| { | |
| "cells": [ | |
| { | |
| "cell_type": "markdown", | |
| "metadata": {}, | |
| "source": [ | |
| "<h3>Semantic crosslinking article recommender</h3><p>@author: Natzir Turrado: Technical SEO / Data Scientist. <a href=\"https://twitter.com/natzir9\">Twitter > @natzir9</a></p>\n" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 1, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "import pandas as pd\n", | |
| "import matplotlib.pyplot as plt\n", | |
| "import nltk\n", | |
| "from sklearn.feature_extraction.text import TfidfVectorizer\n", | |
| "from sklearn.decomposition import NMF\n", | |
| "from sklearn.preprocessing import normalize\n", | |
| "from nltk.corpus import stopwords\n", | |
| "from IPython.display import display" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": {}, | |
| "source": [ | |
| "Crawl your site an get the title and the content of every post. Create an excel file named \"data.xlsx\" and save it in the same work space as this file.\n", | |
| "<ul>\n", | |
| "<li><a href=\"https://builtvisible.com/seo-guide-to-xpath/\">XPATH for SEO's</a></li>\n", | |
| "<li><a href=\"https://www.screamingfrog.co.uk/web-scraping/\">Web Scraping & Data Extraction</a></li>\n", | |
| "</ul>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 2, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/html": [ | |
| "<div>\n", | |
| "<style scoped>\n", | |
| " .dataframe tbody tr th:only-of-type {\n", | |
| " vertical-align: middle;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe tbody tr th {\n", | |
| " vertical-align: top;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe thead th {\n", | |
| " text-align: right;\n", | |
| " }\n", | |
| "</style>\n", | |
| "<table border=\"1\" class=\"dataframe\">\n", | |
| " <thead>\n", | |
| " <tr style=\"text-align: right;\">\n", | |
| " <th></th>\n", | |
| " <th>title</th>\n", | |
| " <th>article</th>\n", | |
| " </tr>\n", | |
| " </thead>\n", | |
| " <tbody>\n", | |
| " <tr>\n", | |
| " <td>0</td>\n", | |
| " <td>SEO para Progressive Web APPs (PWA) y JavaScript</td>\n", | |
| " <td>Este artículo es un resumen que hemos hecho Ch...</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>1</td>\n", | |
| " <td>Cómo mejorar el SEO incrementando la frecuenci...</td>\n", | |
| " <td>Siempre digo que es mejor remar a favor que ir...</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>2</td>\n", | |
| " <td>CTR y SEO: Manipulación del CTR para influir e...</td>\n", | |
| " <td>Últimamente se han puesto pesaditos con el tem...</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>3</td>\n", | |
| " <td>Las mejores herramientas de visualización de d...</td>\n", | |
| " <td>Artículo publicado en Doctor Metrics sobre her...</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>4</td>\n", | |
| " <td>Cómo hacer un Heatmap de las visitas de tu web...</td>\n", | |
| " <td>Visualizar la información en forma de mapa de ...</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>\n", | |
| "</div>" | |
| ], | |
| "text/plain": [ | |
| " title \\\n", | |
| "0 SEO para Progressive Web APPs (PWA) y JavaScript \n", | |
| "1 Cómo mejorar el SEO incrementando la frecuenci... \n", | |
| "2 CTR y SEO: Manipulación del CTR para influir e... \n", | |
| "3 Las mejores herramientas de visualización de d... \n", | |
| "4 Cómo hacer un Heatmap de las visitas de tu web... \n", | |
| "\n", | |
| " article \n", | |
| "0 Este artículo es un resumen que hemos hecho Ch... \n", | |
| "1 Siempre digo que es mejor remar a favor que ir... \n", | |
| "2 Últimamente se han puesto pesaditos con el tem... \n", | |
| "3 Artículo publicado en Doctor Metrics sobre her... \n", | |
| "4 Visualizar la información en forma de mapa de ... " | |
| ] | |
| }, | |
| "metadata": {}, | |
| "output_type": "display_data" | |
| } | |
| ], | |
| "source": [ | |
| "df = pd.read_excel('data.xlsx')\n", | |
| "display(df.head())" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 3, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "articles = df.article.tolist()\n", | |
| "titles = df.title.tolist()" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": {}, | |
| "source": [ | |
| "Transforming a list of documents into a word frequency array (TF-IDF). I'm only accepting words (token_pattern) and ignoring terms that appear in more than 60% of the documents (max_df) and that appear in less than 1 document (min_df). You should test than on a bigger website than my blog. <a href=\"http://dfrancis.co/2017/10/06/tf-idf-vectorizer-fit-and-transform/\">More info on min_df & max_df here</a>." | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 4, | |
