Skip to content

Instantly share code, notes, and snippets.

Show Gist options
  • Save wakusei-meron-/6219f89b4e3e32e48fd3edb566e08169 to your computer and use it in GitHub Desktop.
Save wakusei-meron-/6219f89b4e3e32e48fd3edb566e08169 to your computer and use it in GitHub Desktop.
Desktop/PPP/python/statistics/Untitled1.ipynb
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "from scipy.stats import norm\n\n# 定数\nxlim = (-4, 4)\nylim = (0, 1)\nplot_interval = 0.1\nmu = 1\nsigma = 0.5\n\n# 求めたいパラメータ分布\nsrc_norm = norm(loc=mu, scale=sigma)\nx_orig = np.arange(*xlim, plot_interval)\ny_orig = src_norm.pdf(x_orig)\nplt.xlim(*xlim)\nplt.ylim(*ylim)\nplt.plot(x_orig, y_orig)",
"execution_count": 253,
"outputs": [
{
"output_type": "execute_result",
"execution_count": 253,
"data": {
"text/plain": "[<matplotlib.lines.Line2D at 0x1276672e8>]"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": "<matplotlib.figure.Figure at 0x127568eb8>",
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "# 上側p%のデータを生成\ndef gen_data(dist, size, p):\n data = dist.rvs(size=size)\n p_x = dist.isf(p)\n return data[data>p_x]\n\n# ヒストグラムのデータ生成\ndef hist(data, bins, p_value):\n y, x = np.histogram(data, bins=bins, density=True)\n y = y * p_value\n x = (x + np.roll(x, -1))[:-1] /2.0\n return x, y\n\n# p値に含まれるデータの分布生成\np_value = 0.1\np_data = gen_data(src_norm, 10000, p_value)\nxdata, ydata = hist(p_data, 100, p_value)\nplt.scatter(xdata, ydata, s=5)\nplt.plot(x_orig, y_orig)\nplt.xlim(*xlim)\nplt.ylim(*ylim)",
"execution_count": 254,
"outputs": [
{
"output_type": "execute_result",
"execution_count": 254,
"data": {
"text/plain": "(0, 1)"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": "<matplotlib.figure.Figure at 0x12760bf28>",
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "# p値のみの分布\ndef norm_percentile(x, loc, scale, p):\n return np.where(x < norm.isf(p, loc=loc, scale=scale), 0., norm.pdf(x, loc=loc, scale=scale))\n\n# p値 = 0.8以上のみの正規分布の関数\ny = np.vectorize(lambda x: norm_percentile(x, 0, 1, 0.8), otypes=[np.float])(x)\nplt.plot(x, y)",
"execution_count": 237,
"outputs": [
{
"output_type": "execute_result",
"execution_count": 237,
"data": {
"text/plain": "[<matplotlib.lines.Line2D at 0x1270e18d0>]"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": "<matplotlib.figure.Figure at 0x126fb92b0>",
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "# 上側データのみからパラメータを推測する\nfrom scipy.optimize import curve_fit\n\n# 初期値を適切に指定しないと収束しない\n# popt, pcov = curve_fit(lambda x, loc, scale: norm_percentile(x, loc, scale, p_value), xdata, ydata)\npopt, pcov = curve_fit(lambda x, loc, scale: norm_percentile(x, loc, scale, p_value), xdata, ydata, p0=[1,0.1])\n\nplt.scatter(xdata, ydata, s=5)\nplt.plot(x, norm.pdf(x, *popt))\nprint(\"真のパラメータ: μ={}, σ={}\".format(mu, sigma))\nprint(\"推測されたパラメータ: μ={}, σ={}\".format(*popt))",
"execution_count": 257,
"outputs": [
{
"output_type": "stream",
"text": "真のパラメータ: μ=1, σ=0.5\n推測されたパラメータ: μ=0.9849949055284954, σ=0.5102662015325604\n",
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"text/plain": "<matplotlib.figure.Figure at 0x12796d198>",
"image/png": "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\n"
},
"metadata": {}
}
]
}
],
"metadata": {
"kernelspec": {
"name": "python3",
"display_name": "Python 3",
"language": "python"
},
"language_info": {
"name": "python",
"version": "3.6.3",
"mimetype": "text/x-python",
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"pygments_lexer": "ipython3",
"nbconvert_exporter": "python",
"file_extension": ".py"
},
"gist": {
"id": "",
"data": {
"description": "Desktop/PPP/python/statistics/Untitled1.ipynb",
"public": true
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment