awesome-notebooks/GitHub/GitHub_Get_most_starred_repos.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "177a878f-37b4-4931-a05e-1781d7d11c29",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-02-23T14:22:16.610471Z",
     "iopub.status.busy": "2021-02-23T14:22:16.610129Z",
     "iopub.status.idle": "2021-02-23T14:22:16.627784Z",
     "shell.execute_reply": "2021-02-23T14:22:16.626866Z",
     "shell.execute_reply.started": "2021-02-23T14:22:16.610384Z"
    },
    "papermill": {},
    "tags": []
   },
   "source": [
    "<img width=\"8%\" alt=\"GitHub.png\" src=\"https://raw.githubusercontent.com/jupyter-naas/awesome-notebooks/master/.github/assets/logos/GitHub.png\" style=\"border-radius: 15%\">"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e74d4d6a-9b35-4e41-8617-5124decf3bc9",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "# GitHub - Get most starred repos\n",
    "<a href=\"https://bit.ly/3JyWIk6\">Give Feedback</a> | <a href=\"https://github.com/jupyter-naas/awesome-notebooks/issues/new?assignees=&labels=bug&template=bug_report.md&title=GitHub+-+Get+most+starred+repos:+Error+short+description\">Bug report</a>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e56f09a7-a3fe-4c4a-9bf0-7f7b280e030f",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "**Tags:** #github #repos #stars #snippet"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "56a78043-5105-4b22-8e6b-5c853777e1b4",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "**Author:** [Sanjeet Attili](https://www.linkedin.com/in/sanjeet-attili-760bab190)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6142adaa-cdeb-4f01-a57a-6a16084ec466",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "**Last update:** 2023-04-12 (Created: 2022-06-06)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "naas-description",
   "metadata": {
    "papermill": {},
    "tags": [
     "description"
    ]
   },
   "source": [
    "**Description:** This notebook provides a list of the most popular GitHub repositories based on the number of stars they have received."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5225edb4-ead5-4c32-9386-c12e3d38da28",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "## Input"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3299f3b7-330f-4145-8d8e-f9163e8c7c64",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "### Import libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8de808ad-6416-4cc4-9085-d373246c745d",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "outputs": [],
   "source": [
    "import requests\n",
    "import pandas as pd\n",
    "import plotly.express as px\n",
    "import naas"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bf7b7a18-a011-4468-b6cc-7c3127ee417e",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "### Setup Variables"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "32b38b7b-4526-40f4-8474-5ca1920b760f",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "* The Github search API provides up to 1,000 results for each search.\n",
    "\n",
    "* Please visit [this link](https://docs.github.com/en/rest/search#about-the-search-api) to know more about Github search limitation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1a95c818-e23e-4690-867c-e3ecd332dcf6",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Query number of repositories with stars greater than the given threshold\n",
    "threshold = 500  # provides list of repos with stars greater than 500\n",
    "\n",
    "# Setup how many top repository results are to be shown\n",
    "top_n = 250\n",
    "\n",
    "# if you want to fetch all the repository results with the\n",
    "# given threshold instead of top_n number, then put in top_n value to 'all'\n",
    "\n",
    "# Github token\n",
    "GITHUB_TOKEN = None or naas.secret.get(\"GITHUB_TOKEN\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3f0db106-0361-4672-ba06-2d9f6525be08",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "## Model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "85edc940-b57b-425d-a693-6f7942ddbe7b",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "### Get most starred repos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "824580df-24f1-4f97-b9a3-818ad478a312",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "outputs": [],
   "source": [
    "def fetch_results(top_n, threshold, token):\n",
    "    URL = (\n",
    "        f\"https://api.github.com/search/repositories?q=stars:%3E{threshold}&sort=stars\"\n",
    "    )\n",
    "    headers = {\"Authorization\": f\"token {token}\"}\n",
    "    df = pd.DataFrame()\n",
    "    cnt, page = 0, 1\n",
    "\n",
    "    while True:\n",
    "        params = {\n",
    "            \"state\": \"open\",\n",
    "            \"per_page\": \"100\",\n",
    "            \"page\": page,\n",
    "        }\n",
    "        res = requests.get(URL, headers=headers, params=params)\n",
    "        try:\n",
    "            res.raise_for_status()\n",
    "        except requests.HTTPError as e:\n",
    "            if \"422 Client Error: Unprocessable Entity for url:\" in str(e):\n",
    "                print(\"Github Search API limit reached!\")\n",
    "                print(\"Collecting the search results\")\n",
    "                break\n",
    "        res_json = res.json()\n",
    "\n",
    "        for r in res_json[\"items\"]:\n",
    "            df.loc[cnt, \"repo_id\"] = r[\"id\"]\n",
    "            df.loc[cnt, \"name\"], df.loc[cnt, \"url\"] = r[\"name\"], r[\"html_url\"]\n",
    "            df.loc[cnt, \"stars\"], df.loc[cnt, \"forks\"], df.loc[cnt, \"issues_open\"] = (\n",
    "                r[\"watchers\"],\n",
    "                r[\"forks\"],\n",
    "                r[\"open_issues\"],\n",
    "            )\n",
    "            df.loc[cnt, \"created_at\"], df.loc[cnt, \"updated_at\"] = (\n",
    "                r[\"created_at\"],\n",
    "                r[\"updated_at\"],\n",
    "            )\n",
    "            if len(r[\"topics\"]):\n",
    "                df.loc[cnt, \"topics\"] = \",\".join(r[\"topics\"])\n",
    "            else:\n",
    "                df.loc[cnt, \"topics\"] = \"None\"\n",
    "\n",
    "            if r[\"description\"]:\n",
    "                df.loc[cnt, \"description\"] = r[\"description\"]\n",
    "            else:\n",
    "                df.loc[cnt, \"description\"] = \"None\"\n",
    "\n",
    "            cnt += 1\n",
    "            if cnt == top_n:\n",
    "                break\n",
    "\n",
    "        if cnt == top_n:\n",
    "            break\n",
    "\n",
    "        page += 1\n",
    "\n",
    "    df.stars, df.forks, df.issues_open, df.repo_id = (\n",
    "        df.stars.astype(\"int\"),\n",
    "        df.forks.astype(\"int\"),\n",
    "        df.issues_open.astype(\"int\"),\n",
    "        df.repo_id.astype(\"int\"),\n",
    "    )\n",
    "    return df\n",
    "\n",
    "\n",
    "df_results = fetch_results(top_n, threshold, GITHUB_TOKEN)\n",
    "df_results.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ca4b723e-eb05-42d1-9882-3ab83279573b",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "## Output"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "443e61ad-8c87-418b-8752-4dc448458e38",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "source": [
    "### Display result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5de75d14-bcdd-43f2-b779-9b09aaf59b1f",
   "metadata": {
    "papermill": {},
    "tags": []
   },
   "outputs": [],
   "source": [
    "df_results.head(10)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.9.6"
  },
  "naas": {
   "notebook_id": "f8b2a5b06ad0b1bc4d25de7e3aa1130a926d75e334885b7f4ad7abe3b774087d",
   "notebook_path": "GitHub/GitHub_Get_most_starred_repos.ipynb"
  },
  "papermill": {
   "default_parameters": {},
   "environment_variables": {},
   "parameters": {},
   "version": "2.3.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}