Massive renaming!

20-plugins/plugins-src/compile.sh

@@ -0,0 +1,2 @@
+python -m compileall .
+cp *.pyc ../plugins

20-plugins/plugins-src/frequencies1.py

@@ -0,0 +1,11 @@
+import operator
+
+def top25(word_list):
+    word_freqs = {}
+    for w in word_list:
+        if w in word_freqs:
+            word_freqs[w] += 1
+        else:
+            word_freqs[w] = 1
+    return sorted(word_freqs.items(), key=operator.itemgetter(1), reverse=True)[:25]
+

20-plugins/plugins-src/frequencies2.py

@@ -0,0 +1,6 @@
+import operator, collections
+
+def top25(word_list):
+    counts = collections.Counter(w for w in word_list)
+    return counts.most_common(25)
+

20-plugins/plugins-src/words1.py

@@ -0,0 +1,14 @@
+import sys, re, string
+
+def extract_words(path_to_file):
+    with open(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]
+

20-plugins/plugins-src/words2.py

@@ -0,0 +1,7 @@
+import sys, re, string
+
+def extract_words(path_to_file):
+    words = re.findall('[a-z]{2,}', open(path_to_file).read().lower())
+    stopwords = set(open('../stop_words.txt').read().split(','))
+    return [w for w in words if w not in stopwords]
+