Skip to content

Instantly share code, notes, and snippets.

@brockmanmatt

brockmanmatt/generaterhyme.ipynb

Created July 25, 2020 02:09
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save brockmanmatt/ce9a2a83a55d9abefc5ca95aa2af8ee0 to your computer and use it in GitHub Desktop.
Save brockmanmatt/ce9a2a83a55d9abefc5ca95aa2af8ee0 to your computer and use it in GitHub Desktop.
Download ZIP
generateRhyme
Display the source blob
Display the rendered blob
Raw
generaterhyme.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "generateRhyme",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyPUVFUtjD2iCz1AVVkDI/FW",
"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/ce9a2a83a55d9abefc5ca95aa2af8ee0/generaterhyme.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "8QamcNLAUwRT",
"colab_type": "text"
},
"source": [
"upload api key"
]
},
{
"cell_type": "code",
"metadata": {
"id": "7oSe-wM1UonK",
"colab_type": "code",
"colab": {
"resources": {
"http://localhost:8080/nbextensions/google.colab/files.js": {
"data": "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",
"ok": true,
"headers": [
[
"content-type",
"application/javascript"
]
],
"status": 200,
"status_text": ""
}
},
"base_uri": "https://localhost:8080/",
"height": 89
},
"outputId": "b7af26ce-6eae-48fa-844c-3c793f72760a"
},
"source": [
"from google.colab import files\n",
"uploaded = files.upload()\n",
"print(\"done\")"
],
"execution_count": 1,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"\n",
" <input type=\"file\" id=\"files-caf53db2-a68c-456f-b2fc-b3dd361abb83\" name=\"files[]\" multiple disabled\n",
" style=\"border:none\" />\n",
" <output id=\"result-caf53db2-a68c-456f-b2fc-b3dd361abb83\">\n",
" Upload widget is only available when the cell has been executed in the\n",
" current browser session. Please rerun this cell to enable.\n",
" </output>\n",
" <script src=\"/nbextensions/google.colab/files.js\"></script> "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"Saving key.json to key.json\n",
"done\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "D5w-_NLQUvdp",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 292
},
"outputId": "17643220-91ee-483b-d74f-d05f2c39b939"
},
"source": [
"!pip install openai\n",
"import openai, json, pandas as pd"
],
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"text": [
"Collecting openai\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/a8/65/c7461f4c87984534683f480ea5742777bc39bbf5721123194c2d0347dc1f/openai-0.2.4.tar.gz (157kB)\n",
"\u001b[K |████████████████████████████████| 163kB 2.8MB/s \n",
"\u001b[?25hRequirement already satisfied: requests>=2.20 in /usr/local/lib/python3.6/dist-packages (from openai) (2.23.0)\n",
"Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (1.24.3)\n",
"Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (2.10)\n",
"Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (3.0.4)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests>=2.20->openai) (2020.6.20)\n",
"Building wheels for collected packages: openai\n",
" Building wheel for openai (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for openai: filename=openai-0.2.4-cp36-none-any.whl size=170709 sha256=4a200ccfefe2a4800e78778efc87ba497414d3fd654bf193961413fe4a6f03f9\n",
" Stored in directory: /root/.cache/pip/wheels/74/96/c8/c6e170929c276b836613e1b9985343b501fe455e53d85e7d48\n",
"Successfully built openai\n",
"Installing collected packages: openai\n",
"Successfully installed openai-0.2.4\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "zgRTEwfFYpnQ",
"colab_type": "code",
"colab": {}
},
"source": [
"openai.api_key = json.load(open(\"key.json\", \"r\"))[\"key\"]"
],
"execution_count": 3,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "hVfKz9YrYjrK",
"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": 4,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "qtBhLP1gbpcF",
"colab_type": "text"
},
"source": [
