{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Lab05 ##\n",
    "\n",
    "* Consider the following variables, corresponding to information of a football player. The date is in the following URL: 'https://raw.githubusercontent.com/masterfloss/data/main/jogadores.csv'\n",
    "\n",
    "The data store is:\n",
    "\n",
    "- 'Idade' - age \n",
    "\n",
    "- 'Altura' - height \n",
    "\n",
    "- 'Epoca' -season football\n",
    "\n",
    "- 'Minutos' - minutes played\n",
    "\n",
    "- 'Valor de Mercado' – market value\n",
    "\n",
    "- 'Ser Transferido' - being transferred\n",
    "\n",
    "\n",
    "#### The purpose is to explain the market value of the player.  ####\n",
    "\n",
    "from sklearn.XXXX import XXXXX\n",
    "\n",
    "model = XXXXX()\n",
    "\n",
    "result = model.fit(features,target)\n",
    "\n",
    "y_pred = result.predict(X_test)\n",
    "\n",
    "\n",
    "##### Note: Possible algorithms #####\n",
    "\n",
    "OLS\n",
    "RIDGE\n",
    "LASSO\n",
    "\n",
    "See: https://scikit-learn.org/stable/supervised_learning.html\n",
    "\n",
    "https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html\n",
    "\n",
    "https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Lasso.html\n",
    "\n",
    "#### To evaluate the predictive quality of the model, you may calculate the R2 and MSE scores: ####\n",
    "\n",
    "from sklearn.metrics import mean_squared_error, r2_score\n",
    "\n",
    "y_pred1 = result.predict(X_train)\n",
    "\n",
    "r2_score(y_train, y_pred1)\n",
    "\n",
    "y_pred = result.predict(X_test)\n",
    "\n",
    "r2_score(y_test, y_pred)\n",
    "\n",
    "mean_squared_error(y_test, y_pred)\n",
    "\n",
    "\n",
    "**Data collected by Pedro Carapau**\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import libraries\n",
    "import pandas as pd\n",
    "from sklearn import linear_model\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import mean_squared_error, r2_score\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.preprocessing import PolynomialFeatures"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read data\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# preprocessing, train test, ...(not normalized or standarize)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# object creation and model fit OLS\n",
    "\n",
    "# calculate R2, MSE\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# result.coef_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# object creation and model fit Ridge with parameter alpha =0.5\n",
    "\n",
    "# calculate R2, MSE\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# object creation and model fit Lasso with parameter alpha =0.5\n",
    "\n",
    "# calculate R2, MSE\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# object creation and model fit BayesianRidge with parameter compute_score=True\n",
    "\n",
    "# calculate R2, MSE\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Polynomial Regression\n",
    "# if an input sample is two dimensional and of the form [a, b], \n",
    "# the degree-2 polynomial features are [1, a, b, a^2, ab, b^2].\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Object creation Neural Network\n",
    "from sklearn.neural_network import MLPRegressor\n",
    "model = MLPRegressor(random_state=1,hidden_layer_sizes = (9,7), activation='relu', max_iter=5000, solver='lbfgs')\n",
    "result=model.fit(X_train, y_train)\n",
    "# calculate R2, MSE\n",
    "y_pred=result.predict(X_test)\n",
    "r2_score(y_train, y_train),r2_score(y_test, y_pred), mean_squared_error(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Standardize for the specific case of OLS\n",
    "from sklearn.preprocessing import StandardScaler\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}