#85 Savepoint

senzing-garage · Sep 27, 2024 · d5c487e · d5c487e
1 parent 6474927
commit d5c487e
Show file tree

Hide file tree

Showing 5 changed files with 76 additions and 52 deletions.
diff --git a/rootfs/notebooks/load_truthsets.ipynb b/rootfs/notebooks/load_truthsets.ipynb
@@ -172,9 +172,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sz_abstract_factory = SzAbstractFactory(\n",
-    "    grpc_channel=grpc.insecure_channel(\"localhost:8261\")\n",
-    ")\n",
     "sz_config = sz_abstract_factory.create_sz_config()\n",
     "sz_configmanager = sz_abstract_factory.create_sz_configmanager()\n",
     "sz_diagnostic = sz_abstract_factory.create_sz_diagnostic()\n",

diff --git a/rootfs/notebooks/load_user_data.ipynb b/rootfs/notebooks/load_user_data.ipynb
@@ -5,7 +5,7 @@
    "id": "671ae8b2-3d6a-4802-a544-2ca4c66a2497",
    "metadata": {},
    "source": [
-    "# Load Senzing truth-sets\n",
+    "# Load user data\n",
     "\n",
     "These instructions show how to load user data into the Senzing engine."
    ]
@@ -52,7 +52,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "de03a1c2-d7b1-40a9-8154-1df47cd49fef",
    "metadata": {},
    "outputs": [],
@@ -72,7 +72,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "ff9189d1-852d-46b0-9e2e-36f524c9038e",
    "metadata": {},
    "outputs": [],
@@ -85,12 +85,12 @@
    "id": "a2f2238a-dc2c-4385-9c19-1633ee035bcd",
    "metadata": {},
    "source": [
-    "![Modify](img/pencil2.png) Identify uploaded file."
+    "![Modify](img/pencil2.png) **Modify the following.** Identify uploaded file."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "04555a6e-9c48-4a9b-b8b0-e7285b602fc8",
    "metadata": {},
    "outputs": [],
@@ -116,10 +116,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "id": "7f5cecdf-649a-4a8b-ad64-d2fc3f37166d",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found the following DATA_SOURCE values in the data: ['MY_DATASOURCE']\n"
+     ]
+    }
+   ],
    "source": [
     "datasources = []\n",
     "\n",
@@ -130,8 +138,7 @@
     "        if datasource not in datasources:\n",
     "            datasources.append(datasource)\n",
     "\n",
-    "print(f\"Found the following DATA_SOURCE values in the data: {datasources}\")\n",
-    "                "
+    "print(f\"Found the following DATA_SOURCE values in the data: {datasources}\")"
    ]
   },
   {
@@ -152,7 +159,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "3272f76c-dc95-4ff8-b573-8bddd55fb779",
    "metadata": {},
    "outputs": [],
@@ -172,14 +179,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "301ce7eb-9069-4c8d-a1c4-ebe8f78d1bf6",
    "metadata": {},
    "outputs": [],
    "source": [
-    "sz_abstract_factory = SzAbstractFactory(\n",
-    "    grpc_channel=grpc.insecure_channel(\"localhost:8261\")\n",
-    ")\n",
     "sz_config = sz_abstract_factory.create_sz_config()\n",
     "sz_configmanager = sz_abstract_factory.create_sz_configmanager()\n",
     "sz_diagnostic = sz_abstract_factory.create_sz_diagnostic()\n",
@@ -196,14 +200,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "id": "fbf17cc3-3273-4097-90a2-f0b9a21674a1",
    "metadata": {},
    "outputs": [],
    "source": [
     "old_config_id = sz_configmanager.get_default_config_id()\n",
     "old_json_config = sz_configmanager.get_config(old_config_id)\n",
-    "config_handle = sz_config.import_config(old_json_config)  "
+    "config_handle = sz_config.import_config(old_json_config)"
    ]
   },
   {
@@ -216,10 +220,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "id": "97854ac2-ad01-4663-9f6c-4afd816230f9",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\"id\":\"SZSDK60014001\",\"reason\":\"SENZ2208|Data source code [MY_DATASOURCE] already exists.\"}\n"
+     ]
+    }
+   ],
    "source": [
     "for datasource in datasources:\n",
     "    try:\n",
@@ -238,16 +250,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "32217742-9e09-4778-b7fe-1e23817251ec",
    "metadata": {},
    "outputs": [],
    "source": [
     "new_json_config = sz_config.export_config(config_handle)\n",
     "new_config_id = sz_configmanager.add_config(\n",
-    "    new_json_config, \"Add TruthSet datasources\"\n",
+    "    new_json_config, \"Add user datasources\"\n",
     ")\n",
-    "sz_configmanager.replace_default_config_id(old_config_id, new_config_id)    "
+    "sz_configmanager.replace_default_config_id(old_config_id, new_config_id)"
    ]
   },
   {
@@ -260,7 +272,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "id": "df805089-7a9a-4e4e-b959-c320819e855b",
    "metadata": {},
    "outputs": [],
@@ -287,14 +299,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "id": "cb8318ec-cd73-4e43-8349-586c8dd0dbfb",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\"DATA_SOURCE\":\"MY_DATASOURCE\",\"RECORD_ID\":\"157616467\",\"AFFECTED_ENTITIES\":[],\"INTERESTING_ENTITIES\":{\"ENTITIES\":[]}}\n",
+      "{\"DATA_SOURCE\":\"MY_DATASOURCE\",\"RECORD_ID\":\"115212881\",\"AFFECTED_ENTITIES\":[],\"INTERESTING_ENTITIES\":{\"ENTITIES\":[]}}\n",
+      "{\"DATA_SOURCE\":\"MY_DATASOURCE\",\"RECORD_ID\":\"645217904\",\"AFFECTED_ENTITIES\":[],\"INTERESTING_ENTITIES\":{\"ENTITIES\":[]}}\n",
+      "{\"DATA_SOURCE\":\"MY_DATASOURCE\",\"RECORD_ID\":\"212359276\",\"AFFECTED_ENTITIES\":[],\"INTERESTING_ENTITIES\":{\"ENTITIES\":[]}}\n",
+      "{\"DATA_SOURCE\":\"MY_DATASOURCE\",\"RECORD_ID\":\"526429955\",\"AFFECTED_ENTITIES\":[],\"INTERESTING_ENTITIES\":{\"ENTITIES\":[]}}\n",
+      "{\"DATA_SOURCE\":\"MY_DATASOURCE\",\"RECORD_ID\":\"604947448\",\"AFFECTED_ENTITIES\":[],\"INTERESTING_ENTITIES\":{\"ENTITIES\":[]}}\n",
+      "{\"DATA_SOURCE\":\"MY_DATASOURCE\",\"RECORD_ID\":\"513789670\",\"AFFECTED_ENTITIES\":[],\"INTERESTING_ENTITIES\":{\"ENTITIES\":[]}}\n",
+      "{\"DATA_SOURCE\":\"MY_DATASOURCE\",\"RECORD_ID\":\"212442489\",\"AFFECTED_ENTITIES\":[],\"INTERESTING_ENTITIES\":{\"ENTITIES\":[]}}\n"
+     ]
+    }
+   ],
    "source": [
     "with open(filepath, \"r\") as file:\n",
     "    for line in file:\n",
-    "        try: \n",
+    "        try:\n",
     "            line_as_dict = json.loads(line)\n",
     "            info = sz_engine.add_record(\n",
     "                line_as_dict.get(\"DATA_SOURCE\"),\n",
@@ -304,7 +331,7 @@
     "            )\n",
     "            print(info)\n",
     "        except SzError as err:\n",
-    "            print(err)                "
+    "            print(err)"
    ]
   }
  ],

diff --git a/src/senzing_quickstart/hello_world.py b/src/senzing_quickstart/hello_world.py
@@ -2,9 +2,9 @@
 # coding: utf-8
 
 # # Senzing Hello World
-#
+# 
 # The following is a quick test of connectivity to Senzing using Python over gRPC.
-#
+# 
 
 # Import python packages.
 
@@ -16,6 +16,7 @@
 import grpc
 from senzing_grpc import SzAbstractFactory
 
+
 # Create an abstract factory for accessing Senzing via gRPC.
 
 # In[ ]:
@@ -40,3 +41,4 @@
 
 
 print(json.dumps(json.loads(sz_product.get_version()), indent=2))
+
diff --git a/src/senzing_quickstart/load_truthsets.py b/src/senzing_quickstart/load_truthsets.py
@@ -2,9 +2,9 @@
 # coding: utf-8
 
 # # Load Senzing truth-sets
-#
+# 
 # These instructions load the [Senzing truth-sets] into the Senzing engine.
-#
+# 
 # [Senzing truth-sets]: https://github.com/Senzing/truth-sets
 
 # ## Prepare Python enviroment
@@ -21,6 +21,7 @@
 import requests
 from senzing_grpc import SzAbstractFactory, SzEngineFlags, SzError
 
+
 # Set environment specific variables.
 
 # In[ ]:
@@ -68,6 +69,7 @@
                 datasources.append(datasource)
 
 print(f"Found the following DATA_SOURCE values in the data: {datasources}")
+
 
 
 # ## Update Senzing configuration
@@ -87,9 +89,6 @@
 # In[ ]:
 
 
-sz_abstract_factory = SzAbstractFactory(
-    grpc_channel=grpc.insecure_channel("localhost:8261")
-)
 sz_config = sz_abstract_factory.create_sz_config()
 sz_configmanager = sz_abstract_factory.create_sz_configmanager()
 sz_diagnostic = sz_abstract_factory.create_sz_diagnostic()
@@ -103,7 +102,7 @@
 
 old_config_id = sz_configmanager.get_default_config_id()
 old_json_config = sz_configmanager.get_config(old_config_id)
-config_handle = sz_config.import_config(old_json_config)
+config_handle = sz_config.import_config(old_json_config)  
 
 
 # Add DataSources to Senzing configuration.
@@ -124,8 +123,10 @@
 
 
 new_json_config = sz_config.export_config(config_handle)
-new_config_id = sz_configmanager.add_config(new_json_config, "Add TruthSet datasources")
-sz_configmanager.replace_default_config_id(old_config_id, new_config_id)
+new_config_id = sz_configmanager.add_config(
+    new_json_config, "Add TruthSet datasources"
+)
+sz_configmanager.replace_default_config_id(old_config_id, new_config_id)    
 
 
 # With the change in Senzing configuration, Senzing objects need to be updated.
@@ -148,7 +149,7 @@
     filepath = home_path + filename
     with open(filepath, "r") as file:
         for line in file:
-            try:
+            try: 
                 line_as_dict = json.loads(line)
                 info = sz_engine.add_record(
                     line_as_dict.get("DATA_SOURCE"),
@@ -158,7 +159,7 @@
                 )
                 print(info)
             except SzError as err:
-                print(err)
+                print(err)                
 
 
 # ## View results
@@ -183,3 +184,4 @@
 }
 search_result = sz_engine.search_by_attributes(json.dumps(search_query))
 print(json.dumps(json.loads(search_result), indent=2))
+
diff --git a/src/senzing_quickstart/load_user_data.py b/src/senzing_quickstart/load_user_data.py
@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # coding: utf-8
 
-# # Load Senzing truth-sets
+# # Load user data
 # 
 # These instructions show how to load user data into the Senzing engine.
 
@@ -37,7 +37,7 @@
 home_path = "/notebooks/"
 
 
-# ![Modify](img/pencil2.png) Identify uploaded file.
+# ![Modify](img/pencil2.png) **Modify the following.** Identify uploaded file.
 
 # In[ ]:
 
@@ -62,7 +62,6 @@
             datasources.append(datasource)
 
 print(f"Found the following DATA_SOURCE values in the data: {datasources}")
-
 
 
 # ## Update Senzing configuration
@@ -82,9 +81,6 @@
 # In[ ]:
 
 
-sz_abstract_factory = SzAbstractFactory(
-    grpc_channel=grpc.insecure_channel("localhost:8261")
-)
 sz_config = sz_abstract_factory.create_sz_config()
 sz_configmanager = sz_abstract_factory.create_sz_configmanager()
 sz_diagnostic = sz_abstract_factory.create_sz_diagnostic()
@@ -98,7 +94,7 @@
 
 old_config_id = sz_configmanager.get_default_config_id()
 old_json_config = sz_configmanager.get_config(old_config_id)
-config_handle = sz_config.import_config(old_json_config)  
+config_handle = sz_config.import_config(old_json_config)
 
 
 # Add DataSources to Senzing configuration.
@@ -120,9 +116,9 @@
 
 new_json_config = sz_config.export_config(config_handle)
 new_config_id = sz_configmanager.add_config(
-    new_json_config, "Add TruthSet datasources"
+    new_json_config, "Add user datasources"
 )
-sz_configmanager.replace_default_config_id(old_config_id, new_config_id)    
+sz_configmanager.replace_default_config_id(old_config_id, new_config_id)
 
 
 # With the change in Senzing configuration, Senzing objects need to be updated.
@@ -143,7 +139,7 @@
 
 with open(filepath, "r") as file:
     for line in file:
-        try: 
+        try:
             line_as_dict = json.loads(line)
             info = sz_engine.add_record(
                 line_as_dict.get("DATA_SOURCE"),
@@ -153,5 +149,5 @@
             )
             print(info)
         except SzError as err:
-            print(err)                
+            print(err)