{ "cells": [ { "cell_type": "markdown", "source": [ "# Changamoto: Kuchambua Maandishi Kuhusu Sayansi ya Data\n", "\n", "> *Katika daftari hili la kumbukumbu, tunajaribu kutumia URL tofauti - makala ya Wikipedia kuhusu Kujifunza kwa Mashine. Unaweza kuona kwamba, tofauti na Sayansi ya Data, makala hii ina maneno mengi, hii ikifanya uchambuzi kuwa na changamoto zaidi. Tunahitaji kufikiria njia nyingine ya kusafisha data baada ya kuchukua maneno muhimu, ili kuondoa mchanganyiko wa maneno yanayotokea mara nyingi, lakini yasiyo na maana.*\n", "\n", "Katika mfano huu, tufanye zoezi rahisi linalojumuisha hatua zote za mchakato wa jadi wa sayansi ya data. Huna haja ya kuandika msimbo wowote, unaweza kubofya seli zilizo hapa chini kuziendesha na kuangalia matokeo. Kama changamoto, unahimizwa kujaribu msimbo huu kwa data tofauti.\n", "\n", "## Lengo\n", "\n", "Katika somo hili, tumekuwa tukijadili dhana mbalimbali zinazohusiana na Sayansi ya Data. Hebu tujifunze zaidi kuhusu dhana zinazohusiana kwa kufanya **uchimbaji wa maandishi**. Tutaanza na maandishi kuhusu Sayansi ya Data, kuchukua maneno muhimu kutoka ndani yake, na kisha kujaribu kuona matokeo hayo kwa njia ya picha.\n", "\n", "Kama maandishi, nitumie ukurasa wa Sayansi ya Data kutoka Wikipedia:\n" ], "metadata": {} }, { "cell_type": "markdown", "source": [], "metadata": {} }, { "cell_type": "code", "execution_count": 2, "source": [ "url = 'https://en.wikipedia.org/wiki/Data_science'\r\n", "url = 'https://en.wikipedia.org/wiki/Machine_learning'" ], "outputs": [], "metadata": {} }, { "cell_type": "markdown", "source": [ "## Hatua ya 1: Kupata Data\n", "\n", "Hatua ya kwanza katika kila mchakato wa sayansi ya data ni kupata data. Tutatumia maktaba ya `requests` kufanya hivyo:\n" ], "metadata": {} }, { "cell_type": "code", "execution_count": 3, "source": [ "import requests\r\n", "\r\n", "text = requests.get(url).content.decode('utf-8')\r\n", "print(text[:1000])" ], "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "\n", "\n", "\n", "Machine learning - Wikipedia\n", "