{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import sklearn as sk\n",
"import matplotlib.pyplot as plt\n",
"import json\n",
"import math\n",
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 1. Read Dataset and remove NAN values"
]
},
{
"cell_type": "code",
"execution_count": 3,
"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>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.23</td>\n",
" <td>Ideal</td>\n",
" <td>E</td>\n",
" <td>SI2</td>\n",
" <td>61.5</td>\n",
" <td>55.0</td>\n",
" <td>326</td>\n",
" <td>3.95</td>\n",
" <td>3.98</td>\n",
" <td>2.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.21</td>\n",
" <td>Premium</td>\n",
" <td>E</td>\n",
" <td>SI1</td>\n",
" <td>59.8</td>\n",
" <td>61.0</td>\n",
" <td>326</td>\n",
" <td>3.89</td>\n",
" <td>3.84</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.23</td>\n",
" <td>Good</td>\n",
" <td>E</td>\n",
" <td>VS1</td>\n",
" <td>56.9</td>\n",
" <td>65.0</td>\n",
" <td>327</td>\n",
" <td>4.05</td>\n",
" <td>4.07</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.29</td>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>VS2</td>\n",
" <td>62.4</td>\n",
" <td>58.0</td>\n",
" <td>334</td>\n",
" <td>4.20</td>\n",
" <td>4.23</td>\n",
" <td>2.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.31</td>\n",
" <td>Good</td>\n",
" <td>J</td>\n",
" <td>SI2</td>\n",
" <td>63.3</td>\n",
" <td>58.0</td>\n",
" <td>335</td>\n",
" <td>4.34</td>\n",
" <td>4.35</td>\n",
" <td>2.75</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" carat cut color clarity depth table price x y z\n",
"0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43\n",
"1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31\n",
"2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31\n",
"3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63\n",
"4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds = pd.read_csv('diamonds.csv')\n",
"\n",
"diamonds.dropna(inplace=True)\n",
"diamonds.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 2. Mapping non-numerical values to numerical ones"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Cut Quality**\n",
"| Cut | Mapping |\n",
"|------------|------|\n",
"| Ideal | 0 |\n",
"| Premium | 1 |\n",
"| Good | 2 |\n",
"| Very Good | 3 |\n",
"| Fair | 4 |\n",
"\n",
"**Color Grade**\n",
"| Color | Mapping |\n",
"|-------|------|\n",
"| E | 0 |\n",
"| I | 1 |\n",
"| J | 2 |\n",
"| H | 3 |\n",
"| F | 4 |\n",
"| G | 5 |\n",
"| D | 6 |\n",
"\n",
"**Clarity Grade**\n",
"| Clarity | Mapping |\n",
"|---------|------|\n",
"| SI2 | 0 |\n",
"| SI1 | 1 |\n",
"| VS1 | 2 |\n",
"| VS2 | 3 |\n",
"| VVS2 | 4 |\n",
"| VVS1 | 5 |\n",
"| I1 | 6 |\n",
"| IF | 7 |"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"cut_mapping = {cut: i for i, cut in enumerate(diamonds['cut'].unique())}\n",
"color_mapping = {color: i for i, color in enumerate(diamonds['color'].unique())}\n",
"clarity_mapping = {clarity: i for i, clarity in enumerate(diamonds['clarity'].unique())}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 3. Replace the non-numerical columns with their numerical mappings"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"diamonds_numerical = diamonds.copy()\n",
"diamonds_numerical['cut'] = diamonds['cut'].map(cut_mapping)\n",
"diamonds_numerical['color'] = diamonds['color'].map(color_mapping)\n",
"diamonds_numerical['clarity'] = diamonds['clarity'].map(clarity_mapping)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"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>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.23</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>61.5</td>\n",
" <td>55.0</td>\n",
" <td>326</td>\n",
" <td>3.95</td>\n",
" <td>3.98</td>\n",
" <td>2.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.21</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>59.8</td>\n",
" <td>61.0</td>\n",
" <td>326</td>\n",
" <td>3.89</td>\n",
" <td>3.84</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.23</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>56.9</td>\n",
