{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import csv\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "def gerar_metricas(nome_projeto):\n",
    "    list_output_MbR = []\n",
    "    with open(\"metricas/metricas_{}_MbR.csv\".format(nome_projeto), \"r\") as arquivo:\n",
    "        arquivo_csv = csv.reader(arquivo)\n",
    "        for i, linha in enumerate(arquivo_csv):\n",
    "            list_output_MbR.append(float(linha[0]))\n",
    "    list_output_NEOSP_SVR = []\n",
    "    with open(\"metricas/metricas_{}_NEOSP_SVR.csv\".format(nome_projeto), \"r\") as arquivo:\n",
    "        arquivo_csv = csv.reader(arquivo)\n",
    "        for i, linha in enumerate(arquivo_csv):\n",
    "            list_output_NEOSP_SVR.append(float(linha[0]))\n",
    "    list_output_TFIDF_SVR = []\n",
    "    with open(\"metricas/metricas_{}_TFIDF.csv\".format(nome_projeto), \"r\") as arquivo:\n",
    "        arquivo_csv = csv.reader(arquivo)\n",
    "        for i, linha in enumerate(arquivo_csv):\n",
    "            list_output_TFIDF_SVR.append(float(linha[0]))\n",
    "            \n",
    "    list_results = [[\"MbR Regressor\", np.mean(list_output_MbR)], [\"NEOSP-SVR Regressor\", np.mean(list_output_NEOSP_SVR)], [\"TFIDF-SVR Regressor\", np.mean(list_output_TFIDF_SVR)]]\n",
    "    \n",
    "    df = pd.DataFrame(list_results, columns=[\"Model\", \"MAE\"])\n",
    "    \n",
    "    df_list_output_MbR = pd.DataFrame(list_output_MbR, columns=[\"MAE_MbR\"])\n",
    "    df_list_output_NEOSP = pd.DataFrame(list_output_NEOSP_SVR, columns=[\"MAE_NEOSP\"])\n",
    "    df_list_output_TFIDF = pd.DataFrame(list_output_TFIDF_SVR, columns=[\"MAE_TFIDF\"])\n",
    "    \n",
    "    return df_list_output_MbR, df_list_output_NEOSP, df_list_output_TFIDF"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "#LIBRARIES_TAWOS = [\"ALOY\", \"APSTUD\", \"CLI\", \"CLOV\", \"COMPASS\", \"CONFCLOUD\", \"CONFSERVER\", \"DAEMON\", \"DM\", \"DNN\", \"DURACLOUD\", \"EVG\", \"FAB\", \n",
    "#             \"MDL\", \"MESOS\" ,\"MULE\", \"NEXUS\", \"SERVER\", \"STL\", \"TIDOC\", \"TIMOB\", \"TISTUD\", \"XD\"]\n",
    "\n",
    "LIBRARIES_NEO = [\"7764\", \n",
    "                 \"250833\", \n",
    "                 #\"278964\"\n",
    "                 \"734943\", \n",
    "                 #\"1304532\",\n",
    "                 #\"1714548\", \n",
    "                 \"2009901\",\n",
    "                 \"2670515\", \n",
    "                 \"3828396\",\n",
    "                 \"3836952\", \n",
    "                 \"4456656\", \n",
    "                 \"5261717\",\n",
    "                 \"6206924\", \n",
    "                 \"7071551\", \n",
    "                 \"7128869\",\n",
    "                 \"7603319\",\n",
    "                 \"7776928\", \n",
    "                 \"10152778\",\n",
    "                 \"10171263\", \n",
    "                 \"10171270\", \n",
    "                 \"10171280\",\n",
    "                 \"10174980\", \n",
    "                 \"12450835\",\n",
    "                 \"12584701\",\n",
    "                 \"12894267\",\n",
    "                 \"14052249\",\n",
    "                 \"14976868\", \n",
    "                 \"15502567\",\n",
    "                 \"19921167\",  \n",
    "                 \"21149814\", \n",
    "                 \"23285197\", \n",
    "                 \"28419588\",\n",
    "                 \"28644964\",  \n",
    "                 \"28847821\"\n",
    "                 ]\n",
    "#RETIRADOS = [] Muito grande\n",
    "#RETIRADO2 = [] valores NaN\n",
    "lista = list()\n",
    "for project_name in LIBRARIES_NEO:\n",
    "    df_list_output_MbR, df_list_output_NEOSP, df_list_output_TFIDF = gerar_metricas(project_name)\n",
    "    lista.append([project_name, df_list_output_MbR[\"MAE_MbR\"].mean(), df_list_output_NEOSP[\"MAE_NEOSP\"].mean(), df_list_output_TFIDF[\"MAE_TFIDF\"].mean()])\n",
    "\n",
    "df_media = pd.DataFrame(lista, columns=[\"Projeto\", \"MAE_MbR\", \"MAE_NEOSP\", \"MAE_TFIDF\"])\n",
    "df_media.to_csv(\"_METRICAS_NEO.csv\")"
   ]
  }
 ],
 "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": "3.10.11"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}