initial commit + add: function to get channel stats.

Youtube API + Data Analysis/yt.ipynb

@@ -0,0 +1,216 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### **Importing Libraries**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import pandas as pd\n",
+    "import seaborn as sns\n",
+    "\n",
+    "from googleapiclient.discovery import build"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### **Setting up YouTube API.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "api_service_name = \"youtube\"\n",
+    "api_version = \"v3\"\n",
+    "\n",
+    "yt_api_key = os.environ[\"YT_API_KEY\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### **I. Scraping Channel Statistics.**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Getting Channel ID's."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "channel_ids = [\n",
+    "    \"UCX6OQ3DkcsbYNE6H8uQQuVA\",\n",
+    "    \"UC59ZRYCHev_IqjUhremZ8Tg\",\n",
+    "    \"UCvgfXK4nTYKudb0rFR6noLA\",\n",
+    "    \"UCc0YbtMkRdhcqwhu3Oad-lw\",\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Building YouTube API Service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "youtube = build(api_service_name, api_version, developerKey=yt_api_key)  "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Function to obtain channel statistics."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_channel_statistics(youtube, channel_ids):\n",
+    "    data = []\n",
+    "\n",
+    "    request = youtube.channels().list(\n",
+    "        part=\"snippet,contentDetails,statistics\", id=\",\".join(channel_ids)\n",
+    "    )\n",
+    "\n",
+    "    response = request.execute()\n",
+    "\n",
+    "    for i in range(len(response[\"items\"])):\n",
+    "        info = dict(\n",
+    "            channel_name=response[\"items\"][i][\"snippet\"][\"title\"],\n",
+    "            subscribers=response[\"items\"][i][\"statistics\"][\"subscriberCount\"],\n",
+    "            videos=response[\"items\"][i][\"statistics\"][\"videoCount\"],\n",
+    "            views=response[\"items\"][i][\"statistics\"][\"viewCount\"],\n",
+    "            # --------\n",
+    "            playlist_id=response[\"items\"][i][\"contentDetails\"][\"relatedPlaylists\"]['uploads'],\n",
+    "        )\n",
+    "\n",
+    "        data.append(info)\n",
+    "\n",
+    "    return data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "channel_statistics = get_channel_statistics(youtube, channel_ids)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Create a dataframe. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "channel_df = pd.DataFrame(channel_statistics)\n",
+    "channel_df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Change datatype from object to integer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "channel_df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "exclude_cols = ['channel_name']\n",
+    "\n",
+    "cols_to_include = [col for col in channel_df.columns if col not in exclude_cols]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "channel_df[cols_to_include] = channel_df[cols_to_include].applymap(pd.to_numeric, errors='coerce')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "channel_df.dtypes"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}