Skip to content

Instantly share code, notes, and snippets.

@brusangues

brusangues/ridge_vs_lasso.ipynb

Last active January 27, 2025 17:29
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save brusangues/0f887c83e92a3d3df12438ec2d1d0da9 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save brusangues/0f887c83e92a3d3df12438ec2d1d0da9 to your computer and use it in GitHub Desktop.
Download ZIP
ridge_vs_lasso
Display the source blob
Display the rendered blob
Raw
ridge_vs_lasso.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"collapsed_sections": [
"zZcLVkscs8bn"
],
"authorship_tag": "ABX9TyOCgCb2npK38ai2CMCZ1FbS",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/brusangues/0f887c83e92a3d3df12438ec2d1d0da9/ridge_vs_lasso.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"source": [
"# Fontes e Inicialização"
],
"metadata": {
"id": "zZcLVkscs8bn"
}
},
{
"cell_type": "code",
"source": [
"# https://www.analyticsvidhya.com/blog/2016/01/ridge-lasso-regression-python-complete-tutorial/\n",
"# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LinearRegression.html\n",
"# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html\n",
"# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Lasso.html\n",
"# https://www.youtube.com/watch?v=Xm2C_gTAl8c"
],
"metadata": {
"id": "q0WnEONgnJ7c"
},
"execution_count": 1,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import random\n",
"\n",
"import matplotlib.pyplot as plt\n",
"from matplotlib.pylab import rcParams\n",
"\n",
"pd.set_option('display.max_columns', 500)\n",
"pd.set_option('display.max_rows', 500)"
],
"metadata": {
"id": "vxamxUdBnSoL"
},
"execution_count": 2,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# Criando dataset"
],
"metadata": {
"id": "0jn0DL8QsLqb"
}
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 452
},
"id": "Tm0LgRspl6LI",
"outputId": "16c4b87f-1d8f-48ec-daa6-534ee1defef8"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
],
"source": [
"#Define input array with angles from 60deg to 300deg converted to radians\n",
"x = np.array([i*np.pi/180 for i in range(60,300,4)])\n",
"np.random.seed(10) #Setting seed for reproducibility\n",
"y = np.sin(x) + np.random.normal(0,0.15,len(x))\n",
"data = pd.DataFrame(np.column_stack([x,y]),columns=['x','y'])\n",
"plt.plot(data['x'],data['y'],'.')\n",
"plt.title(\"Dataset\")\n",
"plt.show()"
]
},
{
"cell_type": "code",
"source": [
"# Use standard scaler\n",
"from sklearn.preprocessing import StandardScaler\n",
"scaler = StandardScaler()\n",
"data[['x']] = scaler.fit_transform(data[['x']])\n",
"data.head()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "kIiOR90NwW9S",
"outputId": "1ee68c0c-da0c-4070-8488-42866e4efdbe"
},
"execution_count": 4,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" x y\n",
"0 -1.703420 1.065763\n",
"1 -1.645677 1.006086\n",
"2 -1.587934 0.695374\n",
"3 -1.530191 0.949799\n",
"4 -1.472448 1.063496"
],
"text/html": [
"\n",
" <div id=\"df-e809b94a-65fa-463a-a5da-185e8b07b64e\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>-1.703420</td>\n",
" <td>1.065763</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>-1.645677</td>\n",
" <td>1.006086</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>-1.587934</td>\n",
" <td>0.695374</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>-1.530191</td>\n",
" <td>0.949799</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>-1.472448</td>\n",
" <td>1.063496</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e809b94a-65fa-463a-a5da-185e8b07b64e')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-e809b94a-65fa-463a-a5da-185e8b07b64e button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-e809b94a-65fa-463a-a5da-185e8b07b64e');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-25d7e4f3-47b4-4fb5-b0c6-78547556e2f9\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-25d7e4f3-47b4-4fb5-b0c6-78547556e2f9')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-25d7e4f3-47b4-4fb5-b0c6-78547556e2f9 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "data",
"summary": "{\n \"name\": \"data\",\n \"rows\": 60,\n \"fields\": [\n {\n \"column\": \"x\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.0084389681792214,\n \"min\": -1.7034198966380234,\n \"max\": 1.7034198966380238,\n \"num_unique_values\": 60,\n \"samples\": [\n -1.7034198966380234,\n -1.4147046599197144,\n 0.3753298077338016\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"y\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.7913519693242002,\n \"min\": -1.0803726877190007,\n \"max\": 1.1507513323478282,\n \"num_unique_values\": 60,\n \"samples\": [\n 1.0657633794038663,\n 0.8767949189043736,\n -0.34670514483794757\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 4
}
]
},
{
"cell_type": "markdown",
"source": [
"Agora, vamos criar as demais features.\n",
"\n",
"Cada feature adicional é apenas a potência de X.\n",
"\n",
"Assim, conseguiremos plotar em 2D."
],
"metadata": {
"id": "Pyegm7KHsO_S"
}
},
{
"cell_type": "code",
"source": [
"for i in range(2,16): #power of 1 is already there\n",
" colname = 'x_%d'%i #new var will be x_power\n",
" data[colname] = data['x']**i\n",
"data.head()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 226
},
"id": "a5_Rny5bl_ya",
"outputId": "421d0390-a8fe-47be-ca51-78826b0fd545"
},
"execution_count": 5,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" x y x_2 x_3 x_4 x_5 x_6 \\\n",
"0 -1.703420 1.065763 2.901639 -4.942710 8.419511 -14.341962 24.430384 \n",
"1 -1.645677 1.006086 2.708252 -4.456908 7.334630 -12.070432 19.864030 \n",
"2 -1.587934 0.695374 2.521534 -4.004029 6.358132 -10.096294 16.032246 \n",
"3 -1.530191 0.949799 2.341484 -3.582917 5.482546 -8.389341 12.837293 \n",
"4 -1.472448 1.063496 2.168102 -3.192417 4.700667 -6.921487 10.191528 \n",
"\n",
" x_7 x_8 x_9 x_10 x_11 x_12 \\\n",
"0 -41.615202 70.888164 -120.752308 205.691884 -350.379648 596.843664 \n",
"1 -32.689774 53.796804 -88.532155 145.695318 -239.767413 394.579680 \n",
"2 -25.458145 40.425849 -64.193572 101.935143 -161.866259 257.032904 \n",
"3 -19.643507 30.058312 -45.994951 70.381049 -107.696431 164.796083 \n",
"4 -15.006491 22.096274 -32.535608 47.906981 -70.540524 103.867233 \n",
"\n",
" x_13 x_14 x_15 \n",
"0 -1016.675373 1731.825059 -2950.025263 \n",
"1 -649.350645 1068.621323 -1758.605373 \n",
"2 -408.151236 648.117144 -1029.167120 \n",
"3 -252.169442 385.867349 -590.450649 \n",
"4 -152.939069 225.194781 -331.587539 "
],
"text/html": [
"\n",
" <div id=\"df-5a73229c-e083-4db7-ad4e-9b2e1d3e7c49\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>x_2</th>\n",
" <th>x_3</th>\n",
" <th>x_4</th>\n",
" <th>x_5</th>\n",
" <th>x_6</th>\n",
" <th>x_7</th>\n",
" <th>x_8</th>\n",
" <th>x_9</th>\n",
" <th>x_10</th>\n",
" <th>x_11</th>\n",
" <th>x_12</th>\n",
" <th>x_13</th>\n",
" <th>x_14</th>\n",
" <th>x_15</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>-1.703420</td>\n",
" <td>1.065763</td>\n",
" <td>2.901639</td>\n",
" <td>-4.942710</td>\n",
" <td>8.419511</td>\n",
" <td>-14.341962</td>\n",
" <td>24.430384</td>\n",
" <td>-41.615202</td>\n",
" <td>70.888164</td>\n",
" <td>-120.752308</td>\n",
" <td>205.691884</td>\n",
" <td>-350.379648</td>\n",
" <td>596.843664</td>\n",
" <td>-1016.675373</td>\n",
" <td>1731.825059</td>\n",
" <td>-2950.025263</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>-1.645677</td>\n",
" <td>1.006086</td>\n",
" <td>2.708252</td>\n",
" <td>-4.456908</td>\n",
" <td>7.334630</td>\n",
" <td>-12.070432</td>\n",
" <td>19.864030</td>\n",
" <td>-32.689774</td>\n",
" <td>53.796804</td>\n",
" <td>-88.532155</td>\n",
" <td>145.695318</td>\n",
" <td>-239.767413</td>\n",
" <td>394.579680</td>\n",
" <td>-649.350645</td>\n",
" <td>1068.621323</td>\n",
" <td>-1758.605373</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>-1.587934</td>\n",
" <td>0.695374</td>\n",
" <td>2.521534</td>\n",
" <td>-4.004029</td>\n",
" <td>6.358132</td>\n",
" <td>-10.096294</td>\n",
" <td>16.032246</td>\n",
" <td>-25.458145</td>\n",
" <td>40.425849</td>\n",
" <td>-64.193572</td>\n",
" <td>101.935143</td>\n",
" <td>-161.866259</td>\n",
" <td>257.032904</td>\n",
" <td>-408.151236</td>\n",
" <td>648.117144</td>\n",
" <td>-1029.167120</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>-1.530191</td>\n",
" <td>0.949799</td>\n",
" <td>2.341484</td>\n",
" <td>-3.582917</td>\n",
" <td>5.482546</td>\n",
" <td>-8.389341</td>\n",
" <td>12.837293</td>\n",
" <td>-19.643507</td>\n",
" <td>30.058312</td>\n",
" <td>-45.994951</td>\n",
" <td>70.381049</td>\n",
" <td>-107.696431</td>\n",
" <td>164.796083</td>\n",
" <td>-252.169442</td>\n",
" <td>385.867349</td>\n",
" <td>-590.450649</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>-1.472448</td>\n",
" <td>1.063496</td>\n",
" <td>2.168102</td>\n",
" <td>-3.192417</td>\n",
" <td>4.700667</td>\n",
" <td>-6.921487</td>\n",
" <td>10.191528</td>\n",
" <td>-15.006491</td>\n",
" <td>22.096274</td>\n",
" <td>-32.535608</td>\n",
" <td>47.906981</td>\n",
" <td>-70.540524</td>\n",
" <td>103.867233</td>\n",
" <td>-152.939069</td>\n",
" <td>225.194781</td>\n",
" <td>-331.587539</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-5a73229c-e083-4db7-ad4e-9b2e1d3e7c49')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-5a73229c-e083-4db7-ad4e-9b2e1d3e7c49 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-5a73229c-e083-4db7-ad4e-9b2e1d3e7c49');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-100f4a92-05fd-47a0-9a8c-39ffbf5815b8\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-100f4a92-05fd-47a0-9a8c-39ffbf5815b8')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-100f4a92-05fd-47a0-9a8c-39ffbf5815b8 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "data",
"summary": "{\n \"name\": \"data\",\n \"rows\": 60,\n \"fields\": [\n {\n \"column\": \"x\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.0084389681792214,\n \"min\": -1.7034198966380234,\n \"max\": 1.7034198966380238,\n \"num_unique_values\": 60,\n \"samples\": [\n -1.7034198966380234,\n -1.4147046599197144,\n 0.3753298077338016\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"y\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.7913519693242002,\n \"min\": -1.0803726877190007,\n \"max\": 1.1507513323478282,\n \"num_unique_values\": 60,\n \"samples\": [\n 1.0657633794038663,\n 0.8767949189043736,\n -0.34670514483794757\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_2\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.9015992277924595,\n \"min\": 0.0008335648791330948,\n \"max\": 2.901639344262296,\n \"num_unique_values\": 48,\n \"samples\": [\n 0.02083912197832726,\n 1.267852181161434,\n 0.04084467907752165\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_3\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.9794343157597878,\n \"min\": -4.9427101918841,\n \"max\": 4.942710191884103,\n \"num_unique_values\": 60,\n \"samples\": [\n -4.9427101918841,\n -2.831374733370853,\n 0.0528736350433557\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_4\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.4165561716926502,\n \"min\": 6.948304077241709e-07,\n \"max\": 8.419510884170926,\n \"num_unique_values\": 48,\n \"samples\": [\n 0.00043426900482760233,\n 1.607449153275806,\n 0.001668287808945735\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_5\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 4.7309893603125,\n \"min\": -14.341962360057137,\n \"max\": 14.341962360057156,\n \"num_unique_values\": 60,\n \"samples\": [\n -14.341962360057137,\n -5.666683024304043,\n 0.007448439279516896\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_6\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6.4509937569934666,\n \"min\": 5.791862248325975e-10,\n \"max\": 24.43038404095499,\n \"num_unique_values\": 48,\n \"samples\": [\n 9.049784763009195e-06,\n 2.0380079150868307,\n 6.814068016533029e-05\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_7\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 12.129417094214949,\n \"min\": -41.6152022578707,\n \"max\": 41.61520225787078,\n \"num_unique_values\": 60,\n \"samples\": [\n -41.6152022578707,\n -11.34123862852515,\n 0.0010492799985315536\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_8\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 17.505101083514894,\n \"min\": 4.827892954981376e-13,\n \"max\": 70.88816352867269,\n \"num_unique_values\": 48,\n \"samples\": [\n 1.885895685539561e-07,\n 2.5838927803671052,\n 2.783184213476961e-06\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_9\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 32.242324016067805,\n \"min\": -120.75230819087068,\n \"max\": 120.75230819087096,\n \"num_unique_values\": 60,\n \"samples\": [\n -120.75230819087068,\n -22.698233354061305,\n 0.00014781465942081054\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_10\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 48.16338368349153,\n \"min\": 4.024362007486571e-16,\n \"max\": 205.69188433729622,\n \"num_unique_values\": 48,\n \"samples\": [\n 3.930041022936002e-09,\n 3.2759940974757167,\n 1.1367826601309097e-07\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_11\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 87.60703416246355,\n \"min\": -350.3796483571165,\n \"max\": 350.3796483571175,\n \"num_unique_values\": 60,\n \"samples\": [\n -350.3796483571165,\n -45.42800079169312,\n 2.0823015372700986e-05\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_12\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 133.92087762542272,\n \"min\": 3.354566830358362e-19,\n \"max\": 596.8436643885482,\n \"num_unique_values\": 48,\n \"samples\": [\n 8.189860425679339e-11,\n 4.1534762619565715,\n 4.643152293393837e-09\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_13\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 241.54905571289513,\n \"min\": -1016.6753731017967,\n \"max\": 1016.6753731018002,\n \"num_unique_values\": 60,\n \"samples\": [\n -1016.6753731017967,\n -90.91911356003487,\n 2.9333894954041087e-06\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_14\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 375.37496608859607,\n \"min\": 2.796249094491557e-22,\n \"max\": 1731.825058963493,\n \"num_unique_values\": 48,\n \"samples\": [\n 1.7066950039620699e-12,\n 5.265993938123879,\n 1.8964806533172993e-10\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"x_15\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 672.9428842788795,\n \"min\": -2950.025262934721,\n \"max\": 2950.0252629347324,\n \"num_unique_values\": 60,\n \"samples\": [\n -2950.025262934721,\n -181.96453875324565,\n 4.1323380777157025e-07\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 5
}
]
},
{
"cell_type": "markdown",
"source": [
"# Treinando regressão linear sem regularização\n",
"\n",
"Variando apenas o número de variáveis."
