{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "Note: This notebook is free from any Personal Identifiable Information (PII)exposed API tokens, and outdated or vulnerable libraries."
      ],
      "metadata": {
        "id": "lNScDliRLnLV"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "R6ZAQbX7LB5l"
      },
      "outputs": [],
      "source": [
        "# Importing Safe and Updated Libraries\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "import datetime\n",
        "from matplotlib import pyplot as plt\n",
        "from sklearn.linear_model import LinearRegression"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Time Series Analysis using Pandas\n",
        "# Create a date range\n",
        "date_rng = pd.date_range(start='1/01/2023', end='1/10/2023', freq='H')"
      ],
      "metadata": {
        "id": "oxMnBJncLJyH"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Create a DataFrame\n",
        "df = pd.DataFrame(date_rng, columns=['date'])"
      ],
      "metadata": {
        "id": "gOX_vL4lLMmq"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Generate some random data\n",
        "df['data'] = np.random.randint(0,100,size=(len(date_rng)))"
      ],
      "metadata": {
        "id": "52rGQNM-LRsO"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Set the date column as index\n",
        "df['datetime'] = pd.to_datetime(df['date'])\n",
        "df = df.set_index('datetime')\n",
        "df.drop(['date'], axis=1, inplace=True)"
      ],
      "metadata": {
        "id": "Oz4NQyeqLXKW"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Resample the DataFrame to calculate daily means\n",
        "df_resampled = df.resample('D').mean()"
      ],
      "metadata": {
        "id": "ees6U5rfLaw-"
      },
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Display the resampled DataFrame\n",
        "print(df_resampled)"
      ],
      "metadata": {
        "id": "sdkU13xrLdKT"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Prediction part\n",
        "X = [i for i in range(0, len(df_resampled))]\n",
        "X = np.reshape(X, (len(X), 1))\n",
        "y = df_resampled['data'].tolist()\n",
        "model = LinearRegression()\n",
        "model.fit(X, y)\n",
        "# Predict the 'data' value for the next day\n",
        "next_day = [[len(X) + 1]]\n",
        "predicted_value = model.predict(next_day)\n",
        "print('The predicted average value for the next day is: ', predicted_value[0])"
      ],
      "metadata": {
        "id": "8x0pvqnrLiKF"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}