Make sure Windows uses UTF-8 encoding

mchesterkadwell · Feb 25, 2021 · bfb6ec7 · bfb6ec7
1 parent 9efe2b1
commit bfb6ec7
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/4-cleaning-and-exploring-text.ipynb b/4-cleaning-and-exploring-text.ipynb
@@ -60,7 +60,7 @@
     "text_file = Path('data', 'PREPPED-2199-0.txt')\n",
     "\n",
     "# Open the file, read it and store the text with the name `iliad`\n",
-    "with open(text_file) as file:\n",
+    "with open(text_file, encoding='utf-8') as file:\n",
     "    iliad = file.read()\n",
     "\n",
     "iliad[0:200]"
@@ -311,7 +311,7 @@
     "tokens_file = Path('data', 'CLEAN-2199-0.txt')\n",
     "\n",
     "# Open a file and save the list of tokens inside it\n",
-    "with open(tokens_file, 'w') as file:\n",
+    "with open(tokens_file, 'w', encoding='utf-8') as file:\n",
     "    file.writelines(' '.join(tokens))"
    ]
   },

diff --git a/5-analysis-and-visualisation.ipynb b/5-analysis-and-visualisation.ipynb
@@ -28,7 +28,7 @@
     "tokens = []\n",
     "\n",
     "# Open the text file and append all the words to a list of tokens\n",
-    "with open(tokens_file) as file:\n",
+    "with open(tokens_file, encoding='utf-8') as file:\n",
     "    for token in file.read().split():\n",
     "        tokens.append(token)\n",
     "\n",