Added style #17

17-introspective/README.md

@@ -0,0 +1,15 @@
+Style #17
+==============================
+
+Constraints:
+
+- The problem is decomposed using some form of abstraction (procedures, functions, objects, etc.)
+
+- The abstractions have access to information about themselves, although they cannot modify that information
+
+
+Possible names:
+
+- Introspective
+- Navel-gazing
+

17-introspective/tf-17.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python
+
+import sys, re, operator, string, inspect
+
+#
+# The functions
+#
+def extract_words(path_to_file):
+    """
+    Takes a path to a file and returns the non-stop
+    words, after properly removing nonalphanumeric chars
+    and normalizing for lower case
+    """
+    print "My name is " + inspect.stack()[0][3] + " and my arguments are " + str(locals().keys())
+    with open(locals()['path_to_file']) as f:
+        str_data = f.read()
+    pattern = re.compile('[\W_]+')
+    word_list = pattern.sub(' ', str_data).lower().split()
+    with open('../stop_words.txt') as f:
+        stop_words = f.read().split(',')
+    stop_words.extend(list(string.ascii_lowercase))
+    return [w for w in word_list if not w in stop_words]
+
+def frequencies(word_list):
+    """
+    Takes a list of words and returns a dictionary associating
+    words with frequencies of occurrence
+    """
+    print "My name is " + inspect.stack()[0][3] + " and my arguments are " + str(locals().keys())
+    word_freqs = {}
+    for w in locals()['word_list']:
+        if w in word_freqs:
+            word_freqs[w] += 1
+        else:
+            word_freqs[w] = 1
+    return word_freqs
+
+def sort(word_freq):
+    """
+    Takes a dictionary of words and their frequencies
+    and returns a list of pairs where the entries are
+    sorted by frequency 
+    """
+    print "My name is " + inspect.stack()[0][3] + " and my arguments are " + str(locals().keys())
+    return sorted(locals()['word_freq'].iteritems(), key=operator.itemgetter(1), reverse=True)
+
+#
+# The main function
+#
+word_freqs = sort(frequencies(extract_words(sys.argv[1])))
+
+for tf in word_freqs[0:25]:
+    print tf[0], ' - ', tf[1]
+