{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "

Density estimation: nonparametric and parametric" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "In /Users/holtz/anaconda3/lib/python3.7/site-packages/matplotlib/mpl-data/stylelib/_classic_test.mplstyle: \n", "The text.latex.preview rcparam was deprecated in Matplotlib 3.3 and will be removed two minor releases later.\n", "In /Users/holtz/anaconda3/lib/python3.7/site-packages/matplotlib/mpl-data/stylelib/_classic_test.mplstyle: \n", "The mathtext.fallback_to_cm rcparam was deprecated in Matplotlib 3.3 and will be removed two minor releases later.\n", "In /Users/holtz/anaconda3/lib/python3.7/site-packages/matplotlib/mpl-data/stylelib/_classic_test.mplstyle: Support for setting the 'mathtext.fallback_to_cm' rcParam is deprecated since 3.3 and will be removed two minor releases later; use 'mathtext.fallback : 'cm' instead.\n", "In /Users/holtz/anaconda3/lib/python3.7/site-packages/matplotlib/mpl-data/stylelib/_classic_test.mplstyle: \n", "The validate_bool_maybe_none function was deprecated in Matplotlib 3.3 and will be removed two minor releases later.\n", "In /Users/holtz/anaconda3/lib/python3.7/site-packages/matplotlib/mpl-data/stylelib/_classic_test.mplstyle: \n", "The savefig.jpeg_quality rcparam was deprecated in Matplotlib 3.3 and will be removed two minor releases later.\n", "In /Users/holtz/anaconda3/lib/python3.7/site-packages/matplotlib/mpl-data/stylelib/_classic_test.mplstyle: \n", "The keymap.all_axes rcparam was deprecated in Matplotlib 3.3 and will be removed two minor releases later.\n", "In /Users/holtz/anaconda3/lib/python3.7/site-packages/matplotlib/mpl-data/stylelib/_classic_test.mplstyle: \n", "The animation.avconv_path rcparam was deprecated in Matplotlib 3.3 and will be removed two minor releases later.\n", "In /Users/holtz/anaconda3/lib/python3.7/site-packages/matplotlib/mpl-data/stylelib/_classic_test.mplstyle: \n", "The animation.avconv_args rcparam was deprecated in Matplotlib 3.3 and will be removed two minor releases later.\n" ] } ], "source": [ "%matplotlib inline\n", "import matplotlib.pyplot as plt\n", "import numpy as np" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's work with the APOGEE DR17 data set, looking in 2D at [Mg/Fe] vs [Fe/H]. First we will download data from the SDSS Catalog archive server using an SQL query with astroquery.\n", "
\n", "To learn about what is in the data base, you can peruse the \n", " schema browser . We will be interested in quantities from the aspcapStar table (select that from the Tables item on the right to browse the contents), specifically FE_H (which gives the logarithm of the abundance of iron to hydrogen relative to that of the Sun), MG_FE (logarithmic abundance of magnesium relative to irorn relative to that ratio in the Sun), and LOGG (surface gravity). Construct a query that selects FE_H and MG_FE from this table for object with 1 < logg < 2. Remember, the basic structure of an SQL query:\n", "
\n",
    "   SELECT  columnnames\n",
    "   FROM  tablename\n",
    "   WHERE conditions\n",
    "
" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/holtz/anaconda3/lib/python3.7/site-packages/requests/__init__.py:91: RequestsDependencyWarning: urllib3 (1.26.9) or chardet (3.0.4) doesn't match a supported version!\n", " RequestsDependencyWarning)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " SELECT FE_H, MG_FE, apogeeStar.extratarg FROM aspcapStar JOIN apogeeStar ON aspcapStar.apstar_id = apogeeStar.apstar_id WHERE LOGG>1 AND LOGG<2 AND apogeeStar.extratarg = 0 \n", "67267\n" ] } ], "source": [ "from astroquery.sdss import SDSS\n", "sql=\" SELECT FE_H, MG_FE, apogeeStar.extratarg \\\n", " FROM aspcapStar \\\n", " JOIN apogeeStar ON aspcapStar.apstar_id = apogeeStar.apstar_id \\\n", " WHERE LOGG>1 AND LOGG<2 AND apogeeStar.extratarg = 0 \\\n", " \"\n", "print(sql)\n", "dr17=SDSS.query_sql(sql, data_release=17) \n", "print(len(dr17))\n" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " FE_H MG_FE extratarg\n", "--------- ------------ ---------\n", " 0.35839 0.003715992 0\n", " 0.2297 0.0008270144 0\n", " 0.10624 0.0788789 0\n", " -0.84662 0.341623 0\n", " -0.27705 0.277463 0\n", " 0.37835 -0.054977 0\n", " -0.1863 0.189303 0\n", " -0.18991 0.275463 0\n", " 0.26089 0.03521502 0\n", " 0.33715 0.03567898 0\n", " ... ... ...\n", " -1.1376 0.159043 0\n", " -1.0695 0.1186619 0\n", " -0.31406 0.14725 0\n", " -0.57243 0.353973 0\n", " -0.37482 0.08792439 0\n", " -1.0257 0.121325 0\n", " -0.38679 0.103378 0\n", "-0.099163 0.111828 0\n", " -0.29464 0.088771 0\n", " -0.14344 -0.009474009 0\n", " -0.68592 0.09890097 0\n", "Length = 67267 rows\n" ] } ], "source": [ "print(dr17)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "How many objects did you get?\n", "
ANSWER HERE:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "OK, let's make a scatter plot of FE_H vs MG_FE. Note that bad values are filled with -999, so let's clean the data by restricting our data to those with good values. Let's also make sure we don't have any NaN or inf. Note that we could have included these constraints in the SQL query!\n", "

\n", "For your scatter plot, choose the smallest point sizes (s= keyword with plt.scatter)." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "67211\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "

" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "gd=np.where((dr17['FE_H']>-900) & (dr17['MG_FE']>-900) & np.isfinite(dr17['FE_H']*dr17['MG_FE']))[0]\n", "dr17=dr17[gd]\n", "print(len(dr17))\n", "\n", "# use a point size of 1 for the scatter plot\n", "plt.scatter(dr17['FE_H'],dr17['MG_FE'],s=1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "You can see that it's hard to see structure, even with the smallest point sizes. So let's use density estimation to display the data." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Start with a Gaussian KDE using scikit-learn routine: see http://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KernelDensity.html#sklearn.neighbors.KernelDensity. As with many routines that we'll use, this wants an input array of dimesions [npts, ndim], where ndim is the number dimensions of the data. For us, we'll use two dimensions (FE_H and MG_FE), so want a [npts,2] array.\n", "

\n", "As you will see, working with so many data points can take a non-negligible amount of time, especially on a laptop (always consider using appropriate hardware when working with large data sets - your laptop may not be the best choice!). To help with this, we'll set a sampling variable, nsamp, and we'll just take every nsamp'th point in the cells below: you can set nsamp=1 to use every point, but you might want to start with smaller samples, eg. nsamp=10, so you're not waiting too long!" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(6722, 2)\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "

" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "nsamp=10 # value for sampling of data point, to speed things up!\n", "\n", "# put the data into a [npts,2] array, sampling every nsamp point\n", "X=np.array([dr17['FE_H'][::nsamp],dr17['MG_FE'][::nsamp]]).T\n", "print(X.shape)\n", "\n", "# plot it\n", "plt.scatter(X[:,0],X[:,1],s=1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "OK, let's set up the KDE . You need to specify a kernel type, and a bandwidth" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "xg shape: (100, 100)\n", "yg shape: (100, 100)\n", "xy: (10000, 2)\n", "dens shape: (100, 100)\n" ] } ], "source": [ "# do the KDE\n", "from sklearn.neighbors import KernelDensity\n", "kde=KernelDensity(kernel='gaussian',bandwidth=0.01)\n", "\n", "# do the fit\n", "kde.fit(X)\n", "\n", "# sample it on a grid as specified by these x and y values\n", "x=np.linspace(-2.5,1,100)\n", "y=np.linspace(-0.6,0.8,100)\n", "\n", "# meshgrid returns two 2D arrays with the values\n", "yg,xg=np.meshgrid(x,y)\n", "print('xg shape: ',xg.shape)\n", "print('yg shape: ',yg.shape)\n", "# ravel turns the 2D arrays into the long lists of (npts,2) that we need\n", "xy=np.vstack([yg.ravel(),xg.ravel()]).T\n", "print('xy:',xy.shape)\n", "\n", "# get the KDE samples at the grid locations and reshape it back to 100x100\n", "dens=kde.score_samples(xy).reshape(xg.shape)\n", "print('dens shape: ',dens.shape)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Display the KDE results as an image, using imshow()" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plt.imshow(dens,origin='lower',interpolation='nearest',vmin=-5,vmax=2,\n", " extent=(x[0],x[-1],y[0],y[-1]),aspect='equal')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Experiment with using different bandwidths and, if you want, more data points by adjusting nsamp. Describe your experiments. What bandwidth do you prefer?\n", "\n", "
ANSWER HERE: " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "scikit-learn has some nice built-in tools. In particular, it has a generic grid search routine which can sample a range of parameters for any of a number of algorithms, and determine the best parameters using cross validation. Here, we will use cross-validation to get optimal smoothing size. See http://scikit-learn.org/stable/modules/grid_search.html#grid-search" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{'mean_fit_time': array([0.00170732, 0.00161457, 0.00133924]),\n", " 'mean_score_time': array([0.21335025, 0.28337469, 0.33063979]),\n", " 'mean_test_score': array([182.80971854, 983.74659461, 863.75945678]),\n", " 'param_bandwidth': masked_array(data=[0.01, 0.03, 0.05],\n", " mask=[False, False, False],\n", " fill_value='?',\n", " dtype=object),\n", " 'params': [{'bandwidth': 0.01}, {'bandwidth': 0.03}, {'bandwidth': 0.05}],\n", " 'rank_test_score': array([3, 1, 2], dtype=int32),\n", " 'split0_test_score': array([791.9537312 , 950.13771295, 798.28260058]),\n", " 'split1_test_score': array([1052.17670855, 1282.27252636, 1084.34337275]),\n", " 'split2_test_score': array([-1376.78901489, 836.02542266, 815.93729457]),\n", " 'split3_test_score': array([ 258.38555008, 1023.0449526 , 908.00376771]),\n", " 'split4_test_score': array([188.32161779, 827.25235848, 712.23024829]),\n", " 'std_fit_time': array([3.79823859e-04, 3.30181964e-04, 5.06735456e-05]),\n", " 'std_score_time': array([0.01263417, 0.0138603 , 0.01323818]),\n", " 'std_test_score': array([844.38684122, 166.19484973, 126.60971681])}\n", "best parameters from CV: {'bandwidth': 0.03}\n" ] } ], "source": [ "from sklearn.model_selection import GridSearchCV\n", "# note that GridSearchCV has its own parameters for choosing cross-validation samples, etc.\n", "# here, we set the grid of bandwidth parameters for it to try\n", "bandwidths=np.linspace(0.01,0.05,3) # set array of bandwidths to try -- don't try too many!\n", "grid=GridSearchCV(KernelDensity(),{'bandwidth': bandwidths})\n", "grid.fit(X)\n", "\n", "# check out some of the output from the grid search\n", "import pprint\n", "pprint.pprint(grid.cv_results_)\n", "print('best parameters from CV: ',grid.best_params_)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Run the KDE with the \"best\" bandwidth from the cross-validation test and display" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "kde=KernelDensity(kernel='gaussian',bandwidth=grid.best_params_['bandwidth'])\n", "kde.fit(X)\n", "\n", "# get the KDE samples at the grid locations\n", "dens=kde.score_samples(xy).reshape(xg.shape)\n", "plt.imshow(dens,origin='lower',interpolation='nearest',vmin=-5,vmax=2,\n", " extent=(-2.5,1,-0.6,0.8),aspect='equal')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "How does the cross-validation result compare with your preferred bandwidth?\n", "
ANSWER HERE: " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now try a nearest neighbors density estimation, http://www.astroml.org/modules/generated/astroML.density_estimation.KNeighborsDensity.html.\n", "Here we will smooth each point with a width depending on a specified number of nearest neighbors. Experiment with different numbers." ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAClCAYAAABC87pHAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAAAx+klEQVR4nO2deZDd11Xnv+f31l7V3dqszZYdy46XOLERTkgyk5jg4BiICQU1JkzIBBiPmXiGbShcQ1WKYpYKMEtBETCeTKqSKUgqBEwMcWwngWCy2XKCN8WWJUuytbSWVu/L2+/80c/vfs/Re09P6id1t3Q+VV193/vd3+93332/d8+9Z7sSQoDjOI7jtCJZ7gY4juM4KxsXFI7jOE5bXFA4juM4bXFB4TiO47TFBYXjOI7TFhcUjuM4TlvSy92AcyEruZBH33I3w3EcZ1Uxg4mxEML6sz2vK4JCRO4A8IcAUgA+GUL4uDn+mwB+ju55HYD1IYRxETkIYAZAFUAlhLDzTPfLow9vlfd0o+mO4ziXDF8NX3j1XM5bsqAQkRSATwC4HcBhALtE5OEQwvdfrxNC+AMAf1Cv/xMAfi2EME6XuS2EMLbUtjiO4zjdpxs2ilsB7Ash7A8hlAB8DsBdber/LIDPduG+juM4zgWgG4JiC4BD9Ppw/b3TEJFeAHcA+Ct6OwB4XES+KyL3dKE9juM4Thfpho1CmrzXKoHUTwD4plE7vSOEcFRENgD4ioi8FEJ44rSbLAqRewAgj96lttlxHMfpkG6sKA4D2EavtwI42qLu3TBqpxDC0fr/EwAewqIq6zRCCA+GEHaGEHZmkFtyox3HcZzO6Iag2AVgh4hcKSJZLAqDh20lEVkD4F0Avkjv9YnIwOtlAO8F8EIX2uQ4juN0iSWrnkIIFRG5D8BjWHSP/VQIYbeI3Fs//kC96gcAPB5CmKPTNwJ4SEReb8tfhBAeXWqbHMdxnO4hq3E/ikEZCR5H4TiOc3Z8NXzhu53Eqlk8hYfjOI7TFhcUjuM4TltcUDiO4zhtcUHhOI7jtMUFheM4jtMWFxSO4zhOW1xQOI7jOG1xQeE4juO0xQWF4ziO0xYXFI7jOE5bXFA4juM4bXFB4TiO47TFBYXjOI7TFhcUjuM4TltcUDiO4zht6YqgEJE7RGSPiOwTkfubHH+3iEyJyDP1v491eq7jXEgknW78OY6zyJJ/DSKSAvAJALdjcf/sXSLycAjh+6bqP4UQfvwcz3Ucx3GWiW5Mm24FsC+EsB8ARORzAO4C0Mlgv5RzHWfJJPm8ei35XKNcm1tolEO5dMHa5DgrjW4Iii0ADtHrwwDe2qTeD4nIswCOAvhPIYTdZ3Gu43SPxT3aF4t9vfpQNtsoJ7W4TXC1UtbXWIVbCDvOudINQSFN3rO/ou8BuCKEMCsidwL4GwA7Ojx38SYi9wC4BwDy6G1W5bwgmThw+KxyhZOkYrlWbV2tp6dRlt42z1Iuri5SiX5UawuFeI1UvG+tUGx5Oa4HAAi1eIwEVKiattPrUKm0bq/jnCe6Ycw+DGAbvd6KxVVDgxDCdAhhtl5+BEBGRNZ1ci5d48EQws4Qws4Mcs2qOI7jOOeBbqwodgHYISJXAjgC4G4AH+QKInIZgOMhhCAit2JRQJ0CMHmmc7tGomdzSU/UTauZnpn1SW+cfdZOjcdyoQBn+Ul4RcAz+5kZXZHVTbRSCD160iGlqGKSXrJfVDL6vrTSlHS8rwzUVD2Q+kqy+hqB70W2EZhVQ6jFa4ap6Xhp+wzSZ3TVmNNNliwoQggVEbkPwGMAUgA+FULYLSL31o8/AOCnAfyyiFQALAC4O4QQADQ9d6ltakZqzaB6LbksHYw/dDtwVAfiQJQiFUDtmAuKriJGC9lioGNVIABIX18sp+ICWez1+BwS/iGlF9WBhQMN5DCDPA/6tQFSZVVNu+lzVHNG2BSiKrOaJ9tIyaiXSFAk5LYrM7O6Hj/HxagCq83Pw3GWQlecxevqpEfMew9Q+Y8B/HGn5zqO4zgrh4s7qqiNd0ugGRzXqw73qXrF9XGG2TvXHw8cP6Hv1Wapz+oRNlTyrO9Shw3MABDKcVYtGZpF54x9amggnsP1evX1lEG4j9SJZpbPVruEVwMDxo22Gmf5xXXxeklFPwdCqqdyv/65ZWbjZ6lm441TJa2+Suh1KhuvkZhVjnreydhuV2u1uTk4ztlwUQuKhHXRea2yCKwTTsUfUmlEDwgzW2MX5Y/GY3Zg4+W9HcySkeH4gvTP1VMTuk2r1KuqXRRzOy8d7qfTBAAPeiRolS4fQHUoCvZqLqpekooZ2Cuk50/HQbnSZ9RBNChXe+MzUxzR9VKFWG92czyWGIclFhwLa7WaKzdJtg0SSonpsux0vKiQsMnmWvd7aooESmLUa/Sd+GTF6YSLWlAgQz9u82Nh4cADQrlP1yusjfVqvfF66TaDIxvKAaBGs142libGGFmdPH+CggPL7GDLs/dOZ5upQbL52EGeXElr45PmXvEzKgFj+lMSNj6T6+iAXhnyQF8eoGtYUwEdyk3E76A0qO8b6OuvpWkCMaBn5alSHOTnL6O2Glt2qhSPzW7TB4vTZFMpx3oZ8xUUB+OxhMwmfWndpnJvvN7AATKiZ/RnTJHNozYxGcvuoOG0wJMCOo7jOG25uFcUjLEhKFUE6YetjjlDjiWBg65s8BRjZtjVwfg6KZJ6ZFx3P9sylAunUQ/wCkC9bwK1ErLLsM5ezIpH+Hqsy68aXTnp9mV4KNbraa02SkybAgeqKZuCbhN7HLEnUmVIq/yq+difs5tiOTOnv8fCSPyOhxdoRp3Rs/LpK8hWQN1eHFbVkKZZf3mAbBm9rW1Vtazuz9T26MJbLMSVUWFM92dmhp7PEq9e9PMzuy0ey07HPgsmWJB7MOHnmFxvAaA2yw+/u9teylzcgqJWa3lI5mnAqsSfTnZKD8L9R3jZT4OejZ7laxs1SjUfX/OPNmXsHBBa4JG6KpnXKgHlf08+/GFhQdUTun4YjIb4Wt64ehZIHcb3MaoIGYxtqq6N5Uq/sf+QWi8/Z9rE6kBWKVn3UypX1sa2L1ymBUqgiuWB1iqg+U1xoBs8FD9lqV8PorNvjKqx9BjZHkwGjxKbndaw/UPfePtV0elhIKsF/oHxkUZ509qpRnnCPBcLr0Q1X426aXarbnt6Z7R5Ffeuiecb20hSjnadbCY+P6m0iSEidWUgleRp7rYUo8QG9mCEi9tDVi8XtaBgo11iZ+H0OjUXB4dUxcz6CnEwS82Qb7p56JV/f84MnKzrJntI9qjRy5NPf3lDHBzSk8a7hQRFrYf876esBw8ZbUfIm8uGGFCbUjTLT6b0AFMdigN2cW0cREpr9Oeo5Glme9LkUponwdZPgiyt7yU0wy4Nx/bNr9P1eNbPE+ya6Qq2FcxtiG2o9BnbQz5OACrDJHgK+r7p9VGIZlPxmSnN6+++XI33OjmvPeq2rInCoVhNN30fAPb0k7ddimwPl+tnsFqkD70ltnfmav3sZ2djG2u5WC+f0n3BK8hkmhwP2qVg50BW48hQdUGxanEbheM4jtOWi3pFofTtRgXCSeOSSdLFFrXnUTJH+uJya7dCFSthlvCsB69lW6dZYP/+hY3xvj2n2VfijLAyQCsU4y/PKqXKQJxtirHDVHvifCFD9pqMUa9VB+O9eBWxsFbft9JLHmV9Wt/OPVMZoJTeGaMeIXVduT+eVTD3yp+Kn6XSF8u8ggCAajYem6XsYuVho0IsUzsq8RphQM+OyzOxL65+w7FG+S1XH1b1jiwMxbZX9c/tDf1jsZyPKqonp69S9fYPrW2Ur1hP6qWKvt6hV9fFppOH1cBmnc5k+sqoNyv1m6UXkRTj95Ol+I2UdXnm55PjV8xvqdOkjc7K46IWFCq4zeb+YSMe1zPZP9mV1Bp3W2JtI/SS/e9t+ogaDY6FIRqwZ/WPucZxH4OkHy6a+I0ech3tI120CejiY+xWmuo1ahTy4a9yk4ydk/X51R5jsCc7T7WHcjMZtUeNBFa5Jx6rGGOxUNxjaiHWm75WD2apuXi9ah9/IeZ6c7G9I5fHQblW09/V9P6hRvm/XfXXjfKfHb9N1fvopq81yp888S51bFM2qpiOl6NNYcT4x/6PH/hCo/zQqR9olAfS2oa0UI5fym9e81ij/McHfljVm7o5fq6ZvfFzpEpmOKCu6afvo3dG2yg4qJAdG8SoezmnWnBBsaq4qAUFz3ROsymkyejGHjYm6I0jcE9L/8y3oh9FUjHeR+V4jfQ8/XhsZK26YCxWevQgNbeRB32qZ2aH1VwcOMukiw8mpoQHYp6JV42gqJI+O0XCoHdMCx7rZcOUhngVQQLAfMYqHZvbTLaCYFdDLe5ljMpVMg8kC/FeNbNSSObjsfGxaLC/7LJJfb0r4yD/31+LGze+cGSTbgZF4D17YrM69ssb/75RnqzGFWlfop/VPz/19kb5tqEXG+U/3KsFAAuzFxe2NMr/+vInVb1P7n9Hozx7WRQ2MwXjecaLX7JL5Mb6VbVknh4GEvhijeNs6F6lwaWXKm6jcBzHcdpyca8oGGsP6HBGc071jPoqMx2P1SjtQq3Xekc1l9vBqGXmaYbdd4RWTSZSd34dqXboVjbGoEKOSWGGViEmark4SOqwuThjz43rWXmlt3lqCgAojJBLbJtpSnFNbMfCpjgrz5/Qs9Qqadu4Xnrcrq5iO7KT8cYFnVQYuXFaUS3Etk6+ulHVK18T1S/PHd7eKA9dPqnq7R6PK4zbtuxVx357/081yjsGTzbKj710nar3s296ulH+3ly814euekrV+9Xhg43yfzz6g43yjT3abnLD2mhTeSHE9k2Y70MOxxXG7Nb4/sAhvfLIzFA8DKdVnzPu1e1ij5wVzaUjKLoB5x/KmkG+RMJgTutwUzPxB1PtjeoMVsMAQKrM9ov4ftUEhfGgF1preVRcQapIP+B2CQxL8VhhWP+wefCukVDLn9LX0ColfY3CEKvAWjYDZUpbkZ5je42pyDGQpDYKafMZhXIpkUzPH9LfI5kNML2BzjGenTVK4YHBqHqZPDSkK26bbBS/9MoN6tAVa6Ot4IlDb2iUb95+SNWbprxVw5n4bB0xUYD/+XiUeh/b+PVG+dcPv0/Vy1CQCdsy3pLTe4bd+Ze/0ShXrowdMH1EC4qecQp0nCVhfVxVa6u6dVY2LijOApsIkOFhyQqKdJEC5Gi/gtI6Peu1M/N4kn6ZKlJeoHlKYpfTFYV+lzzAFobsrJyCCskjqtyrr1dYT6sX8t7iFQSg4yiSsr5GhWwKxRhvpgZoACiMkAcTf95ZKwBisbqdjomux6sIthWXrLBivfxw/N7sECcU2xKGYr3e13RfTA5E48i6tdqh4uWXo83i37z9G43y/3tBbxv/phvjAP746Bsb5WxKt+qaNdGyv6ccn9WRrH4e19HD8CcHo/H9317xT6pesjWed+Pm0Ub5he1Xq3rseJCbiB3Y28YGZ5NAejDeyqYrNgoRuUNE9ojIPhG5v8nxnxOR5+p/3xKRN9OxgyLyvIg8IyJP23Mdx3Gc5WXJKwoRSQH4BIDbsbgH9i4ReTiE8H2qdgDAu0IIEyLyPgAPAuBp020hhDGsQDjiWgbI28Mso9kV8LQlNu8NwG76ZgXAc6zcVFwp2HQUfYfjbDl/Kt6rPGC8TOg8XilUrc2D0lsMvcLqJeOySuqcwlpaGQ3q+QarqDJ6MotS9AJV6qFg7iXb47RfXor9ni4Y+0qO1WvN1VWAtuVwXxRH9H15ldP/fPxGKmYxySugwrpYL20+b34v6fl7TYxOMbbxrw405k4YXqPdY/nYVora3n9yrar3W1c+2ig/PvOmRnl7Xv+0vnoy2kCEVl4nKwOq3hs3xRXKwcnYMTWj1itSBHuVVpPDxgaX9NNuhDV9jbYpQpxlpxuqp1sB7Ash7AcAEfkcgLsANARFCOFbVP87ALZilcBpDDAUdcBiDNYJudhWZ/UPPbC7LA3eZZM+ggdL3oPABqPlplktw3YNk4KBAsY4TXbK2udZ3ZJqXgaA9AILEQp0yxuBQjYKm7adVWA1GthTJsN1eI3yEU3G9629huk5xqm69UDUd4ziN0i4SMXspU6enmsO0DnZ1vfNTZEazniYZtg54FltOU9RTMjM0ThIzxrDU8jFdoxsiCqgvQeuUPX+y+CPNcoLpaj2qZoYkJ5s/JDv3/p8o/zU5JWqXkIK1auGoyHqu31rVD2OS8mSvcLmAMuuHYovSjp5VsIxRbz3uVHjeqDe8tANQbEFAFvfDkOvFiy/CODL9DoAeFwWpzZ/FkJ4sNlJInIPgHsAII/eZlXOC5xYr7ImllMmWA6cZHDBentQXTIkp22weIpn4rTBkVHLs32AhUsw3yYLIvYOGjyolyh9lCSPVxF2JcNGYLY9lPS4gRqNvVYYspDifEzFIX0NHvTZEF81iWp5kx8WDj0mtiMzR7m9CvHaA6+11r720L7oxbX6xjwj5iDKhfVaL88xcVI1TgkkVHoPUeJII6B51fPNF8k+MKRtWqP71jfKN73pYGyD2U2pREmx/vbIjY3yOzfuV/V2jUVBVCZh86brX1P1vn84ek5VZymK3tjgQhKFYapgAiJ7KcPyFK3i7Z7mPEGjeCBfhZxfuiEomk21mrrViMhtWBQU76S33xFCOCoiGwB8RUReCiE8cdoFFwXIgwAwKCNNr+84juN0n24IisMAKHsOtgI4aiuJyE0APgngfSGExjo2hHC0/v+EiDyERVXWaYLigmHyJXH0dJV2UxOTzoNXGHYWpNJpk1tpumCuQWqkZIH2jDYpN1i1w1HQ1qbA8J4JxiHoNL3/65RMjAGfJ5XW9WqUV8lmZ2U1Esd2FNfpWW9+jNQP9LnKOigYvcfIS6uvTV9Q29ML8V59x7QKhPeuTooUbV9q48FTZVWg7kt+HaS1ixWvBq36auBgPG9uS2xHZcD02bHYZ7vnYr6o6iatJn3XNTGe4/lXohb40YKO3/jotf/YKP/FoVsb5SHjRVVl17G+2CbeRhjQ6rt0we4fHj9XjlYKifmdqdT5pNJNTNoc362vu3RDUOwCsENErgRwBMDdAD7IFUTkcgB/DeBDIYSX6f0+AEkIYaZefi+A3+1Cm84LwQoRhlOLm8CikGG1Aqej0JdIUyoElRbBkKbNeipUtvp75R47wyolfWNOz10coBxLg7peejZeI0eenqepgygNSGG7HqTyT1NlvrwZQ1n9UiSbbXG9Hhx7j1EOJzInWVdhFhysKspMmuBIbkPG6IBU+6Rp2doyODDRft8sRObJIGz3vsjMtN5Pm2FVIQcO1ma05Pl2fnujnB1lN1/d9j/cHVOEpNOx33sz2uh9103PNspPHInxILPTI9DQJGnePFtky0pKsb3ZUpsEhCREbEpzuKDoKksWFCGEiojcB+AxLCYH/VQIYbeI3Fs//gCAjwFYC+BPZHGwrYQQdgLYCOCh+ntpAH8RQni0yW0uHDYYjYxuKZ7lF9tsXGSD8SixYEL7XaTnzGyJEuYlM2QQN4InKcTrpXgjJBMUwAMH2wPMxmgo0gDBXjs2tqHKH4u6ye79wNfIHNd9wYNjhfIvpdfqH3YtEw9ysJvdGEhId8424KppE2e7zczSfh5Z07clShCZNF+5Ld44FgsjlOnWrqBokF9Yp4+lF8iL7IpovOnfo/usQOelyK6VXK4lSkhoQsK3Mo90+Wjs29paMtgf0ALg+p0HG+XnX7y8UX6tqp+z0em4pEwlFNeT1TfmvimbDaOytLleZp42jCoZdzO6JCeYTM2ZehMTcLpHVwLuQgiPAHjEvPcAlX8JwC81OW8/gDfb9x3HcZyVg0dmnwH2skhP0XTOZIhVr01EanXA6GZerzZp/OpneZNmOpbR1+OZlJCnj42Q5tl7/hTN5kzG1dIwqTbImyk3bmIW+Dz2ZjRBtZyaIyladVjziOuwV3uy8WojR5PD2hFrK6BZ+YY4m82Pm89IKrUs7aths9ZyChNOx36a3z8tKeYpm69NqVJcE4+VrS2HVIVJluJh9EZ4KNGeGfmTZLuZ1z/fwoZYLzNNmX4LZiVDasjSANnFSvr5KdHufKmBuHopHNUNlC3R5zlLKqqQM/YaWgDN3Wi2990f1U1JmVVUJhaD0tykKA5FubFDxz95ptql44LiDNRoH4sUqZBOs0NQCgIxA7uKbyDNSXrS5PW3myu9TkZ/Tcl8fPADbSiTmTFbXvaTWiZpnTxQpTSnMWDgsLVlkIqK1CZWRcV7OVf6TQryVHM1SsoIlIWN8fqZaUoLcUy3iYO90qSts3mk5jc2N6QWjF4+P0Gfi2I+krIRFHR9VuUlZkxS6UyMQJ3fRgL/JG0S9GatNilNRiFaHI43kHHjsjsSb1BOaICd1J3BqkJZoASORs2/5yClTOePnzGJHil54h3bYxr0R556m6o3e1W8wbVbdSKoPfMxLXpmmvY9MYK8RII3N0mqpwFth0l4j/gp0mvZ3y3laDtN7ew0cEFxBnjf7ep4/AEnuearBACAyQnFenCeEcm8mVUtsAKaHmjrRcWeIMrmoXXWqXJzT51gjKX5MZ7BxffTC9bbinL6nGhtaymMkHfYSbP3BanBeSWTmdIDNhvEOd4gZ4XStuarIRvbUVhPQWEkeGZ1zJr6jKxT7zmlV5BstM5O0apmvY30JqOy+TquuDZmcX31aLTYpxPdn3fe8AIdi+344nNaa7t2OErKqQwFbI4YQXGc9rUeigNlpaSf6S2bxxvlYy9saJSrwyYGglYR3zm5vVHe+E7t/Di1EO+rhBCA3Eh89qv5+JDY1W9xmLwL1epUtz03GK+RcKYE+7ulCV6NAmWDNY5f4vh+FI7jOE5bfEVxFrB6qWq3eWTvowHt7J8oNz5KuWHSgARKV8D+4mLsIYF8/TmVSK1XT1kXaCbJUcu5aT1jZfsFq5QSs7c271tRIrVWfqxs6sV2DLym7zVzRUL1yE11SqsEVKoPekrtntkglVppmN28dLXcePPoeG4DABTWcTvYZVW3j+M5OP3IaR5lI6RT36RVi4EMGtdsi6qY3rTWX337WFz2/IcdX2+UM282rsIU9v7izGWN8uYevQz75mCMsbhpXZz1//3s9arekUPklzwY75Ub0M/tusE4E58mj7yMyW67rp9WPJPaJlUuxo4rbebzzP7z1L+cz+u0uIyB+PtJyK3deq/xVscJxbnYSO9LPbutC4pzxeScCTTe2IcqNUt6ZTJEw9TjIKGEgo7E7sFNAx0LESkb11Ea59k2kJgAPiGjZX6CjJHWI5ROk9bewcpmkTJqLrUXBBlm+0aNKyWlOC+sp/fX6HqsV1dGWhPA13+4uTBMFaz+nmw5ZGxmW4iF40hKpn1rro7qSptz6cbhmLdpWz6qeYbZ2ALgzu2N0CM8W1rXKG/PazXKMzPRhXVdLl6j33gbcCLAXcdirGxqUAuonp74euGVaIkf2qoF3lwx2ihSdO25f9ZJCxeuj/a+UDS2AsodxqlOCtfpe9Xm4iSEhUNuRn8/1b5c03Jq3hiR2DGEJnRJWg+NgQRHbU5/P5cCLijOA2FeP9zJFK0UaCVSK7UOqlNGNlNPOPCPBYXJWpsfbx7sZQO/EtL1pilWpGZsI5ynKc0bIZlkVP2jZGQstF69qDYYYzFHyLOP/bxJ88XeTdy+7Ix+tPtGyQGAc2pNW8cDugYlX1zYYIzep+gY2SWql+lBeeIULT2M5P1Wsr1RFomrhuvWnlD1tmSiENlbjCuFd/fuUfXe0bOvUT5Vix31+VO3qnrv3xYTAT706k2N8l3XPqfqsb1hdihe78RJ7b5169UHG+WnX43CKjGjS7kQ+3poo96bY75AnmhkXxkc1L+lyZl4DfYO40BRAMBm8qKi5zNntvFLKB5KTc5s0kLjVfU6l4rQcBuF4ziO0xZfUZwHrH4zNUG6GHadtSolgve0CDbVskpbTiuKgnYRzE0299zg6HAAyMyTvzxnrR02W7WyyqbY3O4C6KyrbE9ZrBwfOU5VkZm39hBa5dDHZ28oQKuRuFyy9eZjP5XWxO/AxoCwe7BKl2Ez+LKbLzuvTekVyrqrourpijXj6thsOfbvidm48vjp9Xr/rs+eiG6mtw2/1Cg/VdBpwT8yGJM4f352qFFez36+AE6UokfQlsG4XJs1uVh+cH3MEvvr13+mUf6x796j6h2aiffKZmOnjdyiXWBP/HPcd3zHv9AZaH998+ON8s8/+QuN8uRJbe9LraHdIo/HZ2l2m/GOoiy2p+2KSCTleI0U2dbSs1pFxavwFP3+LpUVhQuKC4Aa6Cm9R1sXPLJDnLYREgsiqpeYOIzsqfjDt3tVMHm2PdC2rdWcCWLi9AkcmGb1vrTUr5k9CRh2F7WuuOzCyvmSbAputfcF+dz3jOvr6RxbHIioB5EqaURS9Bkzc7r/WKComA2jXjo1FgflMbOf9uCmeLN3bY1qo8cnb1T1nnotqnN+aOiVRvnJKS0o+ihQ4wN90f7xo716UP7sdDRaPz8Rt2O9eWha1ds1HtVhH5mI6dvu3P59Ve9EMX7GW7bFe/3l4VtUvcqW2L6JotYh/s7B9zfKl42Q8OrTz8/0TDyvdn0UgKV5LaALNVJdUj6rlAkqVAkx++OxbM6kN6fnp5c+rxwztoyL1K3WBcUFQGWyZAN2hwE+1jje6mEUY4BLKEI8pOkHkhg9LQ/0FIEsxuuJZ99qRbFgZl804wo9+gfM0d08ELNtBNAGd06WCBMhXVwfV1EzW+JnTI+afTBo/wOOYM9PaIGiAuTo83NiPkB7z/DKo++w7ts5+k7SM/rY/NRQo/x1xH0meBc7ALjmspON8sFCNGa/dc0BVW+8EmffTxVjv3xj7iZVb2s2rmz+1Za4enmtqI3PVw/E+w7Sxhr3r9ul6n187Acb5edmYzbaf7ddJ4H+3ckfQyvGF6IA6MvG52lqSguUHVui/Wb/8dgX115xTNWbpZiQ0akYA1JYa/KhVZpPoHijL0B/x9mpOIHK9Or2Vae1sL1YcBuF4ziO0xZfUVxoziFNQKfLWWsbSSj1h0orYlKMgK+fZf292S+DVgBqnwCbfr3GqiJrK6BVBHlOJSYbb3o2qtHUtrMmnUnYQPsTtHmaVfwKtel0lVd8zXuQ29iTKqkmeGtauy2s0HZ/M28w3yNV5VXE3tENqtrQYPxex+ajzuvbiVY93UMz+M+PR0+ntw3sU/XGKtFrqZ8MLHcPP6Xq7VrY3iiPloca5Zma/hxl0gduzMUZ9W5KywEAv3TDNxvlgURnJajSnPUjg1G99p7Kz6p6N6yJKrV/v+0fGuVHJ/Wq6Xsn48pm+00xVuRAarOqp1zI6fvIGHfbnuOUloZWpJl2GRouIlxQXERYgcI5blgtJcb/PnBAYG8ceNNmT4zsDKmvyA4hZTsAkj3AGLqzHPhHxvbUtNk+djwOnIESJEq/SUhXG4rXYNWYjRWhdnCCP5vsL1WoNj1WS1kBQColEjY29oQdBXQwH5CdjJVfqlE8w5xe6C+MR/VGaYjatE332X+dvLNR3jAU9fdffeUaVa+P4iN+5sp/bpTLeX3flwvRFXeABMoDE3qn48dfe2OjvG1oslH+4GVPqnqbM9Gw//lT+hofGIkqsC/PR5XSBy/Xhv1beqK6ba4Wn+Ore7RL8VuujLaS785EW8v8NXqS1JuJz/ixqWh72GzsNaNfid9PpY/yY+Va2+AuJlxQXMSw4FBCxG7qQnmleKiwg3eavEJULEabVZKYjWfyp+IPMzNJ+4xP6B9mdWIyXp4EUSoYj62ZGI2XnaIArAkTe0JGeo7tsMGHvGFUUmqtmeU9LdrtTZLQbkoDB/QglZ2lqG0ystqNi9SueSSJCtt0vfTuaKM4cX2s98bN2vvoxSNRADw3E2f9T4xdrep9cHMc6F8uxNxMk2Wtl79yuLFhJd458gpacZJWMjWzg/LfTt7cKC/QZiJ/tvXbqt4dL/1Eo/zoG7/UKH/frH4nyNsgQ5Gi7938kqp3kjzA1uajB9Pu45epehlarHMwKNLGu+IipSs2ChG5Q0T2iMg+Ebm/yXERkT+qH39ORG7p9FzHcRxneVnyikJEUgA+AeB2LO6fvUtEHg4hsA/d+wDsqP+9FcCfAnhrh+c65xuKxajNRpVF2rrbjjff0vW0eBBWZc1rj63sGKml5uKKokYrCKB1bp2aaVN6Ir7uZd3xmEnhTjaPzFRUWaiUKjArII5XsasmVq9RFG9tQKvG2Duq74S1w1BUMPnzW5sPR63PbaaYlwM6bobVXpVT8djceqMeORRXOc+k44qiZPZ++MfeqFJ6bizq9n/xqm+qeptzcSVznDbd+JVhbRv5tdGobvr6q3r1MtIfv68F6osfnx9S9ebLsY0/ufdHG+V7t3xd1XtyLm7J+t6hGIl+tDys6iUUILOHvKNKRb36E1pEyRguObqheroVwL76bnUQkc8BuAsAD/Z3AfhMCCEA+I6IDInIJgDbOzjXuZBw/MaUVgepcAHeB9wkN1QpR4radTZZiHUDqcBqHe5xbDehSU3GWIQ8x0pMm0CoMqmUpslQbtOokJBTad/bqNd4L3UxxnYhFUhS1Av47ET8zCkaAG3qlMD7gJDNIz1v8huR6SldiPVGj21V9WqUqLAyTUnxTNoTzgO1mQLzXpjT1+OkhZNT8fM+NaZzuK/viZOQn7r6WXXsy4eua5RLldiOwYx+Li7vi3aOa3qjS+xnjr9d1ZsuR0H54mxUI13Rq4MeD8xFl+BpCli13zanqV/zCm/g0ibp2UVENwTFFgCH6PVhLK4azlRnS4fnAgBE5B4A9wBAHr3Nqjhdpjqp/fmVNpaM42HB7KvBg6/N1kmDaq0LGTl5JZKwkDP5tvRJbSLiaU+C6uQkHWgT3Uu+9Elez/LTFOkeMiZ+hXKAJRTnYT3Fqv1xME/PRYFiPbF4dNM2JF3tFO2zsX7zZKM8/S3tbVWk6O4Tb4732vOy9mZikvn4GV8b03tOLFwTp+LZpPUAy0Jp16ta2Ajt1fHsUFzlvHPjflVvU3ayUX7i1I5G+Qu7b1b1BgficzLJebkMuVnOxByf72AmQhcr3bBRNItYsb+qVnU6OXfxzRAeDCHsDCHszODScElzHMdZCXRjRXEYAPtfbAVwtMM62Q7OdVYIaoXBO/DVOl9+d3uzSc61ozy7jNur2neA1QV2r48O1U2qDRS/IsavPj1Fea9sGpWZ2HYpkAuw3dGQFg79o3HFYjPzctxLjXJsVU1sR3ou/uyPjw41ykN6B1aVjXeeorbzZtQoDcX79o7G+xZ/QOeYOn442gdOvKKjwHuO0l7gPxKVDJUpbTfJjsT+ZBXVlw7coOqVaf+Q0gTt6GdygE1VaKVwjDIZGGemHnIcy07RiqJDlelqpxuCYheAHSJyJYAjAO4G8EFT52EA99VtEG8FMBVCGBWRkx2c66xEzkI4XCg63VxGqcpMHq1ObSWt4D3WASBF+1qL2a+5xuoxSqanhDB0+uve0Thw2hgVIfVVdSDet5Yx24ROUvteitfrO26EJo2pavvYLXYPj3gsNxmFa/GgNuyzebj/VXUIPafiZzl081Bsn4kpKSXxs8zside3e6QnlJojNcDb9prULqOk1muzAdXAUXLRJuFfswk7L1KWLChCCBURuQ/AY1hUY38qhLBbRO6tH38AwCMA7gSwD8A8gI+0O3epbXIcCxvB2Q5hBcWS72ODHtmby+TY4j1H2CHgNIM4rTDSxzimwqx4OFqeVi+1tLab9JJAqFAixdyE2bWx2nxFVTWrJqEEfLzxFfbqz1vNxXr9R/W9stNko9kbbQW9Zv+SoDb04kboNnLCSXYisBtkZebjRaq0eKml9QXzJ+L3k0zFlVJtBU6YzgddCbgLITyCRWHA7z1A5QDgo52e6ziO46wcPDLbueS4kHsInIsqy7oAq5gNul6wqVMIzhycmdMqoEovrSJI356ZNq7MlFWYXYB7TQruzFxUlfWMxXMyM1qFxm6+uZMmZQtt4zuwP65YsnNavUaps1Dup/xLPXoFkGGtHmX+7T9q3Kt5/5XeOBzaFUVqjvpi/tJQNzEuKBxnhaMEGwfjtUudMh3VTdlx7faZlKKOJUMBixwAufiajpF9JZ82goK2k01T2pe0qcdtT6bmWh4bfJW2MTWp7tkhYHYz6YpMX3D6+NxUVA9lT+r7ckBoqo/iKGwq/pnYF9VpbaS/FHBB4TiriU49saaiUT1l4gOkECOzWd9uZ8o1NvqToEhMGxJOjDffXLgsXpC8smbNgE0roDwZmG3MSy0f75VdQ7vTlU2215O0UhqneJWTk6peIK83zogc8trbijcfO23Fdwng+1E4juM4bfEVheNchCgvr0mTioVWCrUZ8uAxEfatXKDZWwsAhLf3telcOmjfYqMohxW7B5tswameuBrKD7ZOe8KZiZMTMUCkanKKqSbQvaSsPcVq7SL9LwFcUDjORU51QkfSSYYG9nNQo5y2NW8XUrGwUKqOtc66lxqIacEzJ2jTKqPmSiiYUaWsb9PWGgVpJiYHGCfLvBRxQeE4lxgrXsfexg7De1KnKJ5DTE4xFggdB2JSv1RXeh9dYNxG4TiO47TFVxSO46xKqqdiyvCkx+zN0Q11mNPABYXjOKsT3nDrAgZRXoq46slxHMdpiwsKx3Ecpy0uKBzHcZy2uKBwHMdx2uKCwnEcx2nLkgSFiIyIyFdEZG/9/3CTOttE5B9E5EUR2S0iv0LHfkdEjojIM/W/O5fSHsdxHKf7LHVFcT+Ar4UQdgD4Wv21pQLgN0II1wF4G4CPisj1dPx/hxDeUv/zDYwcx3FWGEsVFHcB+HS9/GkAP2krhBBGQwjfq5dnALwIYMsS7+s4juNcIJYqKDaGEEaBRYEAYEO7yiKyHcDNAJ6kt+8TkedE5FPNVFd07j0i8rSIPF2GR106juNcKM4oKETkqyLyQpO/u87mRiLSD+CvAPxqCOH1zF5/CuANAN4CYBTA/2x1fgjhwRDCzhDCzgxyrao5juM4XeaMKTxCCD/S6piIHBeRTSGEURHZBOBEi3oZLAqJPw8h/DVd+zjV+T8A/u5sGu84juOcf5aqenoYwIfr5Q8D+KKtICIC4P8CeDGE8L/MsU308gMAXlhiexzHcZwus1RB8XEAt4vIXgC3119DRDaLyOseTO8A8CEAP9zEDfb3ReR5EXkOwG0Afm2J7XEcx3G6zJKyx4YQTgF4T5P3jwK4s17+BgCxderHPrSU+zuO4zjnH4/MdhzHcdrigsJxHMdpiwsKx3Ecpy0uKBzHcZy2uKBwHMdx2uKCwnEcx2mLCwrHcRynLS4oHMdxnLa4oHAcx3Ha4oLCcRzHaYsLCsdxHKctLigcx3GctrigcBzHcdrigsJxHMdpiwsKx3Ecpy1LEhQiMiIiXxGRvfX/wy3qHaxvUPSMiDx9tuc7juM4y8dSVxT3A/haCGEHgK/VX7fithDCW0IIO8/xfMdxHGcZWKqguAvAp+vlTwP4yQt8vuM4jnOeWaqg2BhCGAWA+v8NLeoFAI+LyHdF5J5zOB8ico+IPC0iT5dRXGKzHcdxnE45457ZIvJVAJc1OfTbZ3Gfd4QQjorIBgBfEZGXQghPnMX5CCE8COBBABiUkXA25zqO4zjnzhkFRQjhR1odE5HjIrIphDAqIpsAnGhxjaP1/ydE5CEAtwJ4AkBH5zuO4zjLx1JVTw8D+HC9/GEAX7QVRKRPRAZeLwN4L4AXOj3fcRzHWV6WKig+DuB2EdkL4Pb6a4jIZhF5pF5nI4BviMizAJ4C8KUQwqPtznccx3FWDmdUPbUjhHAKwHuavH8UwJ318n4Abz6b8x3HcZyVg0dmO47jOG1xQeE4juO0xQWF4ziO0xYXFI7jOE5bJITVF7smIjMA9ix3O5bAOgBjy92IJbCa27+a2w54+5eb1d7+a0MIA2d70pK8npaRPSa54KpCRJ729i8Pq7ntgLd/ubkY2n8u57nqyXEcx2mLCwrHcRynLatVUDy43A1YIt7+5WM1tx3w9i83l2T7V6Ux23Ecx7lwrNYVheM4jnOBWBWCQkT+QEReEpHnROQhERlqUa/p3tzLzVm0/w4R2SMi+0RkxWwLKyI/IyK7RaQmIi09PlZi/59F21dq3y9pX/rl4kz9KYv8Uf34cyJyy3K0sxUdtP/dIjJV7+9nRORjy9HOZojIp0TkhIi80OL42fd9CGHF/2ExNXm6Xv49AL/Xot5BAOuWu73n0n4AKQCvALgKQBbAswCuX+6219t2HYBrAXwdwM429VZc/3fS9hXe978P4P56+f7V8Ox30p9YTBr6ZQAC4G0Anlzudp9l+98N4O+Wu60t2v8vAdwC4IUWx8+671fFiiKE8HgIoVJ/+R0AW5ezPWdLh+2/FcC+EML+EEIJwOewuKf4shNCeDGEsCoDHDts+4rte6zOfeU76c+7AHwmLPIdAEP1zctWAiv5eTgjYXH30PE2Vc6671eFoDD8AhalYTNa7c29kmjV/i0ADtHrw/X3VhOrof+bsZL7fqn70i8HnfTnSu7zTtv2QyLyrIh8WURuuDBN6wpn3fcrJjK73d7cIYQv1uv8NoAKgD9vcZkl7819rnSh/dLkvQvmktZJ+ztgWfq/C21fsX1/FpdZtme/CZ3057L2+RnopG3fA3BFCGFWRO4E8DcAdpzvhnWJs+77FSMoQpu9uQFARD4M4McBvCfUFW1NrtFqb+7zThfafxjANnq9FcDR7rWwPWdqf4fXWJb+70LbV2zfd2Ff+uWgk/5c1j4/A2dsWwhhmsqPiMifiMi6EMJqyAN11n2/KlRPInIHgN8C8P4QwnyLOu325l5WOmk/gF0AdojIlSKSBXA3FvcUXxWs5P7vgJXc90vdl3456KQ/Hwbw83UPnLcBmHpdxbYCOGP7ReQyEZF6+VYsjqWnLnhLz42z7/vlttB3aMXfh0Wd2jP1vwfq728G8Ei9fBUWvROeBbAbi2qHZW97p+0P0RvhZSx6XKyk9n8Ai7OQIoDjAB5bLf3fSdtXeN+vBfA1AHvr/0dWQ983608A9wK4t14WAJ+oH38ebbzpVmj776v39bNYdFB5+3K3mdr+WQCjAMr1Z/8Xl9r3HpntOI7jtGVVqJ4cx3Gc5cMFheM4jtMWFxSO4zhOW1xQOI7jOG1xQeE4juO0xQWF4ziO0xYXFI7jOE5bXFA4juM4bfn/PVojKNtVWwcAAAAASUVORK5CYII=\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "from astroML.density_estimation import KNeighborsDensity\n", "\n", "nneighbors=5 # number of neighbors for smoothing\n", "knd=KNeighborsDensity('bayesian',nneighbors)\n", "knd.fit(X)\n", "\n", "# again, evaluate on our grid and display as an image\n", "dens=np.array(knd.eval(xy)).reshape(xg.shape)\n", "dens=np.log(dens)\n", "\n", "plt.imshow(dens,origin='lower',interpolation='nearest',extent=(-2.5,1,-0.6,0.8),aspect='equal',\n", " vmin=5,vmax=12)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Describe your results and preferred values.\n", "
ANSWER HERE: " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "OK, now let's look at a parametric estimator, Gaussian mixtures, see http://scikit-learn.org/stable/modules/mixture.html. Here we are going to try multiple numbers of components and calculate the AIC and BIC for each, for comparison." ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "n 1 BIC -8100.666066722 AIC -8175.610617813136\n", "n 3 BIC -11147.16671422455 AIC -11303.868957415107\n", "n 5 BIC -11804.10889514543 AIC -12042.568830435406\n", "n 7 BIC -11884.675341816775 AIC -12204.892969206172\n", "n 9 BIC -11859.900058272846 AIC -12261.875377761664\n", "n 11 BIC -11840.29597914924 AIC -12324.028990737477\n", "n 13 BIC -11792.370892698773 AIC -12357.861596386432\n", "n 15 BIC -11749.547858008935 AIC -12396.796253796014\n", "n 17 BIC -11706.934039339092 AIC -12435.940127225593\n", "n 19 BIC -11654.200359971679 AIC -12464.9641399576\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "from sklearn.mixture import GaussianMixture\n", "\n", "# array of number of gaussian components to try\n", "ngauss=np.arange(1,20,2)\n", "\n", "nplots=len(ngauss)\n", "# setup plot grid\n", "fig,ax=plt.subplots(nplots//3+1,3,figsize=(16,12))\n", "fig.subplots_adjust(hspace=0.001,wspace=0.001)\n", "\n", "# initialize accumulators for AIC and BIC\n", "aic=[]\n", "bic=[]\n", "\n", "# loop over the different numbers of components\n", "for iplot,n in enumerate(ngauss) :\n", " gmm=GaussianMixture(n+1)\n", " gmm.fit(X)\n", " dens=gmm.score_samples(xy).reshape(xg.shape)\n", " \n", " # calculate and store AIC and BIC\n", " print('n',n,'BIC',gmm.bic(X),'AIC',gmm.aic(X))\n", " aic.append(gmm.aic(X))\n", " bic.append(gmm.bic(X))\n", "\n", " # show the mixture model\n", " ax[iplot//3,iplot%3].imshow(dens,origin='lower',interpolation='nearest',extent=(-2.5,1,-0.6,0.8),\n", " aspect='equal',vmin=-5,vmax=2)\n", " # plot the location of the component centers\n", " ax[iplot//3,iplot%3].plot(gmm.means_[:,0],gmm.means_[:,1],'ro')\n", " \n", "\n", "#plot AIC/BIC vs number of components\n", "plt.figure()\n", "plt.plot(ngauss,aic,label='AIC')\n", "plt.plot(ngauss,bic,label='BIC')\n", "plt.legend()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "How many components are preferred by AIC/BIC? How many components do you prefer?\n", "
ANSWER HERE: " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "OK, now we try extreme deconvolution, which attempts to get an underlying gaussian mixture which, when convolved with uncertainties, matches the observed data. Now we have to pass a covariance matrix for each point; for simplicity here, we take a simple covariance matrix with an uncertainty of 0.02 in each coordinate. See http://www.astroml.org/user_guide/density_estimation.html#extreme-deconvolution\n", "\n", "

\n", "WARNING: This can take some time!" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "scrolled": true }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/holtz/anaconda3/lib/python3.7/site-packages/sklearn/mixture/_base.py:282: ConvergenceWarning: Initialization 1 did not converge. Try different init parameters, or increase max_iter, tol or check for degenerate data.\n", " ConvergenceWarning,\n" ] }, { "data": { "text/plain": [ "XDGMM(n_components=3)" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from astroML.density_estimation import XDGMM\n", "\n", "# set number of components\n", "n_components=3\n", "xdgmm = XDGMM(n_components=n_components)\n", "nobs=X.shape[0]\n", "\n", "# set covariance matrix for uncertainties\n", "Xerr = np.zeros([nobs,2,2])\n", "Xerr[:] = np.diag([0.02,0.02])\n", "xdgmm.fit(X, Xerr)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Plot the results, both as samples drawn from the extreme deconvolution model, as well as the model ellipses themselves." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/holtz/anaconda3/envs/pyvista/lib/python3.9/site-packages/astroML/linear_model/linear_regression_errors.py:10: UserWarning: LinearRegressionwithErrors requires PyMC3 to be installed\n", " warnings.warn('LinearRegressionwithErrors requires PyMC3 to be installed')\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[[-0.41364984 0.1947744 ]\n", " [-1.17557249 0.24075951]\n", " [ 0.0819235 0.05999104]]\n" ] }, { "data": { "image/png": "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", "text/plain": [ "

" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# data on top\n", "fig,ax=plt.subplots(2,1,sharex=True,sharey=True)\n", "ax[0].scatter(X[:,0],X[:,1],s=2)\n", "ax[0].set_xlim(-2.5,1)\n", "ax[0].set_ylim(-0.3,0.5)\n", "\n", "# sammpling from mmodel\n", "dens=xdgmm.sample(nobs)\n", "ax[1].scatter(dens[:,0],dens[:,1],s=2)\n", "\n", "from astroML.plotting.tools import draw_ellipse\n", "for i in range(n_components) :\n", " draw_ellipse(xdgmm.mu[i],xdgmm.V[i],scales=[2],ax=ax[1],ec='k',fc='gray',alpha=0.4)\n", "\n", "print(xdgmm.mu)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "What do you think about the results:\n", "
ANSWER HERE: " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "OK, now let's try some clustering routines, specifically, K means. Remember, for K means you need to specify the number of clusters for it to separate object into. We will use the sklean.cluster.KMeans() routine.\n", "

\n", "Experiment with different numbers of clusters." ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/holtz/anaconda3/envs/pyvista/lib/python3.9/site-packages/sklearn/cluster/_kmeans.py:1412: FutureWarning: The default value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n_init` explicitly to suppress the warning\n", " super()._check_params_vs_input(X, default_n_init=10)\n" ] }, { "data": { "text/plain": [ "(-0.5, 0.8)" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "

" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from sklearn.cluster import KMeans\n", "n_clusters=9\n", "clf=KMeans(n_clusters=n_clusters)\n", "clf.fit(X)\n", "centers=clf.cluster_centers_\n", "#print(centers)\n", "labels=clf.predict(X)\n", "\n", "#set up an array of color/point types to cycle through for different clusters\n", "color=['ro','go','bo','co','yo','mo','bo','r^','g^','b^','c^','y^','m^','b^']\n", "for i in range(n_clusters) :\n", " gd=np.where(labels == i)[0]\n", " plt.plot(X[gd,0],X[gd,1],color[i])\n", "plt.ylim(-0.5,0.8)\n", " " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "What do you think about the results?\n", "
ANSWER HERE: " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Try the MeanShift routine. Here it will choose the number of clusters, but you have to choose the bandwidth, which will affect the results.\n", "

\n", "WARNING: can take a long time!" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "6722\n", "37\n" ] }, { "ename": "ValueError", "evalue": "s must be a scalar, or float array-like with the same size as x and y", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[15], line 10\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(\u001b[38;5;28mlen\u001b[39m(centers)) :\n\u001b[1;32m 9\u001b[0m gd \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mwhere(labels \u001b[38;5;241m==\u001b[39m i)[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m---> 10\u001b[0m \u001b[43mplt\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mscatter\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m[\u001b[49m\u001b[43mgd\u001b[49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43mX\u001b[49m\u001b[43m[\u001b[49m\u001b[43mgd\u001b[49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43mcolor\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[38;5;241;43m%\u001b[39;49m\u001b[38;5;241;43m14\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/anaconda3/envs/pyvista/lib/python3.9/site-packages/matplotlib/pyplot.py:2862\u001b[0m, in \u001b[0;36mscatter\u001b[0;34m(x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, edgecolors, plotnonfinite, data, **kwargs)\u001b[0m\n\u001b[1;32m 2857\u001b[0m \u001b[38;5;129m@_copy_docstring_and_deprecators\u001b[39m(Axes\u001b[38;5;241m.\u001b[39mscatter)\n\u001b[1;32m 2858\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mscatter\u001b[39m(\n\u001b[1;32m 2859\u001b[0m x, y, s\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, c\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, marker\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, cmap\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, norm\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m 2860\u001b[0m vmin\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, vmax\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, alpha\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, linewidths\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m,\n\u001b[1;32m 2861\u001b[0m edgecolors\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, plotnonfinite\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m, data\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m-> 2862\u001b[0m __ret \u001b[38;5;241m=\u001b[39m \u001b[43mgca\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mscatter\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 2863\u001b[0m \u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43ms\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43ms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mc\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmarker\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmarker\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcmap\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcmap\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnorm\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnorm\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2864\u001b[0m \u001b[43m \u001b[49m\u001b[43mvmin\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvmin\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvmax\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvmax\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43malpha\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43malpha\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlinewidths\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlinewidths\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2865\u001b[0m \u001b[43m \u001b[49m\u001b[43medgecolors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43medgecolors\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mplotnonfinite\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mplotnonfinite\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2866\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mdata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[43m}\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2867\u001b[0m sci(__ret)\n\u001b[1;32m 2868\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m __ret\n", "File \u001b[0;32m~/anaconda3/envs/pyvista/lib/python3.9/site-packages/matplotlib/__init__.py:1446\u001b[0m, in \u001b[0;36m_preprocess_data..inner\u001b[0;34m(ax, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1443\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 1444\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minner\u001b[39m(ax, \u001b[38;5;241m*\u001b[39margs, data\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 1445\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m data \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1446\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[43max\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mmap\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43msanitize_sequence\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1448\u001b[0m bound \u001b[38;5;241m=\u001b[39m new_sig\u001b[38;5;241m.\u001b[39mbind(ax, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 1449\u001b[0m auto_label \u001b[38;5;241m=\u001b[39m (bound\u001b[38;5;241m.\u001b[39marguments\u001b[38;5;241m.\u001b[39mget(label_namer)\n\u001b[1;32m 1450\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m bound\u001b[38;5;241m.\u001b[39mkwargs\u001b[38;5;241m.\u001b[39mget(label_namer))\n", "File \u001b[0;32m~/anaconda3/envs/pyvista/lib/python3.9/site-packages/matplotlib/axes/_axes.py:4587\u001b[0m, in \u001b[0;36mAxes.scatter\u001b[0;34m(self, x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, edgecolors, plotnonfinite, **kwargs)\u001b[0m\n\u001b[1;32m 4583\u001b[0m s \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mma\u001b[38;5;241m.\u001b[39mravel(s)\n\u001b[1;32m 4584\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\u001b[38;5;28mlen\u001b[39m(s) \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m (\u001b[38;5;241m1\u001b[39m, x\u001b[38;5;241m.\u001b[39msize) \u001b[38;5;129;01mor\u001b[39;00m\n\u001b[1;32m 4585\u001b[0m (\u001b[38;5;129;01mnot\u001b[39;00m np\u001b[38;5;241m.\u001b[39missubdtype(s\u001b[38;5;241m.\u001b[39mdtype, np\u001b[38;5;241m.\u001b[39mfloating) \u001b[38;5;129;01mand\u001b[39;00m\n\u001b[1;32m 4586\u001b[0m \u001b[38;5;129;01mnot\u001b[39;00m np\u001b[38;5;241m.\u001b[39missubdtype(s\u001b[38;5;241m.\u001b[39mdtype, np\u001b[38;5;241m.\u001b[39minteger))):\n\u001b[0;32m-> 4587\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 4588\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124ms must be a scalar, \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 4589\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mor float array-like with the same size as x and y\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 4591\u001b[0m \u001b[38;5;66;03m# get the original edgecolor the user passed before we normalize\u001b[39;00m\n\u001b[1;32m 4592\u001b[0m orig_edgecolor \u001b[38;5;241m=\u001b[39m edgecolors\n", "\u001b[0;31mValueError\u001b[0m: s must be a scalar, or float array-like with the same size as x and y" ] }, { "data": { "image/png": "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", "text/plain": [ "

" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from sklearn.cluster import MeanShift\n", "ms = MeanShift(bandwidth=0.1)\n", "ms.fit(X)\n", "centers=ms.cluster_centers_\n", "labels=ms.labels_\n", "print(len(labels))\n", "print(len(centers))\n", "for i in range(len(centers)) :\n", " gd = np.where(labels == i)[0]\n", " plt.scatter(X[gd,0],X[gd,1],color[i%14])\n", " " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ " What do you think about the results?\n", "
ANSWER HERE: " ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.7.11" } }, "nbformat": 4, "nbformat_minor": 4 }