{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Clean Data (Duplicate Removal)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import json" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "with open(\"/home/pwxcoo/projects/chinese-xinhua/archived/idiom.json\") as fp:\n", " idioms = json.load(fp)\n", "\n", "len(idioms)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "idioms[:5]" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "unique_idioms = set(idiom[\"word\"] for idiom in idioms)\n", "unique_idioms" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "len(unique_idioms)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "check = dict()\n", "for idiom in idioms:\n", " if idiom[\"word\"] in check and str(idiom) > str(check[idiom[\"word\"]]):\n", "# print(idiom)\n", "# print(check[idiom[\"word\"]])\n", " check[idiom[\"word\"]] = idiom\n", " else:\n", " check[idiom[\"word\"]] = idiom\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "with open(\"/home/pwxcoo/projects/chinese-xinhua/data/idiom-clean.json\", \"w+\", encoding=\"utf-8\") as fp:\n", " json.dump(list(check.values()), fp, ensure_ascii=False)" ] }, { "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": "3.7.0" } }, "nbformat": 4, "nbformat_minor": 2 }