commit 5cc446afedd3319a2c71cff8c797aba4bc3368ba
parent b9f652a32b16232616cd2807b1ff99580f67eeb8
Author: Andrew <andrewlaack1@gmail.com>
Date: Wed, 26 Jun 2024 23:00:27 -0500
Created some more models for student performance
Diffstat:
4 files changed, 2249 insertions(+), 59 deletions(-)
diff --git a/recidivism/RecidivismLogReg.ipynb b/recidivism/RecidivismLogReg.ipynb
@@ -1,8 +1,15 @@
{
"cells": [
{
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "https://www.kaggle.com/datasets/slonnadube/recidivism"
+ ]
+ },
+ {
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 33,
"metadata": {},
"outputs": [
{
@@ -26,7 +33,7 @@
" 'Part of Target Population']"
]
},
- "execution_count": 1,
+ "execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
@@ -40,7 +47,7 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 34,
"metadata": {},
"outputs": [
{
@@ -126,7 +133,7 @@
"0 NaN No "
]
},
- "execution_count": 2,
+ "execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
@@ -137,7 +144,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 35,
"metadata": {},
"outputs": [
{
@@ -149,7 +156,7 @@
"Name: count, dtype: int64"
]
},
- "execution_count": 3,
+ "execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
@@ -164,7 +171,7 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 36,
"metadata": {},
"outputs": [
{
@@ -182,7 +189,7 @@
"dtype: object"
]
},
- "execution_count": 4,
+ "execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
@@ -193,7 +200,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
@@ -210,7 +217,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 38,
"metadata": {},
"outputs": [],
"source": [
@@ -225,7 +232,7 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 39,
"metadata": {},
"outputs": [],
"source": [
@@ -237,7 +244,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 40,
"metadata": {},
"outputs": [
{
@@ -261,13 +268,13 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 41,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
- "<style>#sk-container-id-1 {\n",
+ "<style>#sk-container-id-2 {\n",
" /* Definition of color scheme common for light and dark mode */\n",
" --sklearn-color-text: black;\n",
" --sklearn-color-line: gray;\n",
@@ -297,15 +304,15 @@
" }\n",
"}\n",
"\n",
- "#sk-container-id-1 {\n",
+ "#sk-container-id-2 {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
- "#sk-container-id-1 pre {\n",
+ "#sk-container-id-2 pre {\n",
" padding: 0;\n",
"}\n",
"\n",
- "#sk-container-id-1 input.sk-hidden--visually {\n",
+ "#sk-container-id-2 input.sk-hidden--visually {\n",
" border: 0;\n",
" clip: rect(1px 1px 1px 1px);\n",
" clip: rect(1px, 1px, 1px, 1px);\n",
@@ -317,7 +324,7 @@
" width: 1px;\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+ "#sk-container-id-2 div.sk-dashed-wrapped {\n",
" border: 1px dashed var(--sklearn-color-line);\n",
" margin: 0 0.4em 0.5em 0.4em;\n",
" box-sizing: border-box;\n",
@@ -325,7 +332,7 @@
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-container {\n",
+ "#sk-container-id-2 div.sk-container {\n",
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
" so we also need the `!important` here to be able to override the\n",
@@ -335,7 +342,7 @@
" position: relative;\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+ "#sk-container-id-2 div.sk-text-repr-fallback {\n",
" display: none;\n",
"}\n",
"\n",
@@ -351,14 +358,14 @@
"\n",
"/* Parallel-specific style estimator block */\n",
"\n",
- "#sk-container-id-1 div.sk-parallel-item::after {\n",
+ "#sk-container-id-2 div.sk-parallel-item::after {\n",
" content: \"\";\n",
" width: 100%;\n",
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
" flex-grow: 1;\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-parallel {\n",
+ "#sk-container-id-2 div.sk-parallel {\n",
" display: flex;\n",
" align-items: stretch;\n",
" justify-content: center;\n",
@@ -366,28 +373,28 @@
" position: relative;\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-parallel-item {\n",
+ "#sk-container-id-2 div.sk-parallel-item {\n",
" display: flex;\n",
" flex-direction: column;\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+ "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
" align-self: flex-end;\n",
" width: 50%;\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+ "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
" align-self: flex-start;\n",
" width: 50%;\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+ "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
" width: 0;\n",
"}\n",
"\n",
"/* Serial-specific style estimator block */\n",
"\n",
- "#sk-container-id-1 div.sk-serial {\n",
+ "#sk-container-id-2 div.sk-serial {\n",
" display: flex;\n",
" flex-direction: column;\n",
" align-items: center;\n",
@@ -405,14 +412,14 @@
"\n",
"/* Pipeline and ColumnTransformer style (default) */\n",
"\n",
- "#sk-container-id-1 div.sk-toggleable {\n",
+ "#sk-container-id-2 div.sk-toggleable {\n",
" /* Default theme specific background. It is overwritten whether we have a\n",
" specific estimator or a Pipeline/ColumnTransformer */\n",
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"/* Toggleable label */\n",
- "#sk-container-id-1 label.sk-toggleable__label {\n",
+ "#sk-container-id-2 label.sk-toggleable__label {\n",
" cursor: pointer;\n",
" display: block;\n",
" width: 100%;\n",
@@ -422,7 +429,7 @@
" text-align: center;\n",
"}\n",
"\n",
- "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+ "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
" /* Arrow on the left of the label */\n",
" content: \"▸\";\n",
" float: left;\n",
@@ -430,13 +437,13 @@
" color: var(--sklearn-color-icon);\n",
"}\n",
"\n",
- "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+ "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"/* Toggleable content - dropdown */\n",
"\n",
- "#sk-container-id-1 div.sk-toggleable__content {\n",
+ "#sk-container-id-2 div.sk-toggleable__content {\n",
" max-height: 0;\n",
" max-width: 0;\n",
" overflow: hidden;\n",
@@ -445,12 +452,12 @@
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+ "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+ "#sk-container-id-2 div.sk-toggleable__content pre {\n",
" margin: 0.2em;\n",
" border-radius: 0.25em;\n",
" color: var(--sklearn-color-text);\n",
@@ -458,79 +465,79 @@
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+ "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
- "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
" /* Expand drop-down */\n",
" max-height: 200px;\n",
" max-width: 100%;\n",
" overflow: auto;\n",
"}\n",
"\n",
- "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
" content: \"▾\";\n",
"}\n",
"\n",
"/* Pipeline/ColumnTransformer-specific style */\n",
"\n",
- "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator-specific style */\n",
"\n",
"/* Colorize estimator box */\n",
- "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
- "#sk-container-id-1 div.sk-label label {\n",
+ "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-2 div.sk-label label {\n",
" /* The background is the default theme color */\n",
" color: var(--sklearn-color-text-on-default-background);\n",
"}\n",
"\n",
"/* On hover, darken the color of the background */\n",
- "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+ "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"/* Label box, darken color on hover, fitted */\n",
- "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator label */\n",
"\n",
- "#sk-container-id-1 div.sk-label label {\n",
+ "#sk-container-id-2 div.sk-label label {\n",
" font-family: monospace;\n",
" font-weight: bold;\n",
" display: inline-block;\n",
" line-height: 1.2em;\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-label-container {\n",
+ "#sk-container-id-2 div.sk-label-container {\n",
" text-align: center;\n",
"}\n",
"\n",
"/* Estimator-specific */\n",
- "#sk-container-id-1 div.sk-estimator {\n",
+ "#sk-container-id-2 div.sk-estimator {\n",
" font-family: monospace;\n",
" border: 1px dotted var(--sklearn-color-border-box);\n",
" border-radius: 0.25em;\n",
@@ -540,18 +547,18 @@
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-estimator.fitted {\n",
+ "#sk-container-id-2 div.sk-estimator.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"/* on hover */\n",
- "#sk-container-id-1 div.sk-estimator:hover {\n",
+ "#sk-container-id-2 div.sk-estimator:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
- "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+ "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
@@ -638,7 +645,7 @@
"\n",
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
"\n",
- "#sk-container-id-1 a.estimator_doc_link {\n",
+ "#sk-container-id-2 a.estimator_doc_link {\n",
" float: right;\n",
" font-size: 1rem;\n",
" line-height: 1em;\n",
@@ -653,31 +660,31 @@
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
"}\n",
"\n",
- "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+ "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
" /* fitted */\n",
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-fitted-level-1);\n",
"}\n",
"\n",
"/* On hover */\n",
- "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+ "#sk-container-id-2 a.estimator_doc_link:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
- "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+ "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-3);\n",
"}\n",
- "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> LogisticRegression<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>LogisticRegression()</pre></div> </div></div></div></div>"
+ "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> LogisticRegression<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>LogisticRegression()</pre></div> </div></div></div></div>"
],
"text/plain": [
"LogisticRegression()"
]
},
- "execution_count": 9,
+ "execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
@@ -692,7 +699,7 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 42,
"metadata": {},
"outputs": [
{
@@ -701,7 +708,7 @@
"0.8881693648816936"
]
},
- "execution_count": 10,
+ "execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
@@ -712,6 +719,124 @@
"\n",
"accuracy_score(y_test,y_test_pred)"
]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 49,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Level of Supervision_Low Risk Probation -0.5339620957982494\n",
+ "Level of Supervision_Minimum -0.5147264201803158\n",
+ "Level of Supervision_Minimum Risk Program -0.44074785427274304\n",
+ "Convicting Offense Classification_Serious Misdemeanor -0.35849865449503004\n",
+ "Region Code_6JD -0.29377538041752616\n",
+ "Race - Ethnicity_Unknown -0.27944493177025126\n",
+ "Race - Ethnicity_Unknown - Non-Hispanic -0.2387566286558007\n",
+ "Convicting Offense Classification_Simple Misdemeanor -0.18613662623857888\n",
+ "Race - Ethnicity_Unk - NH -0.16798593793197264\n",
+ "Level of Supervision_Low Normal -0.16017010735222512\n",
+ "Convicting Offense Subtype_OWI -0.13559556625348412\n",
+ "Convicting Offense Subtype_Health/Medical -0.10074187085953795\n",
+ "Region Code_4JD -0.08036165789589228\n",
+ "Sex_Unknown -0.07636769248279494\n",
+ "Convicting Offense Type_Public Order -0.06674645656428356\n",
+ "Convicting Offense Subtype_Gambling -0.057086978034176485\n",
+ "Convicting Offense Subtype_Tax Laws -0.05657269492640917\n",
+ "Race - Ethnicity_A/PI - H -0.05553311522652603\n",
+ "Region Code_7JD -0.054376673533109036\n",
+ "Sex_Female -0.054225227388666336\n",
+ "Level of Supervision_nan -0.036915563071045106\n",
+ "Level of Supervision_Administrative -0.030359219733896957\n",
+ "Race - Ethnicity_Asian or Pacific Islander - Non-Hispanic -0.028799189656285896\n",
+ "Region Code_1JD -0.02615414378498509\n",
+ "Convicting Offense Subtype_Other Violent -0.024412840107090127\n",
+ "Convicting Offense Subtype_Trafficking -0.02108978164071303\n",
+ "Convicting Offense Subtype_Other Drug -0.018756200863952213\n",
+ "Convicting Offense Subtype_Animals -0.01822380470925885\n",
+ "Convicting Offense Subtype_Other Criminal -0.017046827026266573\n",
+ "Convicting Offense Subtype_Kidnap -0.016342620349334896\n",
+ "Region Code_3JD -0.01632764665874275\n",
+ "Convicting Offense Subtype_Business -0.016213443754824055\n",
+ "Race - Ethnicity_AI/AN - H -0.01547977017003544\n",
+ "Region Code_8JD -0.015345871062002029\n",
+ "Convicting Offense Subtype_Natural Resources -0.015169899630659534\n",
+ "Convicting Offense Classification_NCIC Virtual Code -0.011600908676106038\n",
+ "Convicting Offense Subtype_Vandalism -0.011287419364530349\n",
+ "Convicting Offense Subtype_Murder/Manslaughter -0.008866576866914002\n",
+ "Convicting Offense Subtype_Arson -0.005156165190029143\n",
+ "Convicting Offense Subtype_Sex -0.0018102182593264116\n",
+ "Convicting Offense Classification_nan -0.0005600927940130159\n",
+ "Convicting Offense Type_nan -0.0005600927939903566\n",
+ "Convicting Offense Subtype_nan -0.0005600927939903566\n",
+ "Convicting Offense Subtype_Stolen Property 0.0005304053063805491\n",
+ "Race - Ethnicity_White - Non-Hispanic 0.001153812183389463\n",
+ "Level of Supervision_Not Available for Supervision 0.001490247455119801\n",
+ "Convicting Offense Subtype_Prostitution/Pimping 0.0015013093121284365\n",
+ "Convicting Offense Type_Drug 0.0030623870110162584\n",
+ "Convicting Offense Type_Violent 0.0034292202922170233\n",
+ "Convicting Offense Type_Other 0.006015780723941681\n",
+ "Convicting Offense Subtype_Other Property 0.006130852235344804\n",
+ "Level of Supervision_Unknown 0.007781758222531563\n",
+ "Region Code_2JD 0.010238861163768128\n",
+ "Convicting Offense Classification_Other Misdemeanor 0.012591486492788916\n",
+ "Convicting Offense Subtype_Robbery 0.014053669830263436\n",
+ "Convicting Offense Classification_Special Sentence 2005 0.014561589545323982\n",
+ "Race - Ethnicity_Asian or Pacific Islander - Hispanic 0.015679057334770714\n",
+ "Race - Ethnicity_American Indian or Alaska Native - Hispanic 0.01773867652759473\n",
+ "Race - Ethnicity_Black - Hispanic 0.01798930728110183\n",
+ "Race - Ethnicity_A/PI - NH 0.018819321480771305\n",
+ "Race - Ethnicity_AI/AN - NH 0.020800565434265\n",
+ "Region Code_5JD 0.020852413776690646\n",
+ "Race - Ethnicity_White - Hispanic 0.02327628518150384\n",
+ "Convicting Offense Subtype_Drug Possession 0.027225124801652227\n",
+ "Convicting Offense Subtype_Other Government 0.028715642473623113\n",
+ "Convicting Offense Subtype_Assault 0.029569856997337447\n",
+ "Convicting Offense Subtype_Flight/Escape 0.03012428515800137\n",
+ "Convicting Offense Subtype_Traffic 0.03430715996827982\n",
+ "Convicting Offense Subtype_Weapons 0.03527466491386668\n",
+ "Convicting Offense Subtype_Forgery/Fraud 0.036233812269670415\n",
+ "Convicting Offense Classification_B Felony 0.03792206013687437\n",
+ "Race - Ethnicity_American Indian or Alaska Native - Non-Hispanic 0.03923757766380635\n",
+ "Convicting Offense Subtype_Burglary 0.045489691213388105\n",
+ "Convicting Offense Subtype_Theft 0.047935190983844966\n",
+ "Sex_Male 0.05874268187558015\n",
+ "Convicting Offense Type_Property 0.07168268636948888\n",
+ "Race - Ethnicity_Black - Non-Hispanic 0.07207116769606338\n",
+ "Convicting Offense Subtype_Alcohol 0.07341854193314533\n",
+ "Convicting Offense Subtype_Other Public Order 0.08202232001715717\n",
+ "Convicting Offense Classification_Felony - Enhancement to Original Penalty 0.08742027870862958\n",
+ "Recidivism Reporting Year 0.12049374422377804\n",
+ "Fiscal Year Admitted 0.12049374422377804\n",
+ "Convicting Offense Classification_Aggravated Misdemeanor 0.13924900491864936\n",
+ "Convicting Offense Classification_C Felony 0.1917830084037748\n",
+ "Convicting Offense Classification_D Felony 0.24811340746039828\n",
+ "Level of Supervision_High Normal 0.2692817282284991\n",
+ "Region Code_nan 0.33019477985094964\n",
+ "Level of Supervision_Intensive 0.9152562744591675\n"
+ ]
+ }
+ ],
+ "source": [
+ "from collections import OrderedDict\n",
+ "# Print coefficients and corresponding feature names\n",
+ "\n",
+ "coeff = logReg.coef_\n",
+ "names = std.feature_names_in_\n",
+ "\n",
+ "\n",
+ "combos = {}\n",
+ "for i in range(0, len(names)):\n",
+ " combos[names[i]] = coeff[0][i]\n",
+ "\n",
+ "sorted_dict : OrderedDict = OrderedDict(sorted(combos.items(), key=lambda item: item[1]))\n",
+ "\n",
+ "for i in sorted_dict:\n",
+ " print(i , \" \" , sorted_dict[i])"
+ ]
}
],
"metadata": {
diff --git a/recidivism/RecidivismNN.ipynb b/recidivism/RecidivismNN.ipynb
@@ -1,6 +1,13 @@
{
"cells": [
{
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "https://www.kaggle.com/datasets/slonnadube/recidivism"
+ ]
+ },
+ {
"cell_type": "code",
"execution_count": 51,
"metadata": {},
diff --git a/studentPerformance/StudentPerformance.ipynb b/studentPerformance/StudentPerformance.ipynb
@@ -0,0 +1,1671 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "https://www.kaggle.com/datasets/rabieelkharoua/students-performance-dataset/data\n",
+ "\n",
+ "MAPE (Average Percent Error)\n",
+ "\n",
+ "SVM:\n",
+ "\n",
+ "18.431351756224238%\n",
+ "\n",
+ "Linear Regression:\n",
+ "\n",
+ "6.027964205816556%\n",
+ "\n",
+ "Random Forest:\n",
+ "\n",
+ "18.610917749737553%\n",
+ "___\n",
+ "\n",
+ "6% error seems sufficient using the Random Forest Model. This is however destroyed by a deep neural network which achieved 3.5% MAPE"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 120,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "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>StudentID</th>\n",
+ " <th>Age</th>\n",
+ " <th>Gender</th>\n",
+ " <th>Ethnicity</th>\n",
+ " <th>ParentalEducation</th>\n",
+ " <th>StudyTimeWeekly</th>\n",
+ " <th>Absences</th>\n",
+ " <th>Tutoring</th>\n",
+ " <th>ParentalSupport</th>\n",
+ " <th>Extracurricular</th>\n",
+ " <th>Sports</th>\n",
+ " <th>Music</th>\n",
+ " <th>Volunteering</th>\n",
+ " <th>GPA</th>\n",
+ " <th>GradeClass</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1001</td>\n",
+ " <td>17</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>19.833723</td>\n",
+ " <td>7</td>\n",
+ " <td>1</td>\n",
+ " <td>2</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>2.929196</td>\n",
+ " <td>2.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " StudentID Age Gender Ethnicity ParentalEducation StudyTimeWeekly \\\n",
+ "0 1001 17 1 0 2 19.833723 \n",
+ "\n",
+ " Absences Tutoring ParentalSupport Extracurricular Sports Music \\\n",
+ "0 7 1 2 0 0 1 \n",
+ "\n",
+ " Volunteering GPA GradeClass \n",
+ "0 0 2.929196 2.0 "
+ ]
+ },
+ "execution_count": 120,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import pandas as pd\n",
+ "\n",
+ "df = pd.read_csv('../datasets/studentPerformance/StudentPerformance.csv')\n",
+ "\n",
+ "df.head(1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 121,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "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>Age</th>\n",
+ " <th>Gender</th>\n",
+ " <th>Ethnicity</th>\n",
+ " <th>ParentalEducation</th>\n",
+ " <th>StudyTimeWeekly</th>\n",
+ " <th>Absences</th>\n",
+ " <th>Tutoring</th>\n",
+ " <th>ParentalSupport</th>\n",
+ " <th>Extracurricular</th>\n",
+ " <th>Sports</th>\n",
+ " <th>Music</th>\n",
+ " <th>Volunteering</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>17</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>19.833723</td>\n",
+ " <td>7</td>\n",
+ " <td>1</td>\n",
+ " <td>2</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Age Gender Ethnicity ParentalEducation StudyTimeWeekly Absences \\\n",
+ "0 17 1 0 2 19.833723 7 \n",
+ "\n",
+ " Tutoring ParentalSupport Extracurricular Sports Music Volunteering \n",
+ "0 1 2 0 0 1 0 "
+ ]
+ },
+ "execution_count": 121,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "X = df.drop(columns=['GPA', 'GradeClass', 'StudentID'], axis=1)\n",
+ "y = df['GradeClass']\n",
+ "\n",
+ "X.head(1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 122,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from sklearn.preprocessing import StandardScaler\n",
+ "\n",
+ "sclr = StandardScaler()\n",
+ "X = sclr.fit_transform(X)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 123,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from sklearn.model_selection import train_test_split\n",
+ "\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X,y)\n",
+ "X_val, X_test, y_val, y_test = train_test_split(X_train,y_train, test_size=.5)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 124,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-47 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: black;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-47 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-47 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-47 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-47 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: block;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-47 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-47 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-47 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-47 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-47 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-47 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-47 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-47 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-47 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 1ex;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-47 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-47 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-47 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-47\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LinearRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-47\" type=\"checkbox\" checked><label for=\"sk-estimator-id-47\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> LinearRegression<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.linear_model.LinearRegression.html\">?<span>Documentation for LinearRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>LinearRegression()</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "LinearRegression()"
+ ]
+ },
+ "execution_count": 124,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "from sklearn.linear_model import LinearRegression\n",
+ "\n",
+ "lin_reg = LinearRegression()\n",
+ "\n",
