Merge pull request #532 from dwvisser/some-small-notebook-improvements

document similarity notebook: Remove unneeded imports, fix set_option call, remove unneeded list construction
amaiya · Jul 9, 2024 · fdbeda6 · fdbeda6
2 parents 59c876a + 329a2bb
commit fdbeda6
Showing 1 changed file with 3 additions and 5 deletions.
diff --git a/examples/text/20newsgroups-document_similarity_scorer.ipynb b/examples/text/20newsgroups-document_similarity_scorer.ipynb
@@ -9,10 +9,8 @@
     "%reload_ext autoreload\n",
     "%autoreload 2\n",
     "%matplotlib inline\n",
-    "import os\n",
-    "import numpy as np\n",
     "import pandas as pd\n",
-    "pd.set_option('display.max_colwidth', -1)"
+    "pd.set_option('display.max_colwidth', None)"
    ]
   },
   {
@@ -402,7 +400,7 @@
    "source": [
     "# display results in Pandas dataframe\n",
     "other_preds = [int(score > 0) for score in other_scores]\n",
-    "data = sorted(list(zip(other_preds, other_scores, other_texts)), key=lambda item:item[1], reverse=True)\n",
+    "data = sorted(zip(other_preds, other_scores, other_texts), key=lambda item:item[1], reverse=True)\n",
     "print('Top Inliers (or Most Similar to Our Technology-Related Topics')\n",
     "print('\\t\\tNumber of Predicted Inliners: %s' % sum(other_preds))\n",
     "df = pd.DataFrame(data, columns=['Prediction', 'Score', 'Text'])\n",
@@ -841,7 +839,7 @@
     "\n",
     "# display results in Pandas dataframe\n",
     "other_preds = [int(score > 0) for score in other_scores]\n",
-    "data = sorted(list(zip(other_preds, other_scores, other_texts)), key=lambda item:item[1], reverse=True)\n",
+    "data = sorted(zip(other_preds, other_scores, other_texts), key=lambda item:item[1], reverse=True)\n",
     "print('Top Inliers (or Most Similar to Our Technology-Related Topics')\n",
     "print('\\t\\tNumber of Predicted Inliners: %s' % sum(other_preds))\n",
     "df = pd.DataFrame(data, columns=['Prediction', 'Score', 'Text'])\n",