{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# In Short" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import arche\n", "from arche import *" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "a = Arche(\"381798/1/4\", schema=\"https://raw.githubusercontent.com/scrapinghub/arche/master/docs/source/nbs/data/books.json\", target=\"381798/1/3\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "a.source_items.df.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "a.report_all()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Some rules are not included in the above (more in [rules](https://arche.readthedocs.io/en/latest/nbs/Rules.html)), so a common case would be:" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "arche.rules.duplicates.find_by(a.source_items.df, [\"title\", \"price\"]).show()" ] }, { "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": "3.7.2" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "state": {}, "version_major": 2, "version_minor": 0 } } }, "nbformat": 4, "nbformat_minor": 4 }