+ "lin_reg.fit(X_train,y_train)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 125,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0.5898980915568777"
+ ]
+ },
+ "execution_count": 125,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "from sklearn.metrics import mean_absolute_error, mean_absolute_percentage_error\n",
+ "\n",
+ "y_pred = lin_reg.predict(X_test)\n",
+ "mean_absolute_error(y_pred=y_pred, y_true=y_test)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 126,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-48 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: black;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-48 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-48 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-48 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-48 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: block;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-48 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-48 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-48 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-48 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-48 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-48 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-48 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-48 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-48 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 1ex;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-48 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-48 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-48 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-48\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestRegressor(max_depth=30)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-48\" type=\"checkbox\" checked><label for=\"sk-estimator-id-48\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> RandomForestRegressor<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.ensemble.RandomForestRegressor.html\">?<span>Documentation for RandomForestRegressor</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestRegressor(max_depth=30)</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "RandomForestRegressor(max_depth=30)"
+ ]
+ },
+ "execution_count": 126,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "from sklearn.ensemble import RandomForestRegressor\n",
+ "\n",
+ "rnd_reg = RandomForestRegressor(max_depth=30, n_estimators=100)\n",
+ "\n",
+ "rnd_reg.fit(X_train,y_train)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 127,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0.18502787068004456"
+ ]
+ },
+ "execution_count": 127,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "y_pred = rnd_reg.predict(X_test)\n",
+ "mean_absolute_error(y_pred=y_pred, y_true=y_test)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 128,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-49 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: black;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-49 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-49 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-49 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-49 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: block;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-49 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-49 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-49 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-49 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-49 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-49 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-49 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-49 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-49 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 1ex;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-49 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-49 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-49 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-49\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LinearSVR(max_iter=1000000)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-49\" type=\"checkbox\" checked><label for=\"sk-estimator-id-49\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> LinearSVR<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.svm.LinearSVR.html\">?<span>Documentation for LinearSVR</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>LinearSVR(max_iter=1000000)</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "LinearSVR(max_iter=1000000)"
+ ]
+ },
+ "execution_count": 128,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "from sklearn.svm import LinearSVR\n",
+ "\n",
+ "svr = LinearSVR(max_iter=1000000)\n",
+ "\n",
+ "svr.fit(X_train,y_train)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 139,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0.5856977527312485"
+ ]
+ },
+ "execution_count": 139,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "y_pred = svr.predict(X_test)\n",
+ "mean_absolute_error(y_pred=y_pred, y_true=y_test)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Let's Check Out Each of These Models (My Bet's On The Random Forest)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 143,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "18.431351756224238"
+ ]
+ },
+ "execution_count": 143,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "y_pred = svr.predict(X_val)\n",
+ "mean_absolute_error(y_pred=y_pred, y_true=y_val) / y_val.mean() * 100"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 144,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "6.027964205816556"
+ ]
+ },
+ "execution_count": 144,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "y_pred = rnd_reg.predict(X_val)\n",
+ "mean_absolute_error(y_pred=y_pred, y_true=y_val) / y_val.mean() * 100"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 145,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "18.610917749737553"
+ ]
+ },
+ "execution_count": 145,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "y_pred = lin_reg.predict(X_val)\n",
+ "mean_absolute_error(y_pred=y_pred, y_true=y_val) / y_val.mean() * 100"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": ".venv",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.11.2"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/studentPerformance/StudentPerformanceNN.ipynb b/studentPerformance/StudentPerformanceNN.ipynb
@@ -0,0 +1,387 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "https://www.kaggle.com/datasets/rabieelkharoua/students-performance-dataset/data\n",
+ "\n",
+ "MAE:\n",
+ "\n",
+ "0.10496861395429209\n",
+ "\n",
+ "3.5% MAPE"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 51,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(1794, 12)"
+ ]
+ },
+ "execution_count": 51,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import pandas as pd\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.preprocessing import StandardScaler\n",
+ "\n",
+ "df = pd.read_csv('../datasets/studentPerformance/StudentPerformance.csv')\n",
+ "X = df.drop(columns=['GPA', 'GradeClass', 'StudentID'], axis=1)\n",
+ "y = df['GradeClass']\n",
+ "sclr = StandardScaler()\n",
+ "X = sclr.fit_transform(X)\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X,y)\n",
+ "X_val, X_test, y_val, y_test = train_test_split(X_train,y_train, test_size=.5)\n",
+ "\n",
+ "X_train.shape"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 52,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import keras\n",
+ "import tensorflow as tf\n",
+ "\n",
+ "model = keras.Sequential(layers=[\n",
+ "\n",
+ " keras.layers.Input(shape=(12,)),\n",
+ " keras.layers.Dense(256, activation='relu'),\n",
+ " keras.layers.Dropout(.1),\n",
+ " keras.layers.Dense(256, activation='relu'),\n",
+ " keras.layers.Dropout(.1),\n",
+ " keras.layers.Dense(256, activation='relu'),\n",
+ " keras.layers.Dropout(.1),\n",
+ " keras.layers.Dense(256, activation='relu'),\n",
+ " keras.layers.Dense(1)\n",
+ "])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 53,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Epoch 1/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 5ms/step - loss: 2.9243 - mae: 1.3415 - val_loss: 0.7946 - val_mae: 0.6464\n",
+ "Epoch 2/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.7969 - mae: 0.6824 - val_loss: 0.6778 - val_mae: 0.6281\n",
+ "Epoch 3/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6274 - mae: 0.5849 - val_loss: 0.6190 - val_mae: 0.6068\n",
+ "Epoch 4/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.5872 - mae: 0.5563 - val_loss: 0.4950 - val_mae: 0.4443\n",
+ "Epoch 5/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.5568 - mae: 0.5244 - val_loss: 0.4614 - val_mae: 0.4691\n",
+ "Epoch 6/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.5457 - mae: 0.5076 - val_loss: 0.4437 - val_mae: 0.4255\n",
+ "Epoch 7/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.5544 - mae: 0.5246 - val_loss: 0.4566 - val_mae: 0.4545\n",
+ "Epoch 8/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - loss: 0.4496 - mae: 0.4792 - val_loss: 0.3990 - val_mae: 0.4142\n",
+ "Epoch 9/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.4472 - mae: 0.4745 - val_loss: 0.3991 - val_mae: 0.4445\n",
+ "Epoch 10/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.4941 - mae: 0.4969 - val_loss: 0.4244 - val_mae: 0.4763\n",
+ "Epoch 11/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.4168 - mae: 0.4510 - val_loss: 0.4499 - val_mae: 0.4338\n",
+ "Epoch 12/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.4840 - mae: 0.4939 - val_loss: 0.3797 - val_mae: 0.4034\n",
+ "Epoch 13/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.4371 - mae: 0.4686 - val_loss: 0.3647 - val_mae: 0.3907\n",
+ "Epoch 14/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.4781 - mae: 0.4995 - val_loss: 0.4937 - val_mae: 0.5747\n",
+ "Epoch 15/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.4719 - mae: 0.4944 - val_loss: 0.3294 - val_mae: 0.3549\n",
+ "Epoch 16/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.3997 - mae: 0.4483 - val_loss: 0.3152 - val_mae: 0.3549\n",
+ "Epoch 17/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.4213 - mae: 0.4487 - val_loss: 0.3297 - val_mae: 0.4052\n",
+ "Epoch 18/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.3893 - mae: 0.4380 - val_loss: 0.3285 - val_mae: 0.4176\n",
+ "Epoch 19/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.3952 - mae: 0.4418 - val_loss: 0.3014 - val_mae: 0.3542\n",
+ "Epoch 20/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.3588 - mae: 0.4229 - val_loss: 0.3074 - val_mae: 0.3983\n",
+ "Epoch 21/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - loss: 0.3325 - mae: 0.4002 - val_loss: 0.2826 - val_mae: 0.3712\n",
+ "Epoch 22/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.3545 - mae: 0.4104 - val_loss: 0.2708 - val_mae: 0.3508\n",
+ "Epoch 23/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.3169 - mae: 0.3996 - val_loss: 0.2538 - val_mae: 0.3331\n",
+ "Epoch 24/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.3375 - mae: 0.4106 - val_loss: 0.3023 - val_mae: 0.4265\n",
+ "Epoch 25/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - loss: 0.2909 - mae: 0.3760 - val_loss: 0.2453 - val_mae: 0.3518\n",
+ "Epoch 26/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - loss: 0.3147 - mae: 0.3939 - val_loss: 0.2206 - val_mae: 0.3004\n",
+ "Epoch 27/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2455 - mae: 0.3495 - val_loss: 0.4073 - val_mae: 0.5486\n",
+ "Epoch 28/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.3003 - mae: 0.4157 - val_loss: 0.2155 - val_mae: 0.3147\n",
+ "Epoch 29/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2819 - mae: 0.3813 - val_loss: 0.2175 - val_mae: 0.3168\n",
+ "Epoch 30/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2887 - mae: 0.3885 - val_loss: 0.2135 - val_mae: 0.3201\n",
+ "Epoch 31/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2825 - mae: 0.3714 - val_loss: 0.1951 - val_mae: 0.2933\n",
+ "Epoch 32/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2718 - mae: 0.3738 - val_loss: 0.2076 - val_mae: 0.3302\n",
+ "Epoch 33/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2659 - mae: 0.3757 - val_loss: 0.1839 - val_mae: 0.3012\n",
+ "Epoch 34/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2200 - mae: 0.3312 - val_loss: 0.1660 - val_mae: 0.2752\n",
+ "Epoch 35/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2170 - mae: 0.3346 - val_loss: 0.1693 - val_mae: 0.2718\n",
+ "Epoch 36/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2241 - mae: 0.3506 - val_loss: 0.1500 - val_mae: 0.2731\n",
+ "Epoch 37/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1994 - mae: 0.3174 - val_loss: 0.1448 - val_mae: 0.2549\n",
+ "Epoch 38/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2183 - mae: 0.3237 - val_loss: 0.1595 - val_mae: 0.2743\n",
+ "Epoch 39/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2041 - mae: 0.3234 - val_loss: 0.1782 - val_mae: 0.3303\n",
+ "Epoch 40/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2374 - mae: 0.3542 - val_loss: 0.1570 - val_mae: 0.2853\n",
+ "Epoch 41/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1880 - mae: 0.3193 - val_loss: 0.1136 - val_mae: 0.2300\n",
+ "Epoch 42/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1670 - mae: 0.2956 - val_loss: 0.1222 - val_mae: 0.2595\n",
+ "Epoch 43/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2178 - mae: 0.3238 - val_loss: 0.1602 - val_mae: 0.2842\n",
+ "Epoch 44/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1981 - mae: 0.3220 - val_loss: 0.1752 - val_mae: 0.3231\n",
+ "Epoch 45/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.2190 - mae: 0.3447 - val_loss: 0.1033 - val_mae: 0.2224\n",
+ "Epoch 46/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1589 - mae: 0.2896 - val_loss: 0.0976 - val_mae: 0.2108\n",
+ "Epoch 47/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1519 - mae: 0.2855 - val_loss: 0.0830 - val_mae: 0.1973\n",
+ "Epoch 48/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1612 - mae: 0.2926 - val_loss: 0.1134 - val_mae: 0.2580\n",
+ "Epoch 49/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1532 - mae: 0.2821 - val_loss: 0.0859 - val_mae: 0.2061\n",
+ "Epoch 50/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1620 - mae: 0.2898 - val_loss: 0.1085 - val_mae: 0.2440\n",
+ "Epoch 51/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1482 - mae: 0.2890 - val_loss: 0.0829 - val_mae: 0.2060\n",
+ "Epoch 52/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1384 - mae: 0.2624 - val_loss: 0.0862 - val_mae: 0.2048\n",
+ "Epoch 53/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - loss: 0.1698 - mae: 0.2971 - val_loss: 0.1102 - val_mae: 0.2372\n",
+ "Epoch 54/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1452 - mae: 0.2742 - val_loss: 0.0799 - val_mae: 0.2044\n",
+ "Epoch 55/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1291 - mae: 0.2642 - val_loss: 0.0784 - val_mae: 0.2106\n",
+ "Epoch 56/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1115 - mae: 0.2429 - val_loss: 0.0709 - val_mae: 0.1973\n",
+ "Epoch 57/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1301 - mae: 0.2654 - val_loss: 0.0734 - val_mae: 0.2040\n",
+ "Epoch 58/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1104 - mae: 0.2438 - val_loss: 0.0709 - val_mae: 0.2018\n",
+ "Epoch 59/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1043 - mae: 0.2390 - val_loss: 0.1021 - val_mae: 0.2712\n",
+ "Epoch 60/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1094 - mae: 0.2521 - val_loss: 0.0577 - val_mae: 0.1695\n",
+ "Epoch 61/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1382 - mae: 0.2671 - val_loss: 0.0514 - val_mae: 0.1597\n",
+ "Epoch 62/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1001 - mae: 0.2352 - val_loss: 0.0511 - val_mae: 0.1575\n",
+ "Epoch 63/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1007 - mae: 0.2296 - val_loss: 0.0517 - val_mae: 0.1556\n",
+ "Epoch 64/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1007 - mae: 0.2289 - val_loss: 0.0489 - val_mae: 0.1612\n",
+ "Epoch 65/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0935 - mae: 0.2201 - val_loss: 0.0707 - val_mae: 0.1960\n",
+ "Epoch 66/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1339 - mae: 0.2470 - val_loss: 0.0883 - val_mae: 0.2245\n",
+ "Epoch 67/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1343 - mae: 0.2542 - val_loss: 0.0594 - val_mae: 0.1778\n",
+ "Epoch 68/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - loss: 0.1072 - mae: 0.2423 - val_loss: 0.0512 - val_mae: 0.1513\n",
+ "Epoch 69/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - loss: 0.1180 - mae: 0.2368 - val_loss: 0.0663 - val_mae: 0.1832\n",
+ "Epoch 70/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0984 - mae: 0.2299 - val_loss: 0.0417 - val_mae: 0.1391\n",
+ "Epoch 71/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0837 - mae: 0.2177 - val_loss: 0.0346 - val_mae: 0.1242\n",
+ "Epoch 72/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0960 - mae: 0.2116 - val_loss: 0.0540 - val_mae: 0.1525\n",
+ "Epoch 73/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0995 - mae: 0.2215 - val_loss: 0.0543 - val_mae: 0.1666\n",
+ "Epoch 74/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1190 - mae: 0.2285 - val_loss: 0.0403 - val_mae: 0.1366\n",
+ "Epoch 75/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0802 - mae: 0.2053 - val_loss: 0.0432 - val_mae: 0.1350\n",
+ "Epoch 76/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0952 - mae: 0.2193 - val_loss: 0.0439 - val_mae: 0.1392\n",
+ "Epoch 77/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1020 - mae: 0.2256 - val_loss: 0.0387 - val_mae: 0.1320\n",
+ "Epoch 78/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0946 - mae: 0.2127 - val_loss: 0.0648 - val_mae: 0.2079\n",
+ "Epoch 79/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0882 - mae: 0.2201 - val_loss: 0.0460 - val_mae: 0.1463\n",
+ "Epoch 80/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1007 - mae: 0.2220 - val_loss: 0.0440 - val_mae: 0.1515\n",
+ "Epoch 81/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.1145 - mae: 0.2329 - val_loss: 0.0507 - val_mae: 0.1608\n",
+ "Epoch 82/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0999 - mae: 0.2143 - val_loss: 0.0429 - val_mae: 0.1396\n",
+ "Epoch 83/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0860 - mae: 0.2129 - val_loss: 0.0424 - val_mae: 0.1305\n",
+ "Epoch 84/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0933 - mae: 0.2084 - val_loss: 0.0455 - val_mae: 0.1348\n",
+ "Epoch 85/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0860 - mae: 0.2102 - val_loss: 0.0403 - val_mae: 0.1489\n",
+ "Epoch 86/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0746 - mae: 0.1942 - val_loss: 0.0390 - val_mae: 0.1293\n",
+ "Epoch 87/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0756 - mae: 0.1961 - val_loss: 0.0345 - val_mae: 0.1207\n",
+ "Epoch 88/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0724 - mae: 0.1843 - val_loss: 0.0352 - val_mae: 0.1299\n",
+ "Epoch 89/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0866 - mae: 0.1971 - val_loss: 0.0398 - val_mae: 0.1482\n",
+ "Epoch 90/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0777 - mae: 0.1965 - val_loss: 0.0336 - val_mae: 0.1218\n",
+ "Epoch 91/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - loss: 0.0859 - mae: 0.2065 - val_loss: 0.0318 - val_mae: 0.1220\n",
+ "Epoch 92/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - loss: 0.0538 - mae: 0.1644 - val_loss: 0.0318 - val_mae: 0.1289\n",
+ "Epoch 93/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0655 - mae: 0.1806 - val_loss: 0.0357 - val_mae: 0.1242\n",
+ "Epoch 94/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0698 - mae: 0.1770 - val_loss: 0.0311 - val_mae: 0.1224\n",
+ "Epoch 95/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0716 - mae: 0.1887 - val_loss: 0.0315 - val_mae: 0.1187\n",
+ "Epoch 96/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0782 - mae: 0.1907 - val_loss: 0.0349 - val_mae: 0.1142\n",
+ "Epoch 97/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0609 - mae: 0.1673 - val_loss: 0.0417 - val_mae: 0.1586\n",
+ "Epoch 98/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - loss: 0.0655 - mae: 0.1834 - val_loss: 0.0480 - val_mae: 0.1177\n",
+ "Epoch 99/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0569 - mae: 0.1673 - val_loss: 0.0425 - val_mae: 0.1254\n",
+ "Epoch 100/100\n",
+ "\u001b[1m57/57\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.0719 - mae: 0.1797 - val_loss: 0.0276 - val_mae: 0.1050\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "<keras.src.callbacks.history.History at 0x7efb79f8c990>"
+ ]
+ },
+ "execution_count": 53,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "model.compile(optimizer='adam', loss='mse', metrics=['mae'])\n",
+ "model.fit(X_train,y_train, validation_data=[X_test,y_test], epochs=100, batch_size=32)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 83,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[1m29/29\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 1ms/step \n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "3.4900187146428183"
+ ]
+ },
+ "execution_count": 83,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "from sklearn.metrics import mean_absolute_error\n",
+ "\n",
+ "y_pred = model.predict(X_val)\n",
+ "mean_absolute_error(y_pred=y_pred, y_true=y_val) / y_val.mean() * 100"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 76,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[1m29/29\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 1ms/step \n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "0.1043893000154591"
+ ]
+ },
+ "execution_count": 76,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "y_pred = model.predict(X_val)\n",
+ "mean_absolute_error(y_pred=y_pred, y_true=y_val)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "This kills the others models.\n",
+ "\n",
+ "This only had an average error of 3.5%"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": ".venv",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.11.2"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