| "metadata": { | |
| "scrolled": true | |
| }, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "['aarrr',\n", | |
| " 'abajo',\n", | |
| " 'abandonamos',\n", | |
| " 'abandonar',\n", | |
| " 'abandone',\n", | |
| " 'abandono',\n", | |
| " 'abandonos',\n", | |
| " 'abarcan',\n", | |
| " 'abc',\n", | |
| " 'abierta',\n", | |
| " 'abiertas',\n", | |
| " 'ability',\n", | |
| " 'abismales',\n", | |
| " 'about',\n", | |
| " 'above',\n", | |
| " 'abrazando',\n", | |
| " 'abril',\n", | |
| " 'abrimos',\n", | |
| " 'abrir',\n", | |
| " 'abrirlo',\n", | |
| " 'absoluta',\n", | |
| " 'absolutamente',\n", | |
| " 'absolutas',\n", | |
| " 'absoluto',\n", | |
| " 'abuelo',\n", | |
| " 'abundancia',\n", | |
| " 'aburriros',\n", | |
| " 'acaba',\n", | |
| " 'acababan',\n", | |
| " 'acabado',\n", | |
| " 'acaban',\n", | |
| " 'acabar',\n", | |
| " 'acabaremos',\n", | |
| " 'acabe',\n", | |
| " 'acaben',\n", | |
| " 'acabo',\n", | |
| " 'acceda',\n", | |
| " 'accede',\n", | |
| " 'acceder',\n", | |
| " 'accedido',\n", | |
| " 'accesibilidad',\n", | |
| " 'accesible',\n", | |
| " 'accesibles',\n", | |
| " 'accesiblesanaliza',\n", | |
| " 'accesiblesporcentaje',\n", | |
| " 'acceso',\n", | |
| " 'accesos',\n", | |
| " 'accionable',\n", | |
| " 'accionables',\n", | |
| " 'acciones',\n", | |
| " 'acento',\n", | |
| " 'acepta',\n", | |
| " 'aceptada',\n", | |
| " 'aceptadas',\n", | |
| " 'aceptados',\n", | |
| " 'aceptar',\n", | |
| " 'aceptarlas',\n", | |
| " 'acerca',\n", | |
| " 'acercarse',\n", | |
| " 'acertar',\n", | |
| " 'acierto',\n", | |
| " 'aconsejar',\n", | |
| " 'aconsejo',\n", | |
| " 'acordamos',\n", | |
| " 'acordaros',\n", | |
| " 'acortar',\n", | |
| " 'acostumbrados',\n", | |
| " 'acotar',\n", | |
| " 'acquisition',\n", | |
| " 'across',\n", | |
| " 'action',\n", | |
| " 'actionsitelinksrich',\n", | |
| " 'actitud',\n", | |
| " 'actitudes',\n", | |
| " 'activa',\n", | |
| " 'activado',\n", | |
| " 'activador',\n", | |
| " 'activan',\n", | |
| " 'activar',\n", | |
| " 'activas',\n", | |
| " 'activation',\n", | |
| " 'actividad',\n", | |
| " 'actividades',\n", | |
| " 'activity',\n", | |
| " 'activo',\n", | |
| " 'activos',\n", | |
| " 'actual',\n", | |
| " 'actuales',\n", | |
| " 'actualesa',\n", | |
| " 'actualidad',\n", | |
| " 'actualiza',\n", | |
| " 'actualizada',\n", | |
| " 'actualizar',\n", | |
| " 'actualizarse',\n", | |
| " 'actualizo',\n", | |
| " 'actualmente',\n", | |
| " 'actuamos',\n", | |
| " 'actuar',\n", | |
| " 'acuerda',\n", | |
| " 'acuerdo',\n", | |
| " 'ad',\n", | |
| " 'adams',\n", | |
| " 'adaptado',\n", | |
| " 'adaptan',\n", | |
| " 'adaptar',\n", | |
| " 'adaptarlos',\n", | |
| " 'adaptarse',\n", | |
| " 'adapten',\n", | |
| " 'addeventlistener',\n", | |
| " 'adding',\n", | |
| " 'addon',\n", | |
| " 'adecuada',\n", | |
| " 'adecuadas',\n", | |
| " 'adecuado',\n", | |
| " 'adecuados',\n", | |
| " 'adelantado',\n", | |
| " 'adelante',\n", | |
| " 'adelantee',\n", | |
| " 'adelanto',\n", | |
| " 'ademas',\n", | |
| " 'adjuntado',\n", | |
| " 'adjust',\n", | |
| " 'admin',\n", | |
| " 'administrador',\n", | |
| " 'administrativas',\n", | |
| " 'admitan',\n", | |
| " 'adora',\n", | |
| " 'adquirido',\n", | |
| " 'adquiriendo',\n", | |
| " 'adquirir',\n", | |
| " 'adquisitivo',\n", | |
| " 'adri',\n", | |
| " 'ads',\n", | |
| " 'adsense',\n", | |
| " 'advance',\n", | |
| " 'adversario',\n", | |
| " 'adversidad',\n", | |
| " 'adverstising',\n", | |
| " 'advertisign',\n", | |
| " 'advertising',\n", | |
| " 'advocate',\n", | |
| " 'adwords',\n", | |
| " 'adwordsgoogle',\n", | |
| " 'aede',\n", | |
| " 'afecta',\n", | |
| " 'afectadas',\n", | |
| " 'afectado',\n", | |
| " 'afectan',\n", | |
| " 'afectando',\n", | |
| " 'afectar',\n", | |
| " 'afectarnos',\n", | |
| " 'afiliado',\n", | |
| " 'afiliados',\n", | |
| " 'afines',\n", | |
| " 'afirma',\n", | |
| " 'afirmaciones',\n", | |
| " 'afirman',\n", | |
| " 'afirme',\n", | |
| " 'afrontar',\n", | |
| " 'after',\n", | |
| " 'again',\n", | |
| " 'against',\n", | |
| " 'agencia',\n", | |
| " 'agencias',\n", | |
| " 'agents',\n", | |
| " 'agilidad',\n", | |
| " 'agilizar',\n", | |
| " 'agosto',\n", | |
| " 'agotados',\n", | |
| " 'agradece',\n", | |
| " 'agradecer',\n", | |
| " 'agradecido',\n", | |
| " 'agrega',\n", | |
| " 'agregado',\n", | |
| " 'agregados',\n", | |
| " 'agregas',\n", | |
| " 'agrupados',\n", | |
| " 'agrupar',\n", | |
| " 'agruparlos',\n", | |