],
"metadata": {
"id": "w0yQHu9ytiGp"
}
},
{
"cell_type": "code",
"source": [
"#Import Linear Regression model from scikit-learn.\n",
"from sklearn.linear_model import LinearRegression\n",
"\n",
"#Fit the model\n",
"linreg = LinearRegression()\n",
"linreg.fit(data.filter(regex=\"x$\"),data['y'])\n",
"y_pred = linreg.predict(data.filter(regex=\"x$\"))\n",
"\n",
"#Check if a plot is to be made for the entered power\n",
"plt.plot(data['x'],y_pred)\n",
"plt.plot(data['x'],data['y'],'.')\n",
"plt.title(\"Modelo utilizando apenas uma variável\")\n",
"plt.show()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 453
},
"id": "dxJQ6WdduNsO",
"outputId": "e9bb8fd2-d40d-4cfe-9637-80a19b5f2e33"
},
"execution_count": 6,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"# Na regressão ridge, vamos adicionar o seguinte termo na função objetivo:\n",
"display(linreg.coef_)\n",
"sum(linreg.coef_ ** 2)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 52
},
"id": "TD2Ecg5uyadq",
"outputId": "608b8939-03d5-47a8-8e77-94c461fbfbf7"
},
"execution_count": 25,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"array([-0.74908525])"
]
},
"metadata": {}
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.5611287137007841"
]
},
"metadata": {},
"execution_count": 25
}
]
},
{
"cell_type": "code",
"source": [
"# Já no lasso, vamos adicionar o seguinte termo na função objetivo:\n",
"display(linreg.coef_)\n",
"sum(abs(linreg.coef_))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 52
},
"id": "ZlyUXit3yomb",
"outputId": "a5008754-d35c-4390-806a-47fffdb658ae"
},
"execution_count": 26,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"array([-0.74908525])"
]
},
"metadata": {}
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.7490852512903883"
]
},
"metadata": {},
"execution_count": 26
}
]
},
{
"cell_type": "code",
"source": [
"# Configurando tamanho de fig padrão\n",
"rcParams['figure.figsize'] = 12, 10\n",
"\n",
"def linear_regression(data, power, models_to_plot):\n",
" #initialize predictors:\n",
" predictors=['x']\n",
" if power>=2:\n",
" predictors.extend(['x_%d'%i for i in range(2,power+1)])\n",
"\n",
" #Fit the model\n",
" linreg = LinearRegression()\n",
" linreg.fit(data[predictors],data['y'])\n",
" y_pred = linreg.predict(data[predictors])\n",
"\n",
" #Check if a plot is to be made for the entered power\n",
" if power in models_to_plot:\n",
" plt.subplot(models_to_plot[power])\n",
" plt.tight_layout()\n",
" plt.plot(data['x'],y_pred)\n",
" plt.plot(data['x'],data['y'],'.')\n",
" plt.title('Plot for power: %d'%power)\n",
"\n",
" #Return the result in pre-defined format\n",
" rss = sum((y_pred-data['y'])**2)\n",
" ret = [rss]\n",
" ret.extend([linreg.intercept_])\n",
" ret.extend(linreg.coef_)\n",
" return ret\n",
"#Initialize a dataframe to store the results:\n",
"col = ['rss','intercept'] + ['coef_x_%d'%i for i in range(1,16)]\n",
"ind = ['model_pow_%d'%i for i in range(1,16)]\n",
"coef_matrix_simple = pd.DataFrame(index=ind, columns=col)\n",
"\n",
"#Define the powers for which a plot is required:\n",
"models_to_plot = {1:231,3:232,6:233,9:234,12:235,15:236}\n",
"\n",
"#Iterate through all powers and assimilate results\n",
"for i in range(1,16):\n",
" coef_matrix_simple.iloc[i-1,0:i+2] = linear_regression(data, power=i, models_to_plot=models_to_plot)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 919
},
"id": "ZkK08D3PmHnt",
"outputId": "9f3b6787-c4bc-4e81-960f-04d74842b13a"
},
"execution_count": 7,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 1200x1000 with 6 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"#Set the display format to be scientific for ease of analysis\n",
"pd.options.display.float_format = '{:,.2g}'.format\n",
"coef_matrix_simple"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 540
},
"id": "M0fe-fg6mWP_",
"outputId": "0250448a-88a6-4c56-cc01-67a91975d5be"
},
"execution_count": 8,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" rss intercept coef_x_1 coef_x_2 coef_x_3 coef_x_4 coef_x_5 \\\n",
"model_pow_1 3.3 0.038 -0.75 NaN NaN NaN NaN \n",
"model_pow_2 3.3 0.047 -0.75 -0.0087 NaN NaN NaN \n",
"model_pow_3 1.1 0.047 -1.2 -0.0087 0.24 NaN NaN \n",
"model_pow_4 1.1 0.07 -1.2 -0.085 0.24 0.03 NaN \n",
"model_pow_5 1 0.07 -1.3 -0.085 0.42 0.03 -0.053 \n",
"model_pow_6 0.99 0.094 -1.3 -0.26 0.42 0.2 -0.053 \n",
"model_pow_7 0.93 0.094 -1.1 -0.26 -0.056 0.2 0.3 \n",
"model_pow_8 0.92 0.11 -1.1 -0.44 -0.056 0.54 0.3 \n",
"model_pow_9 0.87 0.11 -1.3 -0.44 0.77 0.54 -0.78 \n",
"model_pow_10 0.87 0.11 -1.3 -0.49 0.77 0.69 -0.78 \n",
"model_pow_11 0.87 0.11 -1.4 -0.49 1.1 0.69 -1.5 \n",
"model_pow_12 0.87 0.11 -1.4 -0.4 1.1 0.3 -1.5 \n",
"model_pow_13 0.86 0.11 -1.5 -0.4 2.6 0.3 -5.6 \n",
"model_pow_14 0.79 0.07 -1.5 1 2.6 -7.8 -5.6 \n",
"model_pow_15 0.7 0.07 -1.9 1 7.8 -7.8 -26 \n",
"\n",
" coef_x_6 coef_x_7 coef_x_8 coef_x_9 coef_x_10 coef_x_11 \\\n",
"model_pow_1 NaN NaN NaN NaN NaN NaN \n",
"model_pow_2 NaN NaN NaN NaN NaN NaN \n",
"model_pow_3 NaN NaN NaN NaN NaN NaN \n",
"model_pow_4 NaN NaN NaN NaN NaN NaN \n",
"model_pow_5 NaN NaN NaN NaN NaN NaN \n",
"model_pow_6 -0.043 NaN NaN NaN NaN NaN \n",
"model_pow_7 -0.043 -0.073 NaN NaN NaN NaN \n",
"model_pow_8 -0.24 -0.073 0.035 NaN NaN NaN \n",
"model_pow_9 -0.24 0.44 0.035 -0.082 NaN NaN \n",
"model_pow_10 -0.39 0.44 0.097 -0.082 -0.0088 NaN \n",
"model_pow_11 -0.39 1.1 0.097 -0.3 -0.0088 0.028 \n",
"model_pow_12 0.21 1.1 -0.32 -0.3 0.12 0.028 \n",
"model_pow_13 0.21 6.1 -0.32 -3.3 0.12 0.87 \n",
"model_pow_14 18 6.1 -18 -3.3 9.3 0.87 \n",
"model_pow_15 18 40 -18 -33 9.3 15 \n",
"\n",
" coef_x_12 coef_x_13 coef_x_14 coef_x_15 \n",
"model_pow_1 NaN NaN NaN NaN \n",
"model_pow_2 NaN NaN NaN NaN \n",
"model_pow_3 NaN NaN NaN NaN \n",
"model_pow_4 NaN NaN NaN NaN \n",
"model_pow_5 NaN NaN NaN NaN \n",
"model_pow_6 NaN NaN NaN NaN \n",
"model_pow_7 NaN NaN NaN NaN \n",
"model_pow_8 NaN NaN NaN NaN \n",
"model_pow_9 NaN NaN NaN NaN \n",
"model_pow_10 NaN NaN NaN NaN \n",
"model_pow_11 NaN NaN NaN NaN \n",
"model_pow_12 -0.015 NaN NaN NaN \n",
"model_pow_13 -0.015 -0.091 NaN NaN \n",
"model_pow_14 -2.4 -0.091 0.24 NaN \n",
"model_pow_15 -2.4 -3.4 0.24 0.31 "
],
"text/html": [
"\n",
" <div id=\"df-45d96347-0be5-4537-be09-3503d753da54\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>rss</th>\n",
" <th>intercept</th>\n",
" <th>coef_x_1</th>\n",
" <th>coef_x_2</th>\n",
" <th>coef_x_3</th>\n",
" <th>coef_x_4</th>\n",
" <th>coef_x_5</th>\n",
" <th>coef_x_6</th>\n",
" <th>coef_x_7</th>\n",
" <th>coef_x_8</th>\n",
" <th>coef_x_9</th>\n",
" <th>coef_x_10</th>\n",
" <th>coef_x_11</th>\n",
" <th>coef_x_12</th>\n",
" <th>coef_x_13</th>\n",
" <th>coef_x_14</th>\n",
" <th>coef_x_15</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>model_pow_1</th>\n",
" <td>3.3</td>\n",
" <td>0.038</td>\n",
" <td>-0.75</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_2</th>\n",
" <td>3.3</td>\n",
" <td>0.047</td>\n",
" <td>-0.75</td>\n",
" <td>-0.0087</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_3</th>\n",
" <td>1.1</td>\n",
" <td>0.047</td>\n",
" <td>-1.2</td>\n",
" <td>-0.0087</td>\n",
" <td>0.24</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_4</th>\n",
" <td>1.1</td>\n",
" <td>0.07</td>\n",
" <td>-1.2</td>\n",
" <td>-0.085</td>\n",
" <td>0.24</td>\n",
" <td>0.03</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_5</th>\n",
" <td>1</td>\n",
" <td>0.07</td>\n",
" <td>-1.3</td>\n",
" <td>-0.085</td>\n",
" <td>0.42</td>\n",
" <td>0.03</td>\n",
" <td>-0.053</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_6</th>\n",
" <td>0.99</td>\n",
" <td>0.094</td>\n",
" <td>-1.3</td>\n",
" <td>-0.26</td>\n",
" <td>0.42</td>\n",
" <td>0.2</td>\n",
" <td>-0.053</td>\n",
" <td>-0.043</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_7</th>\n",
" <td>0.93</td>\n",
" <td>0.094</td>\n",
" <td>-1.1</td>\n",
" <td>-0.26</td>\n",
" <td>-0.056</td>\n",
" <td>0.2</td>\n",
" <td>0.3</td>\n",
