{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "baabf11e-66a5-43a0-af86-25d998eab011",
   "metadata": {},
   "outputs": [],
   "source": [
    "# DEMO: Text Analytics with API call, required API key\n",
    "# Developed by Dr. Benyawarath \"Yaa\" Nithithanatchinnapat\n",
    "# Reference: Data Science from Scratch: First Principles with Python 2nd Edition by Joel Grus\n",
    "\n",
    "# Cell 1: Install the required packages\n",
    "# We add '--quiet' to hide the long installation text\n",
    "!pip install --quiet vaderSentiment wordcloud requests pandas matplotlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "091f728f-3d09-4ae1-982d-070e56a1badf",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Cell 2: Import the libraries (now that they're installed)\n",
    "import requests\n",
    "import pandas as pd\n",
    "from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer\n",
    "from wordcloud import WordCloud\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# --- Students: Change this to your API key ---\n",
    "API_KEY = \"---YOUR API KEY---\" \n",
    "COMPANY = \"COMPANY NAME\" \n",
    "\n",
    "# This is the \"menu item\" we're ordering\n",
    "url = f\"https://gnews.io/api/v4/search?q={COMPANY}&lang=en&token={API_KEY}\"\n",
    "\n",
    "# Make the request\n",
    "response = requests.get(url)\n",
    "data = response.json()\n",
    "\n",
    "# Show the raw, messy data\n",
    "print(\"Raw JSON data from the API:\")\n",
    "print(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "86996a7a-e1dd-46ed-8b40-f61896627534",
   "metadata": {},
   "outputs": [],
   "source": [
    "# The 'articles' key contains the list we want\n",
    "df = pd.DataFrame(data['articles'])\n",
    "\n",
    "# Let's just keep the columns we care about\n",
    "df = df[['title', 'description', 'url', 'source']]\n",
    "\n",
    "print(\"\\nCleaned Pandas DataFrame:\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e3725bea-a3e8-402a-a952-5dfea38eb16a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer\n",
    "\n",
    "# Create our analyzer \"object\"\n",
    "analyzer = SentimentIntensityAnalyzer()\n",
    "\n",
    "# A 'lambda' function is just a small, one-line function.\n",
    "# This one takes text (x) and gets the 'compound' score.\n",
    "# The 'compound' score is a single value from -1 (very negative) to +1 (very positive).\n",
    "\n",
    "df['sentiment_score'] = df['description'].apply(\n",
    "    lambda x: analyzer.polarity_scores(x)['compound']\n",
    ")\n",
    "\n",
    "print(\"\\nDataFrame with Sentiment Scores:\")\n",
    "print(df[['source', 'sentiment_score', 'title']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d800cea4-6c2b-4352-b731-517e2f562175",
   "metadata": {},
   "outputs": [],
   "source": [
    "from wordcloud import WordCloud\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Combine all descriptions into one big block of text\n",
    "all_text = \" \".join(df['description'])\n",
    "\n",
    "# Create the word cloud\n",
    "wordcloud = WordCloud(width=800, height=400, background_color='white').generate(all_text)\n",
    "\n",
    "# Display the visualization\n",
    "print(\"\\nKey Themes in the News:\")\n",
    "plt.figure(figsize=(10, 5))\n",
    "plt.imshow(wordcloud, interpolation='bilinear')\n",
    "plt.axis('off') # Hide the\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b9012ffb-a3c9-4614-b654-7845f0e7b836",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}