checkXKCD_corrections.ipynb

checkxkcd_corrections.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "checkXKCD_corrections.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyPk9Vtfx4Ro69XSQOvxYn8I",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/brockmanmatt/a65f54e33b48a14eb306494a686f0988/checkxkcd_corrections.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "J7wnsgT2kPut",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from google.colab import files\n",
        "uploaded = files.upload()\n",
        "print(\"done\")"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "WHPHrUnhpKnI",
        "colab_type": "text"
      },
      "source": [
        "I'll install the API"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zq0ltp2xn4yt",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "!pip install openai\n",
        "import openai, json, pandas as pd"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Q2yE0jcnpMEV",
        "colab_type": "text"
      },
      "source": [
        "Loading in key.json that I uploaded; I do this so I don't need to worry about accidently leaking creds if I share the colab (which I'm 99% sure is just a json file that won't expose them)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bwNXXwHen5x9",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "openai.api_key = json.load(open(\"key.json\", \"r\"))[\"key\"]"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "k67w5H0fpTkT",
        "colab_type": "text"
      },
      "source": [
        "Default keyword arguments to pass the aPI"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "e1EwpqqJkTYh",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "#arguments to send the API\n",
        "kwargs = {\n",
        "\"engine\":\"davinci\",\n",
        "\"temperature\":0,\n",
        "\"max_tokens\":150,\n",
        "\"stop\":\"\\n\\n\",\n",
        "}"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zZubgPoOpWDH",
        "colab_type": "text"
      },
      "source": [
        "Quick wrapper to automatically save prompts and responses sent for later analysis if needed"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "sXTDJx0An9Bl",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import datetime\n",
        "def query(prompt, myKwargs = kwargs):\n",
        "  \"\"\"\n",
        "  wrapper for the API to save the prompt and the result\n",
        "  \"\"\"\n",
        "\n",
        "  r = openai.Completion.create(prompt=prompt, **myKwargs)[\"choices\"][0][\"text\"].strip()\n",
        "  with open(\"{}.json\".format(datetime.datetime.now().strftime(\"%Y%m%d%s\")), \"w\") as fh:\n",
        "    json.dump({\"prompt\":prompt, \"response\":r}, fh, indent=4)\n",
        "  return r"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EdFXafcJpZ3Q",
        "colab_type": "text"
      },
      "source": [
        "Test to make sure my query works"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rtWJBF0iSXAr",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "def interpretCorrections(text):\n",
        "  prompt = \"\"\"Text: I left my homework on the bus\n",
        "Text: *CAR\n",
        "Q: What is the sender trying to rephrase the text to say?\n",
        "A: I left my homework in the car\n",
        "\n",
        "Text: I'm gonna take a quick nap and get it done\n",
        "Text: *LONG\n",
        "Q: What is the sender trying to rephrase the text to say?\n",
        "A: I'm gonna take a long nap and get it done\n",
        "\n",
        "\"\"\"\n",
        "\n",
        "  suffix = \"\"\"\n",
        "Q: What is the sender trying to rephrase the text to say?\n",
        "A:\"\"\"\n",
        "  kwargs = {\"engine\":\"davinci\", \"temperature\":0, \"max_tokens\":150, \"stop\":\"\\n\",}\n",
        "  return query(prompt + text + suffix, kwargs)\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fEI2Djm3Qif_",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "outputId": "97881225-1643-4249-e1a4-3c5acd05bb71"
      },
      "source": [
        "text = \"\"\"Text: I'm gonna ride a horse on the beach at dawn\n",
        "Text: *EAT\n",
        "Text: *3AM\n",
        "Text: *COUCH\n",
        "Text: *PIZZA\"\"\"\n",
        "interpretCorrections(text)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            },
            "text/plain": [
              "\"I'm gonna eat pizza on the couch at 3am\""
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 106
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xsNhLwdcQx10",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "outputId": "097130c8-9cb3-48db-8752-06f58258c6f3"
      },
      "source": [
        "text = \"\"\"Text: I'd love to meet up, maybe in a few days? Next week is looking pretty empty.\n",
        "Text: *WITCHCRAFT\"\"\"\n",
        "interpretCorrections(text)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            },
            "text/plain": [
              "\"I'd love to meet up, maybe in a few days? Next week is looking pretty busy.\""
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 51
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "woA5gTQcQyss",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "outputId": "a6e64417-c487-4d6a-99b4-f2a3ec1d63e7"
      },
      "source": [
        "text = \"\"\"Text: I'd love to meet up, maybe in a few days? Next week is looking pretty empty.\n",
        "Text: *WEEKS\"\"\"\n",
        "interpretCorrections(text)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            },
            "text/plain": [
              "\"I'd love to meet up, maybe in a few weeks? Next week is looking pretty empty.\""
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 50
        }
      ]
    }
  ]
}