| " 'agua',\n", | |
| " 'agujeros',\n", | |
| " 'ah',\n", | |
| " 'ahora',\n", | |
| " 'ahorrar',\n", | |
| " 'ahrefs',\n", | |
| " 'ai',\n", | |
| " 'aida',\n", | |
| " 'aidas',\n", | |
| " 'airways',\n", | |
| " 'aisladas',\n", | |
| " 'aislar',\n", | |
| " 'alberto',\n", | |
| " 'alcachofas',\n", | |
| " 'alcance',\n", | |
| " 'alcanzables',\n", | |
| " 'alcanzablesderivado',\n", | |
| " 'alcanzar',\n", | |
| " 'alchemyapi',\n", | |
| " 'alemania',\n", | |
| " 'alerta',\n", | |
| " 'alerting',\n", | |
| " 'alexa',\n", | |
| " 'aleyda',\n", | |
| " 'algoritmia',\n", | |
| " 'algoritmo',\n", | |
| " 'algoritmos',\n", | |
| " 'alguien',\n", | |
| " 'alguna',\n", | |
| " 'alguno',\n", | |
| " 'aliada',\n", | |
| " 'alignment',\n", | |
| " 'alinea',\n", | |
| " 'alineadas',\n", | |
| " 'alinean',\n", | |
| " 'alinearlo',\n", | |
| " 'alineen',\n", | |
| " 'all',\n", | |
| " 'allows',\n", | |
| " 'allowscriptaccess',\n", | |
| " 'almacenado',\n", | |
| " 'almacene',\n", | |
| " 'almost',\n", | |
| " 'alone',\n", | |
| " 'along',\n", | |
| " 'alpha',\n", | |
| " 'alphami',\n", | |
| " 'alphaprobar',\n", | |
| " 'alquiler',\n", | |
| " 'already',\n", | |
| " 'alrededor',\n", | |
| " 'also',\n", | |
| " 'alta',\n", | |
| " 'altas',\n", | |
| " 'alterando',\n", | |
| " 'alterativas',\n", | |
| " 'alternate',\n", | |
| " 'alternativa',\n", | |
| " 'alternativas',\n", | |
| " 'alto',\n", | |
| " 'altruismo',\n", | |
| " 'altura',\n", | |
| " 'alturas',\n", | |
| " 'alucinar',\n", | |
| " 'alumnos',\n", | |
| " 'always',\n", | |
| " 'amateur',\n", | |
| " 'amateurs',\n", | |
| " 'amazoncart',\n", | |
| " 'amb',\n", | |
| " 'ambas',\n", | |
| " 'ambientadas',\n", | |
| " 'ambiente',\n", | |
| " 'ambiguaciones',\n", | |
| " 'ambos',\n", | |
| " 'ameno',\n", | |
| " 'americano',\n", | |
| " 'amigable',\n", | |
| " 'amigo',\n", | |
| " 'amigos',\n", | |
| " 'amiguetes',\n", | |
| " 'amoldarnos',\n", | |
| " 'amos',\n", | |
| " 'amp',\n", | |
| " 'amphtml',\n", | |
| " 'amplia',\n", | |
| " 'ampliando',\n", | |
| " 'amplio',\n", | |
| " 'an',\n", | |
| " 'analicemos',\n", | |
| " 'analista',\n", | |
| " 'analistas',\n", | |
| " 'analistaseo',\n", | |
| " 'analitica',\n", | |
| " 'analiza',\n", | |
| " 'analizada',\n", | |
| " 'analizado',\n", | |
| " 'analizados',\n", | |
| " 'analizamos',\n", | |
| " 'analizando',\n", | |
| " 'analizar',\n", | |
| " 'analizarlos',\n", | |
| " 'analizaron',\n", | |
| " 'analizo',\n", | |
| " 'analyst',\n", | |
| " 'analyticator',\n", | |
| " 'analytics',\n", | |
| " 'analyticsdescubre',\n", | |
| " 'analyticseste',\n", | |
| " 'analyticsgracias',\n", | |
| " 'analyticsla',\n", | |
| " 'analyticslas',\n", | |
| " 'analyticslo',\n", | |
| " 'analyticspasadas',\n", | |
| " 'analyticspero',\n", | |
| " 'analyticspor',\n", | |
| " 'analyticstracking',\n", | |
| " 'ancho',\n", | |
| " 'anchor',\n", | |
| " 'anchoring',\n", | |
| " 'anchors',\n", | |
| " 'anchos',\n", | |
| " 'ancla',\n", | |
| " 'and',\n", | |
| " 'andorra',\n", | |
| " 'andrew',\n", | |
| " 'android',\n", | |
| " 'angular',\n", | |
| " 'anillo',\n", | |
| " 'anima',\n", | |
| " 'animado',\n", | |
| " 'animales',\n", | |
| " 'animar',\n", | |
| " 'animo',\n", | |
| " 'anne',\n", | |
| " 'ano',\n", | |
| " 'anotaciones',\n", | |
| " 'another',\n", | |
| " 'ansias',\n", | |
| " 'ansidad',\n", | |
| " 'ansiedad',\n", | |
| " 'answering',\n", | |
| " 'antecedentes',\n", | |
| " 'antecedentesos',\n", | |
| " 'anterior',\n", | |
| " 'anteriores',\n", | |
| " 'anterioridad',\n", | |
| " 'anteriormente',\n", | |
| " 'anti',\n", | |
| " 'antiguo',\n", | |
| " 'antiguos',\n", | |
| " 'antivirus',\n", | |
| " 'antojo',\n", | |
| " 'anual',\n", | |
| " 'anunciado',\n", | |
| " 'anunciante',\n", | |
| " 'anunciar',\n", | |
| " 'anuncio',\n", | |
| " 'anuncios',\n", | |
| " 'anyone',\n", | |
| " 'aol',\n", | |
| " 'aov',\n", | |
| " 'apagar',\n", | |
| " 'aparatejo',\n", | |
| " 'aparece',\n", | |
| " 'aparecen',\n", | |
| " 'aparecer',\n", | |
| " 'apareces',\n", | |
| " 'aparecido',\n", | |
| " 'apareciendo',\n", | |
| " 'aparecieran',\n", | |
| " 'aparezca',\n", | |
| " 'aparezcan',\n", | |
| " 'apartado',\n", | |
| " 'aparte',\n", | |
| " 'apelar',\n", | |
| " 'apenas',\n", | |
| " 'apertura',\n", | |
| " 'api',\n", | |
| " 'apis',\n", | |
| " 'aplica',\n", | |
| " 'aplicables',\n", | |
| " 'aplicaciones',\n", | |
| " 'aplicada',\n", | |
| " 'aplicadas',\n", | |
| " 'aplicado',\n", | |
| " 'aplicados',\n", | |
| " 'aplicamos',\n", | |
| " 'aplicando',\n", | |
| " 'aplicar',\n", | |
