{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Example: fit a baseline\n",
"\n",
"## Load the libraries and create a signal\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# load libraries\n",
"%matplotlib inline\n",
"import numpy as np\n",
"import rampy\n",
"\n",
"# the following code is for the rendering of plotly graphs in Rampy docs, you don't need it\n",
"# Set renderer for Jupyter notebooks\n",
"import plotly.io as pio\n",
"pio.renderers.default = 'notebook'\n",
"\n",
"# create signal\n",
"nb_points =500\n",
"x = np.linspace(50, 500, nb_points)\n",
"\n",
"# gaussian peaks\n",
"p1 = 20.0 * np.exp(-np.log(2) * ((x-150.0)/15.0)**2)\n",
"p2 = 100.0 * np.exp(-np.log(2) * ((x-250.0)/5.0)**2)\n",
"p3 = 50.0 * np.exp(-np.log(2) * ((x-450.0)/1.0)**2)\n",
"p4 = 20.0 * np.exp(-np.log(2) * ((x-350.0)/30.0)**2)\n",
"p5 = 30.0 * np.exp(-np.log(2) * ((x-460.0)/5.0)**2)\n",
"\n",
"# background: a large sin distortion + linear \n",
"bkg = 10*np.sin(x/50) + 0.1*x\n",
"\n",
"#noise\n",
"noise = 2.0 * np.random.normal(size=nb_points)\n",
"\n",
"#observation\n",
"y = p1 + p2 + p3 + p4 + p5 + noise +bkg\n",
"\n",
"# we use the rampy API (plotly behind it!) to plot the spectrum\n",
"fig = rampy.plot_spectrum(x, y, title = \"our spectrum\", xaxis_title=\"X\", yaxis_title=\"Y\")\n",
"fig.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Now using different baselines to retrieve the true background\n",
"\n",
"We also use the plot_spectrum function to show the different baselines."
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_2305391/347025575.py:8: DeprecationWarning:\n",
"\n",
"The 'roi' parameter now has a default value of np.array([[0, 100]]). Please specify 'roi' explicitly in future calls to avoid this warning.\n",
"\n",
"/tmp/ipykernel_2305391/347025575.py:9: DeprecationWarning:\n",
"\n",
"The 'roi' parameter now has a default value of np.array([[0, 100]]). Please specify 'roi' explicitly in future calls to avoid this warning.\n",
"\n",
"/tmp/ipykernel_2305391/347025575.py:10: DeprecationWarning:\n",
"\n",
"The 'roi' parameter now has a default value of np.array([[0, 100]]). Please specify 'roi' explicitly in future calls to avoid this warning.\n",
"\n"
]
},
{
"data": {
"text/html": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# need to define some fitting regions for the spline\n",
"roi = [[0,100],[200,220],[280, 290],[420,430],[480,500]]\n",
"\n",
"# calculating the baselines\n",
"ycalc_poly, base_poly = rampy.baseline(x, y, roi, method='poly', polynomial_order=4)\n",
"ycalc_gcvspl, base_gcvspl = rampy.baseline(x,y,roi, method='gcvspline')\n",
"ycalc_uni, base_uni = rampy.baseline(x, y, roi, method='unispline', s=1.2)\n",
"ycalc_als, base_als = rampy.baseline(x, y, method='als', lam=10**5, p=0.05)\n",
"ycalc_arpls, base_arpsl = rampy.baseline(x, y, method='arPLS', lam=10**6, ratio=0.001)\n",
"ycalc_drpls, base_drpsl = rampy.baseline(x, y, method='drPLS', lam=10**6)\n",
"ycalc_rubberband, base_rubberband = rampy.baseline(x, y, roi, method='rubberband')\n",
"ycalc_whittaker, base_whittaker = rampy.baseline(x, y, roi, method='whittaker', lam=10**5)\n",
"\n",
"# doing the figure\n",
"fig = rampy.plot_spectrum(x, y, baselines=[base_poly, base_gcvspl, base_uni, base_als, base_arpsl, base_drpsl, base_rubberband, base_whittaker],\n",
" baseline_labels=['poly', 'gcvspline', 'unispline', 'als', 'arPLS', 'drPLS', 'rubberband', 'whittaker'],\n",
" title = \"Various baseline comparison\", xaxis_title=\"X\", yaxis_title=\"Y\")\n",
"fig.show()\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Automatic selection of smoothing coefficient for GCV spline\n",
"\n",
"For the GCV spline, we can forget about the s parameter and it will be determined using the GCV method, or we can set it to a desired value. Here is a comparison:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# calculating the baselines\n",
"ycalc_gcvspl, base_gcvspl = rampy.baseline(x,y,roi,'gcvspline')\n",
"ycalc_gcvspl_2, base_gcvspl_2 = rampy.baseline(x,y,roi,'gcvspline', s=1.0)\n",
"\n",
"# figure\n",
"fig = rampy.plot_spectrum(x, y, \n",
" baselines=[base_gcvspl, base_gcvspl_2],\n",
" baseline_labels=['s calculated by GCV', 'manual s'],\n",
" title = \"Comparing manual and GCV smoothing splines for baselines\", xaxis_title=\"X\", yaxis_title=\"Y\")\n",
"fig.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Machine learning baseline!\n",
"\n",
"You can use a Gaussian process to fit the baseline."
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# calculating the baselines\n",
"ycalc_GP, base_GP = rampy.baseline(x,y,roi,'GP')\n",
"\n",
"# figure\n",
"fig = rampy.plot_spectrum(x, y, \n",
" baselines=[base_gcvspl, base_GP],\n",
" baseline_labels=['GCV spline', 'Gaussian Process'],\n",
" title = \"Comparing GCV smoothing spline and Gaussian Process baselines\", xaxis_title=\"X\", yaxis_title=\"Y\")\n",
"fig.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "gpvisc",
"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": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 1
}