{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "![Logo 1](https://git.wmi.amu.edu.pl/AITech/Szablon/raw/branch/master/Logotyp_AITech1.jpg)\n", "
\n", "

Ekstrakcja informacji

\n", "

3. tfidf (1) [ćwiczenia]

\n", "

Jakub Pokrywka (2021)

\n", "
\n", "\n", "![Logo 2](https://git.wmi.amu.edu.pl/AITech/Szablon/raw/branch/master/Logotyp_AITech2.jpg)" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "def word_to_index(word):\n", " vec = np.zeros(len(vocabulary))\n", " if word in vocabulary:\n", " idx = vocabulary.index(word)\n", " vec[idx] = 1\n", " else:\n", " vec[-1] = 1\n", " return vec" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "def tf(document):\n", " document_vector = None\n", " for word in document:\n", " if document_vector is None:\n", " document_vector = word_to_index(word)\n", " else:\n", " document_vector += word_to_index(word)\n", " return document_vector" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "def similarity(query, document):\n", " numerator = np.sum(query * document)\n", " denominator = np.sqrt(np.sum(query*query)) * np.sqrt(np.sum(document*document)) \n", " return numerator / denominator" ] } ], "metadata": { "author": "Jakub Pokrywka", "email": "kubapok@wmi.amu.edu.pl", "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "lang": "pl", "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.3" }, "subtitle": "3.tfidf (1)[ćwiczenia]", "title": "Ekstrakcja informacji", "year": "2021" }, "nbformat": 4, "nbformat_minor": 4 }