| " 'aplicarlo',\n", | |
| " 'aplicarlos',\n", | |
| " 'aplicas',\n", | |
| " 'aplication',\n", | |
| " 'aplico',\n", | |
| " 'aplique',\n", | |
| " 'aporta',\n", | |
| " 'aportado',\n", | |
| " 'aportar',\n", | |
| " 'aporten',\n", | |
| " 'apostado',\n", | |
| " 'apostar',\n", | |
| " 'apoyar',\n", | |
| " 'apoyas',\n", | |
| " 'apoyo',\n", | |
| " 'app',\n", | |
| " 'appanalytics',\n", | |
| " 'apple',\n", | |
| " 'approved',\n", | |
| " 'apps',\n", | |
| " 'appuna',\n", | |
| " 'aprendan',\n", | |
| " 'aprende',\n", | |
| " 'aprender',\n", | |
| " 'aprendido',\n", | |
| " 'aprendiendo',\n", | |
| " 'aprendizaje',\n", | |
| " 'aprendizajes',\n", | |
| " 'aprendo',\n", | |
| " 'aprobados',\n", | |
| " 'aprovechado',\n", | |
| " 'aprovechando',\n", | |
| " 'aprovechar',\n", | |
| " 'aprovecharlo',\n", | |
| " 'aprovecho',\n", | |
| " 'aprox',\n", | |
| " 'aproxima',\n", | |
| " 'aproximada',\n", | |
| " 'aproximadamente',\n", | |
| " 'aproximado',\n", | |
| " 'apunte',\n", | |
| " 'aquel',\n", | |
| " 'aquella',\n", | |
| " 'aquellas',\n", | |
| " 'aquello',\n", | |
| " 'aquellos',\n", | |
| " 'arcas',\n", | |
| " 'archidemostrada',\n", | |
| " 'archivada',\n", | |
| " 'archive',\n", | |
| " 'archivo',\n", | |
| " 'archivos',\n", | |
| " 'are',\n", | |
| " 'argumentos',\n", | |
| " 'armar',\n", | |
| " 'armoniosa',\n", | |
| " 'arquitectura',\n", | |
| " 'arquitecturaa',\n", | |
| " 'arreglado',\n", | |
| " 'arreglan',\n", | |
| " 'arreglando',\n", | |
| " 'arreglar',\n", | |
| " 'arriba',\n", | |
| " 'arruinar',\n", | |
| " 'arte',\n", | |
| " 'artesanales',\n", | |
| " 'articles',\n", | |
| " 'artificial',\n", | |
| " 'artificialmente',\n", | |
| " 'arturo',\n", | |
| " 'arturomarimon',\n", | |
| " 'as',\n", | |
| " 'asegura',\n", | |
| " 'asegurar',\n", | |
| " 'asegurarnos',\n", | |
| " 'asegurarse',\n", | |
| " 'aseguras',\n", | |
| " 'asesorados',\n", | |
| " 'asignado',\n", | |
| " 'asignando',\n", | |
| " 'asignar',\n", | |
| " 'asignarles',\n", | |
| " 'asimilado',\n", | |
| " 'asimilar',\n", | |
| " 'asistencial',\n", | |
| " 'asistentes',\n", | |
| " 'asistidas',\n", | |
| " 'asistiendo',\n", | |
| " 'ask',\n", | |
| " 'asociada',\n", | |
| " 'asociados',\n", | |
| " 'asociar',\n", | |
| " 'asociarse',\n", | |
| " 'asociativo',\n", | |
| " 'asombrados',\n", | |
| " 'asp',\n", | |
| " 'aspecto',\n", | |
| " 'aspectos',\n", | |
| " 'assesor',\n", | |
| " 'assets',\n", | |
| " 'assisted',\n", | |
| " 'asumidas',\n", | |
| " 'asumir',\n", | |
| " 'asunciones',\n", | |
| " 'asunto',\n", | |
| " 'asustarnos',\n", | |
| " 'async',\n", | |
| " 'atacante',\n", | |
| " 'atacaremos',\n", | |
| " 'atado',\n", | |
| " 'ataque',\n", | |
| " 'atenta',\n", | |
| " 'aterrice',\n", | |
| " 'aterriza',\n", | |
| " 'aterrizado',\n", | |
| " 'aterrizaje',\n", | |
| " 'aterrizan',\n", | |
| " 'aterrizaron',\n", | |
| " 'aterrize',\n", | |
| " 'atractivas',\n", | |
| " 'atrae',\n", | |
| " 'atraen',\n", | |
| " 'atraer',\n", | |
| " 'atraigan',\n", | |
| " 'atribuir',\n", | |
| " 'atributos',\n", | |
| " 'atts',\n", | |
| " 'aturar',\n", | |
| " 'auc',\n", | |
| " 'audiencia',\n", | |
| " 'auditadas',\n", | |
| " 'auditado',\n", | |
| " 'auditar',\n", | |
| " 'auditivo',\n", | |
| " 'augure',\n", | |
| " 'august',\n", | |
| " 'aumenta',\n", | |
| " 'aumentado',\n", | |
| " 'aumentan',\n", | |
| " 'aumentando',\n", | |
| " 'aumentar',\n", | |
| " 'aumentaremos',\n", | |
| " 'aumentaron',\n", | |
| " 'aumentas',\n", | |
| " 'aumente',\n", | |
| " 'aumento',\n", | |
| " 'aun',\n", | |
| " 'aunque',\n", | |
| " 'author',\n", | |
| " 'authority',\n", | |
| " 'authorrank',\n", | |
| " 'auto',\n", | |
| " 'autor',\n", | |
| " 'autores',\n", | |
| " 'autoridad',\n", | |
| " 'autoridadpara',\n", | |
| " 'autoritario',\n", | |
| " 'av',\n", | |
| " 'avanza',\n", | |
| " 'avanzadas',\n", | |
| " 'avanzado',\n", | |
| " 'avanzados',\n", | |
| " 'avanzar',\n", | |
| " 'aveces',\n", | |
| " 'avecinaba',\n", | |
| " 'aventurero',\n", | |
| " 'average',\n", | |
| " 'avg',\n", | |
| " 'avinash',\n", | |
| " 'avisa',\n", | |
| " 'avisando',\n", | |
| " 'avisarte',\n", | |
| " 'avises',\n", | |
| " 'aviso',\n", | |
| " 'awareness',\n", | |
| " 'awarness',\n", | |
| " 'ayer',\n", | |
| " 'ayuda',\n", | |
| " 'ayudado',\n", | |
| " 'ayudamos',\n", | |
| " 'ayudan',\n", | |
| " 'ayudar',\n", | |
| " 'ayudaron',\n", | |
| " 'ayuden',\n", | |
| " 'azar',\n", | |
| " 'azul',\n", | |
| " 'azules',\n", | |
| " 'b',\n", | |
| " 'back',\n", | |
| " 'backend',\n", | |
| " 'backlinks',\n", | |
