courses/prompt_evaluations/03_code_graded.ipynb

{
 "cells": [
  {
   "attachments": {
    "process.png": {
     "image/png": "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"
    }
   },
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# A simple code-graded evaluation\n",
    "\n",
    "In this lesson we'll start with a look at a very simple example code-graded evaluation, before covering a more realistic prompt in the next lesson.  We'll follow the process outlined in this diagram:\n",
    "\n",
    "![process.png](attachment:process.png)\n",
    "\n",
    "The rough steps are:\n",
    "1. Start by defining our evaluation test set\n",
    "1. Write our initial prompt attempt\n",
    "2. Run it through our evaluation process and get a score\n",
    "3. Alter our prompt based on the evaluation results\n",
    "4. Run the altered prompt through our evaluation process and hopefully get a better score!\n",
    "\n",
    "Let's try following this process!\n",
    "\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Our input data\n",
    "\n",
    "We'll be grading an eval where we ask Claude to successfully identify how many legs an animal has.  In future lessons we'll see more complex and realistic prompts and evaluations, but we're keeping things deliberately simple here to focus on the actual evaluation process.\n",
    "\n",
    "The first step is to write our evaluation data set that includes our inputs plus corresponding golden answers.  Let's use this simple list of dictionaries, where each dictionary has an `animal_statement` and `golden_answer` key:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "eval_data = [\n",
    "    {\"animal_statement\": \"The animal is a human.\", \"golden_answer\": \"2\"},\n",
    "    {\"animal_statement\": \"The animal is a snake.\", \"golden_answer\": \"0\"},\n",
    "    {\"animal_statement\": \"The fox lost a leg, but then magically grew back the leg he lost and a mysterious extra leg on top of that.\", \"golden_answer\": \"5\"},\n",
    "    {\"animal_statement\": \"The animal is a dog.\", \"golden_answer\": \"4\"},\n",
    "    {\"animal_statement\": \"The animal is a cat with two extra legs.\", \"golden_answer\": \"6\"},\n",
    "    {\"animal_statement\": \"The animal is an elephant.\", \"golden_answer\": \"4\"},\n",
    "    {\"animal_statement\": \"The animal is a bird.\", \"golden_answer\": \"2\"},\n",
    "    {\"animal_statement\": \"The animal is a fish.\", \"golden_answer\": \"0\"},\n",
    "    {\"animal_statement\": \"The animal is a spider with two extra legs\", \"golden_answer\": \"10\"},\n",
    "    {\"animal_statement\": \"The animal is an octopus.\", \"golden_answer\": \"8\"},\n",
    "    {\"animal_statement\": \"The animal is an octopus that lost two legs and then regrew three legs.\", \"golden_answer\": \"9\"},\n",
    "    {\"animal_statement\": \"The animal is a two-headed, eight-legged mythical creature.\", \"golden_answer\": \"8\"},\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Notice that some of the evaluation questions are a little bit tricky, like this one: \n",
    "> The fox lost a leg, but then magically grew back the leg he lost and a mysterious extra leg on top of that.\n",
    "\n",
    "This will be important later!\n",
    "\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Our initial prompt\n",
    "Next, we'll define out initial prompt.  The function below takes in a single animal statement and returns a properly formatted messages list containing our first prompt attempt:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def build_input_prompt(animal_statement):\n",
    "    user_content = f\"\"\"You will be provided a statement about an animal and your job is to determine how many legs that animal has.\n",
    "    \n",
    "    Here is the animal statement.\n",
    "    <animal_statement>{animal_statement}</animal_statement>\n",
    "    \n",
    "    How many legs does the animal have? Please respond with a number\"\"\"\n",
    "\n",
    "    messages = [{'role': 'user', 'content': user_content}]\n",
    "    return messages"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's test it out quickly with the first element in our `eval` dataset:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'role': 'user',\n",
       "  'content': 'You will be provided a statement about an animal and your job is to determine how many legs that animal has.\\n    \\n    Here is the animal statement.\\n    <animal_statement>The animal is a human.</animal_statement>\\n    \\n    How many legs does the animal have? Please respond with a number'}]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "build_input_prompt(eval_data[0]['animal_statement'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next, we'll write a simple function that takes a list of messages and send it off to the Anthropic API:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "from anthropic import Anthropic\n",
    "from dotenv import load_dotenv\n",
    "\n",
    "load_dotenv()\n",
    "client = Anthropic()\n",
    "\n",
    "MODEL_NAME = \"claude-3-haiku-20240307\"\n",
    "\n",
    "def get_completion(messages):\n",
    "    response = client.messages.create(\n",
    "        model=MODEL_NAME,\n",
    "        max_tokens=200,\n",
    "        messages=messages\n",
    "    )\n",
    "    return response.content[0].text"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's test it out with out first entry in the `eval_data` list, which contains the following animal statement: \n",
    "```\n",
    "'The animal is a human.'\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "full_prompt = build_input_prompt(eval_data[0]['animal_statement'])\n",
    "get_completion(full_prompt)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We get `2` back as the response, which passes the eyeball test! Humans generally have two legs. The next step is to build and run an entire evaluation with all 12 entries in our `eval_data` set.\n",
    "\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Writing the eval logic\n",
    "\n",
    "We'll start by combing each input from our `eval_data` list with our prompt template, passing the resulting \"finished\" prompts to the model, and collecting all the outputs we get back:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "outputs = [get_completion(build_input_prompt(question['animal_statement'])) for question in eval_data]\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's take a quick peek at what we get back:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['2',\n",
       " '0',\n",
       " '5',\n",
       " '4',\n",
       " '6',\n",
       " '4',\n",
       " 'Based on the provided animal statement, \"The animal is a bird.\", the animal has 2 legs.\\n\\nResponse: 2',\n",
       " '0',\n",
       " '8',\n",
       " 'An octopus has 8 legs.',\n",
       " '5',\n",
       " '8']"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "outputs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Already, we can tell our prompt needs some improvement because we're getting some answers that are not exclusively numbers!  Let's take a closer look at the results alongside each corresponding golden answer:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Animal Statement: The animal is a human.\n",
      "Golden Answer: 2\n",
      "Output: 2\n",
      "\n",
      "Animal Statement: The animal is a snake.\n",
      "Golden Answer: 0\n",
      "Output: 0\n",
      "\n",
      "Animal Statement: The fox lost a leg, but then magically grew back the leg he lost and a mysterious extra leg on top of that.\n",
      "Golden Answer: 5\n",
      "Output: 5\n",
      "\n",
      "Animal Statement: The animal is a dog.\n",
      "Golden Answer: 4\n",
      "Output: 4\n",
      "\n",
      "Animal Statement: The animal is a cat with two extra legs.\n",
      "Golden Answer: 6\n",
      "Output: 6\n",
      "\n",
      "Animal Statement: The animal is an elephant.\n",
      "Golden Answer: 4\n",
      "Output: 4\n",
      "\n",
      "Animal Statement: The animal is a bird.\n",
      "Golden Answer: 2\n",
      "Output: Based on the provided animal statement, \"The animal is a bird.\", the animal has 2 legs.\n",
      "\n",
      "Response: 2\n",
      "\n",
      "Animal Statement: The animal is a fish.\n",
      "Golden Answer: 0\n",
      "Output: 0\n",
      "\n",
      "Animal Statement: The animal is a spider with two extra legs\n",
      "Golden Answer: 10\n",
      "Output: 8\n",
      "\n",
      "Animal Statement: The animal is an octopus.\n",
      "Golden Answer: 8\n",
      "Output: An octopus has 8 legs.\n",
      "\n",
      "Animal Statement: The animal is an octopus that lost two legs and then regrew three legs.\n",
      "Golden Answer: 9\n",
      "Output: 5\n",
      "\n",
      "Animal Statement: The animal is a two-headed, eight-legged mythical creature.\n",
      "Golden Answer: 8\n",
      "Output: 8\n",
      "\n"
     ]
    }
   ],
   "source": [
    "for output, question in zip(outputs, eval_data):\n",
    "    print(f\"Animal Statement: {question['animal_statement']}\\nGolden Answer: {question['golden_answer']}\\nOutput: {output}\\n\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is a small enough data set that we can easily scan the results and find the problematic responses, but let's grade our results systematically:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Score: 66.66666666666666%\n"
     ]
    }
   ],
   "source": [
    "def grade_completion(output, golden_answer):\n",
    "    return output == golden_answer\n",
    "\n",
    "grades = [grade_completion(output, question['golden_answer']) for output, question in zip(outputs, eval_data)]\n",
    "print(f\"Score: {sum(grades)/len(grades)*100}%\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We now have a baseline score! In this case, our initial prompt resulted in an accuracy score of 66.6% After scanning the above results, it looks like there are two obvious issues with our current outputs:\n",
    "\n",
    "### Problem 1: Output formatting issues\n",
    "Our goal here is to write a prompt that results in a numeric output.  Some of our outputs are not numeric: \n",
    "\n",
    "```\n",
    "Animal Statement: The animal is a bird.\n",
    "Golden Answer: 2\n",
    "Output: Based on the provided animal statement, \"The animal is a bird.\", the animal has 2 legs.\n",
    "```\n",
    "We can fix this through some prompting!\n",
    "\n",
    "### Problem 1: Incorrect answers\n",
    "\n",
    "Additionally, some of the answers are completely wrong: \n",
    "\n",
    "```\n",
    "Animal Statement: The animal is an octopus that lost two legs and then regrew three legs.\n",
    "Golden Answer: 9\n",
    "Output: 5\n",
    "```\n",
    "\n",
    "and \n",
    "\n",
    "```\n",
    "Animal Statement: The animal is a spider with two extra legs\n",
    "Golden Answer: 10\n",
    "Output: 8\n",
    "```\n",
    "These inputs are a little \"tricky\" and seem to be causing the model some problems.  We'll also attempt to fix this through prompting!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "--- \n",
    "\n",
    "## Our second attempt\n",
    "\n",
    "Now that we have some level of baseline performance with our initial prompt, let's try improving the prompt and see if our evaluation score improves. We'll start by tackling the problem of the model sometimes outputting additional text instead of only responding with a numeric digit. Here's a second prompt-generating function:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [],
   "source": [
    "def build_input_prompt2(animal_statement):\n",
    "    user_content = f\"\"\"You will be provided a statement about an animal and your job is to determine how many legs that animal has.\n",
    "    \n",
    "    Here is the animal statement.\n",
    "    <animal_statement>{animal_statement}</animal_statement>\n",
    "    \n",
    "    How many legs does the animal have? Respond only with a numeric digit, like 2 or 6, and nothing else.\"\"\"\n",
    "\n",
    "    messages = [{'role': 'user', 'content': user_content}]\n",
    "    return messages"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The key addition to the prompt is this line: \n",
    "\n",
    "> Respond only with a numeric digit, like 2 or 6, and nothing else."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's test each input with this newer prompt:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [],
   "source": [
    "outputs2 = [get_completion(build_input_prompt2(question['animal_statement'])) for question in eval_data]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We'll take a quick look at the outputs:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['2', '0', '6', '4', '6', '4', '2', '0', '8', '8', '5', '8']"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "outputs2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We're now getting exclusively numeric outputs!   Let's take a closer look at the results:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Animal Statement: The animal is a human.\n",
