{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [],
   "source": [
    "import csv\n",
    "\n",
    "list_output_ALOY_MbR = []\n",
    "with open(\"metricas_ALOY_MbR.csv\", \"r\") as arquivo:\n",
    "    arquivo_csv = csv.reader(arquivo)\n",
    "    for i, linha in enumerate(arquivo_csv):\n",
    "        list_output_ALOY_MbR.append(float(linha[0]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [],
   "source": [
    " list_output_ALOY_NEOSP_SVR = []\n",
    "with open(\"metricas_ALOY_NEOSP_SVR.csv\", \"r\") as arquivo:\n",
    "    arquivo_csv = csv.reader(arquivo)\n",
    "    for i, linha in enumerate(arquivo_csv):\n",
    "        list_output_ALOY_NEOSP_SVR.append(float(linha[0]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.5313348545588383"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "\n",
    "np.mean(list_output_ALOY_NEOSP_SVR)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.dummy import DummyRegressor\n",
    "from nltk.corpus import stopwords\n",
    "from textblob import TextBlob\n",
    "import textstat\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn import svm\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.feature_selection import SelectKBest\n",
    "import pandas as pd\n",
    "from util import escape_tags_and_content, escape_tags, escape_strings, escape_links, escape_hex_character_codes, escape_punctuation_boundaries, escape_odd_spaces\n",
    "from sklearn.model_selection import cross_val_score\n",
    "from sklearn.model_selection import RepeatedKFold\n",
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.feature_selection import f_classif, f_regression\n",
    "from sklearn.pipeline import Pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "project_name = \"7764\"\n",
    "\n",
    "df = pd.read_json(\"database\\\\neo\\\\json\\\\{}.json\".format(project_name))\n",
    "\n",
    "def extract_leg_features():\n",
    "    return \"Extract Leg, Sent, Subj Features\"\n",
    "    \n",
    "# pipeline = Pipeline(\n",
    "#     [\n",
    "#         (\"vect\", Tfi()),\n",
    "#         #(\"red\", SelectKBest(f_regression, k=50)),\n",
    "#         (\"scaler\", StandardScaler()),\n",
    "#         (\"clf\",  svm.SVR()),\n",
    "#     ]\n",
    "# )\n",
    "# pipeline\n",
    "\n",
    "# pipeline = Pipeline(\n",
    "#     [\n",
    "#         (\"vect\", extract_leg_features()),\n",
    "#         (\"red\", SelectKBest(f_regression, k=50)),\n",
    "#         (\"scaler\", StandardScaler()),\n",
    "#         (\"clf\",  svm.SVR()),\n",
    "#     ]\n",
    "# )\n",
    "# pipeline\n",
    "\n",
    "\n",
    "pipeline = Pipeline(\n",
    "    [        \n",
    "        (\"clf\",  DummyRegressor(strategy=\"mean\")),\n",
    "    ]\n",
    ")\n",
    "pipeline\n",
    "\n",
    "\n",
    "    "
   ]
  }
 ],
 "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
}