From 3b1bbc841b103ebe27cc26c1cdb1ec70b7e09364 Mon Sep 17 00:00:00 2001
From: Kenny Cardenas-Parra <75261600+kennycp06@users.noreply.github.com>
Date: Wed, 24 May 2023 14:09:42 -0500
Subject: [PATCH] Solution in a Jupyter Notebook of the assignment 1
---
.../solution/Solution Assignment 1.ipynb | 832 ++++++++++++++++++
1 file changed, 832 insertions(+)
create mode 100644 1-Introduction/01-defining-data-science/solution/Solution Assignment 1.ipynb
diff --git a/1-Introduction/01-defining-data-science/solution/Solution Assignment 1.ipynb b/1-Introduction/01-defining-data-science/solution/Solution Assignment 1.ipynb
new file mode 100644
index 00000000..147f265d
--- /dev/null
+++ b/1-Introduction/01-defining-data-science/solution/Solution Assignment 1.ipynb
@@ -0,0 +1,832 @@
+{
+ "cells": [
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Analyzing Data Mining about Big Data and Machine Learning\n",
+ "\n",
+ "This exercise serves as a practical application of the concepts and tools covered in Lesson 1. It provides an opportunity to apply and demonstrate the knowledge and skills acquired during the lesson.\n",
+ "\n",
+ "## Sources\n",
+ "\n",
+ "We will use the text from the wikipedia page \n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "url_bigdata = \"https://en.wikipedia.org/wiki/Big_data\"\n",
+ "url_machinelearning = \"https://en.wikipedia.org/wiki/Machine_learning\""
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 1:\n",
+ "\n",
+ "First step in every data science process is getting the data. We will use `requests` library to do that:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 26,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "-----------------------------------------------\n",
+ "Big Data Text\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "Big data - Wikipedia\n",
+ "