correcting mistake

labeling_data/labeling_occupation_data_with_Wikipedia_and_GoogleNews.ipynb

@@ -159,7 +159,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Closely inspecting the DataFrame reveals that some rows are near duplicates with differing amounts in the occurence counts and description fields. We wish to retain the higher of the two occurence counts, and otherwise colasce multiple rows."
+    "## Closely inspecting the DataFrame reveals that some rows are near duplicates with differing amounts in the occurence counts and description fields. We wish to retain the higher of the two occurence counts, and otherwise coalesce multiple rows."
    ]
   },
   {
@@ -831,7 +831,6 @@
    "source": [
     "# Strategies for Deciding Which Items to Label\n",
     "* random selections\n",
-    "* Kmeans clustering (on embeddings)\n",
     "* suffix analysis"
    ]
   },
@@ -850,19 +849,12 @@
     "        fout.write(f'\"{word}\",\\n')"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## KMeans\n",
-    "KMeans clustering can increase the chances that you'll a representative sampling by selecting from clusters in the feature space. This is very helpful with multidimensional data. However, with single string occupation labeling such as we are doing, sampling from character features--such as via suffix analysis, is likely more helpful."
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "# Suffix Analysis\n",
+    "With single string occupation labeling such as we are doing, sampling from character features--such as via suffix analysis, is likely helpful.\n",
     "A large amount of domain information is typically encoded into the suffix of word. Let's group by the word endings and take a look."
    ]
   },
@@ -2021,7 +2013,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -2035,9 +2027,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.0"
+   "version": "3.9.5"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 2
-}
+}