" <td>-0.043</td>\n",
" <td>-0.073</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_8</th>\n",
" <td>0.92</td>\n",
" <td>0.11</td>\n",
" <td>-1.1</td>\n",
" <td>-0.44</td>\n",
" <td>-0.056</td>\n",
" <td>0.54</td>\n",
" <td>0.3</td>\n",
" <td>-0.24</td>\n",
" <td>-0.073</td>\n",
" <td>0.035</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_9</th>\n",
" <td>0.87</td>\n",
" <td>0.11</td>\n",
" <td>-1.3</td>\n",
" <td>-0.44</td>\n",
" <td>0.77</td>\n",
" <td>0.54</td>\n",
" <td>-0.78</td>\n",
" <td>-0.24</td>\n",
" <td>0.44</td>\n",
" <td>0.035</td>\n",
" <td>-0.082</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_10</th>\n",
" <td>0.87</td>\n",
" <td>0.11</td>\n",
" <td>-1.3</td>\n",
" <td>-0.49</td>\n",
" <td>0.77</td>\n",
" <td>0.69</td>\n",
" <td>-0.78</td>\n",
" <td>-0.39</td>\n",
" <td>0.44</td>\n",
" <td>0.097</td>\n",
" <td>-0.082</td>\n",
" <td>-0.0088</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_11</th>\n",
" <td>0.87</td>\n",
" <td>0.11</td>\n",
" <td>-1.4</td>\n",
" <td>-0.49</td>\n",
" <td>1.1</td>\n",
" <td>0.69</td>\n",
" <td>-1.5</td>\n",
" <td>-0.39</td>\n",
" <td>1.1</td>\n",
" <td>0.097</td>\n",
" <td>-0.3</td>\n",
" <td>-0.0088</td>\n",
" <td>0.028</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_12</th>\n",
" <td>0.87</td>\n",
" <td>0.11</td>\n",
" <td>-1.4</td>\n",
" <td>-0.4</td>\n",
" <td>1.1</td>\n",
" <td>0.3</td>\n",
" <td>-1.5</td>\n",
" <td>0.21</td>\n",
" <td>1.1</td>\n",
" <td>-0.32</td>\n",
" <td>-0.3</td>\n",
" <td>0.12</td>\n",
" <td>0.028</td>\n",
" <td>-0.015</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_13</th>\n",
" <td>0.86</td>\n",
" <td>0.11</td>\n",
" <td>-1.5</td>\n",
" <td>-0.4</td>\n",
" <td>2.6</td>\n",
" <td>0.3</td>\n",
" <td>-5.6</td>\n",
" <td>0.21</td>\n",
" <td>6.1</td>\n",
" <td>-0.32</td>\n",
" <td>-3.3</td>\n",
" <td>0.12</td>\n",
" <td>0.87</td>\n",
" <td>-0.015</td>\n",
" <td>-0.091</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_14</th>\n",
" <td>0.79</td>\n",
" <td>0.07</td>\n",
" <td>-1.5</td>\n",
" <td>1</td>\n",
" <td>2.6</td>\n",
" <td>-7.8</td>\n",
" <td>-5.6</td>\n",
" <td>18</td>\n",
" <td>6.1</td>\n",
" <td>-18</td>\n",
" <td>-3.3</td>\n",
" <td>9.3</td>\n",
" <td>0.87</td>\n",
" <td>-2.4</td>\n",
" <td>-0.091</td>\n",
" <td>0.24</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>model_pow_15</th>\n",
" <td>0.7</td>\n",
" <td>0.07</td>\n",
" <td>-1.9</td>\n",
" <td>1</td>\n",
" <td>7.8</td>\n",
" <td>-7.8</td>\n",
" <td>-26</td>\n",
" <td>18</td>\n",
" <td>40</td>\n",
" <td>-18</td>\n",
" <td>-33</td>\n",
" <td>9.3</td>\n",
" <td>15</td>\n",
" <td>-2.4</td>\n",
" <td>-3.4</td>\n",
" <td>0.24</td>\n",
" <td>0.31</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-45d96347-0be5-4537-be09-3503d753da54')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-45d96347-0be5-4537-be09-3503d753da54 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-45d96347-0be5-4537-be09-3503d753da54');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-46c7cd07-e3f9-4212-9cb0-d02adef37181\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-46c7cd07-e3f9-4212-9cb0-d02adef37181')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-46c7cd07-e3f9-4212-9cb0-d02adef37181 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_82fba911-4e24-43f0-bda3-e565433c3366\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('coef_matrix_simple')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_82fba911-4e24-43f0-bda3-e565433c3366 button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('coef_matrix_simple');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "coef_matrix_simple",
"summary": "{\n \"name\": \"coef_matrix_simple\",\n \"rows\": 15,\n \"fields\": [\n {\n \"column\": \"rss\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.7048223068162681,\n \"max\": 3.2803155997970506,\n \"num_unique_values\": 15,\n \"samples\": [\n 0.8745780848402316,\n 0.871393007750864,\n 3.2803155997970506\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"intercept\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.0380319968390351,\n \"max\": 0.11215707326125884,\n \"num_unique_values\": 15,\n \"samples\": [\n 0.11215707326125884,\n 0.10861877087456165,\n 0.0380319968390351\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_1\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -1.8832324221215595,\n \"max\": -0.7490852512903883,\n \"num_unique_values\": 14,\n \"samples\": [\n -1.3586363599879248,\n -1.4989986806643285,\n -0.7490852512903883\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_2\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.49213551504808883,\n \"max\": 0.9958330259566528,\n \"num_unique_values\": 14,\n \"samples\": [\n -0.49213551504808883,\n -0.3988321961336914,\n -0.008710231823302213\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_3\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.055887892238329934,\n \"max\": 7.753139063820018,\n \"num_unique_values\": 13,\n \"samples\": [\n 2.559636232166756,\n 1.1327912160050446,\n 0.24263764302479873\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_4\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -7.757843088857618,\n \"max\": 0.6902444807042497,\n \"num_unique_values\": 12,\n \"samples\": [\n -7.757843088857618,\n 0.29610850822394774,\n 0.029741659948734008\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_5\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -25.795227478224987,\n \"max\": 0.2972009336224562,\n \"num_unique_values\": 11,\n \"samples\": [\n -0.7792932138251087,\n -0.05335523102973604,\n -5.62879424866876\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_6\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.3899945649893258,\n \"max\": 17.53391736942613,\n \"num_unique_values\": 10,\n \"samples\": [\n 17.53391736942613,\n -0.04251945300765435,\n -0.3899945649893258\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_7\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.07260597208277274,\n \"max\": 40.4147835045321,\n \"num_unique_values\": 9,\n \"samples\": [\n 6.084019777529303,\n -0.07260597208277264,\n 1.0503773825991338\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_8\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -17.954279867486832,\n \"max\": 0.09717741137463205,\n \"num_unique_values\": 8,\n \"samples\": [\n 0.03504888608623045,\n -0.31772160870949484,\n 0.03504888608623138\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_9\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -33.13741530487261,\n \"max\": -0.0817778293838825,\n \"num_unique_values\": 7,\n \"samples\": [\n -0.08177782938388423,\n -0.0817778293838825,\n -3.2788059253082693\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_10\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.0088158676248354,\n \"max\": 9.296857940840242,\n \"num_unique_values\": 6,\n \"samples\": [\n -0.008815867624833716,\n -0.0088158676248354,\n 9.296857940824667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_11\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.02773721799685913,\n \"max\": 14.722270606585116,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.02773721799685913,\n 14.722270606585116,\n 0.8712618354665408\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_12\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -2.3725834280814904,\n \"max\": -0.015368115009034743,\n \"num_unique_values\": 4,\n \"samples\": [\n -0.015368115009068898,\n -2.372583428076816,\n -0.015368115009034743\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_13\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -3.352061287018822,\n \"max\": -0.09142415438166429,\n \"num_unique_values\": 3,\n \"samples\": [\n -0.09142415438199636,\n -0.09142415438166429,\n -3.352061287018822\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_14\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.2370836773458318,\n \"max\": 0.23708367734637853,\n \"num_unique_values\": 2,\n \"samples\": [\n 0.2370836773458318,\n 0.23708367734637853\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_15\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.3060821950636198,\n \"max\": 0.3060821950636198,\n \"num_unique_values\": 1,\n \"samples\": [\n 0.3060821950636198\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 8
}
]
},
{
"cell_type": "markdown",
"source": [
"# Regressão Ridge, L2\n",
"\n",
"Adicionando a soma dos quadrados dos pesos à função de custo"
],
"metadata": {
"id": "UNIfu0gmtxw0"
}
},
{
"cell_type": "code",
"source": [
"from sklearn.linear_model import Ridge\n",
"def ridge_regression(data, predictors, alpha, models_to_plot={}):\n",
" #Fit the model\n",
" ridgereg = Ridge(alpha=alpha)\n",
" ridgereg.fit(data[predictors],data['y'])\n",
" y_pred = ridgereg.predict(data[predictors])\n",
"\n",
" #Check if a plot is to be made for the entered alpha\n",
" if alpha in models_to_plot:\n",
" plt.subplot(models_to_plot[alpha])\n",
" plt.tight_layout()\n",
" plt.plot(data['x'],y_pred)\n",
" plt.plot(data['x'],data['y'],'.')\n",
" plt.title('Plot for alpha: %.3g'%alpha)\n",
"\n",
" #Return the result in pre-defined format\n",
" rss = sum((y_pred-data['y'])**2)\n",
" ret = [rss]\n",
" ret.extend([ridgereg.intercept_])\n",
" ret.extend(ridgereg.coef_)\n",
" return ret"
],
"metadata": {
"id": "ClmZe89pme3Y"
},
"execution_count": 9,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#Initialize predictors to be set of 15 powers of x\n",
"predictors=['x']\n",
"predictors.extend(['x_%d'%i for i in range(2,16)])\n",
"\n",
"#Set the different values of alpha to be tested\n",
"alpha_ridge = [0, 1e-10, 1e-8, 1e-4, 1e-3,1e-2, 1, 5, 10, 20]\n",
"\n",
"#Initialize the dataframe for storing coefficients.\n",
"col = ['rss','intercept'] + ['coef_x_%d'%i for i in range(1,16)]\n",
"ind = ['alpha_%.2g'%alpha_ridge[i] for i in range(0,10)]\n",
"coef_matrix_ridge = pd.DataFrame(index=ind, columns=col)\n",
"\n",
"models_to_plot = {0:231, 1e-10:232, 1e-4:233, 1e-3:234, 5:235, 20:236}\n",
"for i in range(10):\n",
" coef_matrix_ridge.iloc[i,] = ridge_regression(data, predictors, alpha_ridge[i], models_to_plot)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 919
},
"id": "jSqCkqPImiVL",
"outputId": "3b118ddf-23bc-4055-c839-7552f78c9f45"
},
"execution_count": 10,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 1200x1000 with 6 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"#Set the display format to be scientific for ease of analysis\n",
"pd.options.display.float_format = '{:,.2g}'.format\n",
"coef_matrix_ridge"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 383
},
"id": "SqR88x_5m2US",
"outputId": "f2a5b0c1-bd40-4f9c-a191-b7f384c01706"
},
"execution_count": 11,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" rss intercept coef_x_1 coef_x_2 coef_x_3 coef_x_4 coef_x_5 \\\n",
"alpha_0 0.7 0.07 -1.9 1 7.8 -7.8 -26 \n",
"alpha_1e-10 0.7 0.07 -1.9 1 7.8 -7.8 -26 \n",
"alpha_1e-08 0.7 0.07 -1.9 1 7.8 -7.8 -26 \n",
"alpha_0.0001 0.79 0.097 -1.4 0.1 2.4 -3 -6.2 \n",
"alpha_0.001 0.86 0.11 -1.3 -0.46 0.91 0.21 -1.3 \n",
"alpha_0.01 0.88 0.11 -1.2 -0.39 0.39 0.36 -0.15 \n",
"alpha_1 1.1 0.07 -0.89 -0.092 -0.18 -0.0084 0.012 \n",
"alpha_5 2.1 0.056 -0.62 -0.039 -0.25 -0.014 -0.094 \n",
"alpha_10 3.2 0.051 -0.48 -0.024 -0.23 -0.01 -0.11 \n",
"alpha_20 5 0.047 -0.35 -0.014 -0.19 -0.0067 -0.11 \n",
"\n",
" coef_x_6 coef_x_7 coef_x_8 coef_x_9 coef_x_10 coef_x_11 \\\n",
"alpha_0 18 40 -18 -33 9.3 15 \n",
"alpha_1e-10 18 40 -18 -33 9.3 15 \n",
"alpha_1e-08 18 40 -18 -33 9.3 15 \n",
"alpha_0.0001 7.7 8.7 -8.4 -6.6 4.5 2.8 \n",
"alpha_0.001 1.1 1.1 -1.8 -0.45 1.1 0.11 \n",
"alpha_0.01 0.12 0.029 -0.34 -0.024 0.21 0.057 \n",
"alpha_1 0.021 0.065 0.017 0.042 0.0047 -0.0072 \n",
"alpha_5 0.0028 0.0025 0.011 0.059 0.0086 0.051 \n",
"alpha_10 0.0002 -0.025 0.0062 0.039 0.0059 0.051 \n",
"alpha_20 -0.00095 -0.048 0.0029 0.0079 0.0034 0.035 \n",
"\n",
" coef_x_12 coef_x_13 coef_x_14 coef_x_15 \n",
"alpha_0 -2.4 -3.4 0.24 0.31 \n",
"alpha_1e-10 -2.4 -3.4 0.24 0.31 \n",
"alpha_1e-08 -2.4 -3.4 0.24 0.31 \n",
"alpha_0.0001 -1.2 -0.62 0.12 0.055 \n",
"alpha_0.001 -0.32 -0.016 0.034 0.0008 \n",
"alpha_0.01 -0.057 -0.026 0.006 0.0033 \n",
"alpha_1 -0.011 -0.011 0.0025 0.0026 \n",
"alpha_5 -0.0088 -0.04 0.0017 0.0063 \n",
"alpha_10 -0.0051 -0.027 0.00089 0.0029 \n",
"alpha_20 -0.0022 -0.0016 0.00032 -0.0026 "
],
"text/html": [
"\n",
" <div id=\"df-1a844203-1e5b-402d-8258-04dfb6ab32d9\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>rss</th>\n",
" <th>intercept</th>\n",
" <th>coef_x_1</th>\n",
" <th>coef_x_2</th>\n",
" <th>coef_x_3</th>\n",
" <th>coef_x_4</th>\n",
" <th>coef_x_5</th>\n",
" <th>coef_x_6</th>\n",
" <th>coef_x_7</th>\n",
" <th>coef_x_8</th>\n",
" <th>coef_x_9</th>\n",
" <th>coef_x_10</th>\n",
" <th>coef_x_11</th>\n",
" <th>coef_x_12</th>\n",
" <th>coef_x_13</th>\n",
" <th>coef_x_14</th>\n",
" <th>coef_x_15</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>alpha_0</th>\n",
" <td>0.7</td>\n",
" <td>0.07</td>\n",
" <td>-1.9</td>\n",
" <td>1</td>\n",
" <td>7.8</td>\n",
" <td>-7.8</td>\n",
" <td>-26</td>\n",
" <td>18</td>\n",
" <td>40</td>\n",
" <td>-18</td>\n",
" <td>-33</td>\n",
" <td>9.3</td>\n",
" <td>15</td>\n",
" <td>-2.4</td>\n",
" <td>-3.4</td>\n",
" <td>0.24</td>\n",
" <td>0.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_1e-10</th>\n",
" <td>0.7</td>\n",
" <td>0.07</td>\n",
" <td>-1.9</td>\n",
" <td>1</td>\n",
" <td>7.8</td>\n",
" <td>-7.8</td>\n",
" <td>-26</td>\n",
" <td>18</td>\n",
" <td>40</td>\n",
" <td>-18</td>\n",
" <td>-33</td>\n",
" <td>9.3</td>\n",
" <td>15</td>\n",
" <td>-2.4</td>\n",
" <td>-3.4</td>\n",
" <td>0.24</td>\n",
" <td>0.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_1e-08</th>\n",
" <td>0.7</td>\n",
" <td>0.07</td>\n",
" <td>-1.9</td>\n",
" <td>1</td>\n",
" <td>7.8</td>\n",
" <td>-7.8</td>\n",
" <td>-26</td>\n",
" <td>18</td>\n",
" <td>40</td>\n",
" <td>-18</td>\n",
" <td>-33</td>\n",
" <td>9.3</td>\n",
" <td>15</td>\n",
" <td>-2.4</td>\n",
" <td>-3.4</td>\n",
" <td>0.24</td>\n",
" <td>0.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_0.0001</th>\n",
" <td>0.79</td>\n",
" <td>0.097</td>\n",
" <td>-1.4</td>\n",
" <td>0.1</td>\n",
" <td>2.4</td>\n",
" <td>-3</td>\n",
" <td>-6.2</td>\n",
" <td>7.7</td>\n",
" <td>8.7</td>\n",
" <td>-8.4</td>\n",
" <td>-6.6</td>\n",
" <td>4.5</td>\n",
" <td>2.8</td>\n",
" <td>-1.2</td>\n",
" <td>-0.62</td>\n",
" <td>0.12</td>\n",
" <td>0.055</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_0.001</th>\n",
" <td>0.86</td>\n",
" <td>0.11</td>\n",
" <td>-1.3</td>\n",
" <td>-0.46</td>\n",
" <td>0.91</td>\n",
" <td>0.21</td>\n",
" <td>-1.3</td>\n",
" <td>1.1</td>\n",
" <td>1.1</td>\n",
" <td>-1.8</td>\n",
" <td>-0.45</td>\n",
" <td>1.1</td>\n",
" <td>0.11</td>\n",
" <td>-0.32</td>\n",
" <td>-0.016</td>\n",
" <td>0.034</td>\n",
" <td>0.0008</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_0.01</th>\n",
" <td>0.88</td>\n",
" <td>0.11</td>\n",
" <td>-1.2</td>\n",
" <td>-0.39</td>\n",
" <td>0.39</td>\n",
" <td>0.36</td>\n",
" <td>-0.15</td>\n",
" <td>0.12</td>\n",
" <td>0.029</td>\n",
" <td>-0.34</td>\n",
" <td>-0.024</td>\n",
" <td>0.21</td>\n",
" <td>0.057</td>\n",
" <td>-0.057</td>\n",
" <td>-0.026</td>\n",
" <td>0.006</td>\n",
" <td>0.0033</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_1</th>\n",
" <td>1.1</td>\n",
" <td>0.07</td>\n",
" <td>-0.89</td>\n",
" <td>-0.092</td>\n",
" <td>-0.18</td>\n",
" <td>-0.0084</td>\n",
" <td>0.012</td>\n",
" <td>0.021</td>\n",
" <td>0.065</td>\n",
" <td>0.017</td>\n",
" <td>0.042</td>\n",
" <td>0.0047</td>\n",
" <td>-0.0072</td>\n",
" <td>-0.011</td>\n",
" <td>-0.011</td>\n",
" <td>0.0025</td>\n",
" <td>0.0026</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_5</th>\n",
" <td>2.1</td>\n",
" <td>0.056</td>\n",
" <td>-0.62</td>\n",
" <td>-0.039</td>\n",
" <td>-0.25</td>\n",
" <td>-0.014</td>\n",
" <td>-0.094</td>\n",
" <td>0.0028</td>\n",
" <td>0.0025</td>\n",
" <td>0.011</td>\n",
" <td>0.059</td>\n",
" <td>0.0086</td>\n",
" <td>0.051</td>\n",
" <td>-0.0088</td>\n",
" <td>-0.04</td>\n",
" <td>0.0017</td>\n",
" <td>0.0063</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_10</th>\n",
" <td>3.2</td>\n",
" <td>0.051</td>\n",
" <td>-0.48</td>\n",
" <td>-0.024</td>\n",
" <td>-0.23</td>\n",
" <td>-0.01</td>\n",
" <td>-0.11</td>\n",
" <td>0.0002</td>\n",
" <td>-0.025</td>\n",
" <td>0.0062</td>\n",
" <td>0.039</td>\n",
" <td>0.0059</td>\n",
" <td>0.051</td>\n",
" <td>-0.0051</td>\n",
" <td>-0.027</td>\n",
" <td>0.00089</td>\n",
" <td>0.0029</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_20</th>\n",
" <td>5</td>\n",
" <td>0.047</td>\n",
" <td>-0.35</td>\n",
" <td>-0.014</td>\n",
" <td>-0.19</td>\n",
" <td>-0.0067</td>\n",
" <td>-0.11</td>\n",
" <td>-0.00095</td>\n",
" <td>-0.048</td>\n",
" <td>0.0029</td>\n",
" <td>0.0079</td>\n",
" <td>0.0034</td>\n",
" <td>0.035</td>\n",
" <td>-0.0022</td>\n",
" <td>-0.0016</td>\n",
" <td>0.00032</td>\n",
" <td>-0.0026</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1a844203-1e5b-402d-8258-04dfb6ab32d9')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-1a844203-1e5b-402d-8258-04dfb6ab32d9 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-1a844203-1e5b-402d-8258-04dfb6ab32d9');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-42dbeede-ace9-4bdb-b55b-9cba32cd27eb\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-42dbeede-ace9-4bdb-b55b-9cba32cd27eb')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-42dbeede-ace9-4bdb-b55b-9cba32cd27eb button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_2aa979eb-0c5e-47c4-838f-1ccc257cc94a\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('coef_matrix_ridge')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_2aa979eb-0c5e-47c4-838f-1ccc257cc94a button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('coef_matrix_ridge');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "coef_matrix_ridge",
"summary": "{\n \"name\": \"coef_matrix_ridge\",\n \"rows\": 10,\n \"fields\": [\n {\n \"column\": \"rss\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.7048223068160637,\n \"max\": 4.999293151629137,\n \"num_unique_values\": 10,\n \"samples\": [\n 3.1800408304121834,\n 0.7048223068180357,\n 0.876616396673694\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"intercept\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.046757869967216245,\n \"max\": 0.11367589404711011,\n \"num_unique_values\": 10,\n \"samples\": [\n 0.05076201150926239,\n 0.0695330148904614,\n 0.10549749902882795\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_1\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -1.8832324043934514,\n \"max\": -0.3504737051135752,\n \"num_unique_values\": 10,\n \"samples\": [\n -0.48216414606962804,\n -1.883230156531545,\n -1.2387216610204852\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_2\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.46489110722798255,\n \"max\": 0.9958335154150136,\n \"num_unique_values\": 10,\n \"samples\": [\n -0.024303416285411918,\n 0.9958314966667315,\n -0.38985205687664926\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_3\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.24656283505467844,\n \"max\": 7.753138692048954,\n \"num_unique_values\": 10,\n \"samples\": [\n -0.22879298555779384,\n 7.753110742801179,\n 0.38897656226120075\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_4\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -7.757845817084339,\n \"max\": 0.3565935169337166,\n \"num_unique_values\": 10,\n \"samples\": [\n -0.010021372783033772,\n -7.757835000363109,\n 0.3565935169337166\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_5\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -25.79522568412038,\n \"max\": 0.01177553326997804,\n \"num_unique_values\": 10,\n \"samples\": [\n -0.11145870859225389,\n -25.795123563608758,\n -0.14958359895545764\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_6\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.0009483332372733572,\n \"max\": 17.53392308430858,\n \"num_unique_values\": 10,\n \"samples\": [\n 0.0001984442703173078,\n 17.53390107678801,\n 0.11981969449170493\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_7\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.04784045642392969,\n \"max\": 40.41478001800435,\n \"num_unique_values\": 10,\n \"samples\": [\n -0.025191432525253944,\n 40.414614068657116,\n 0.029193970878680916\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_8\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -17.954285569444853,\n \"max\": 0.017356823134421967,\n \"num_unique_values\": 10,\n \"samples\": [\n 0.006215230811120363,\n -17.954264098172658,\n -0.34481471583660744\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_9\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -33.137411988383946,\n \"max\": 0.058996861521950356,\n \"num_unique_values\": 10,\n \"samples\": [\n 0.03886922905764376,\n -33.13727286008943,\n -0.024296977540913405\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_10\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.0033790074574293356,\n \"max\": 9.296860859376599,\n \"num_unique_values\": 10,\n \"samples\": [\n 0.005889768647223833,\n 9.296850062825934,\n 0.21094582197857\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_11\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.007186026736185571,\n \"max\": 14.722268965273278,\n \"num_unique_values\": 10,\n \"samples\": [\n 0.050565707467948695,\n 14.722206315475649,\n 0.05678466341561064\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_12\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -2.3725841680455577,\n \"max\": -0.0022491613972543856,\n \"num_unique_values\": 10,\n \"samples\": [\n -0.005122794056474715,\n -2.3725814698626166,\n -0.05732520880495162\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_13\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -3.3520608812768673,\n \"max\": -0.0015777137200878996,\n \"num_unique_values\": 10,\n \"samples\": [\n -0.026847165324807843,\n -3.3520464903161424,\n -0.026309576075094983\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_14\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.0003212954297420006,\n \"max\": 0.2370837509569799,\n \"num_unique_values\": 10,\n \"samples\": [\n 0.000892215817653915,\n 0.23708348572373683,\n 0.006010939446101114\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_15\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.0026060271804397178,\n \"max\": 0.30608215549249546,\n \"num_unique_values\": 10,\n \"samples\": [\n 0.0028521832449852013,\n 0.30608083206682873,\n 0.003346986267353794\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 11
}
]
},
{
"cell_type": "markdown",
"source": [
"# Regressão Lasso, L1\n",
"Adicionando a soma dos valores absolutos dos pesos à função de custo"
],
"metadata": {
"id": "3rkSOWRot9v4"
}
},
{
"cell_type": "code",
"source": [
"from sklearn.linear_model import Lasso\n",
"def lasso_regression(data, predictors, alpha, models_to_plot={}):\n",
" #Fit the model\n",
" lassoreg = Lasso(alpha=alpha)\n",
" lassoreg.fit(data[predictors],data['y'])\n",
" y_pred = lassoreg.predict(data[predictors])\n",
"\n",
" #Check if a plot is to be made for the entered alpha\n",
" if alpha in models_to_plot:\n",
" plt.subplot(models_to_plot[alpha])\n",
" plt.tight_layout()\n",
" plt.plot(data['x'],y_pred)\n",
" plt.plot(data['x'],data['y'],'.')\n",
" plt.title('Plot for alpha: %.3g'%alpha)\n",
"\n",
" #Return the result in pre-defined format\n",
" rss = sum((y_pred-data['y'])**2)\n",
" ret = [rss]\n",
" ret.extend([lassoreg.intercept_])\n",
" ret.extend(lassoreg.coef_)\n",
" return ret"
],
"metadata": {
"id": "CAVYRDTauE20"
},
"execution_count": 12,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#Initialize predictors to all 15 powers of x\n",
"predictors=['x']\n",
"predictors.extend(['x_%d'%i for i in range(2,16)])\n",
"\n",
"#Define the alpha values to test\n",
"alpha_lasso = [1e-15, 1e-10, 1e-8, 1e-5,1e-4, 1e-3,1e-2, 1, 5, 10]\n",
"\n",
"#Initialize the dataframe to store coefficients\n",
"col = ['rss','intercept'] + ['coef_x_%d'%i for i in range(1,16)]\n",
"ind = ['alpha_%.2g'%alpha_lasso[i] for i in range(0,10)]\n",
"coef_matrix_lasso = pd.DataFrame(index=ind, columns=col)\n",
"\n",
"#Define the models to plot\n",
"models_to_plot = {1e-10:231, 1e-5:232, 1e-3:233, 1e-2:234, 1:235, 10:236}\n",
"\n",
"#Iterate over the 10 alpha values:\n",
"for i in range(10):\n",
" coef_matrix_lasso.iloc[i,] = lasso_regression(data, predictors, alpha_lasso[i], models_to_plot)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "GNbOz0-jvUwm",
"outputId": "0abc01e5-ee25-43b1-fc4f-8a8d3e015f5b"
},
"execution_count": 13,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.11/dist-packages/sklearn/linear_model/_coordinate_descent.py:695: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.459e-01, tolerance: 3.695e-03\n",
" model = cd_fast.enet_coordinate_descent(\n",
"/usr/local/lib/python3.11/dist-packages/sklearn/linear_model/_coordinate_descent.py:695: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.459e-01, tolerance: 3.695e-03\n",
" model = cd_fast.enet_coordinate_descent(\n",
"/usr/local/lib/python3.11/dist-packages/sklearn/linear_model/_coordinate_descent.py:695: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.459e-01, tolerance: 3.695e-03\n",
" model = cd_fast.enet_coordinate_descent(\n",
"/usr/local/lib/python3.11/dist-packages/sklearn/linear_model/_coordinate_descent.py:695: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.459e-01, tolerance: 3.695e-03\n",
" model = cd_fast.enet_coordinate_descent(\n",
"/usr/local/lib/python3.11/dist-packages/sklearn/linear_model/_coordinate_descent.py:695: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.444e-01, tolerance: 3.695e-03\n",
" model = cd_fast.enet_coordinate_descent(\n",
"/usr/local/lib/python3.11/dist-packages/sklearn/linear_model/_coordinate_descent.py:695: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 4.404e-01, tolerance: 3.695e-03\n",
" model = cd_fast.enet_coordinate_descent(\n",
"/usr/local/lib/python3.11/dist-packages/sklearn/linear_model/_coordinate_descent.py:695: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 5.501e-02, tolerance: 3.695e-03\n",
" model = cd_fast.enet_coordinate_descent(\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 1200x1000 with 6 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"coef_matrix_lasso"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 383
},
"id": "vmXSbKcDw7Aa",
"outputId": "8a10d99c-f9b2-4791-e3ab-1c746d544bfe"
},
"execution_count": 14,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" rss intercept coef_x_1 coef_x_2 coef_x_3 coef_x_4 coef_x_5 \\\n",
"alpha_1e-15 0.89 0.095 -1.2 -0.28 0.17 0.23 0.024 \n",
"alpha_1e-10 0.89 0.095 -1.2 -0.28 0.17 0.23 0.024 \n",
"alpha_1e-08 0.89 0.095 -1.2 -0.28 0.17 0.23 0.024 \n",
"alpha_1e-05 0.89 0.095 -1.2 -0.28 0.17 0.23 0.024 \n",
"alpha_0.0001 0.89 0.093 -1.2 -0.26 0.16 0.21 0.029 \n",
"alpha_0.001 0.92 0.071 -1.1 -0.11 0.069 0.031 0.073 \n",
"alpha_0.01 1.1 0.038 -1 -0 0 -0 0 \n",
"alpha_1 24 0.038 -0 -0 -0 -0 -0 \n",
"alpha_5 30 0.038 -0 -0 -0 -0 -0 \n",
"alpha_10 30 0.038 -0 -0 -0 -0 -0 \n",
"\n",
" coef_x_6 coef_x_7 coef_x_8 coef_x_9 coef_x_10 coef_x_11 \\\n",
"alpha_1e-15 -0.036 0.015 -0.0088 0.0022 -0.00072 -0.00033 \n",
"alpha_1e-10 -0.036 0.015 -0.0088 0.0022 -0.00072 -0.00033 \n",
"alpha_1e-08 -0.036 0.015 -0.0088 0.0022 -0.00072 -0.00033 \n",
"alpha_1e-05 -0.034 0.015 -0.0089 0.0022 -0.00074 -0.00033 \n",
"alpha_0.0001 -0.025 0.015 -0.0095 0.0021 -0.00088 -0.00034 \n",
"alpha_0.001 0.02 0.012 -0.0012 0.00085 -0.003 -0.00041 \n",
"alpha_0.01 -0 0.046 -0 0.0041 -0 0 \n",
"alpha_1 0 -0 0 -0 0 -0.019 \n",
"alpha_5 0 -0 0 -0 0 -0 \n",
"alpha_10 0 -0 0 -0 0 -0 \n",
"\n",
" coef_x_12 coef_x_13 coef_x_14 coef_x_15 \n",
"alpha_1e-15 0.00024 -0.00039 0.00019 -0.00019 \n",
"alpha_1e-10 0.00024 -0.00039 0.00019 -0.00019 \n",
"alpha_1e-08 0.00024 -0.00039 0.00019 -0.00019 \n",
"alpha_1e-05 0.00023 -0.0004 0.00019 -0.00019 \n",
"alpha_0.0001 0.00021 -0.0004 0.00019 -0.00019 \n",
"alpha_0.001 -0.0001 -0.00044 0.00016 -0.00017 \n",
"alpha_0.01 0 -0.00094 2.4e-06 -0.00026 \n",
"alpha_1 0 -0 0 0.002 \n",
"alpha_5 0 -0.0014 0 -0 \n",
"alpha_10 0 -0 0 -0.00047 "
],
"text/html": [
"\n",
" <div id=\"df-32b3c12e-5253-41aa-8f6f-7ba8e64be33d\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>rss</th>\n",
" <th>intercept</th>\n",
" <th>coef_x_1</th>\n",
" <th>coef_x_2</th>\n",
" <th>coef_x_3</th>\n",
" <th>coef_x_4</th>\n",
" <th>coef_x_5</th>\n",
" <th>coef_x_6</th>\n",
" <th>coef_x_7</th>\n",
" <th>coef_x_8</th>\n",
" <th>coef_x_9</th>\n",
" <th>coef_x_10</th>\n",
" <th>coef_x_11</th>\n",
" <th>coef_x_12</th>\n",
" <th>coef_x_13</th>\n",
" <th>coef_x_14</th>\n",
" <th>coef_x_15</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>alpha_1e-15</th>\n",
" <td>0.89</td>\n",
" <td>0.095</td>\n",
" <td>-1.2</td>\n",
" <td>-0.28</td>\n",
" <td>0.17</td>\n",
" <td>0.23</td>\n",
" <td>0.024</td>\n",
" <td>-0.036</td>\n",
" <td>0.015</td>\n",
" <td>-0.0088</td>\n",
" <td>0.0022</td>\n",
" <td>-0.00072</td>\n",
" <td>-0.00033</td>\n",
" <td>0.00024</td>\n",
" <td>-0.00039</td>\n",
" <td>0.00019</td>\n",
" <td>-0.00019</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_1e-10</th>\n",
" <td>0.89</td>\n",
" <td>0.095</td>\n",
" <td>-1.2</td>\n",
" <td>-0.28</td>\n",
" <td>0.17</td>\n",
" <td>0.23</td>\n",
" <td>0.024</td>\n",
" <td>-0.036</td>\n",
" <td>0.015</td>\n",
" <td>-0.0088</td>\n",
" <td>0.0022</td>\n",
" <td>-0.00072</td>\n",
" <td>-0.00033</td>\n",
" <td>0.00024</td>\n",
" <td>-0.00039</td>\n",
" <td>0.00019</td>\n",
" <td>-0.00019</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_1e-08</th>\n",
" <td>0.89</td>\n",
" <td>0.095</td>\n",
" <td>-1.2</td>\n",
" <td>-0.28</td>\n",
" <td>0.17</td>\n",
" <td>0.23</td>\n",
" <td>0.024</td>\n",
" <td>-0.036</td>\n",
" <td>0.015</td>\n",
" <td>-0.0088</td>\n",
" <td>0.0022</td>\n",
" <td>-0.00072</td>\n",
" <td>-0.00033</td>\n",
" <td>0.00024</td>\n",
" <td>-0.00039</td>\n",
" <td>0.00019</td>\n",
" <td>-0.00019</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_1e-05</th>\n",
" <td>0.89</td>\n",
" <td>0.095</td>\n",
" <td>-1.2</td>\n",
" <td>-0.28</td>\n",
" <td>0.17</td>\n",
" <td>0.23</td>\n",
" <td>0.024</td>\n",
" <td>-0.034</td>\n",
" <td>0.015</td>\n",
" <td>-0.0089</td>\n",
" <td>0.0022</td>\n",
" <td>-0.00074</td>\n",
" <td>-0.00033</td>\n",
" <td>0.00023</td>\n",
" <td>-0.0004</td>\n",
" <td>0.00019</td>\n",
" <td>-0.00019</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_0.0001</th>\n",
" <td>0.89</td>\n",
" <td>0.093</td>\n",
" <td>-1.2</td>\n",
" <td>-0.26</td>\n",
" <td>0.16</td>\n",
" <td>0.21</td>\n",
" <td>0.029</td>\n",
" <td>-0.025</td>\n",
" <td>0.015</td>\n",
" <td>-0.0095</td>\n",
" <td>0.0021</td>\n",
" <td>-0.00088</td>\n",
" <td>-0.00034</td>\n",
" <td>0.00021</td>\n",
" <td>-0.0004</td>\n",
" <td>0.00019</td>\n",
" <td>-0.00019</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_0.001</th>\n",
" <td>0.92</td>\n",
" <td>0.071</td>\n",
" <td>-1.1</td>\n",
" <td>-0.11</td>\n",
" <td>0.069</td>\n",
" <td>0.031</td>\n",
" <td>0.073</td>\n",
" <td>0.02</td>\n",
" <td>0.012</td>\n",
" <td>-0.0012</td>\n",
" <td>0.00085</td>\n",
" <td>-0.003</td>\n",
" <td>-0.00041</td>\n",
" <td>-0.0001</td>\n",
" <td>-0.00044</td>\n",
" <td>0.00016</td>\n",
" <td>-0.00017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_0.01</th>\n",
" <td>1.1</td>\n",
" <td>0.038</td>\n",
" <td>-1</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0.046</td>\n",
" <td>-0</td>\n",
" <td>0.0041</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>-0.00094</td>\n",
" <td>2.4e-06</td>\n",
" <td>-0.00026</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_1</th>\n",
" <td>24</td>\n",
" <td>0.038</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0.019</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>0.002</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_5</th>\n",
" <td>30</td>\n",
" <td>0.038</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0.0014</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_10</th>\n",
" <td>30</td>\n",
" <td>0.038</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0</td>\n",
" <td>0</td>\n",
" <td>-0.00047</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-32b3c12e-5253-41aa-8f6f-7ba8e64be33d')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-32b3c12e-5253-41aa-8f6f-7ba8e64be33d button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-32b3c12e-5253-41aa-8f6f-7ba8e64be33d');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-03f6cb99-230d-479f-b451-843f9c2e3e83\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-03f6cb99-230d-479f-b451-843f9c2e3e83')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-03f6cb99-230d-479f-b451-843f9c2e3e83 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_7d8fc80d-a1c0-4a4c-8c6f-cac7da0b4aa0\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('coef_matrix_lasso')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_7d8fc80d-a1c0-4a4c-8c6f-cac7da0b4aa0 button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('coef_matrix_lasso');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "coef_matrix_lasso",
"summary": "{\n \"name\": \"coef_matrix_lasso\",\n \"rows\": 10,\n \"fields\": [\n {\n \"column\": \"rss\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.8918570677901976,\n \"max\": 30.404552613458634,\n \"num_unique_values\": 10,\n \"samples\": [\n 29.62875647179211,\n 0.891857069162331,\n 0.9200251053873001\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"intercept\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.03768480618064033,\n \"max\": 0.09499296767044654,\n \"num_unique_values\": 10,\n \"samples\": [\n 0.038031996839035166,\n 0.09499296536187492,\n 0.07119351521383752\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_1\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -1.1807357109609238,\n \"max\": -0.0,\n \"num_unique_values\": 8,\n \"samples\": [\n -1.1807357057136982,\n -1.1282348594799363,\n -1.1807357109609238\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_2\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.2784940685006169,\n \"max\": -0.0,\n \"num_unique_values\": 7,\n \"samples\": [\n -0.2784940685006169,\n -0.27849405054003196,\n -0.10779439105506051\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_3\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.0,\n \"max\": 0.17040616029711084,\n \"num_unique_values\": 7,\n \"samples\": [\n 0.17040616029711084,\n 0.17040615021774969,\n 0.06949187388414274\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_4\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.0,\n \"max\": 0.2294850575920852,\n \"num_unique_values\": 7,\n \"samples\": [\n 0.2294850575920852,\n 0.22948503326997957,\n 0.030715022316576964\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_5\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.0,\n \"max\": 0.0730886885733731,\n \"num_unique_values\": 7,\n \"samples\": [\n 0.023895073242198625,\n 0.023895078150769498,\n 0.0730886885733731\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_6\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.03550704069091949,\n \"max\": 0.020004763674861516,\n \"num_unique_values\": 7,\n \"samples\": [\n -0.03550704069091949,\n -0.03550703047410142,\n 0.020004763674861516\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_7\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.0,\n \"max\": 0.04563360576032447,\n \"num_unique_values\": 8,\n \"samples\": [\n 0.014966142974238221,\n 0.011952062944257682,\n 0.01496614327787519\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_8\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.00954505314939373,\n \"max\": -0.0,\n \"num_unique_values\": 7,\n \"samples\": [\n -0.008788270171941585,\n -0.00878827094317381,\n -0.001191909132710785\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_9\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.0,\n \"max\": 0.0041059341431223355,\n \"num_unique_values\": 8,\n \"samples\": [\n 0.0021889590792181783,\n 0.0008494732635121587,\n 0.002188959207171395\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_10\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.0029518743404299045,\n \"max\": -0.0,\n \"num_unique_values\": 7,\n \"samples\": [\n -0.0007228802521565218,\n -0.0007228804126653177,\n -0.0029518743404299045\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_11\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.01903594065160902,\n \"max\": 0.0,\n \"num_unique_values\": 8,\n \"samples\": [\n -0.0003319370498408516,\n -0.00040532500800355523,\n -0.0003319370404247819\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_12\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.00010451074969717404,\n \"max\": 0.00023504747873874223,\n \"num_unique_values\": 7,\n \"samples\": [\n 0.00023504747873874223,\n 0.00023504745234822675,\n -0.00010451074969717404\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_13\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.0013736060161198581,\n \"max\": -0.0,\n \"num_unique_values\": 9,\n \"samples\": [\n -0.0,\n -0.00039466434635258916,\n -0.00044354309718004273\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_14\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": 0.0,\n \"max\": 0.0001921936333602257,\n \"num_unique_values\": 8,\n \"samples\": [\n 0.00018758259237406188,\n 0.00016444795575133833,\n 0.0001875825876898844\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"coef_x_15\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": -0.0004729332458524307,\n \"max\": 0.001954975267182855,\n \"num_unique_values\": 10,\n \"samples\": [\n -0.0,\n -0.00019369633017839353,\n -0.00017212482474928114\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 14
}
]
},
{
"cell_type": "code",
"source": [
"coef_matrix_lasso.apply(lambda x: sum(x.values==0),axis=1)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 398
},
"id": "eqIlm4BWw55O",
"outputId": "7d10ca0f-4feb-454c-a0b7-92462a081cdc"
},
"execution_count": 15,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"alpha_1e-15 0\n",
"alpha_1e-10 0\n",
"alpha_1e-08 0\n",
"alpha_1e-05 0\n",
"alpha_0.0001 0\n",
"alpha_0.001 0\n",
"alpha_0.01 9\n",
"alpha_1 13\n",
"alpha_5 14\n",
"alpha_10 14\n",
"dtype: int64"
],
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>alpha_1e-15</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_1e-10</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_1e-08</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_1e-05</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_0.0001</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_0.001</th>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_0.01</th>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_1</th>\n",
" <td>13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_5</th>\n",
" <td>14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>alpha_10</th>\n",
" <td>14</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div><br><label><b>dtype:</b> int64</label>"
]
},
"metadata": {},
"execution_count": 15
}
]
},
{
"cell_type": "markdown",
"source": [
"# Comparação: Porque os coeficientes do Lasso ficam zerados?"
],
"metadata": {
"id": "Jyxu36mHyQTF"
}
},
{
"cell_type": "markdown",
"source": [
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment