Skip to content

Instantly share code, notes, and snippets.

@rwest
Created April 21, 2015 17:11
Show Gist options
  • Save rwest/954a086e8a724bc717fe to your computer and use it in GitHub Desktop.
Save rwest/954a086e8a724bc717fe to your computer and use it in GitHub Desktop.
An investigation of correlated random variables when sampling a model
Display the source blob
Display the rendered blob
Raw
{
"metadata": {
"name": "",
"signature": "sha256:ee6adb6cf5427bac88e67943855bc42233201c17a8c4cb1ac06aace6ffd8da4e"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"%matplotlib inline\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First, define a simple model, of at least 2 parameters, but one that is not very sensitive to the third or higher dimensions."
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"def model(params):\n",
" \"A simple model of N parameters, not very sensitive to the third or higher\"\n",
" answer = params[0] + params[1]\n",
" for i, p in enumerate(params[2:]):\n",
" answer += p/(i+10.)\n",
" return answer"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 2
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now make a simple tool to help analyze a set of at least 3 parameters, ie. to sample the model using the given parameters, and report the range and interquartile range of the output, and draw a histogram. It will also draw a scatter plot of the first two parameters, so you can see how they cover the sample space."
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"def analysis(*variables):\n",
" x,y,z = variables[0:3]\n",
" plt.axes().set_aspect('equal')\n",
" plt.plot(x,y,'.')\n",
" plt.axis([0,1,0,1])\n",
" plt.show()\n",
" f = model(variables)\n",
" plt.hist(f)\n",
" print \"Dimensions:\",len(variables)\n",
" l, u = f.min(), f.max()\n",
" print \"Range:\", (l, u)\n",
" print \"Spread:\", u-l\n",
" lq, uq = np.percentile(f, [25, 75])\n",
" print \"Quartiles:\", (lq, uq)\n",
" print \"IQR:\", uq-lq"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 3
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First, lets take a 3-dimensional model, and sample 100 times with uncorrelated, uniform, random variables."
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"samples = 1000\n",
"x = np.random.uniform(size=samples)\n",
"y = np.random.uniform(size=samples)\n",
"z = np.random.uniform(size=samples)\n",
"analysis(x,y,z)"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAQcAAAD9CAYAAACx1bJsAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nr0WoSQAAAABJRU5ErkJggg==\n",
"text": [
"<matplotlib.figure.Figure at 0x111e20850>"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
"Dimensions: 3\n",
"Range: (0.074536201373853958, 1.9835613235751917)\n",
"Spread: 1.9090251222\n",
"Quartiles: (0.74325320177344545, 1.321817080914355)\n",
"IQR: 0.578563879141\n"
]
},
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAD9CAYAAACyYrxEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAElFTkSuQmCC\n",
"text": [
"<matplotlib.figure.Figure at 0x111e2d0d0>"
]
}
],
"prompt_number": 4
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now lets try again with the three variables being perfectly correlated.\n",
"We are now sampling from a much smaller hypercube, meaning our accessible output range must be a subset of before, but how is it distributed?"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"samples = 100\n",
"x = np.random.uniform(size=samples)\n",
"y = x\n",
"z = x\n",
"analysis(x,y,z)"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAQcAAAD9CAYAAACx1bJsAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nhOQAAD79P2xpz5Cj2lSKAAAAAElFTkSuQmCC\n",
"text": [
"<matplotlib.figure.Figure at 0x111f746d0>"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
"Dimensions: 3\n",
"Range: (0.0069745342010285706, 2.0883658973018875)\n",
"Spread: 2.0813913631\n",
"Quartiles: (0.48384743083709303, 1.4917298284895473)\n",
"IQR: 1.00788239765\n"
]
},
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAXMAAAD9CAYAAABOd5eOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAhAmAOAAIQ5AAjwfyWHHDmZ7a/TAAAAAElFTkSuQmCC\n",
"text": [
"<matplotlib.figure.Figure at 0x111f95c10>"
]
}
],
"prompt_number": 5
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The interquartile range (and interdecile range) have expanded. i.e. the model predictions appeared to get *less* certain, with correlated random inputs.\n",
"\n",
"Lets go back to the uncorrelated case, but this time have 100 dimensions (most of which don't matter much) and see if it matters that our sampling of the multidimensional hypercube is very sparse"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"samples = 1000\n",
"dimensions = 100\n",
"variables = []\n",
"for n in range(dimensions):\n",
" variables.append(np.random.uniform(size=samples))\n",
"analysis(*variables)\n"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAQcAAAD9CAYAAACx1bJsAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n",
"text": [
"<matplotlib.figure.Figure at 0x111f70890>"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
"Dimensions: 100\n",
"Range: (1.091285855493636, 3.1650517132706737)\n",
"Spread: 2.07376585778\n",
"Quartiles: (1.9088146382717646, 2.498248267336904)\n",
"IQR: 0.589433629065\n"
]
},
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAD9CAYAAACyYrxEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAUBxhB4AFPf/C4pNLezirfgAAAAASUVORK5CYII=\n",
"text": [
"<matplotlib.figure.Figure at 0x111e20d90>"
]
}
],
"prompt_number": 6
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Nope! It seems we still have a reasonable coverage of the sensitive parameters."
]
}
],
"metadata": {}
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment