{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 14 Standard deviation of residuals or root mean square deviation (RMSD)"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"%%html\n",
""
]
},
{
"cell_type": "code",
"execution_count": 80,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"from pandas import Series, DataFrame\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"from scipy import stats\n",
"from sklearn.linear_model import LinearRegression\n",
"from sklearn.metrics import mean_squared_error"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"[khanacademy](https://www.khanacademy.org/math/ap-statistics/bivariate-data-ap/assessing-fit-least-squares-regression/v/standard-dev-residuals?modal=1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
""
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"x = np.array([1, 2, 2, 3])\n",
"y = np.array([1, 2, 3, 6])"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"slope, intercept, rvalue, pvalue, stderr = stats.linregress(x, y)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"yhat = intercept + slope * x"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {},
"outputs": [],
"source": [
"x_test = x.reshape(-1, 1)\n",
"y_test = y.reshape(-1, 1)\n",
"reg = LinearRegression()\n",
"reg.fit(x_test, y_test)\n",
"y_pred = reg.predict(x_test)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"df = DataFrame({\n",
" 'x': x,\n",
" 'y': y,\n",
" 'yhat': yhat,\n",
" '(y - yhat)**2': (y - yhat)**2\n",
"})"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" x | \n",
" y | \n",
" yhat | \n",
" (y - yhat)**2 | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 1 | \n",
" 1 | \n",
" 0.5 | \n",
" 0.25 | \n",
"
\n",
" \n",
" | 1 | \n",
" 2 | \n",
" 2 | \n",
" 3.0 | \n",
" 1.00 | \n",
"
\n",
" \n",
" | 2 | \n",
" 2 | \n",
" 3 | \n",
" 3.0 | \n",
" 0.00 | \n",
"
\n",
" \n",
" | 3 | \n",
" 3 | \n",
" 6 | \n",
" 5.5 | \n",
" 0.25 | \n",
"
\n",
" \n",
"
\n",
"