{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Systematic Sampling"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:35:07.360138Z",
"iopub.status.busy": "2024-04-17T07:35:07.360020Z",
"iopub.status.idle": "2024-04-17T07:35:07.677935Z",
"shell.execute_reply": "2024-04-17T07:35:07.677643Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import numpy as np\n",
"from lets_plot import *\n",
"\n",
"LetsPlot.setup_html()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:35:07.691885Z",
"iopub.status.busy": "2024-04-17T07:35:07.691717Z",
"iopub.status.idle": "2024-04-17T07:35:07.693874Z",
"shell.execute_reply": "2024-04-17T07:35:07.693679Z"
}
},
"outputs": [],
"source": [
"N = 10000\n",
"X = np.arange(N)\n",
"np.random.seed(1)\n",
"Y = np.random.normal(0, 1, N)\n",
"p = ggplot(dict(x=X, y=Y), aes('x', 'y'))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:35:07.694874Z",
"iopub.status.busy": "2024-04-17T07:35:07.694798Z",
"iopub.status.idle": "2024-04-17T07:35:07.760137Z",
"shell.execute_reply": "2024-04-17T07:35:07.759926Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Linear regression is computed using the entire data \n",
"# therefore it is same on all plots regardless the sampling applied to 'lines' layer.\n",
"p + geom_line() + geom_smooth()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:35:07.762083Z",
"iopub.status.busy": "2024-04-17T07:35:07.762005Z",
"iopub.status.idle": "2024-04-17T07:35:07.779723Z",
"shell.execute_reply": "2024-04-17T07:35:07.779539Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Systematic sampling often looks better than 'random' sampling\n",
"p + geom_line(sampling=sampling_systematic(50)) + geom_smooth()\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"execution": {
"iopub.execute_input": "2024-04-17T07:35:07.780910Z",
"iopub.status.busy": "2024-04-17T07:35:07.780788Z",
"iopub.status.idle": "2024-04-17T07:35:07.798339Z",
"shell.execute_reply": "2024-04-17T07:35:07.798140Z"
}
},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"p + geom_line(sampling=sampling_random(50, seed=33)) + geom_smooth()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.10.13"
}
},
"nbformat": 4,
"nbformat_minor": 1
}