Bugfix: Data race during xf diff (#21)

gretelai · Dec 9, 2020 · 64d9db8 · 64d9db8
1 parent 2659bdb
commit 64d9db8
Showing 1 changed file with 14 additions and 17 deletions.
diff --git a/gretel/gc-nlp_text_analysis/blueprint.ipynb b/gretel/gc-nlp_text_analysis/blueprint.ipynb
@@ -94,7 +94,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "project = client.get_project(create=True)"
+    "project = client.get_project(display_name=\"Blueprint: NLP Text Analysis\", create=True)"
    ]
   },
   {
@@ -217,13 +217,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "orig_records = [record for record in project.iter_records(direction=\"backward\")]\n",
+    "\n",
     "xf_records = [\n",
-    "    pipeline.transform_record(record)[\"record\"]\n",
+    "    pipeline.transform_record(record)\n",
     "    for record in \n",
-    "    project.iter_records(direction=\"backward\")\n",
-    "]\n",
-    "\n",
-    "xf_df = pd.DataFrame(xf_records)"
+    "    orig_records\n",
+    "]\n"
    ]
   },
   {
@@ -242,17 +242,14 @@
     "from gretel_client.demo_helpers import show_record_diff\n",
     "\n",
     "\n",
-    "# Lookup the comparison email by subject line.\n",
-    "c_key = \"subject_line\"\n",
-    "c_value = \"Confidentiality Agreement-Human Code\"\n",
-    "\n",
-    "# The comparison email contains multiple lines. For this\n",
-    "# demonstration we only want to examine the first line \n",
-    "# so we strip any extraneous newlines.\n",
-    "orig = source_df[source_df[c_key] == c_value][TEXT_FIELD].iloc[0].split(\"\\n\")[0]\n",
-    "xf = xf_df[xf_df[c_key] == c_value][TEXT_FIELD].iloc[0].split(\"\\n\")[0]\n",
-    "\n",
-    "show_record_diff({\"\": orig}, {\"\": xf})"
+    "for orig, xf in zip(orig_records, xf_records):\n",
+    "    # Take the first line of text from each record\n",
+    "    orig_line = orig[\"record\"][TEXT_FIELD].split(\"\\n\")[0]\n",
+    "    xf_line = xf[\"record\"][TEXT_FIELD].split(\"\\n\")[0]\n",
+    "    \n",
+    "    if orig_line != xf_line:\n",
+    "        show_record_diff({\"\": orig_line}, {\"\": xf_line})\n",
+    "        input(\"\\nPress [enter] to compare the next record\")\n"
    ]
   },
   {