{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Importing necessary libraries\n",
    "from dotenv import load_dotenv\n",
    "from datetime import datetime, timedelta\n",
    "import requests\n",
    "import os\n",
    "import time\n",
    "import pandas as pd \n",
    "from textblob import TextBlob"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Defining a function to process news articles\n",
    "def process_news_articles(news_articles):\n",
    "    # Convert list of dictionaries to DataFrame\n",
    "    df = pd.DataFrame(news_articles)\n",
    "\n",
    "    # Drop rows where the description is NaN\n",
    "    df = df.dropna(subset=['description'])\n",
    "\n",
    "    # Fill missing 'amp_url' and 'keywords' with specific placeholders\n",
    "    df['amp_url'] = df['amp_url'].fillna('No URL provided')\n",
    "    df['keywords'] = df['keywords'].fillna('No keywords')\n",
    "\n",
    "    # Sentiment analysis on descriptions\n",
    "    df['sentiment'] = df['description'].apply(lambda text: TextBlob(text).sentiment.polarity)\n",
    "\n",
    "    # Convert 'published_utc' to datetime and extract date and time\n",
    "    df['published_utc'] = pd.to_datetime(df['published_utc'])\n",
    "    df['date'] = df['published_utc'].dt.date\n",
    "    df['time'] = df['published_utc'].dt.time\n",
    "\n",
    "    # Dropping unnecessary columns\n",
    "    df.drop(['published_utc'], axis=1, inplace=True)\n",
    "    # set date to index\n",
    "    df = df.set_index(\"date\")\n",
    "    df.reset_index(inplace=True)\n",
    "    df.index = pd.to_datetime(df.index)\n",
    "    df = df.groupby(['date', 'ticker'])['sentiment'].mean().reset_index()\n",
    "\n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Defining a function for the exponential moving average\n",
    "\n",
    "def exponential_moving_average(df, window):\n",
    "   # Calculate EMA on the 'sentiment' column\n",
    "    df[f'exp_mean_{window}_days'] = df['sentiment'].ewm(span=window, adjust=False).mean()\n",
    "    return df"
   ]
  }
 ],
 "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": "3.11.9"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}