From d7afbd511d5bdb40d0d56e2392ac086009fbc74a Mon Sep 17 00:00:00 2001
From: Ian Beauregard <ian.beauregard@gmail.com>
Date: Tue, 11 Aug 2020 09:57:53 -0400
Subject: [PATCH] Better regex to match numbers in 03_classification

The previous regex would not match any decimal number where there is no "E" notation. Also added the option "+/-" sign in the "E" part.
---
 03_classification.ipynb | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/03_classification.ipynb b/03_classification.ipynb
index ca683d8..f088b87 100644
--- a/03_classification.ipynb
+++ b/03_classification.ipynb
@@ -2342,7 +2342,7 @@
     "                for url in urls:\n",
     "                    text = text.replace(url, \" URL \")\n",
     "            if self.replace_numbers:\n",
-    "                text = re.sub(r'\\d+(?:\\.\\d*(?:[eE]\\d+))?', 'NUMBER', text)\n",
+    "                text = re.sub(r'\\d+(?:\\.\\d*)?(?:[eE][+-]?\\d+)?', 'NUMBER', text)\n",
     "            if self.remove_punctuation:\n",
     "                text = re.sub(r'\\W+', ' ', text, flags=re.M)\n",
     "            word_counts = Counter(text.split())\n",