| " 'backlinkwatches',\n", | |
| " 'baeza',\n", | |
| " 'baezaeste',\n", | |
| " 'baidu',\n", | |
| " 'baja',\n", | |
| " 'bajada',\n", | |
| " 'bajadas',\n", | |
| " 'bajamos',\n", | |
| " 'bajar',\n", | |
| " 'baje',\n", | |
| " 'bajo',\n", | |
| " 'balas',\n", | |
| " 'banca',\n", | |
| " 'bandera',\n", | |
| " 'banderas',\n", | |
| " 'bandwidth',\n", | |
| " 'baneadas',\n", | |
| " 'banner',\n", | |
| " 'bar',\n", | |
| " 'barcelona',\n", | |
| " 'barra',\n", | |
| " 'barreras',\n", | |
| " 'barrio',\n", | |
| " 'barry',\n", | |
| " 'basaba',\n", | |
| " 'basadas',\n", | |
| " 'basado',\n", | |
| " 'basados',\n", | |
| " 'basamos',\n", | |
| " 'basan',\n", | |
| " 'basarse',\n", | |
| " 'base',\n", | |
| " 'bases',\n", | |
| " 'basis',\n", | |
| " 'basta',\n", | |
| " 'bastante',\n", | |
| " 'basura',\n", | |
| " 'batch',\n", | |
| " 'baymard',\n", | |
| " 'bbdd',\n", | |
| " 'be',\n", | |
| " 'beefeater',\n", | |
| " 'before',\n", | |
| " 'behavior',\n", | |
| " 'behavioral',\n", | |
| " 'benchmark',\n", | |
| " 'benedict',\n", | |
| " 'beneficiado',\n", | |
| " 'beneficie',\n", | |
| " 'beneficio',\n", | |
| " 'beneficios',\n", | |
| " 'beneficiosa',\n", | |
| " 'beneficiosas',\n", | |
| " 'best',\n", | |
| " 'bestia',\n", | |
| " 'beta',\n", | |
| " 'better',\n", | |
| " 'bettman',\n", | |
| " 'bichotoblog',\n", | |
| " 'bien',\n", | |
| " 'big',\n", | |
| " 'bigbadlondon',\n", | |
| " 'bill',\n", | |
| " 'billete',\n", | |
| " 'billion',\n", | |
| " 'billones',\n", | |
| " 'binario',\n", | |
| " 'bing',\n", | |
| " 'binocular',\n", | |
| " 'biology',\n", | |
| " 'bits',\n", | |
| " 'bj',\n", | |
| " 'black',\n", | |
| " 'blackhat',\n", | |
| " 'blanca',\n", | |
| " 'blanco',\n", | |
| " 'blog',\n", | |
| " 'blogactualmente',\n", | |
| " 'blogs',\n", | |
| " 'bloguismo',\n", | |
| " 'bloqueado',\n", | |
| " 'bloqueados',\n", | |
| " 'bloquean',\n", | |
| " 'bloqueando',\n", | |
| " 'bloquedos',\n", | |
| " 'bobbink',\n", | |
| " 'body',\n", | |
| " 'bola',\n", | |
| " 'bonito',\n", | |
| " 'booksquery',\n", | |
| " 'boom',\n", | |
| " 'boost',\n", | |
| " 'booster',\n", | |
| " 'borra',\n", | |
| " 'borrado',\n", | |
| " 'borran',\n", | |
| " 'borrar',\n", | |
| " 'borre',\n", | |
| " 'bot',\n", | |
| " 'botella',\n", | |
| " 'botones',\n", | |
| " 'bots',\n", | |
| " 'bottom',\n", | |
| " 'bounce',\n", | |
| " 'brainsins',\n", | |
| " 'brand',\n", | |
| " 'branding',\n", | |
| " 'branzai',\n", | |
| " 'breadcrumb',\n", | |
| " 'break',\n", | |
| " 'breve',\n", | |
| " 'brexit',\n", | |
| " 'brillantes',\n", | |
| " 'brin',\n", | |
| " 'brindan',\n", | |
| " 'british',\n", | |
| " 'brock',\n", | |
| " 'broken',\n", | |
| " 'broma',\n", | |
| " 'browser',\n", | |
| " 'brqhcbfwsg',\n", | |
| " 'brutal',\n", | |
| " 'brutos',\n", | |
| " 'budget',\n", | |
| " 'buen',\n", | |
| " 'buena',\n", | |
| " 'buenas',\n", | |
| " 'bueno',\n", | |
| " 'buenodos',\n", | |
| " 'buenos',\n", | |
| " 'buffer',\n", | |
| " 'bug',\n", | |
| " 'builder',\n", | |
| " 'building',\n", | |
| " 'builing',\n", | |
| " 'bulo',\n", | |
| " 'bumm',\n", | |
| " 'busca',\n", | |
| " 'buscaba',\n", | |
| " 'buscaban',\n", | |
| " 'buscado',\n", | |
| " 'buscador',\n", | |
| " 'buscadoren',\n", | |
| " 'buscadores',\n", | |
| " 'buscadoreslos',\n", | |
| " 'buscadorespero',\n", | |
| " 'buscadorporque',\n", | |
| " 'buscamos',\n", | |
| " 'buscan',\n", | |
| " 'buscando',\n", | |
| " 'buscar',\n", | |
| " 'buscarlo',\n", | |
| " 'buscaron',\n", | |
| " 'buscas',\n", | |
| " 'busquen',\n", | |
| " 'busques',\n", | |
| " 'by',\n", | |
| " 'byte',\n", | |
| " 'c',\n", | |
| " 'cabeceras',\n", | |
| " 'cabecerasse',\n", | |
| " 'cabeza',\n", | |
| " 'cabezas',\n", | |
| " 'cabo',\n", | |
| " 'cache',\n", | |
| " 'cacheada',\n", | |
| " 'cacheo',\n", | |
| " 'cacioppo',\n", | |
| " 'cada',\n", | |
| " 'cadenas',\n", | |
| " 'caduco',\n", | |
| " 'cae',\n", | |
| " 'caer',\n", | |
| " 'caffeine',\n", | |
| " 'caja',\n", | |
| " 'calcula',\n", | |
| " 'calculadora',\n", | |
| " 'calculamos',\n", | |
| " 'calcular',\n", | |
| " 'calcularlo',\n", | |
| " 'caldeado',\n", | |
| " 'calendario',\n", | |
| " 'calidad',\n", | |
| " 'calidadal',\n", | |
| " 'calientes',\n", | |
| " 'california',\n", | |
| " 'call',\n", | |
| " 'calma',\n", | |
| " 'calor',\n", | |
| " 'cambia',\n", | |
| " 'cambiado',\n", | |
| " 'cambian',\n", | |
| " 'cambiando',\n", | |
| " 'cambiar',\n", | |
| " 'cambiarle',\n", | |
| " 'cambiarlo',\n", | |
| " 'cambie',\n", | |
| " 'cambies',\n", | |
