Skip to content

Commit b51ebad

Browse files
committed
Add printed info on token stripping
1 parent d6f5b05 commit b51ebad

File tree

2 files changed

+5
-1
lines changed

2 files changed

+5
-1
lines changed

part1/src/main/java/Classify.java

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -105,6 +105,11 @@ private static void testAccuracyOfClassifier(SpamEmailClassifier classifier, Lis
105105
double accuracy = ((double) numCorrectlyClassified / testEmails.size()) * 100;
106106
String accuracyString = String.format("%.3f", accuracy);
107107

108+
double percentOfTokensRemoved = ((double) EmailTokenizer.tokensStripped / EmailTokenizer.tokensParsed) * 100;
109+
String percentOfTokensRemovedString = String.format("%.3f", percentOfTokensRemoved);
110+
System.out.println("Stripped " + percentOfTokensRemovedString + "% of tokens.");
111+
System.out.println(EmailTokenizer.tokensAccepted + "/" + EmailTokenizer.tokensParsed + " tokens remaining.");
112+
108113
System.out.println("\nAccuracy of " + classifier.getAlgorithmName() + " was " + accuracyString + "%.");
109114
System.out.println(numCorrectlyClassified + "/" + testEmails.size() + " emails classified correctly.");
110115
}

part1/src/main/java/EmailTokenizer.java

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -229,7 +229,6 @@ public List<String> tokenizeEmail(EmailData email) {
229229
if (token.matches(dollarAmountRegex)) {
230230
token = "dollaramount";
231231
}
232-
233232
tokens.add(token);
234233
tokensAccepted++;
235234
}

0 commit comments

Comments
 (0)