGCTTACTTAG') == 'GGCCTTCTCGAATGAATC'
@@ -194,7 +253,10 @@ def get_reverse_complement(s):
     Return the reverse complement of string s
     (complement reversed in order).
     """
-    return None
+    # use two functions defined earlier: get_complement() and reverse_string()
+    string = "".join(get_complement(s))
+    r_string = reverse_string(string)
+    return r_string
 
 
 def test_get_reverse_complement():
@@ -208,7 +270,8 @@ def remove_substring(substring, string):
     """
     Returns string with all occurrences of substring removed.
     """
-    return None
+    out = string.replace(substring, "") # note the replace() method!
+    return out
 
 
 def test_remove_substring():
@@ -226,8 +289,19 @@ def get_position_indices(triplet, dna):
     in a DNA sequence. We start counting from 0
     and jump by 3 characters from one position to the next.
     """
-    return None
-
+    # first split the seq by triplets
+    # use range(start, stop, step) to jump 
+    out = []
+    out_index = []
+    for i in range(0, len(dna), 3):
+        out.append(dna[i:i+3])
+    for j in range(0,len(out)):
+        if out[j] == triplet:
+            out_index.append(j)
+    return out_index
+#    l = []
+#    for i in range(len(dna)//3):  # // gives integer 
+#       if triplet == i   ....
 
 def test_get_position_indices():
     assert get_position_indices('GAA', 'CCGGAAGAGCTTACTTAG') == [1]
@@ -245,7 +319,29 @@ def get_3mer_usage_chart(s):
     The list is alphabetically sorted by the name
     of the 3-mer.
     """
-    return None
+    # compared to the above, here no need to define the step because moving the character one by one. but note the stop should be len(s)-2, otherwise the last two elements in the list would have < 3-mers. 
+    mylist = []
+    mylist2 = []
+    for i in range(0, len(s)-2):
+        mylist.append(s[i:i+3])
+    # use list(set()) to get the unique elements only:
+    uniqlist = list(set(mylist))
+    for j in sorted(uniqlist):
+        c = mylist.count(j)        
+        mylist2.append((j,c))
+    return mylist2
+#  can use dictionary instead! in the end, convert the dictionary to list using items() method.
+#  use += 1 to add to the counter! 
+# d = {}
+# for i in range(len(s)-2):
+#   kmer = s[i:i+3]
+#   if kmer in d: 
+#      d[kmer] += 1 
+#   else: 
+#      d[kmer] = 1 
+# l = list(d.iterms())
+# l.sort()
+# return l
 
 
 def test_get_3mer_usage_chart():
@@ -276,7 +372,13 @@ def read_column(file_name, column_number):
     Reads column column_number from file file_name
     and returns the values as floats in a list.
     """
-    return None
+    out = []
+    with open(file_name, 'r') as f: # r is read, w is write 
+       for line in f:
+          parts = line.split() # this will also create a first empty line!
+          if len(parts) > 0: 
+             out.append(float(parts[column_number-1])) # add float 
+    return out
 
 
 def test_read_column():
@@ -291,10 +393,12 @@ def test_read_column():
 4   0.4  0.004
 5   0.5  0.005
 6   0.6  0.006"""
+# this way the first line is empty.
+# if text = """1 0.1 .... , then it will not be a problem.
 
     # we save this text to a temporary file
     file_name = tempfile.mkstemp()[1]
-    with open(file_name, 'w') as f:
+    with open(file_name, 'w') as f:  # open it and write in text
         f.write(text)
 
     # and now we pass the file name to the function which will read the column
@@ -315,7 +419,20 @@ def character_statistics(file_name):
     Use the isalpha() method to figure out
     whether the character is in the alphabet.
     """
-    return None
+    d = {}  
+    with open(file_name, 'r') as f:
+      for c in f.read().lower():
+         if c.isalpha():
+            if c in d: # d is adding up! not just empty dictionary
+                d[c] += 1
+            else: 
+                d[c] = 1
+    l = list(d.items())
+    # then sort on the value, not the key!
+    l = sorted(l, key=lambda x: x[1], reverse = True) 
+    most = l[0][0]
+    least = l[-1][0]    
+    return (most, least)
 
 
 def test_character_statistics():
@@ -367,7 +484,7 @@ def test_character_statistics():
 
     # and now we pass the file name to the function which will get the stats
     (most_abundant, least_abundant) = character_statistics(file_name)
-    assert (most_abundant, least_abundant) == ('e', 'q')
+    assert (most_abundant, least_abundant) == ('e', 'z')  # here q and z are least abundant.
 
     # we remove the temporary file
     os.unlink(file_name)
@@ -393,4 +510,10 @@ def pythagorean_triples(n):
 # ------------------------------------------------------------------------------
 
 def test_pythagorean_triples():
-    pass  # so far we do not test anything, check also test coverage
+    assert pythagorean_triples(12) == [(3,4,5), (6,8,10)]
+#    pass  # so far we do not test anything, check also test coverage
+
+# in an interactive python session, can import this script.
+# import exercises 
+# then, just write the function name to run the funciton:
+# e.g. excercises.pythagorean_triples(200)