Update CEN_SKILLNETslice_overview.ipynb

Updated notebook: added variable "person of interest" to avoid confusion having to enter it two times (for sender/receiver), now only once.
lilimelgar · Jan 6, 2023 · eb7e3ef · eb7e3ef
1 parent a01710f
commit eb7e3ef
Showing 1 changed file with 17 additions and 6 deletions.
diff --git a/src/CEN_SKILLNETslice_overview.ipynb b/src/CEN_SKILLNETslice_overview.ipynb
@@ -326,7 +326,7 @@
     "        cen_letters_imp[column] = cen_letters_imp[column].astype(str)\n",
     "        \n",
     "# # Handle exceptions\n",
-    "cen_letters_imp['emloLetterId_inferredSK'] = cen_letters_imp['emloLetterId_inferredSK'].astype(str)\n",
+    "# cen_letters_imp['emloLetterId_inferredSK'] = cen_letters_imp['emloLetterId_inferredSK'].astype(str)\n",
     "\n",
     "# make a copy\n",
     "cen_letters = cen_letters_imp.copy()"
@@ -971,7 +971,7 @@
    "outputs": [],
    "source": [
     "# date-related columns\n",
-    "letters_dates_df = cen_letters[['SKletterId','ISBD_OriginalCEN', 'titleOriginal', 'YEAR_Original', 'yearItem_start','yearItem_end', 'isYearRange', 'yearRangeType', 'isYearRangeInferredSk', 'isYearItemInferredSk', 'isYearItemInferredSk', 'isYearItemUncertain', 'DATERING_OriginalCEN','dayDatingSk', 'monthDatingSk', 'isDateringUncertain']]\n",
+    "letters_dates_df = cen_letters[['SKletterId','ISBD_OriginalCEN', 'TITLE_Original', 'YEAR_Original', 'yearItem_start','yearItem_end', 'isYearRange', 'yearRangeType', 'isYearRangeInferredSk', 'isYearItemInferredSk', 'isYearItemInferredSk', 'isYearItemUncertain', 'DATERING_OriginalCEN','dayDatingSk', 'monthDatingSk', 'isDateringUncertain']]\n",
     "# date-related columns to display with original data\n",
     "letters_dates_original_df = letters_dates_df[['SKletterId','YEAR_Original', 'DATERING_OriginalCEN']]\n",
     "letters_dates_original_df.head(500)"
@@ -1283,9 +1283,9 @@
    "outputs": [],
    "source": [
     "# person-related columns from letters file\n",
-    "letters_persons_df = cen_letters[['SKletterId','ISBD_OriginalCEN', 'titleOriginal', 'AFZENDER_OriginalCEN','isUncertainAfzender', 'ONTVANGER_OriginalCEN', 'isUncertainOntvanger']]\n",
+    "letters_persons_df = cen_letters[['SKletterId','ISBD_OriginalCEN', 'TITLE_Original', 'AFZENDER_OriginalCEN','isUncertainAfzender', 'ONTVANGER_OriginalCEN', 'isUncertainOntvanger']]\n",
     "# person-related columns to display with original data\n",
-    "letters_persons_original_df = letters_persons_df[['SKletterId','ISBD_OriginalCEN', 'titleOriginal', 'AFZENDER_OriginalCEN','ONTVANGER_OriginalCEN']]\n",
+    "letters_persons_original_df = letters_persons_df[['SKletterId','ISBD_OriginalCEN', 'TITLE_Original', 'AFZENDER_OriginalCEN','ONTVANGER_OriginalCEN']]\n",
     "letters_persons_original_df.head(50)"
    ]
   },
@@ -1919,6 +1919,17 @@
     "person_of_interest.reset_index(drop=True)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "34934b34",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Second step: paste the person Id below (inside the quotation marks)\n",
+    "person_of_interest = 'skp008594'"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -1928,8 +1939,8 @@
    },
    "outputs": [],
    "source": [
-    "# Second step: paste the person Id below (don't forget to paste it two times!):\n",
-    "firstDegree_df = cen_letters[(cen_letters.SKpersonId_sender.str.contains('skp002285')) | (cen_letters.SKpersonId_receiver.str.contains('skp002285'))]"
+    "\n",
+    "firstDegree_df = cen_letters[(cen_letters.SKpersonId_sender.str.contains(person_of_interest)) | (cen_letters.SKpersonId_receiver.str.contains(person_of_interest))]"
    ]
   },
   {