diff --git a/src/languedoc/predict.py b/src/languedoc/predict.py
--- a/src/languedoc/predict.py
+++ b/src/languedoc/predict.py
@@ -14,39 +14,37 @@ def preprocess(text: str) -> str:
 	return text.lower()
 
 
-def extract_kgram_freqs(text, k):
+def extract_kgram_counts(text, k):
 	n = len(text)
-	d = dict()
+	counts = dict()
 
 	for i in range(0, n-k+1):
 		key = text[i:i+k]
 		if key.isspace():
 			continue
 
-		d[key] = d.get(key, 0) + 1
+		counts[key] = counts.get(key, 0) + 1
 
-	count = sum(d.values())
-
-	return {key: val/count for (key, val) in d.items()}
+	return counts
 
 
-def extract_ngram_freqs(text):
-	frequencies = {}
+def extract_ngram_counts(text):
+	counts = dict()
 
 	for k in range(1, 4):
-		frequencies.update(extract_kgram_freqs(text, k))
+		counts.update(extract_kgram_counts(text, k))
 
-	return frequencies
+	return counts
 
 
-def rank_ngram_freqs(frequencies):
-	ordered_ngrams = sorted(frequencies.items(), key=lambda kv: (-kv[1], len(kv[0]), kv[0]))[:TOP_NGRAM_COUNT]
+def rank_ngram_counts(counts):
+	ordered_ngrams = sorted(counts.items(), key=lambda kv: (-kv[1], len(kv[0]), kv[0]))[:TOP_NGRAM_COUNT]
 	return dict(zip([key for (key, freq) in ordered_ngrams], itertools.count(0)))
 
 
 def extract_ranked_ngrams(text):
-	frequencies = extract_ngram_freqs(text)
-	return rank_ngram_freqs(frequencies)
+	counts = extract_ngram_counts(text)
+	return rank_ngram_counts(counts)
 
 
 class Sample: