From 209c1a12e8d1e314263bceb6b86c5c741dc3b22e Mon Sep 17 00:00:00 2001
From: Colin Jarvis <colintjarvis@gmail.com>
Date: Wed, 26 Oct 2022 16:30:38 +0100
Subject: [PATCH] Resolved PR comments from Boris

---
 .gitignore                                    |  3 +-
 ...ering_for_transaction_classification.ipynb |  5 +--
 ...lass_classification_for_transactions.ipynb | 41 ++++++++-----------
 examples/helpers.py                           |  1 +
 4 files changed, 20 insertions(+), 30 deletions(-)
 create mode 100644 examples/helpers.py

diff --git a/.gitignore b/.gitignore
index d4fa226..32d0573 100644
--- a/.gitignore
+++ b/.gitignore
@@ -128,8 +128,7 @@ dmypy.json
 # Pyre type checker
 .pyre/
 
-# helpers
-*helpers.py
+# Data
 *transactions*.jsonl
 /examples/data/transactions*
 *.DS_Store
diff --git a/examples/Clustering_for_transaction_classification.ipynb b/examples/Clustering_for_transaction_classification.ipynb
index 7071452..e4c3db5 100644
--- a/examples/Clustering_for_transaction_classification.ipynb
+++ b/examples/Clustering_for_transaction_classification.ipynb
@@ -41,10 +41,9 @@
     "from sklearn.manifold import TSNE\n",
     "import matplotlib\n",
     "import matplotlib.pyplot as plt\n",
+    "import os\n",
     "\n",
-    "from helpers import OPENAI_API_KEY\n",
-    "\n",
-    "openai.api_key = OPENAI_API_KEY\n",
+    "openai.api_key = os.getenv(\"OPENAI_API_KEY\")\n",
     "COMPLETIONS_MODEL = \"text-davinci-002\"\n",
     "\n",
     "# This path leads to a file with embeddings created in the notebook linked above\n",
diff --git a/examples/Multiclass_classification_for_transactions.ipynb b/examples/Multiclass_classification_for_transactions.ipynb
index 7029ff2..2fd531d 100644
--- a/examples/Multiclass_classification_for_transactions.ipynb
+++ b/examples/Multiclass_classification_for_transactions.ipynb
@@ -40,10 +40,10 @@
     "import openai\n",
     "import pandas as pd\n",
     "import numpy as np\n",
+    "import json\n",
+    "import os\n",
     "\n",
-    "from helpers import OPENAI_API_KEY\n",
-    "\n",
-    "openai.api_key = OPENAI_API_KEY\n",
+    "openai.api_key = os.getenv(\"OPENAI_API_KEY\")\n",
     "COMPLETIONS_MODEL = \"text-davinci-002\""
    ]
   },
@@ -183,19 +183,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 316,
+   "execution_count": 335,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "31\n",
-      "8\n",
-      "All good\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "def request_completion(prompt):\n",
     "    \n",
@@ -221,7 +211,9 @@
     "    \n",
     "    return classification\n",
     "\n",
-    "import json\n",
+    "# This function takes your training and validation outputs from the prepare_data function of the Finetuning API, and\n",
+    "# confirms that each have the same number of classes.\n",
+    "# If they do not have the same number of classes the fine-tune will fail and return an error\n",
     "\n",
     "def check_finetune_classes(train_file,valid_file):\n",
     "\n",
@@ -270,18 +262,17 @@
    "outputs": [],
    "source": [
     "zero_shot_prompt = '''You are a data expert working for the National Library of Scotland. \n",
-    "                      You are analysing all transactions over £25,000 in value and classifying them into one of five categories.\n",
-    "                      The five categories are Building Improvement, Literature & Archive, Utility Bills, Professional Services and Software/IT.\n",
-    "                      If you can't tell what it is, say Could not classify\n",
-    "                      \n",
-    "                      Transaction:\n",
+    "You are analysing all transactions over £25,000 in value and classifying them into one of five categories.\n",
+    "The five categories are Building Improvement, Literature & Archive, Utility Bills, Professional Services and Software/IT.\n",
+    "If you can't tell what it is, say Could not classify\n",
     "                      \n",
-    "                      Supplier: SUPPLIER_NAME\n",
-    "                      Description: DESCRIPTION_TEXT\n",
-    "                      Value: TRANSACTION_VALUE\n",
+    "Transaction:\n",
     "                      \n",
+    "Supplier: SUPPLIER_NAME\n",
+    "Description: DESCRIPTION_TEXT\n",
+    "Value: TRANSACTION_VALUE\n",
     "                      \n",
-    "                      The classification is:'''"
+    "The classification is:'''"
    ]
   },
   {
diff --git a/examples/helpers.py b/examples/helpers.py
new file mode 100644
index 0000000..fcc4a68
--- /dev/null
+++ b/examples/helpers.py
@@ -0,0 +1 @@
+OPENAI_API_KEY="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"
\ No newline at end of file