"3 Goals:\n",
"* Get end of word\n",
"* Generate rhyming word\n",
"* Add rhyming word to sentence"
]
},
{
"cell_type": "code",
"metadata": {
"id": "UbshzNUeryKZ",
"colab_type": "code",
"colab": {}
},
"source": [
"def getEndOfWord(someWord, verbose=False):\n",
" \"\"\"\n",
" Get the last part of a word that I'll need to rhyme\n",
" \"\"\"\n",
" prompt = \"\"\n",
" prompt += \"full: turtle\\n\"\n",
" prompt += \"ending: tle\\n\\n\"\n",
" \n",
" prompt += \"full: apple\\n\"\n",
" prompt += \"ending: ple\\n\\n\"\n",
"\n",
" prompt += \"full: training\\n\"\n",
" prompt += \"ending: ing\\n\\n\"\n",
"\n",
" prompt += \"full: {}\\n\".format(someWord)\n",
" prompt += \"ending:\"\n",
" \n",
" r = openai.Completion.create(prompt=prompt, **kwargs)[\"choices\"][0][\"text\"].strip()\n",
" return r\n"
],
"execution_count": 10,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "X9kCeNiWry7e",
"colab_type": "code",
"colab": {}
},
"source": [
""
],
"execution_count": 10,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "qQuPhJOsr6s5",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "173e39d9-fa45-48f5-82f4-897129b8e6ec"
},
"source": [
"getEndOfWord(\"hamper\")"
],
"execution_count": 11,
"outputs": [
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "string"
},
"text/plain": [
"'per'"
]
},
"metadata": {
"tags": []
},
"execution_count": 11
}
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "zahem0z5r6s-",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "96c14772-3604-4373-b835-5bf76260980a"
},
"source": [
"getEndOfWord(\"attica\")"
],
"execution_count": 12,
"outputs": [
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "string"
},
"text/plain": [
"'cia'"
]
},
"metadata": {
"tags": []
},
"execution_count": 12
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "iDzGAQFaUmY-",
"colab_type": "code",
"colab": {}
},
"source": [
"def getEndOfWord(someWord, verbose=False):\n",
" \"\"\"\n",
" Get the last part of a word that I'll need to rhyme\n",
" \"\"\"\n",
" prompt = \"\"\n",
" prompt += \"full: turtle\\n\"\n",
" prompt += \"ending: tle\\n\\n\"\n",
" \n",
" prompt += \"full: apple\\n\"\n",
" prompt += \"ending: ple\\n\\n\"\n",
"\n",
" prompt += \"full: training\\n\"\n",
" prompt += \"ending: ing\\n\\n\"\n",
"\n",
" prompt += \"full: whopper\\n\"\n",
" prompt += \"ending: per\\n\\n\"\n",
"\n",
" prompt += \"full: balderdash\\n\"\n",
" prompt += \"ending: ash\\n\\n\"\n",
"\n",
" prompt += \"full: clause\\n\"\n",
" prompt += \"ending: ause\\n\\n\"\n",
"\n",
" prompt += \"full: higher\\n\"\n",
" prompt += \"ending: er\\n\\n\"\n",
"\n",
" prompt += \"full: small\\n\"\n",
" prompt += \"ending: all\\n\\n\"\n",
"\n",
" prompt += \"full: pernicious\\n\"\n",
" prompt += \"ending: us\\n\\n\"\n",
"\n",
" prompt += \"full: {}\\n\".format(someWord)\n",
" prompt += \"ending:\"\n",
"\n",
" if verbose:\n",
" print(prompt)\n",
"\n",
" r = openai.Completion.create(prompt=prompt, **kwargs)[\"choices\"][0][\"text\"].strip()\n",
" return r\n"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "psPNbQ-KVp2Z",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "85b53c06-dc8d-4027-859b-ceab0a52286d"
},
"source": [
"getEndOfWord(\"hamper\")"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic": {
"type": "string"
},
"text/plain": [
"'er'"
]
},
"metadata": {
"tags": []
},
"execution_count": 81
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "ucVwoRhPVpzB",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "00bfd95f-2ad8-4ddf-8229-a644701a0e4a"
},
"source": [
"getEndOfWord(\"attica\")"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic": {
"type": "string"
},
"text/plain": [
"'ica'"
]
},
"metadata": {
"tags": []
},
"execution_count": 49
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "akpAmLXNUmXE",
"colab_type": "code",
"colab": {}
},
"source": [
"def fillInWord(letter, ending, temp=0, verbose=False):\n",
" \"\"\"\n",
" generate a word that ends with the ending and starts with a letter\n",
" \"\"\"\n",
" prompt = \"\"\n",
" prompt += \"Guess: t__ial\\n\"\n",
" prompt += \"Answer: trivial\\n\\n\"\n",
"\n",
" prompt += \"Guess: c__ury\\n\"\n",
" prompt += \"Answer: century\\n\\n\"\n",
"\n",
" prompt += \"Guess: a__al\\n\"\n",
" prompt += \"Answer: animal\\n\\n\"\n",
"\n",
" prompt += \"Guess: a__le\\n\"\n",
" prompt += \"Answer: able\\n\\n\"\n",
"\n",
" prompt += \"Guess: t__ble\\n\"\n",
" prompt += \"Answer: table\\n\\n\"\n",
"\n",
" prompt += \"Guess: {}__{}\\n\".format(letter, ending)\n",
" prompt += \"Answer:\"\n",
"\n",
" if verbose:\n",
" print(prompt)\n",
" myKwargs = kwargs.copy()\n",
" myKwargs[\"temperature\"] = int(temp)\n",
" #print(kwargs)\n",
" #print(myKwargs)\n",
"\n",
" r = openai.Completion.create(prompt=prompt, **myKwargs)[\"choices\"][0][\"text\"].strip()\n",
" return r\n"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "ATYM4ruSNfv3",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "5e62caff-88a7-4117-a76a-ea707a544294"
},
"source": [
"fillInWord(\"a\", \"ing\", temp=1)"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic": {
"type": "string"
},
"text/plain": [
"'aching'"
]
},
"metadata": {
"tags": []
},
"execution_count": 100
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "8TyJj2YeUmTX",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "96b05b7c-e12a-44e0-c34b-e15af2d576d9"
},
"source": [
"fillInWord(\"f\", \"ing\", temp=1)"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic": {
"type": "string"
},
"text/plain": [
"'fighting'"
]
},
"metadata": {
"tags": []
},
"execution_count": 99
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "DubHzLCjUmRW",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "535ba299-ae97-4fa0-f09e-cdfe00c2d38a"
},
"source": [
"fillInWord(\"a\", getEndOfWord(\"hamper\"))"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic": {
"type": "string"
},
"text/plain": [
"'after'"
]
},
"metadata": {
"tags": []
},
"execution_count": 83
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "QDaQ8s0yUmOz",
"colab_type": "code",
"colab": {}
},
"source": [
"import string\n",
"def getPossibleWordChoices(ending, temp=0):\n",
" choices = []\n",
" for x in string.ascii_lowercase:\n",
" choices.append(fillInWord(x, ending, temp=temp))\n",
" return choices"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "UxSU4zu3UmMJ",
"colab_type": "code",
"colab": {}
},
"source": [
"testChoices = getPossibleWordChoices(\"ily\")"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "QTpGDOusUmJJ",
"colab_type": "code",
"colab": {}
},
"source": [
"def generateRelevantWord(context, wordToRhyme, verbose=False):\n",
" \"\"\"\n",
" return semantic the possibleWord with highest semantic similarity to context\n",
" \"\"\"\n",
" possibleWords = getPossibleWordChoices(getEndOfWord(wordToRhyme))\n",
" if verbose:\n",
" print(possibleWords)\n",
" scores = openai.Engine(\"davinci\").search(\n",
" documents=[x for x in possibleWords],\n",
" query=context\n",
" )\n",
"\n",
" return max([(scores[\"data\"][i][\"score\"], possibleWords[i]) for i in range(len(possibleWords))])[1]"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "k5RkazJMUmGQ",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 72
},
"outputId": "6a276970-b877-4743-964e-bff0ffbdc8eb"
},
"source": [
"generateRelevantWord(\"I want to go to sleep but I'm not sure that's a good idea\", \"lousy\", verbose=True)"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"['ally', 'barely', 'clearly', 'daily', 'easily', 'fly', 'gently', 'holy', 'illy', 'July', 'quickly', 'lovely', 'million', 'nicely', 'only', 'play', 'quickly', 'really', 'slyly', 'truly', 'ugly', 'valley', 'weekly', 'xylophone', 'yearly', 'zealously']\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic": {
"type": "string"
},
"text/plain": [
"'quickly'"
]
},
"metadata": {
"tags": []
},
"execution_count": 98
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment