From 1dd80c11aaa5b2f94988767d9f647a49840423f4 Mon Sep 17 00:00:00 2001
From: Claudio Scheer <claudioscheer@protonmail.com>
Date: Sat, 23 May 2020 20:21:54 -0300
Subject: [PATCH] Download nltk punkt

---
 notebooks/data_loader.ipynb | 35 +++++++++++++++++++++++++++++------
 1 file changed, 29 insertions(+), 6 deletions(-)

diff --git a/notebooks/data_loader.ipynb b/notebooks/data_loader.ipynb
index 3e6ea42..c1a1880 100644
--- a/notebooks/data_loader.ipynb
+++ b/notebooks/data_loader.ipynb
@@ -35,19 +35,42 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 3,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2020-05-23T21:04:37.477348Z",
-     "start_time": "2020-05-23T21:04:37.475048Z"
+     "end_time": "2020-05-23T23:20:55.848368Z",
+     "start_time": "2020-05-23T23:20:54.138572Z"
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package punkt to /home/water/nltk_data...\n",
+      "[nltk_data]   Package punkt is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "import os\n",
     "import pandas as pd\n",
     "import numpy as np\n",
-    "from nltk.tokenize import word_tokenize"
+    "import nltk\n",
+    "from nltk.tokenize import word_tokenize\n",
+    "\n",
+    "\n",
+    "nltk.download(\"punkt\")"
    ]
   },
   {
@@ -280,7 +303,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "At least, we go through all the sentences in the dataset and create the token dictionary."
+    "Finally, we go through all the sentences in the dataset and create the token dictionary."
    ]
   },
   {
-- 
GitLab