Compute confidence scores by char, word or line

Closes #33 (closed)

dan/predict/prediction.py

@@ -218,14 +218,11 @@ def compute_prob_by_separator(characters, probabilities, separator):
     # match anything except separators, get start and end index
     pattern = re.compile(f"[^{separator.pattern}]+")
     matches = [(m.start(), m.end()) for m in re.finditer(pattern, characters)]
+    return [
+        np.mean(probabilities[start:end])
+        for (start, end) in matches
+    ]
 
-    # Iterate over text pieces and compute mean confidence
-    probs = []
-    for match in matches:
-        start = match[0]
-        end = match[1]
-        probs.append(np.mean(probabilities[start:end]))
-    return probs
 
 
 def run(