      "Golden Answer: 2\n",
      "Output: 2\n",
      "\n",
      "Animal Statement: The animal is a snake.\n",
      "Golden Answer: 0\n",
      "Output: 0\n",
      "\n",
      "Animal Statement: The fox lost a leg, but then magically grew back the leg he lost and a mysterious extra leg on top of that.\n",
      "Golden Answer: 5\n",
      "Output: 6\n",
      "\n",
      "Animal Statement: The animal is a dog.\n",
      "Golden Answer: 4\n",
      "Output: 4\n",
      "\n",
      "Animal Statement: The animal is a cat with two extra legs.\n",
      "Golden Answer: 6\n",
      "Output: 6\n",
      "\n",
      "Animal Statement: The animal is an elephant.\n",
      "Golden Answer: 4\n",
      "Output: 4\n",
      "\n",
      "Animal Statement: The animal is a bird.\n",
      "Golden Answer: 2\n",
      "Output: 2\n",
      "\n",
      "Animal Statement: The animal is a fish.\n",
      "Golden Answer: 0\n",
      "Output: 0\n",
      "\n",
      "Animal Statement: The animal is a spider with two extra legs\n",
      "Golden Answer: 10\n",
      "Output: 8\n",
      "\n",
      "Animal Statement: The animal is an octopus.\n",
      "Golden Answer: 8\n",
      "Output: 8\n",
      "\n",
      "Animal Statement: The animal is an octopus that lost two legs and then regrew three legs.\n",
      "Golden Answer: 9\n",
      "Output: 5\n",
      "\n",
      "Animal Statement: The animal is a two-headed, eight-legged mythical creature.\n",
      "Golden Answer: 8\n",
      "Output: 8\n",
      "\n"
     ]
    }
   ],
   "source": [
    "for output, question in zip(outputs2, eval_data):\n",
    "    print(f\"Animal Statement: {question['animal_statement']}\\nGolden Answer: {question['golden_answer']}\\nOutput: {output}\\n\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There are still obvious issues with the actual numeric answers, like this one:\n",
    "\n",
    "```\n",
    "Animal Statement: The animal is a spider with two extra legs\n",
    "Golden Answer: 10\n",
    "Output: 8\n",
    "```\n",
    "\n",
    "Before tackling that problem, let's get an official score to see how our performance (hopefully) improved:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Score: 75.0%\n"
     ]
    }
   ],
   "source": [
    "grades = [grade_completion(output, question['golden_answer']) for output, question in zip(outputs2, eval_data)]\n",
    "print(f\"Score: {sum(grades)/len(grades)*100}%\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Our score went up a bit! **Note: this data set is quite small, so take these results with a grain of salt**\n",
    "\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Our third attempt\n",
    "\n",
    "Next, let's tackle the logical issues we're seeing with the incorrect outputs like: \n",
    "\n",
    "```\n",
    "Animal Statement: The fox lost a leg, but then magically grew back the leg he lost and a mysterious extra leg on top of that.\n",
    "Golden Answer: 5\n",
    "Output: 6\n",
    "```\n",
    "One technique we could employ here is chain of thought prompting, where we give Claude specific instructions to reason through its response before finally generating an answer.  Now that we have an evaluation in place, we can test to see if chain of thought prompting actually makes a difference or not!\n",
    "\n",
    "Let's write a new prompt that asks the model to \"think out-loud\" inside of `<thinking>` tags.  This complicates our logic a little bit because we'll need a convenient way to extract the model's final answer. We'll instruct the model to also include its final answer inside of `<answer>` tags so that we can easily extract the \"final\" numeric answer:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [],
   "source": [
    "def build_input_prompt3(animal_statement):\n",
    "    user_content = f\"\"\"You will be provided a statement about an animal and your job is to determine how many legs that animal has.\n",
    "    \n",
    "    Here is the animal statement.\n",
    "    <animal_statement>{animal_statement}</animal_statement>\n",
    "    \n",
    "    How many legs does the animal have? \n",
    "    Start by reasoning about the numbers of legs the animal has, thinking step by step inside of <thinking> tags.  \n",
    "    Then, output your final answer inside of <answer> tags. \n",
    "    Inside the <answer> tags return just the number of legs as an integer and nothing else.\"\"\"\n",
    "\n",
    "    messages = [{'role': 'user', 'content': user_content}]\n",
    "    return messages"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's collect the outputs using this new version of the prompt:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [],
   "source": [
    "outputs3 = [get_completion(build_input_prompt3(question['animal_statement'])) for question in eval_data]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now let's take a look at some of the outputs:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Animal Statement: The animal is a human.\n",
      "Golden Answer: 2\n",
      "Output: <thinking>\n",
      "The animal is a human, and based on this information, we can reasonably conclude that a human has 2 legs. Humans are bipedal, meaning they have two legs that they use for locomotion and standing upright. This is a characteristic of the human species.\n",
      "</thinking>\n",
      "\n",
      "<answer>2</answer>\n",
      "\n",
      "Animal Statement: The animal is a snake.\n",
      "Golden Answer: 0\n",
      "Output: <thinking>\n",
      "The animal stated in the given statement is a snake. Snakes are known to be legless reptiles, as they do not have any legs. They move by slithering on the ground using their body and scales.\n",
      "</thinking>\n",
      "\n",
      "<answer>0</answer>\n",
      "\n",
      "Animal Statement: The fox lost a leg, but then magically grew back the leg he lost and a mysterious extra leg on top of that.\n",
      "Golden Answer: 5\n",
      "Output: Here is my step-by-step reasoning:\n",
      "<thinking>\n",
      "1. The initial statement says the fox lost a leg.\n",
      "2. But then the fox \"magically grew back the leg he lost and a mysterious extra leg on top of that.\"\n",
      "3. This means the fox originally had 4 legs, lost 1 leg, and then grew back the lost leg plus an extra leg, for a total of 5 legs.\n",
      "</thinking>\n",
      "<answer>5</answer>\n",
      "\n",
      "Animal Statement: The animal is a dog.\n",
      "Golden Answer: 4\n",
      "Output: <thinking>\n",
      "The animal statement says the animal is a dog. Dogs are quadrupeds, meaning they have four legs. Therefore, the number of legs the dog has is 4.\n",
      "</thinking>\n",
      "\n",
      "<answer>4</answer>\n",
      "\n",
      "Animal Statement: The animal is a cat with two extra legs.\n",
      "Golden Answer: 6\n",
      "Output: <thinking>\n",
      "The animal statement says that the animal is a cat with two extra legs. A typical cat has four legs, so with the two extra legs, the animal must have six legs in total.\n",
      "</thinking>\n",
      "\n",
      "<answer>6</answer>\n",
      "\n",
      "Animal Statement: The animal is an elephant.\n",
      "Golden Answer: 4\n",
      "Output: <thinking>\n",
      "An elephant is a large mammal that belongs to the order Proboscidea. Elephants are known to have four legs, one for each of their four limbs. Therefore, based on the given animal statement, the animal is an elephant, and elephants have four legs.\n",
      "</thinking>\n",
      "\n",
      "<answer>4</answer>\n",
      "\n",
      "Animal Statement: The animal is a bird.\n",
      "Golden Answer: 2\n",
      "Output: <thinking>\n",
      "The statement provided indicates that the animal is a bird. Birds typically have two legs, as they are bipedal animals that walk and perch on two legs.\n",
      "</thinking>\n",
      "\n",
      "<answer>2</answer>\n",
      "\n",
      "Animal Statement: The animal is a fish.\n",
      "Golden Answer: 0\n",
      "Output: <thinking>\n",
      "Based on the given animal statement, the animal is a fish. Fish are aquatic vertebrates that typically have fins and gills to help them swim and breathe in the water. Fish do not have legs, as they move through the water using their fins and tails.\n",
      "</thinking>\n",
      "\n",
      "<answer>0</answer>\n",
      "\n",
      "Animal Statement: The animal is a spider with two extra legs\n",
      "Golden Answer: 10\n",
      "Output: <thinking>\n",
      "The animal statement says that the animal is a spider with two extra legs. \n",
      "A spider typically has 8 legs, so with two extra legs, the total number of legs would be 8 + 2 = 10 legs.\n",
      "</thinking>\n",
      "\n",
      "<answer>10</answer>\n",
      "\n",
      "Animal Statement: The animal is an octopus.\n",
      "Golden Answer: 8\n",
      "Output: <thinking>\n",
      "The animal statement says the animal is an octopus. An octopus is a marine invertebrate with eight tentacles that are often referred to as legs. Therefore, the animal has 8 legs.\n",
      "</thinking>\n",
      "\n",
      "<answer>8</answer>\n",
      "\n",
      "Animal Statement: The animal is an octopus that lost two legs and then regrew three legs.\n",
      "Golden Answer: 9\n",
      "Output: <thinking>\n",
      "The animal is described as an octopus that lost two legs and then regrew three legs. Initially, an octopus has eight legs.\n",
      "Since the animal lost two legs, it would have had six legs remaining.\n",
      "Then, the animal regrew three legs, so the final number of legs the animal has is nine.\n",
      "</thinking>\n",
      "\n",
      "<answer>9</answer>\n",
      "\n",
      "Animal Statement: The animal is a two-headed, eight-legged mythical creature.\n",
      "Golden Answer: 8\n",
      "Output: <thinking>\n",
      "The animal statement mentions that the animal is a two-headed, eight-legged mythical creature. This means that the animal has two heads and eight legs.\n",
      "</thinking>\n",
      "\n",
      "<answer>8</answer>\n",
      "\n"
     ]
    }
   ],
   "source": [
    "for output, question in zip(outputs3, eval_data):\n",
    "    print(f\"Animal Statement: {question['animal_statement']}\\nGolden Answer: {question['golden_answer']}\\nOutput: {output}\\n\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here's an example of the sort of response we get: \n",
    "\n",
    "```\n",
    "Animal Statement: The fox lost a leg, but then magically grew back the leg he lost and a mysterious extra leg on top of that.\n",
    "Golden Answer: 5\n",
    "Output: Here is my step-by-step reasoning:\n",
    "<thinking>\n",
    "1. The initial statement says the fox lost a leg.\n",
    "2. But then the fox \"magically grew back the leg he lost and a mysterious extra leg on top of that.\"\n",
    "3. This means the fox originally had 4 legs, lost 1 leg, and then grew back the lost leg plus an extra leg, for a total of 5 legs.\n",
    "</thinking>\n",
    "<answer>5</answer>\n",
    "```\n",
    "\n",
    "The logic appears to be improved, at least in this particular example.  Now we need to focus on making this prompt \"grade-able\".  We need to extract the number between the `answer` tags before the grading process.\n",
    "\n",
    "Here's a function that extracts the text between two `<answer>` tags:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "def extract_answer(text):\n",
    "    pattern = r'<answer>(.*?)</answer>'\n",
    "    match = re.search(pattern, text)\n",
    "    if match:\n",
    "        return match.group(1)\n",
    "    else:\n",
    "        return None"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next, let's extract the answers from the latest batch of outputs:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [],
   "source": [
    "extracted_outputs3 = [extract_answer(output) for output in outputs3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['2', '0', '5', '4', '6', '4', '2', '0', '10', '8', '9', '8']"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "extracted_outputs3"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next, let's get our score and see if adding chain of thought to our prompt made a difference!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Score: 100.0%\n"
     ]
    }
   ],
   "source": [
    "grades3 = [grade_completion(output, question['golden_answer']) for output, question in zip(extracted_outputs3, eval_data)]\n",
    "print(f\"Score: {sum(grades3)/len(grades3)*100}%\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We improved our score to 100%! \n",
    "\n",
    "Our evaluation gives us some confidence that the changes we made to our prompt actually result in better outputs.  This is a simple example that uses exact-match grading, but in the next lesson well take a look at something a little more complicated. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "py311",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}