| " 'cambio',\n", | |
| " 'cambiopagina',\n", | |
| " 'cambios',\n", | |
| " 'camello',\n", | |
| " 'camino',\n", | |
| " 'caminos',\n", | |
| " 'camisetas',\n", | |
| " 'campo',\n", | |
| " 'campos',\n", | |
| " 'camposresponsable',\n", | |
| " 'can',\n", | |
| " 'canal',\n", | |
| " 'canales',\n", | |
| " 'canary',\n", | |
| " 'canibalices',\n", | |
| " 'canonical',\n", | |
| " 'canonicalitis',\n", | |
| " 'cansa',\n", | |
| " 'cansado',\n", | |
| " 'cantando',\n", | |
| " 'cantidad',\n", | |
| " 'capaces',\n", | |
| " 'capacidad',\n", | |
| " 'capadas',\n", | |
| " 'capando',\n", | |
| " 'capas',\n", | |
| " 'capaz',\n", | |
| " 'captados',\n", | |
| " 'captar',\n", | |
| " 'captcha',\n", | |
| " 'captchas',\n", | |
| " 'captchaslos',\n", | |
| " 'captology',\n", | |
| " 'capturar',\n", | |
| " 'capturas',\n", | |
| " 'cara',\n", | |
| " 'caracteres',\n", | |
| " 'caramelo',\n", | |
| " 'caras',\n", | |
| " 'card',\n", | |
| " 'cardinal',\n", | |
| " 'cards',\n", | |
| " 'carencia',\n", | |
| " 'carga',\n", | |
| " 'cargando',\n", | |
| " 'cargar',\n", | |
| " 'cargarlos',\n", | |
| " 'cargarse',\n", | |
| " 'cargarte',\n", | |
| " 'carguemos',\n", | |
| " 'carguen',\n", | |
| " 'carlos',\n", | |
| " 'carlosredondo',\n", | |
| " 'caro',\n", | |
| " 'carrito',\n", | |
| " 'carritos',\n", | |
| " 'carrusel',\n", | |
| " 'casa',\n", | |
| " 'casas',\n", | |
| " 'case',\n", | |
| " 'casi',\n", | |
| " 'casilla',\n", | |
| " 'caso',\n", | |
| " 'casos',\n", | |
| " 'casta',\n", | |
| " 'castellano',\n", | |
| " 'casualidad',\n", | |
| " 'casualmente',\n", | |
| " 'cat',\n", | |
| " 'catal',\n", | |
| " 'catalan',\n", | |
| " 'catalunya',\n", | |
| " 'categorizan',\n", | |
| " 'categorizar',\n", | |
| " 'categorizarlo',\n", | |
| " 'category',\n", | |
| " 'categorydelegating',\n", | |
| " 'causa',\n", | |
| " 'causado',\n", | |
| " 'causalidad',\n", | |
| " 'causan',\n", | |
| " 'cause',\n", | |
| " 'caused',\n", | |
| " 'cc',\n", | |
| " 'cd',\n", | |
| " 'cdn',\n", | |
| " 'cedido',\n", | |
| " 'cegados',\n", | |
| " 'cegaron',\n", | |
| " 'cenando',\n", | |
| " 'centenares',\n", | |
| " 'centrada',\n", | |
| " 'centrado',\n", | |
| " 'centrados',\n", | |
| " 'central',\n", | |
| " 'centralizada',\n", | |
| " 'centramos',\n", | |
| " 'centran',\n", | |
| " 'centrando',\n", | |
| " 'centrar',\n", | |
| " 'centrarnos',\n", | |
| " 'centrarse',\n", | |
| " 'centras',\n", | |
| " 'centre',\n", | |
| " 'centremos',\n", | |
| " 'centric',\n", | |
| " 'centro',\n", | |
| " 'ceo',\n", | |
| " 'cercana',\n", | |
| " 'cercanas',\n", | |
| " 'cercano',\n", | |
| " 'cerebro',\n", | |
| " 'cerebros',\n", | |
| " 'cereto',\n", | |
| " 'cero',\n", | |
| " 'cerrado',\n", | |
| " 'cerrados',\n", | |
| " 'cerrar',\n", | |
| " 'certeza',\n", | |
| " 'certificadas',\n", | |
| " 'certificados',\n", | |
| " 'chacras',\n", | |
| " 'chaiken',\n", | |
| " 'change',\n", | |
| " 'channel',\n", | |
| " 'chapter',\n", | |
| " 'charla',\n", | |
| " 'charlas',\n", | |
| " 'chat',\n", | |
| " 'chats',\n", | |
| " 'checkbox',\n", | |
| " 'checkeo',\n", | |
| " 'checker',\n", | |
| " 'checklist',\n", | |
| " 'checklisty',\n", | |
| " 'checkout',\n", | |
| " 'checkoutestas',\n", | |
| " 'chica',\n", | |
| " 'chico',\n", | |
| " 'chicos',\n", | |
| " 'china',\n", | |
| " 'choose',\n", | |
| " 'chorrada',\n", | |
| " 'christian',\n", | |
| " 'chrome',\n", | |
| " 'chulas',\n", | |
| " 'chuleta',\n", | |
| " 'chulos',\n", | |
| " 'chute',\n", | |
| " 'cialdini',\n", | |
| " 'ciclo',\n", | |
| " 'cid',\n", | |
| " 'ciegas',\n", | |
| " 'ciegos',\n", | |
| " 'cientos',\n", | |
| " 'cierre',\n", | |
| " 'cierta',\n", | |
| " 'ciertas',\n", | |
| " 'cierto',\n", | |
| " 'ciertos',\n", | |
| " 'cifrado',\n", | |
| " 'cifrados',\n", | |
| " 'cinco',\n", | |
| " 'cingulado',\n", | |
| " 'circulito',\n", | |
| " 'circunstancias',\n", | |
| " 'cirujano',\n", | |
| " 'cita',\n", | |
| " 'citadas',\n", | |
| " 'citado',\n", | |
| " 'citarlo',\n", | |
| " 'cito',\n", | |
| " 'ciudad',\n", | |
| " 'ciudadanos',\n", | |
| " 'claim',\n", | |
| " 'clara',\n", | |
| " 'claraincluye',\n", | |
| " 'claramente',\n", | |
| " 'claras',\n", | |
| " 'claro',\n", | |
| " 'claros',\n", | |
| " 'clases',\n", | |
| " 'clasificado',\n", | |
| " 'clasificados',\n", | |
| " 'clasificar',\n", | |
| " 'classic',\n", | |
| " 'classification',\n", | |
| " 'classificationmining',\n", | |
| " 'clave',\n", | |
| " 'claveestos',\n", | |
| " 'claves',\n", | |
| " 'cleaner',\n", | |
| " 'clic',\n", | |
| " 'clica',\n", | |
| " 'clicamos',\n", | |
| " 'clicar',\n", | |
| " 'clicarse',\n", | |
| " 'click',\n", | |
| " 'clicks',\n", | |
| " 'clickworker',\n", | |
| " 'clics',\n", | |
| " 'client',\n", | |
| " 'cliente',\n", | |
| " 'clientes',\n", | |
| " 'clienteun',\n", | |
| " 'clinic',\n", | |
| " 'clinicseo',\n", | |
| " 'cliquen',\n", | |
| " 'cloaking',\n", | |
| " 'clusters',\n", | |
| " 'cms',\n", | |
| " 'cnn',\n", | |
| " 'co',\n", | |
| " 'coach',\n", | |
| " 'cobren',\n", | |
| " 'cocacola',\n", | |
| " 'code',\n", | |
| " 'codificado',\n", | |
| " 'coge',\n", | |
| " 'cogen',\n", | |
| " 'coger',\n", | |
| " 'cogerlos',\n", | |
| " 'cogido',\n", | |
| " 'cogiendo',\n", | |
| " 'cognitiva',\n", | |
| " 'cognitivala',\n", | |
| " 'cognitivamente',\n", | |
| " 'cognitivas',\n", | |
| " 'cognitivos',\n", | |
| " 'coherencia',\n", | |
| " 'coherente',\n", | |
| " 'cohort',\n", | |
| " 'coincida',\n", | |
| " 'coincidence',\n", | |
| " 'coincidencias',\n", | |
| " 'coincidiendo',\n", | |
| " 'coincidir',\n", | |
| " 'cojones',\n", | |
| " 'cola',\n", | |
| " 'colabora',\n", | |
| " 'colaborativa',\n", | |
| " 'colarse',\n", | |
| " ...]" | |
| ] | |
| }, | |
| "execution_count": 4, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| } | |
| ], | |
| "source": [ | |
| "tfidf = TfidfVectorizer(stop_words = stopwords.words('spanish'), \n", | |
| " max_df = 0.6, min_df = 1, token_pattern=r'(?u)\\b[A-Za-z]+\\b')\n", | |
| "csr_mat = tfidf.fit_transform(articles)\n", | |
| "words = tfidf.get_feature_names()\n", | |
| "words" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": {}, | |
| "source": [ | |
| "Creating a <a href=\"https://mlexplained.com/2017/12/28/a-practical-introduction-to-nmf-nonnegative-matrix-factorization/\">NMF model (nonnegative matrix factorization)</a>. Here we are <a href=\"https://blog.exploratory.io/demystifying-text-analytics-part-4-dimensionality-reduction-and-clustering-in-r-cbc8c90e0b14\">reducing the dimension</a> of the sparse matrix created before." | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 5, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "model = NMF(n_components=10) #test the number of components for your site(similar to the number of 'topics')\n", | |
| "model.fit(csr_mat)\n", | |
| "nmf_features = model.transform(csr_mat)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": {}, | |
| "source": [ | |
| "Normalizing the NMF features" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 6, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/html": [ | |
| "<div>\n", | |
| "<style scoped>\n", | |
| " .dataframe tbody tr th:only-of-type {\n", | |
| " vertical-align: middle;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe tbody tr th {\n", | |
| " vertical-align: top;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe thead th {\n", | |
| " text-align: right;\n", | |
| " }\n", | |
| "</style>\n", | |
| "<table border=\"1\" class=\"dataframe\">\n", | |
| " <thead>\n", | |
| " <tr style=\"text-align: right;\">\n", | |
| " <th></th>\n", | |
| " <th>0</th>\n", | |
| " <th>1</th>\n", | |
| " <th>2</th>\n", | |
| " <th>3</th>\n", | |
| " <th>4</th>\n", | |
| " <th>5</th>\n", | |
| " <th>6</th>\n", | |
| " <th>7</th>\n", | |
| " <th>8</th>\n", | |
| " <th>9</th>\n", | |
| " </tr>\n", | |
| " </thead>\n", | |
| " <tbody>\n", | |
| " <tr>\n", | |
| " <td>SEO para Progressive Web APPs (PWA) y JavaScript</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.040243</td>\n", | |
| " <td>0.0</td>\n", | |
| " <td>0.052272</td>\n", | |
| " <td>0.379103</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.072834</td>\n", | |
| " <td>0.138624</td>\n", | |
| " <td>0.045398</td>\n", | |
| " <td>0.908486</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>Cómo mejorar el SEO incrementando la frecuencia de rastreo</td>\n", | |
| " <td>0.056258</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.0</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.349612</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.018862</td>\n", | |
| " <td>0.030825</td>\n", | |
| " <td>0.005401</td>\n", | |
| " <td>0.934490</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>CTR y SEO: Manipulación del CTR para influir en los rankings</td>\n", | |
| " <td>0.946162</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.0</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.066596</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.316768</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.000000</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>Las mejores herramientas de visualización de datos gratuitas</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.973158</td>\n", | |
