Track existing code

.gitignore

@@ -0,0 +1,5 @@
+[._]*.s[a-w][a-z]
+[._]s[a-w][a-z]
+*.pyc
+lib
+pyStatParser

code_random_text.py

@@ -0,0 +1,11 @@
+import nltk
+# Natural Language Toolkit: code_random_text
+
+def generate_model(cfdist, word, num=15):
+    for i in range(num):
+        print word,
+        word = cfdist[word].max()
+
+text = nltk.corpus.genesis.words('english-kjv.txt')
+bigrams = nltk.bigrams(text)
+cfd = nltk.ConditionalFreqDist(bigrams) # [_bigram-condition]

generate_poem.py

@@ -0,0 +1,26 @@
+import nltk
+import random
+from stat_parser import Parser
+
+
+class PoemGenerator():
+    def __init__(self, corpus):
+        self.sents = corpus.sents('austen-emma.txt')
+        self.bigrams = list(nltk.bigrams(corpus.words('austen-emma.txt')))
+        self.cfd = nltk.ConditionalFreqDist(self.bigrams)
+        self.parser = Parser()
+        self.history = []
+
+    def generate_poem(self):
+        sent = random.choice(self.sents)
+        parsed = self.parser.parse(' '.join(sent))
+        word = random.choice(self.bigrams)[0]
+        for i in range(15):
+            print word,
+            for gram in self.cfd[word].items():
+                import ipdb; ipdb.set_trace()  # BREAKPOINT
+
+
+if __name__ == '__main__':
+    generator = PoemGenerator(nltk.corpus.gutenberg)
+    print generator.generate_poem()

generate_random.py

@@ -0,0 +1,16 @@
+import nltk
+import random
+
+TEXT = nltk.corpus.genesis.words('english-kjv.txt')
+
+
+def main():
+    bigrams = nltk.bigrams(TEXT)
+    cfdist = nltk.ConditionalFreqDist(bigrams)
+    word = random.choice(bigrams)[0]
+    for i in range(15):
+        print word,
+        word = cfdist[word].max()
+
+if __name__ == '__main__':
+    main()