" <td>65.0</td>\n",
" <td>327</td>\n",
" <td>4.05</td>\n",
" <td>4.07</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.29</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>62.4</td>\n",
" <td>58.0</td>\n",
" <td>334</td>\n",
" <td>4.20</td>\n",
" <td>4.23</td>\n",
" <td>2.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.31</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>63.3</td>\n",
" <td>58.0</td>\n",
" <td>335</td>\n",
" <td>4.34</td>\n",
" <td>4.35</td>\n",
" <td>2.75</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" carat cut color clarity depth table price x y z\n",
"0 0.23 0 0 0 61.5 55.0 326 3.95 3.98 2.43\n",
"1 0.21 1 0 1 59.8 61.0 326 3.89 3.84 2.31\n",
"2 0.23 2 0 2 56.9 65.0 327 4.05 4.07 2.31\n",
"3 0.29 1 1 3 62.4 58.0 334 4.20 4.23 2.63\n",
"4 0.31 2 2 0 63.3 58.0 335 4.34 4.35 2.75"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds_numerical.head()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"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>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.23</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>61.5</td>\n",
" <td>55.0</td>\n",
" <td>3.95</td>\n",
" <td>3.98</td>\n",
" <td>2.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.21</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>59.8</td>\n",
" <td>61.0</td>\n",
" <td>3.89</td>\n",
" <td>3.84</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.23</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>56.9</td>\n",
" <td>65.0</td>\n",
" <td>4.05</td>\n",
" <td>4.07</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.29</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>62.4</td>\n",
" <td>58.0</td>\n",
" <td>4.20</td>\n",
" <td>4.23</td>\n",
" <td>2.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.31</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>63.3</td>\n",
" <td>58.0</td>\n",
" <td>4.34</td>\n",
" <td>4.35</td>\n",
" <td>2.75</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" carat cut color clarity depth table x y z\n",
"0 0.23 0 0 0 61.5 55.0 3.95 3.98 2.43\n",
"1 0.21 1 0 1 59.8 61.0 3.89 3.84 2.31\n",
"2 0.23 2 0 2 56.9 65.0 4.05 4.07 2.31\n",
"3 0.29 1 1 3 62.4 58.0 4.20 4.23 2.63\n",
"4 0.31 2 2 0 63.3 58.0 4.34 4.35 2.75"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X = diamonds_numerical.drop('price', axis = 1)\n",
"y = diamonds_numerical['price']\n",
"X.head()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 326\n",
"1 326\n",
"2 327\n",
"3 334\n",
"4 335\n",
"Name: price, dtype: int64"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"y.head()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" 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 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 sk-toggleable__label-arrow\">LinearRegression</label><div class=\"sk-toggleable__content\"><pre>LinearRegression()</pre></div></div></div></div></div>"
],
"text/plain": [
"LinearRegression()"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.linear_model import LinearRegression\n",
"model = LinearRegression()\n",
"# Train the models\n",
"model.fit(X_train, y_train)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Mean Squared Error: 2029299.0804379764\n",
"R^2 Score: 0.8723456077895886\n"
]
}
],
"source": [
"from sklearn.metrics import mean_squared_error, r2_score\n",
"\n",
"y_pred = model.predict(X_test)\n",
"mse = mean_squared_error(y_test, y_pred)\n",
"r2 = r2_score(y_test, y_pred)\n",
"print(\"Mean Squared Error:\", mse)\n",
"print(\"R^2 Score:\", r2)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style>#sk-container-id-2 {color: black;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
" enable_categorical=False, eval_metric=None, feature_types=None,\n",
" gamma=None, grow_policy=None, importance_type=None,\n",
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=None, max_leaves=None,\n",
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
" multi_strategy=None, n_estimators=100, n_jobs=None,\n",
" num_parallel_tree=None, random_state=42, ...)</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 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 sk-toggleable__label-arrow\">XGBRegressor</label><div class=\"sk-toggleable__content\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
" enable_categorical=False, eval_metric=None, feature_types=None,\n",
" gamma=None, grow_policy=None, importance_type=None,\n",
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=None, max_leaves=None,\n",
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
" multi_strategy=None, n_estimators=100, n_jobs=None,\n",
" num_parallel_tree=None, random_state=42, ...)</pre></div></div></div></div></div>"
],
"text/plain": [
"XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
" enable_categorical=False, eval_metric=None, feature_types=None,\n",
" gamma=None, grow_policy=None, importance_type=None,\n",
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=None, max_leaves=None,\n",
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
" multi_strategy=None, n_estimators=100, n_jobs=None,\n",
" num_parallel_tree=None, random_state=42, ...)"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from xgboost import XGBRegressor\n",
"model2 = XGBRegressor(n_estimators=100,random_state=42)\n",
"model2.fit(X_train, y_train)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Mean Squared Error: 314752.8223018785\n",
"R^2 Score: 0.9802002668730396\n"
]
}
],
"source": [
"y_pred2 = model2.predict(X_test)\n",
"mse2 = mean_squared_error(y_test, y_pred2)\n",
"r22 = r2_score(y_test, y_pred2)\n",
"print(\"Mean Squared Error:\", mse2)\n",
"print(\"R^2 Score:\", r22)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/fadi/Desktop/dev/sas2/ws-23-sas-02/sas2/lib/python3.10/site-packages/sklearn/neural_network/_multilayer_perceptron.py:691: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
" warnings.warn(\n"
]
},
{
"data": {
"text/html": [
"<style>#sk-container-id-3 {color: black;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MLPRegressor(max_iter=500, random_state=42)</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 sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MLPRegressor</label><div class=\"sk-toggleable__content\"><pre>MLPRegressor(max_iter=500, random_state=42)</pre></div></div></div></div></div>"
],
"text/plain": [
"MLPRegressor(max_iter=500, random_state=42)"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.neural_network import MLPRegressor\n",
"model4 = MLPRegressor(random_state=42, max_iter=500)\n",
"model4.fit(X_train, y_train)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Mean Squared Error: 2029299.0804379764\n",
"MSE 2 314752.8223018785\n",
"MSE 4 1320105.4212450413\n",
"R^2 Score: 0.8723456077895886\n",
"R^2 Score: 0.9802002668730396\n",
"R^2 Score: 0.9169579009682819\n"
]
}
],
"source": [
"from sklearn.metrics import mean_squared_error, r2_score\n",
"\n",
"# Predict on the test set\n",
"y_pred = model.predict(X_test)\n",
"y_pred2 = model2.predict(X_test)\n",
"y_pred4 = model4.predict(X_test)\n",
"# Evaluate the model\n",
"mse = mean_squared_error(y_test, y_pred)\n",
"mse2 = mean_squared_error(y_test, y_pred2)\n",
"mse4 = mean_squared_error(y_test, y_pred4)\n",
"r2 = r2_score(y_test, y_pred)\n",
"r22 = r2_score(y_test, y_pred2)\n",
"r24 = r2_score(y_test, y_pred4)\n",
"print(\"Mean Squared Error:\", mse)\n",
"print(\"MSE 2 \", mse2)\n",
"print(\"MSE 4 \", mse4)\n",
"print(\"R^2 Score:\", r2)\n",
"print(\"R^2 Score:\", r22)\n",
"print(\"R^2 Score:\", r24)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([3461.6711], dtype=float32)"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test_diamond = [[\n",
" 1.00,\n",
" 2,\n",
" 1,\n",
" 1,\n",
" 60.4,\n",
" 55,\n",
" 4.20,\n",
" 4.3,\n",
" 2.27\n",
"]]\n",
"model2.predict(test_diamond)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "sas2",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 2
}