| " <td>0.0</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.230139</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.000000</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <td>Cómo hacer un Heatmap de las visitas de tu web por día y hora</td>\n", | |
| " <td>0.352149</td>\n", | |
| " <td>0.654728</td>\n", | |
| " <td>0.0</td>\n", | |
| " <td>0.136502</td>\n", | |
| " <td>0.079182</td>\n", | |
| " <td>0.119675</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.000000</td>\n", | |
| " <td>0.627579</td>\n", | |
| " <td>0.119344</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>\n", | |
| "</div>" | |
| ], | |
| "text/plain": [ | |
| " 0 1 2 \\\n", | |
| "SEO para Progressive Web APPs (PWA) y JavaScript 0.000000 0.040243 0.0 \n", | |
| "Cómo mejorar el SEO incrementando la frecuencia... 0.056258 0.000000 0.0 \n", | |
| "CTR y SEO: Manipulación del CTR para influir en... 0.946162 0.000000 0.0 \n", | |
| "Las mejores herramientas de visualización de da... 0.000000 0.973158 0.0 \n", | |
| "Cómo hacer un Heatmap de las visitas de tu web ... 0.352149 0.654728 0.0 \n", | |
| "\n", | |
| " 3 4 \\\n", | |
| "SEO para Progressive Web APPs (PWA) y JavaScript 0.052272 0.379103 \n", | |
| "Cómo mejorar el SEO incrementando la frecuencia... 0.000000 0.349612 \n", | |
| "CTR y SEO: Manipulación del CTR para influir en... 0.000000 0.066596 \n", | |
| "Las mejores herramientas de visualización de da... 0.000000 0.000000 \n", | |
| "Cómo hacer un Heatmap de las visitas de tu web ... 0.136502 0.079182 \n", | |
| "\n", | |
| " 5 6 \\\n", | |
| "SEO para Progressive Web APPs (PWA) y JavaScript 0.000000 0.072834 \n", | |
| "Cómo mejorar el SEO incrementando la frecuencia... 0.000000 0.018862 \n", | |
| "CTR y SEO: Manipulación del CTR para influir en... 0.000000 0.000000 \n", | |
| "Las mejores herramientas de visualización de da... 0.000000 0.000000 \n", | |
| "Cómo hacer un Heatmap de las visitas de tu web ... 0.119675 0.000000 \n", | |
| "\n", | |
| " 7 8 \\\n", | |
| "SEO para Progressive Web APPs (PWA) y JavaScript 0.138624 0.045398 \n", | |
| "Cómo mejorar el SEO incrementando la frecuencia... 0.030825 0.005401 \n", | |
| "CTR y SEO: Manipulación del CTR para influir en... 0.316768 0.000000 \n", | |
| "Las mejores herramientas de visualización de da... 0.230139 0.000000 \n", | |
| "Cómo hacer un Heatmap de las visitas de tu web ... 0.000000 0.627579 \n", | |
| "\n", | |
| " 9 \n", | |
| "SEO para Progressive Web APPs (PWA) y JavaScript 0.908486 \n", | |
| "Cómo mejorar el SEO incrementando la frecuencia... 0.934490 \n", | |
| "CTR y SEO: Manipulación del CTR para influir en... 0.000000 \n", | |
| "Las mejores herramientas de visualización de da... 0.000000 \n", | |
| "Cómo hacer un Heatmap de las visitas de tu web ... 0.119344 " | |
| ] | |
| }, | |
| "metadata": {}, | |
| "output_type": "display_data" | |
| } | |
| ], | |
| "source": [ | |
| "norm_features = normalize(nmf_features)\n", | |
| "\n", | |
| "df = pd.DataFrame(norm_features,index=titles)\n", | |
| "display(df.head())" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 7, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "article = df.loc['Qué es un buscador semántico']" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": {}, | |
| "source": [ | |
| "Displaying the 10 articles with highest cosine similarity" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 8, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "Qué es un buscador semántico 1.000000\n", | |
| "Qué son las entidades y su implicación en el SEO 0.999439\n", | |
| "SEO Semántico para la Web Semántica 0.998715\n", | |
| "Keyword Research con Google Refine [Vídeo Tutorial] 0.734699\n", | |
| "SEO, rankings y conversión 0.430864\n", | |
| "dtype: float64" | |
| ] | |
| }, | |
| "execution_count": 8, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| } | |
| ], | |
| "source": [ | |
| "similarities = df.dot(article)\n", | |
| "similarities.nlargest()" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": null, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [] | |
| } | |
| ], | |
| "metadata": { | |
| "kernelspec": { | |
| "display_name": "Python 3", | |
| "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": "3.7.3" | |
| } | |
| }, | |
| "nbformat": 4, | |
| "nbformat_minor": 2 | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment