diff --git a/notebooks/ensemble-feature-importance.ipynb b/notebooks/ensemble-feature-importance.ipynb index dea100f7..6341a904 100644 --- a/notebooks/ensemble-feature-importance.ipynb +++ b/notebooks/ensemble-feature-importance.ipynb @@ -225,7 +225,7 @@ }, { "cell_type": "code", - "execution_count": 69, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -238,13 +238,13 @@ " )" ] }, - "execution_count": 69, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -264,39 +264,30 @@ }, { "cell_type": "code", - "execution_count": 66, + "execution_count": 5, "metadata": {}, "outputs": [ { - "ename": "ValueError", - "evalue": "Multi-dimensional indexing (e.g. `obj[:, None]`) is no longer supported. Convert to a numpy array before indexing instead.", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", - "Input \u001b[0;32mIn [66]\u001b[0m, in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43msns\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkdeplot\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43miris\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msepal_length\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/seaborn/distributions.py:1701\u001b[0m, in \u001b[0;36mkdeplot\u001b[0;34m(data, x, y, hue, weights, palette, hue_order, hue_norm, color, fill, multiple, common_norm, common_grid, cumulative, bw_method, bw_adjust, warn_singular, log_scale, levels, thresh, gridsize, cut, clip, legend, cbar, cbar_ax, cbar_kws, ax, **kwargs)\u001b[0m\n\u001b[1;32m 1697\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m p\u001b[38;5;241m.\u001b[39munivariate:\n\u001b[1;32m 1699\u001b[0m plot_kws \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mcopy()\n\u001b[0;32m-> 1701\u001b[0m \u001b[43mp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplot_univariate_density\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1702\u001b[0m \u001b[43m \u001b[49m\u001b[43mmultiple\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmultiple\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1703\u001b[0m \u001b[43m \u001b[49m\u001b[43mcommon_norm\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcommon_norm\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1704\u001b[0m \u001b[43m \u001b[49m\u001b[43mcommon_grid\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcommon_grid\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1705\u001b[0m \u001b[43m \u001b[49m\u001b[43mfill\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfill\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1706\u001b[0m \u001b[43m \u001b[49m\u001b[43mcolor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcolor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1707\u001b[0m \u001b[43m \u001b[49m\u001b[43mlegend\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlegend\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1708\u001b[0m \u001b[43m \u001b[49m\u001b[43mwarn_singular\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mwarn_singular\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1709\u001b[0m \u001b[43m \u001b[49m\u001b[43mestimate_kws\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mestimate_kws\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1710\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mplot_kws\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1711\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1713\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1715\u001b[0m p\u001b[38;5;241m.\u001b[39mplot_bivariate_density(\n\u001b[1;32m 1716\u001b[0m common_norm\u001b[38;5;241m=\u001b[39mcommon_norm,\n\u001b[1;32m 1717\u001b[0m fill\u001b[38;5;241m=\u001b[39mfill,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1727\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m 1728\u001b[0m )\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/seaborn/distributions.py:991\u001b[0m, in \u001b[0;36m_DistributionPlotter.plot_univariate_density\u001b[0;34m(self, multiple, common_norm, common_grid, warn_singular, fill, color, legend, estimate_kws, **plot_kws)\u001b[0m\n\u001b[1;32m 988\u001b[0m artist \u001b[38;5;241m=\u001b[39m ax\u001b[38;5;241m.\u001b[39mfill_between(support, fill_from, density, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39martist_kws)\n\u001b[1;32m 990\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 991\u001b[0m artist, \u001b[38;5;241m=\u001b[39m \u001b[43max\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplot\u001b[49m\u001b[43m(\u001b[49m\u001b[43msupport\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdensity\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[43martist_kws\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 993\u001b[0m artist\u001b[38;5;241m.\u001b[39msticky_edges\u001b[38;5;241m.\u001b[39mx[:] \u001b[38;5;241m=\u001b[39m sticky_support\n\u001b[1;32m 994\u001b[0m artist\u001b[38;5;241m.\u001b[39msticky_edges\u001b[38;5;241m.\u001b[39my[:] \u001b[38;5;241m=\u001b[39m sticky_density\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/axes/_axes.py:1632\u001b[0m, in \u001b[0;36mAxes.plot\u001b[0;34m(self, scalex, scaley, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1390\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 1391\u001b[0m \u001b[38;5;124;03mPlot y versus x as lines and/or markers.\u001b[39;00m\n\u001b[1;32m 1392\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1629\u001b[0m \u001b[38;5;124;03m(``'green'``) or hex strings (``'#008000'``).\u001b[39;00m\n\u001b[1;32m 1630\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 1631\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m cbook\u001b[38;5;241m.\u001b[39mnormalize_kwargs(kwargs, mlines\u001b[38;5;241m.\u001b[39mLine2D)\n\u001b[0;32m-> 1632\u001b[0m lines \u001b[38;5;241m=\u001b[39m [\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_lines(\u001b[38;5;241m*\u001b[39margs, data\u001b[38;5;241m=\u001b[39mdata, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)]\n\u001b[1;32m 1633\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m line \u001b[38;5;129;01min\u001b[39;00m lines:\n\u001b[1;32m 1634\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39madd_line(line)\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/axes/_base.py:312\u001b[0m, in \u001b[0;36m_process_plot_var_args.__call__\u001b[0;34m(self, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m 310\u001b[0m this \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m args[\u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m 311\u001b[0m args \u001b[38;5;241m=\u001b[39m args[\u001b[38;5;241m1\u001b[39m:]\n\u001b[0;32m--> 312\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_plot_args\u001b[49m\u001b[43m(\u001b[49m\u001b[43mthis\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/axes/_base.py:487\u001b[0m, in \u001b[0;36m_process_plot_var_args._plot_args\u001b[0;34m(self, tup, kwargs, return_kwargs)\u001b[0m\n\u001b[1;32m 484\u001b[0m kw[prop_name] \u001b[38;5;241m=\u001b[39m val\n\u001b[1;32m 486\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(xy) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m2\u001b[39m:\n\u001b[0;32m--> 487\u001b[0m x \u001b[38;5;241m=\u001b[39m \u001b[43m_check_1d\u001b[49m\u001b[43m(\u001b[49m\u001b[43mxy\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 488\u001b[0m y \u001b[38;5;241m=\u001b[39m _check_1d(xy[\u001b[38;5;241m1\u001b[39m])\n\u001b[1;32m 489\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/cbook/__init__.py:1327\u001b[0m, in \u001b[0;36m_check_1d\u001b[0;34m(x)\u001b[0m\n\u001b[1;32m 1321\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m warnings\u001b[38;5;241m.\u001b[39mcatch_warnings(record\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m w:\n\u001b[1;32m 1322\u001b[0m warnings\u001b[38;5;241m.\u001b[39mfilterwarnings(\n\u001b[1;32m 1323\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124malways\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 1324\u001b[0m category\u001b[38;5;241m=\u001b[39m\u001b[38;5;167;01mWarning\u001b[39;00m,\n\u001b[1;32m 1325\u001b[0m message\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mSupport for multi-dimensional indexing\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m-> 1327\u001b[0m ndim \u001b[38;5;241m=\u001b[39m \u001b[43mx\u001b[49m\u001b[43m[\u001b[49m\u001b[43m:\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m]\u001b[49m\u001b[38;5;241m.\u001b[39mndim\n\u001b[1;32m 1328\u001b[0m \u001b[38;5;66;03m# we have definitely hit a pandas index or series object\u001b[39;00m\n\u001b[1;32m 1329\u001b[0m \u001b[38;5;66;03m# cast to a numpy array.\u001b[39;00m\n\u001b[1;32m 1330\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(w) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/pandas/core/indexes/base.py:5385\u001b[0m, in \u001b[0;36mIndex.__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m 5383\u001b[0m \u001b[38;5;66;03m# Because we ruled out integer above, we always get an arraylike here\u001b[39;00m\n\u001b[1;32m 5384\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m result\u001b[38;5;241m.\u001b[39mndim \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m-> 5385\u001b[0m \u001b[43mdisallow_ndim_indexing\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresult\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 5387\u001b[0m \u001b[38;5;66;03m# NB: Using _constructor._simple_new would break if MultiIndex\u001b[39;00m\n\u001b[1;32m 5388\u001b[0m \u001b[38;5;66;03m# didn't override __getitem__\u001b[39;00m\n\u001b[1;32m 5389\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_constructor\u001b[38;5;241m.\u001b[39m_simple_new(result, name\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_name)\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/pandas/core/indexers/utils.py:341\u001b[0m, in \u001b[0;36mdisallow_ndim_indexing\u001b[0;34m(result)\u001b[0m\n\u001b[1;32m 333\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 334\u001b[0m \u001b[38;5;124;03mHelper function to disallow multi-dimensional indexing on 1D Series/Index.\u001b[39;00m\n\u001b[1;32m 335\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 338\u001b[0m \u001b[38;5;124;03min GH#30588.\u001b[39;00m\n\u001b[1;32m 339\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 340\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m np\u001b[38;5;241m.\u001b[39mndim(result) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m--> 341\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 342\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMulti-dimensional indexing (e.g. `obj[:, None]`) is no longer \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 343\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msupported. Convert to a numpy array before indexing instead.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 344\u001b[0m )\n", - "\u001b[0;31mValueError\u001b[0m: Multi-dimensional indexing (e.g. `obj[:, None]`) is no longer supported. Convert to a numpy array before indexing instead." - ] + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" }, { "data": { - "image/png": "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", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAu4AAAH0CAYAAABiuKiqAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAB7CAAAewgFu0HU+AABo+klEQVR4nO3dd1ibZ57v/4/oxgUB7h25x44dAy6pk8QiZUomk6B42k6NIcns7J6dAsd79pzt6+CZ3Z2d385OgMxOLzYkmU1mUgxOrzYo7rEdI+y4F0CAsen6/eGRzCOKKUKPyvt1XVyO7kd69DXE6KNb3+e+LR6PxyMAAAAAIS3G7AIAAAAAXBvBHQAAAAgDBHcAAAAgDBDcAQAAgDBAcAcAAADCAMEdAAAACAMEdwAAACAMENwBAACAMEBwBwAAAMIAwR0AAAAIAwR3AAAAIAwQ3AEAAIAwQHAHAAAAwgDBHQAAAAgDBHcAAAAgDBDcAQAAgDBAcAcAAADCQJzZBWDoWltbtXfvXknSpEmTFBfHjxEAACCUdHZ26vz585Kk66+/XklJSSM+J4kvDO3du1erV682uwwAAAAMwo4dO7Rq1aoRn4dWGQAAACAMMOMehiZNmuT77x07dmjatGkmVgMAAAB/p0+f9nVI9MxuI0FwD0M9e9qnTZummTNnmlgNAAAABhKo6xGjqlWmpKREOTk5ys/Pl8PhkMPhkNPpHJXnysrKGrVzAwAAIPpEzYy7w+GQy+XS9u3bZbVaJUkul0tZWVkqKipSXl5ewJ6rsLCQ0A4AAICAiorgXlJSovLycjU0NPhCuyTZbDaVlpbK4XAoOztbmZmZI34up9OpzZs3j/g8AAAAQE9R0SpTWFgou91uCO1eubm5vvsE6rkC8QYAAAAA6Cnig7vT6ZTb7R4wTGdmZqqyslJut3tEz1VYWKjCwkKlpaWN6DwAAACAv4gP7lu2bJEkpaen93sfb9CurKwc9vO4XC653W7Z7fZhnwMAAADoT8QHd28Y76tNxst7bOfOncN+nvz8fBUXFw/78QAAAMBAIj64e9tfBmpf8R4bbqvM5s2bA9YjDwAAAPQl4leVqa+vH5X7erlcLtXU1KigoGDIj+3PiRMnBjx++vTpgD0XAAAAwkPEB/fRlp+fr7KysoCec9asWQE9HwAAAMJfxLfKjCZvi8xA/fMAAABAIET8jHtaWprcbveg2mCGsozjaLTIeB0/fnzA46dPn9bq1asD/rwAAAAIXREf3AczG+4N9UOZOR+NFhmvmTNnjsp5AQAAEL4iPrhnZ2fL6XSqpqam3/u4XC5J0qpVqwZ1TqfTqaqqKmVlZQ14vnXr1vlm8Qd6fgAIlLbOLh2ru6SacxflutCiM42tOt3YqvPNrWpq7VRza4cutXeps9uj7m6PYiwWJcbFKDE+RuOT4jVxXIImjktU+p/+nDguUTNTxyhj4ljNsI5RXCwdlgBglogP7jk5OSopKRlwqUfvsdzc3EGdMzMzUw0NDf0eT01Nldvt1vbt2wfcsRUARsLj8aj2Qot2HXfr/Y/cev94gw6eblZnt2coZ1F7V7ea26QLF9tVe6Gl33vGx1o0KzVZc9KTlTFxnBZNHadFUydo4ZRxSk6I+JcTADBdxP+m9Ybx/nZFdbvdcrlcBGwAIc/j8ch1oUWvHz6vNz+8oOqPGuS+1BG05+/ouvL8rgsteuXQed+4xSLNSUvWoqnjtWjqBC2eOl6Lpo7X3PSxio2xBK0+AIh0ER/cJamoqEiFhYVyuVyy2WyGY1u3bpUklZaW9nqcy+WSw+FQdnb2sHZFHc668ADQU1Nrh94+ckGvHb6g1w+f10n3ZbNL6sXjkY7WXdLRukt6af9Z33hyQqyWTp+g62dYtXxmiq6fmaKM9LGKIcwDwLBERXAvKCjQzp07lZOTo+rqat9FqE6nU4WFhSoqKupzxr24uFhOp1NOp1P5+fmDmpV3u92+1htvrzsADFZXt0d7Tzbq9cPn9frh83r/uFtdQ2p9uWLKhETZJo7TrLQxmpoyRlMmJCo1OUHjk+I0NjFOcTEWxVgs8niu9MW3dnTLfblddRfbdeFimy5cbNP55nada27V0QstamrtHHINl9q7tPNog3YevdpaOC4xTkunT/hTkLdq9dw0TU1JGvK5ASAaWTwez9BfEcJUSUmJysrKZLPZVF9fL7fbrcLCQtnt9j7v73Q65XA4ZLPZVFFRMeC5N2/erOLiYsMsu9vtls1mk9VqVXV1dcD+HidOnPBt0nT8+HFWoQHCmLf95T1Xvd6uuaA3j1wYcvvLpPGJWjnLqpWzU3XDLKuWzpigCUnxAa3RfalDtXUtOnrhyteR8xd18Eyzjl5o0TDeVxjMTU/WWlu674sgDyASjEZei6rgHikI7kD46uzqVs35Fu08Wq/3auv1rqtO55vbhnSOyeMTddvCSbp1wURlz03T9JQkWSzmtJ+0dnTpw7MX9cGZJh0606xDZ5p18EyTLlxsH/Y5bRPH6s7Fk5Vz3RRlzUllJRsAYWk08lpUtMoAQLC1d3br/MU2Ha+/pA9ON+mD0006cLpJh89eVHtn95DOlRAXozUZabp1wUTdtnCSFk0Zb1pQ95cUH6vr/9S/3tO55lbtP9mkPScatfekW3tONOrcIN+guC60yPVmrZ58s1bpYxP0qRXT9ZmVM7R8ZkrI/L0BwAwEdwAYgrbOLp1ratO55jadb27V2aY2nfP92aZzTa0619ym+pbhzzhL0vzJ43Tbgkm6beFErclI15iE2AD9DYJj8vgkTV6cpDsWT/aNnW1q1d4TjdpzslF7TrjlPNZwzd75upZ2/ezto/rZ20e1cMo4ffmmufrMyhksPwkgKtEqE4ZolQFGV0tbp/adbLzSw13XomN1l3Sy4bLONreO2vKLUyYkaq0tXTfa0nXrwkmaYR0zKs8TSrq6PfrgdJPeddXpXVe9dtTWDeoi2AlJcfri2jnKu80ma3JCECoFgKGjxx2SCO5AoHV2dWvn0QZVHDirt45c0Ifnmkd8weW1TE9J0uqMNN8FmXPSk6O+DaSr26P9pxpV+cE5VR44qwOnmwa8//jEOD18q01fu2WuxgfwYlwACASCOyQR3IFAOVbXop+9fVTPvH9y1GbSE+JiNH/SOC2ZNkFLpo3XddMnaMnUCUody0zxtdReaNEz75/U798/qY/qL/V7v8njE/V/P3mdPrl8WtS/+QEQOgjukERwB0bqwKkm/XvlYVV+cFbD/Q2YEBejKRMSNXl8ku/Pyd4/xydqyoQrf1qT4wmTI9Td7dGbRy7oZ28f1csHz/V7v1sXTNQ/33+9ZqcnB7E6AOgbq8oAwAg0XurQv1Uc0i/fPXbNVpjYGIsWThmvhVPGaU5asmalJWtayhhNnpCoKeOTNGFMHIE8SGJiLLpt4STdtnCSas5f1H9Ufqjn9pzq9abrjQ8v6OM/fEP/dP8y3b9yhjnFAsAoIrgDiAqVB86q8Kk9qhtgtZdlMybIvmSKbl0wUUunpygpPrxWcokG8yaN0w8/t1KP3TFPj79wUK8eOm84frGtU/9ryy69/uF5/eOnl2lsIi9zACIHv9EARLSubo9+UHlY/9/LR/o8Pj4pTp9dNUt/tnYuLRZhZPHUCfrpV1bpxX1n9PfPHdCZplbD8aedJ/XB6Wb95MvZmh4FK/QAiA4EdwARq/Fyh7752/f1+uHzvY4lxsXosdvn6+u3Zmgcs7JhyWKx6N7rp+nWhZP098/uV1n1CcPxD0436f4fvaWffHlVrw2iACAcsY80gIjUeLlDX/rJe32GdvuSKar81sf0l/YFhPYIMC4xTt9zrNB/fPaGXj/Pc81teqj4Hb1yqP+LWgEgXBDcAUQcb2jffaLRMB4XY9H/++R1Kv1Slmal0RYTaT59www9981bZJs41jB+uaNL+b+o1ssHz5pUGQAEBsEdQERpbu07tE8cl6jfbFirr92SwWowESxj4lg9/dhNWmtLM4y3d3Ur/5fVqjxAeAcQvgjuACJGd7dHf7Vld6/QPnl8orbmr9XqjLR+HolIYk1O0C++tkb33zDdMN7R5dGjv67Wa320TwFAOCC4A4gYP9j+oSo/MM6oTh6fqN/lrZVt0jiTqoIZEuJi9K8P3aAHM40bnnR0efTYr6q1/1RjP48EgNBFcAcQEV7cd0Y/3P6hYSw1OV6/JbRHrdgYizbnLpcjyxjeW9q79NWf7tRJ92WTKgOA4SG4Awh7Ry+06NtbdxnGYmMs+tHnMzWP0B7VYmMsKnpwuT61wtg2c665TV/57x1qau0wqTIAGDqCO4Cw1t3t0XfLd6ulvcsw/n8+vkQ3zZ9oUlUIJTExFn3fsbzXNQ4fnruogrI98ng8JlUGAENDcAcQ1n769lHtPNpgGHsgc4a+evNccwpCSEqMi1Xpn2Vr/mTjJzAv7j+jJ9+oNakqABgagjuAsFV7oUXfe+mgYWx2WrL+6f5lLPmIXlKS4/XTr6ySNTneMP74iwf1nqvOpKoAYPAI7gDCUne3R98t263Wjm7DeNGDy5WcwG6o6NustGT9YP0N6vm+rqvboz//7fuqu9hmXmEAMAgEdwBh6en3T6rqmLFF5ss3ztGN89JNqgjh4vZFk/WX6xYYxs43t+mvn9lLvzuAkEZwBxB2LrV39tkiU3jvYpMqQrj5izsX6LaFkwxjL+0/q6edJ02qCACujeAOIOw88ZpLZ5uMbQ1/f99SWmQwaDExFv2rY4XSxiYYxv/u2f2s7w4gZBHcAYSV042XVfJ6jWHs1gUTdfuiSf08AujbpPGJ+pfPXG8Ya27r1HfLdtMyAyAkEdwBhJXNLx4yXJAaY5H+5hPXsYoMhuWeZVP1YKZxZ9W3a+pUXn3CpIoAoH8EdwBh4/DZZv1+l7EH+XOrZ2vR1PEmVYRI8Lf3XacZ1jGGsX95/gM1tLSbVBEA9I3gDiBs/OfLR9Szg2F8Ypz+KmeheQUhIkxIitc/3b/MMNZwqUObXvjApIoAoG8EdwBhwXX+ov6w55Rh7Ks3z9XEcYkmVYRIcsfiybp32VTD2NaqE9pRW29SRQDQG8EdQFj40Ss16u4x2z42IVZfuyXDvIIQcf72U0s1NiHWMPY3v9+rzq7ufh4BAMFFcAcQ8j6qu9Srt/1LN82VNTmhn0cAQzc1JUnfvmuRYezw2YvaUnXcpIoAwIjgDiDk/fi1I+rqMd0+Jj5WDzPbjlHwpRvnaMm0CYaxf684rObWDpMqAoCrCO4AQtqFi216qto42/6FNbOVTm87RkFcbIz+5hNLDGMXLrbrx6/W9PMIAAgegjuAkPbb9z5Se48e44TYGOXdZjOxIkS6m+dPlH3JZMPYk2/W6kTDJZMqAoArCO4AQlZHV7d++e4xw9inVkzX5AlJJlWEaLHx40sUF3N1U6/2zm5976VDJlYEAAR3ACHshX1ndK65zTD2lZvmmlMMosq8SeP0xbVzDGPP7j6lQ2eaTaoIAAjuAELYT9+qNdzOnpOq62emmFQNos1frlug8Ylxvtsez5ULVQHALAR3ACFp13G33v/IbRj76s2sJIPgSR2boK/favx/7sX9Z7T3RKNJFQGIdgR3ACHpF28fNdyelpKku5ZOMacYRK2v3ZIha3K8YexfK+h1B2AOgjuAkNN4uUN/3HvaMPbFtXMUH8uvLATXhKR45d82zzD26qHzqjpab1JFAKIZr4IAQs6zu0+prfPqEpBxMRatXzXLxIoQzb580xxN9Ns34IcvHzGpGgDRjOAOIORs3WncYt6+ZEqv4AQES3JCnB673Tjr/vrh89pzwm1OQQCiFsEdQEg5cKpJe08aL/5jth1m+/ya2Zo4LsEw9l+vsJsqgOAiuAMIKVurjLPtUyYk6tYFE02qBrgiKT5WX7/FuGPvi/vP6MOzrOsOIHgI7gBCRltnl36/66RhLDdrpuK4KBUh4ItrZ2tCUpxh7MevMusOIHh4NQQQMrbtPyv3pQ7D2EPZtMkgNIxPiu+1c+//7D6l4/WXzCkIQNQhuAMIGc+8b5xtX2tL05z0sSZVA/T2lZszNCY+1ne7q9ujn7xZO8AjACBwCO4AQkJDS7teP3zeMJabxWw7Qkva2AR9fs1sw9jWquNqvNzRzyMAIHAI7gBCwvP7Tquz2+O7nRgXo7vZKRUh6Ks3z1VsjMV3+1J7l3634yMTKwIQLQjuAELC/+w6ZbhtXzJF45Pi+7k3YJ6Zqcm6d9lUw9jP3j6qjq7ufh4BAIFBcAdgulPuy9pRa9xC/r4bpptUDXBtD99qXBrydGOrnt972qRqAEQLgjsA0z232zjbPj4pTrcvmmRSNcC13TDLquw5qYaxn7xZK4/H088jAGDkCO4ATPesX3C/d9lUJcbF9nNvIDQ8fGuG4faeE43aebTBpGoARAOCOwBTHTnXrP2nmgxjn75hhknVAIOXc91UzU5LNoz94p2j5hQDICoQ3AGY6g97jH3Bk8Ynaq0t3aRqgMGLjbHoSzfOMYy9uO+MzjW1mlQRgEhHcAdgqhf3nTHc/sT10wxL7QGhzJE1S0nxV19KO7s9+g1LQwIYJQR3AKY5eqFFB880G8b8l9kDQllKcrzu92vt+s17H7E0JIBRQXAHYJoX9xtn2yeOS1D23DSTqgGG58/82mXONbfpJb//twEgEAjuAEzzgl+bzF1Lp9Img7CzdHqKsvyWhvzFO8dMqgZAJCO4AzDFKfdl7T7uNozds5Q2GYQn/4tUd9TW6/DZ5n7uDQDDQ3AHYAr/VoKUMfG6cR6rySA83btsmiaOSzSM/ZaLVAEEGMEdgCn822TsS6YoPpZfSQhPCXExcmTPNIw97Typ1o4ukyoCEIl4lQQQdOeb27TzaL1h7B5Wk0GY++yqWYbbjZc7ei13CgAjQXAHEHQvHzwrj+fq7bEJsbp1wUTzCgICYE76WN0839juxZruAAKJ4A4g6Co/OGe4/bFFk5QUH2tSNUDgfG71bMPtHbX1OnLuoknVAIg0BHcAQdXa0aU3P7xgGFu3eIpJ1QCBddd1U5U+NsEwtmUns+4AAoPgDiCo3qmp0+UeF+zFWKQ7Fk82sSIgcBLiYvRglvEi1aecJ9XeyU6qAEaO4A4gqCo+OGu4nTUnVWl+M5RAOPO/SLW+pV2vHDrXz70BYPAI7gCCxuPx6GW//vZ1S2iTQWSxTRqnbL+dVJ+qPmFSNQAiCcEdQNDsP9WkM02thjH7EtpkEHn822VeOXRO9S3tJlUDIFIQ3AEETaVfm8yc9GTNmzTOpGqA0fOJ5dOUGHf1Jbajy6Nnd500sSIAkYDgDiBo/IP7usVTZLFYTKoGGD0TkuJ111LjpmJPOQnuAEYmzuwCgqmkpERlZWWy2Wyqr7+ya+PGjRuVmZk57HO63W5t2rRJTqfTN1ZfX6+NGzcqNzd3xDUDkeJsU6v2nWwyjNmvo00GkevBzBl6bvcp3+29Jxt1+GyzFk4Zb2JVAMJZ1AR3h8Mhl8ul7du3y2q1SpJcLpeysrJUVFSkvLy8IZ/T5XKpsLBQRUVFstlsvvHNmzfL4XAoMzNT1dXVgforAGHttUPnDbfHJ8Zp1dw0k6oBRt+tCyZp8vhEnWtu8409VX1CGz++xMSqAISzqGiVKSkpUXl5uSG0S5LNZlNpaany8/MNM+aD5XA45Ha75Xa7DeMFBQWy2WxyOp0qLCwcYfVAZHj1sHE1mVsWTFR8bFT8CkKUio2x6DMrZxjGnnn/pDq7WNMdwPBExatmYWGh7Ha7IbR7edtZhhOwnU6nKisrtWnTpl7HvDPwlZWVQz4vEGk6u7r1ht9uqbcvmmRSNUDw+K8uc665TW8eudDPvQFgYBEf3J1Op9xu94B97JmZmaqsrOw1c34teXl5slqtys/P7/c+aWm0AgDvH3erubXTMPaxhfS3I/ItnDJe189IMYxxkSqA4Yr44L5lyxZJUnp6er/38Ybroc6OFxcXq6GhQXa7vdcx77kcDseQzglEolf9do1cPHW8pqYkmVQNEFwPZhrbZbbtP6Om1g6TqgEQziI+uHsDdF9tMl7eYzt37gzIc5aXl0u60i4znItegUjzqt+FqbcvYrYd0eO+G2YoPvbqsqdtnd36457TJlYEIFxFfHD3tr8M1LLiPTbUVpm+uFwubdiwgRVlgD8519yq/aeMy0DS345okjY2QXf4vVl9qvqESdUACGcRvxykd732QN+3J++ykC6XS06nUwUFBSoqKhrWuSTpxImBf6GfPs1MDcKH/zKQ4xLjlDUn1aRqAHM8mDVT2w5c3YCs6liDjl5o0dyJY02sCkC4ifjgHgw2m01lZWWSrlwMu2HDBs2bN0/FxcV99r9fy6xZswJdImCaVw8bg/vN89NZBhJR545Fk5WaHK+GS1d72592ntC37lpkYlUAwg2vngHmbZGpr69XTk6Or98diEZd3R692WsZSPrbEX0S4mL06RuMF6k+u/uUPB6PSRUBCEcRH9y9/euDaYMJ5NKN3otSN2zYMOTe+ePHjw/4tWPHjoDVCYymvScb1XjZuHrGxxbS347odL/fZkxH6y5p78lGk6oBEI4ivlVmoNVkvLyhfjD3HaxVq1ZJunLB69atW4e0uszMmTOvfScgDLzh1yYzf/I4TbeOMakawFwrZqZoTnqyjtVd8o09u+uUls+0mlcUgLAS8TPu2dnZkqSampp+7+NyuSRdDduDUVJSotTU1H7XaffunCqJ1WUQtd7w2yHylvkTTaoEMJ/FYtGnlk83jP1hz2l1d9MuA2BwIj645+TkSBp4qUfvsdzc3EGft7i4WG63W+Xl5b7g31PP1pysrKxBnxeIFBfbOuU81mAYu20hwR3R7VMrjMH9TFOrdh4d3opmAKJPxAd3bxjvb1dUt9stl8ulzMzMIZ3XO5Nvs9kMs+teTqfT99/DWVkGCHfvuerU2WMmMT7WojUZ/e9gDESDRVPHa9GU8YaxZ3efMqkaAOEm4oO7JBUVFcnlcvU5M75161ZJUmlpaa9jLpdLWVlZys/P73XM4XAoMzOz3xac4uJiSVcuUu0r2AOR7g2/1WQyZ6dqbGLEX1YDXNN9Nxhn3Z/fe1odXd0mVQMgnERFcC8oKFBubq5ycnIMLTNOp1OFhYUqKirqc8a9uLhYTqdTJSUlhhl06cosen5+vrKysnody8/Pl8vlUm5uri/AA9Hm9Q+NF6bexmoygCT16nNvuNShN/2uBwGAvkTN9FdZWZlKSkrkcDhks9lUX18vt9utsrKyfltZ1q9fr/Lyctlstj6DfV5enux2u29G39vXbrPZVFFRQYsMotZJ92W5zrcYxrgwFbhidnqyVsyyavdxt2/sud2ndAd7HAC4hqgJ7tKVoD2UZRkHaoXxstlszKoDft70m223Jsdr2YwUk6oBQs99K6Ybgvu2/WfV2tGlpPhY84oCEPKiolUGQHD597ffPH+iYmMsJlUDhJ5PLp8mS49/EhfbOvXKwXPmFQQgLBDcAQRUd7dH79TUGcZupU0GMJgyIUlrMoy7dbO6DIBrIbgDCKjD55pV19JuGLuZ4A70ct+KGYbb2w+eU3Nrh0nVAAgHBHcAAfX2EeNs+8zUMZqVlmxSNUDounfZVMX1aCFr7+xWxYGzJlYEINQR3AEE1Nt+bTI3zWPTJaAvqWMTei2TSrsMgIEQ3AEETGdXt95zGYM7bTJA/z61Yprh9hsfXlC9X6sZAHgR3AEEzP5TTWpu6zSM3Whjxh3oT851U5UYd/WluKvboxf3nTGxIgChjOAOIGDeqjEuAzl/8jhNnpBkUjVA6BuXGKd1S4wbL72w77RJ1QAIdQR3AAHjvwwk/e3AtX38emO7zNs1dbTLAOgTwR1AQLR1dmnn0XrDGMEduLY7Fk1WUryxXWbbftplAPRGcAcQELs+cqu1o9t322KR1mQQ3IFrGZsYp9sXGttl/riXdhkAvRHcAQSE/zKQ102boNSxCSZVA4SXjy/v3S7TQLsMAD8EdwABQX87MHzrFk/utboMmzEB8EdwBzBil9o79f7xBsPYTfNYvx0YrLGJcbp9kXEzJtplAPgjuAMYsZ1HG9TR5fHdjo2xaFVGmokVAeHHf3WZt45ckPsS7TIAriK4Axixt/3Wb18xM0XjEuNMqgYIT+uWTFFCj3aZTtplAPghuAMYMf/+9pvn0yYDDNW4xDh9bKGxXeZ52mUA9EBwBzAijZc6tO9ko2HsRi5MBYblE37tMm8euaDGyx0mVQMg1BDcAYzIe7V16r7a3q6EuBhlzk41ryAgjK1bMtnQLtPRRbsMgKsI7gBGxH/99uw5qUqKjzWpGiC8jU+K120LjO0yL9AuA+BPCO4ARoT124HA+sTyqYbbb3x4QU2ttMsAILgDGIHzzW06dLbZMHYj67cDI7JuyRQlxF59eW7v6lYl7TIARHAHMALvuIyz7WMTYrV8ZopJ1QCRYUJSvG5dYHwDzOoyACSCO4AReNcvuK/KSFN8LL9WgJHy34zp9cMX1Ey7DBD1eIUFMGzv+QX3G230twOBYL9uiuJjLb7b7V3devngORMrAhAKCO4AhuV8c5tqzrcYxtYQ3IGASBkT32sjsxf3nTGpGgChguAOYFjeq+3d375s+gSTqgEiz73LjKvLvHrovC61d5pUDYBQQHAHMCzvueoNt7PnpimO/nYgYHKum6rYmKvtMpc7uvTaofMmVgTAbLzKAhgW/xn3NbY0kyoBIlPa2ASt9ft39QLtMkBUI7gDGLK6i206fPaiYWwt/e1AwN2zzLi6zMsHz6mts8ukagCYLajBPT2dF3YgEuyoNbbJJCfE6voZrN8OBNrdS6fIcrVbRhfbOvXmhxfMKwiAqYIa3D0ej5555plgPiWAUfCeX3DPmpPK+u3AKJg8PknZc1INY7TLANEr6K+0ubm52rhxo5qamoL91AACxH/jJdpkgNFzr1+7TMWBs+ro6japGgBmCmpwd7vdeuKJJ2S32/Xwww9r/fr12rVrVzBLADBCDS3tOnim2TC2JoMLU4HRco/fspCNlzv0Tk1dP/cGEMmCGtyLi4u1YcMGrVu3Tlu3blVJSYkqKip0991368knnwxmKQCGacdRY5tMUnyMls+0mlMMEAWmW8doxSyrYYx2GSA6BTW4b9iwwXA7JSVF3/3ud/XSSy8pIyND69ev16OPPqpjx44FsywAQ+DfJpM1J1UJcfS3A6PJfzOmbfvPqKvbY1I1AMwSMq+2q1atUkZGhrZu3Sqbzaa7775bTz/9tNllAfDjv/HSmgz624HR5h/c61rae63uBCDyBTW4Hz16tNfYyy+/rPXr1ys1NVXf+9731NDQoAcffFCPP/646urqdNddd+n73/9+MMsE0I/GSx364IzxwnIuTAVG35z0sbpu2gTD2Iv7TptUDQCzBDW4Z2Vl+f77ySef1IIFC5STk6OysjJlZGTo8ccfV0NDg7Zu3aqVK1dqw4YN2rZtm1auXKlHHnmEGXjAZDuO1svT49P5xLgYrZjF+u1AMPjPur+4/4y6aZcBokrQ13FftWqVYmNjlZ+fr5qaGq1bt04VFRU6cuSIvvvd7yolpXcIWLdunZ544gl5PB4uYgVM9J5ff/vK2VYlxsWaVA0QXe693hjczza16f3jbnOKAWCKoPe4V1dX+y5Kramp0bZt27Ru3bpBPfbBBx9UdXX1KFcIoD/+Gy/RJgMEz/zJ4zV/8jjDGO0yQHQJenDfvHmz6uvr9fjjjysjI2NQj/n+97+ve+65R01NTaqrY+1awAxNrR3af6rRMMaFqUBwfdyvXeb5vWfk8dAuA0SLoAb3tLQ0fec73xny4/7lX/5F27ZtU0ZGhh555JFRqAzAtVQdrVfPdtqE2BitnG01rR4gGt3jt4vqSfdl7TvJTuRAtIgL5pMVFhYO63HV1dWqrKyU3W4f9Cw9gMDyXwbyhtlWJcXT3w4E05Jp4zUnPVnH6i75xl7Yd1rXz+QicSAamLoBU09Hjx7tc7lIScrIyNCGDRsI7YCJ/DdeWpuRZlIlQPSyWCy6x69d5oV9tMsA0SKowf3RRx/t99gTTzyhJ554Qg899JDWr1+vpiY++gNCxcW2Tu07Zfw3uYYLUwFT3OvXLlN7oUWHzjabVA2AYApqq0xlZWW/xx5//HHff7tcLm3YsEFbtmwJRlkArqHqaL1he/X4WIsyZ6eaWBEQvVbMTNH0lCSdamz1jb2w94wWT50wwKMARIKgr+M+GDabTW63e3SLATBo7/r1t6+YadWYBPrbATNcaZcxzrq/uO+MSdUACKagBneLxTKo+23fvl0ul2uUqwEwWO/V+vW30yYDmMp/M6ZDZ5vlOn/RpGoABMuotcrcddddamhoMIy5XC6tWrVqwMe53W65XC4VFBSMVmkAhqClrVN7T/it327jwlTATFmzUzVpfKLON7f5xl7Yd0bfuGO+iVUBGG2jFty3bdumxsZGbdmyRSUlJXI6nZJ0zZ1PrVarvvvd72rTpk2jVRqAIag+1qDOHv3tcTEWZc2hvx0wU0yMRXcvnaJfvfuRb+yFfacJ7kCEG9WLU1NSUpSXl6e8vDw5HA69/PLLqqqq6vf+aWlpSklhLVoglPi3ySyfmaLkhKBe1w6gDx9fNs0Q3PedbNLx+kualZZsYlUARlPQXn1LS0uVnZ3NWuxAmPHfeIllIIHQsDojTanJ8Wq41OEbe3HfGW24zWZiVQBGU9AuTrVarSoqKgrW0wEIgMvtXdp9wm0YW8PGS0BIiIuN0V3X+W/GdNqkagAEQ1BXlXnwwQeD+XQARsj5UYM6uq72t8fGWJQ9l+AOhIp7/FaXcX7k1unGyyZVA2C0BTW4D8X69evNLgGIeu+6jP3ty2akaFwi/e1AqLh53kSNTzL+m3yJNd2BiBWywX2gXVYBBId/f/taloEEQkpCXIxylkwxjL1AcAciVsCD+/e+9z2lp6frJz/5Sa9jCxYsUHp6+jW/YmNj2TkVMFlrR5d2HXcbxtZmcGEqEGruWWZsl9l5tF4XLrb1c28A4SzgwX3Tpk1qaGjQ448/3utYXV2dGhoa1NDQII/H0+eX95jVag10aQCGwPlRg9q7un23YyxS9lzWbwdCzW0LJyk5IdZ3u9sjbdt/1sSKAIyWgAf3xx9/XDabrc/gbrPZVFJSou7ubtXX1/f51d3dre7u7j7ODCCY3vVrk1k2I0Xjk+JNqgZAf5LiY3XH4smGMVaXASJTwIN7Xl6ejhw50ucKMmlpacrOzh7UeVJTmdkDzPSe34Wpa1m/HQhZH182zXD7nZo6uS+1m1QNgNES1ItTt23bphtuuGFQ962urh7dYgD0q7WjS+/797dzYSoQsm5fNEmJcVdf0ju7Pao4QLsMEGlCdlWZlJQUs0sAotb7H7nV3unf305wB0LV2MQ4fWzhJMPYi6wuA0ScoAb3Xbt2Gb68Xn75Zd19991KT0/X3XffrWPHjgWzLAB+3qs1tsksnZ6iCfS3AyHtXr/NmN748IKaWztMqgbAaAhqcC8oKFBWVpY2bdqkqqoqSdL27dtlt9tVUVGhDRs2yG63y2636+jRo8EsDUAP/hsv0SYDhL51S6YoPtbiu93e1a2XD54zsSIAgRbULRAdDocKCwu1bt0631h+fr4sFou2bdvmG3/wwQdVWFioLVu2BLM8ALrS3+78yG0YW8P67UDIm5AUr1vmT9Qrh877xl7Ye0afvmGGiVUBCKSgzrg7nU5DaK+trZXL5ZLNZjOM22w2VpUBTLL7uLG/3WKRVmUw4w6Eg3v9Vpd59fA5XWrvNKkaAIEW1ODuf8FpZWWlJMlut/e6r8Vi6TUGYPT5r9++dPoEpYyhvx0IBznXTVFszNXXz9aObr3WYwYeQHgLanD3D+MVFRWyWCzKysrqdd/6+vpeYwBGn39/O20yQPhIHZvQ65qU51ldBogYQQ3uDQ0Nhtv9zbjv2rVLGRkZQasLwBVtnV1yfmT8d8rGS0B48W+XefmDs2rt6DKpGgCBFNTg7nA4tH79et/yj263W7m5uZo7d67vPk899ZTWrVunv/7rvw5maQAk7T7eqDa//vbVrN8OhJW7lk5Rzw+4W9q79OaHF8wrCEDABDW4r1u3TllZWb7lH3Nzc30rx5SWliotLU0Oh0MNDQ2Gi1UBBId/m8ySqROUkkx/OxBOJo9P0qo5xjfcL9AuA0SEoO+cWlBQoO7ubnV3d2vr1q2+8Q0bNqi2tlYNDQ1qaGjwtdEEUklJiXJycpSfny+HwyGHwyGn0zni827evFk5OTlKTU3VvHnzAnZeINh6r99OmwwQju5ZZtyMqeLAGcNqUQDCU9CD+0BSUlJ8X3l5eQE9t8PhUHFxscrKynx/FhUVad26dSopKRnWOd1ut3JycmSz2VRRUaGGhgaVlZXJ6XQqKytLhYWFAf07AKOp7/522mSAcOQf3JtaO/WO3xtzAOEnpIJ7T4GcsS4pKVF5ebm2b98uq9XqG7fZbCotLVV+fv6wns+7oVRubq5vLDMzU9XV1bJardq8ebPKy8sD8VcARt2eE41q7fDrb2f9diAsTbeO0Q2zrIaxF/edNqcYAAET1J1TJampqUklJSWqqanp9z4ul0sulytgz1lYWCi73W4I7V7e0F1YWKiKiopBn9Mb9Ptag95qtSovL0+bN2/Whg0bDMEeCFXv1hhn4xZPnSBrcoJJ1QAYqXuXTdWu427f7Zf2n9U/frpbcbEhO2cH4BqCGtxra2s1f/58SZLH4xnwvoHaOdXpdMrtdiszM7Pf+2RmZqqyslJut7vPcN+XyspKVVZWKicnp8/An5OTo82bN8vtdvt2hwVC2Xu1xr0TaJMBwtu9y6Zp0wsHfbfrW9r1jqtOty6YZGJVAEYiqME9Pz9f69atk8PhGDDI1tTU6NFHHw3Ic3pXrUlP7/8iu7S0KwGlsrJy0LPj3k8MKisr5XQ6e70x6Pn3czqdBHeEtPbOblUd8w/uXJgKhLPZ6claPjNFe040+sae232K4A6EsaAG9/r6elVVVV3zfuvWrdPmzZsD8pze1WkGmkn3Htu5c+egg3t+fr4qKyuVmZnZ52y+2+3udX4gVO054Tb0t0us3w5Egk8tn24I7i/uO6N/uv96JcTRLgOEo6AG9+zs7EHft6ioKCDP6Q3Q3ln1vniP9Qzb15KZmTlgn37PNyhD+XtL0okTJwY8fvo0FxghsPzbZBZPHa/UsfS3A+HuE8un6Z+f/8B3u6m1U298eF7rlkwxsSoAwxX0i1MHKycnJyDnqa+vv/adhnHfaykuLpYk5eXlDXnGfdasWQGrAxgM1m8HItN06xhlz0lV1bGrS70+t/sUwR0IU0H9rMzhcOj73//+oO6blZU1ytWMnvLycl9fe6A+OQBGS0dXt6qOsn47EKk+uXya4XbFgbNq7egyqRoAIxHU4L5u3TplZGTo0Ucf1e7duwe8b11deG4U4Xa7tWHDBlmtVlVUVAyrv/348eMDfu3YsSPwhSNq7TnRqMt+L+KrM5hxByLFx5dPU4zl6u2W9i69cvCceQUBGLagtsrcfffdqq+vl9vt9u1W6h9svX3mgbqgMy0tTW63e1BtMAP1wQ+Ww+GQJFVXVw97JZmZM2eOuA5gsPzbZBZPHa80+tuBiDF5fJLW2tL1do+9Gv6w57TuvX7aAI8CEIqCGtx37tzZ6wLQhoaGvu8cIIN5A+AN9SN9s7B582ZVVVWNKLQDweYf3NewWyoQcT65fLohuG8/eFYtbZ0amxiyl7oB6ENQW2XS0tJUUlKi7u7uAb8CeZGod0WXa+3UKkmrVq0a9vOUlJSouLhYtbW1hHaEjY6ublUf8+9vp00GiDT3LJuquB79Mq0d3ar84KyJFQEYjqAGd5vNNqilEa1Wa8B2TvWuTjPQUo/eY4Ndw91fZWWliouLVV1d3WvWvry83LeWPBBq9p5s1KV2//52ZtyBSJM2NkE3z59oGHtuN0sLA+EmqMG9rKxMN9xww6DuW11dHZDn9Ibx/sKz2+2Wy+XqcxOlwXA6nSosLNT27dv7bLXZuXMnM/AIWf5tMgunjFP6uESTqgEwmj61Yrrh9muHz6nxcodJ1QAYjqAG95SUFN9/79q1S08//bR27drlG3v55ZfV1NTU674jVVRUJJfL5WuJ6Wnr1q2SpNLS0l7HXC6XsrKylJ+f3+d5vSvIeB/rdrt9Xy6XS06nU+Xl5QR3hKz3XMa2NNpkgMh119IpSoi9+rLf0eXRtv1nTKwIwFAFfc/jXbt2adWqVcrKypLD4fBtVCRJqampys3N1dNPPx3Q5ywoKFBubq5ycnIMLTPe2fKioqI+Z9yLi4vldDpVUlIip9NpOOZ2u5WVlSWn06msrCylpqYavubNmxfWa9Ej8l1Zv53gDkSLCUnx+tiiSYax5/bQLgOEk6BeTt7Y2Kg777xTaWlp2rBhgy/4eq1cuVLbtm3TI488oszMTM2dOzdgz11WVqaSkhI5HA7ZbDbfspRlZWWy2+19Pmb9+vW+GXP/YL9p06Y+Z/D9MduOULXvZKNa6G8HosqnVkxXxYGrF6W+deSC6lvaWQIWCBMWj8fjCdaTPfLII7JarXr88cd9Y48++qh+/OMf97pvf+OQTpw4oVmzZkm6slkT675jOP7r1SPa/OIh3+0Fk8ep4lsfM7EiAKOtpa1TWf9UodaObt/YP39mmb6wZo6JVQGRaTTyWtBbZXqG9oEE8f0EEJXeqTFemEqbDBD5xibGad2SKYax/3n/lEnVABiqoAZ3i8Vy7Tv9yWhvzAREs7bOLu3062+/eT7BHYgG9/mtLrPjaL2O118yqRoAQxHU4D7YjZUaGxsJ7sAoev8jt+GjcouFGXcgWtyxaLKsyfGGsd+/f9KkagAMRVCDe2pqqv76r//aMNZXS4zdbtddd90VrLKAqPO2X5vM0ukTZE3m4jQgGiTExeiTy6cZxp55/yQtqkAYCGpwLyoq0hNPPKF77rlHzzzzjI4ePSqLxaKmpibt2rVLTz75pBYsWCC3263vfOc7wSwNiCpvH7lguH3TvIn93BNAJPrMSuNFcq4LLdp13G1OMQAGLajLQaakpGjr1q266667VFFR4RsvKSnx/XdGRobhGIDAamnr7PUCfdM82mSAaJI526q56ck6Wne1t/2Z909q5exUE6sCcC1BX1XGbrervr5eDzzwgDwej+8rJSVFGzZs0JEjR5SRkRHssoCoseNovTq7r34kHhdj0aq5rN8ORBOLxaL7V84wjD23+5TaO7v7eQSAUBD04C5JVqtVZWVl6u7uVk1NjRoaGlRfX68nnnjCjHKAqOK/DOQNs6wamxjUD98AhIDP+AX3hksdeu3weZOqATAYpgT3njIyMpSSkmJ2GUDUeLvGr799Pv3tQDSakz5WWXOMrTHPvH/CpGoADEZQp9lefvlluVwu1dTUKD09XTabTXa7XRMmTAhmGUDUcl9q1/5TTYYx+tuB6PWZlTNUfezq8suVH5xT4+UOpYyJH+BRAMwy6sF9165d2rRpk8rLy/u9T1ZWloqKinTHHXeMdjlAVHvXVaeeK74lxcdo5WyrafUAMNcnl0/TPzx3QO1dV3rb2zu79fze0/rc6tkmVwagL6PaKrNx40ZlZWWpvLzccCGq/1dVVZXsdrs++9nPjmY5QNR764ixv33V3DQlxsWaVA0As1mTE3TH4kmGsWecbMYEhKpRm3Ffv369ysrKJEmZmZmy2+2aN2+e0tLSZLVaJUlut1sul0s7d+5UeXm5tm7dKpfLpR07doxWWUBU8+9vv5E2GSDqfWblTL20/6zv9o6j9Tpef0mz0pJNrApAX0YluP/v//2/VVZWptzcXBUVFQ1qecfGxkYVFBSotLRUjz32mP7rv/5rNEoDotaZxlbVnG8xjN3MxktA1Ltj8SRZk+PlvtThG/v9+yf1zXULTKwKQF8C3ipTW1urzZs3q7CwUFu3bh30muwpKSkqLi7W448/ruLiYh07dizQpQFR7R2XcbZ9fFKcls1gRScg2iXGxeqTy6cZxp55/6Q8PS+IARASAh7ci4uLlZmZqU2bNg3r8QUFBVq3bp0ef/zxAFcGRLe3/frb19rSFRtjMakaAKHkMytnGm67LrTofb8dlgGYL+DBvby8XJs3bx7ROQoKClRZWRmgigB4PB697bfxEstAAvDKnG3V3HRjT3tZ1XGTqgHQn4AH94aGBt15550jOofdbpfL5QpQRQA+qr+kk+7LhrGb6G8H8CcWi0UPZhpn3Z/bfVqX2jtNqghAXwIe3APVE8duqkDg+C8DOXFcghZOGWdSNQBCUW72TPXsnrvY1qnn954xryAAvQQ8uKelpYXUeQD0tQzkRFks9LcDuGpayhjdttC4pvvWnbTLAKEk4ME9UGGAUAEEhsfj0Tt+/e03098OoA8PZc8y3N5xtF6u8xdNqgaAv1HdORWA+T443ay6lnbDGP3tAPpiXzJFaWMTDGNbq06YVA0AfwHfgKmmpkavvPLKoNdv7+8cXJwKBMYbH5433J6VNkaz0saYVA2AUJYQF6PPrJyhn7xZ6xt7ynlC375roeJjmesDzDYqO6fa7fbROC2AYXjjQ2N/+20LJtGKBqBfD2XPMgT3881t2v7BOd2zbKqJVQGQRqlVxuPxjPgLwMhdbu/SjqP1hrFbF0zq594AIC2aOl43zLIaxn6z4yNzigFgMCoz7uXl5crIyJDVah3yY91ut2pqarR+/frAFwZEmR1H69Xe2e27HRtj0Y1cmArgGr6wZrZ29dg59Y0Pz+ujukua7bdJE4DgCnhwT01N1QMPPDCic6xcuXJYoR+A0RuHjf3tN8yyKmVMvEnVAAgXn1w+Xf/whwNqbr2yAZPHI/1250cqvGexyZUB0S3grTKpqakhdR4gmvn3t9+6gNVkAFzbmITYXjupllUdN3yCByD4Ah7cjxw5ElLnAaLVmcZWHTrbbBijvx3AYH1hzWzD7QsX21Vx4KxJ1QCQWMcdiFj+y0COT4rTipkpJlUDINwsmDJeq+cadzH/1bvHTKoGgERwByKWf5vMzfMmKo51mAEMwef9Zt3fcdXpQ79P8gAED6/iQATq7vbozSN+67cvpE0GwNDcs2xqr51Uf/7OUXOKAUBwByLRgdNNqm9pN4xxYSqAoUqKj9XnVs8yjD3tPKmm1g6TKgKiG8EdiECv+/W3Z0wcq1lprL8MYOi+uHaOYmOu7rZ8qb1LZVUnTKwIiF4EdyACvXGYZSABBMa0lDG6e+kUw9gv3zmq7m52OQeCjeAORJhL7Z2qOlZvGGMZSAAj8eUb5xpuH627pNf8NngDMPoI7kCEec9Vr46uqzNhcTEWrbWlDfAIABjY6ow0LZ463jD207ePmlMMEMUI7kCE8e9vz5ydqvFJ8SZVAyASWCwWffmmuYax1w+f16EzLA0JBBPBHYgwr/t9fE1/O4BAuP+GGb2WhnzyDZdJ1QDRieAORJCT7suqOd9iGGP9dgCBMCYhVl9cO8cw9vtdJ3WuqdWkioDoQ3AHIsibfm0y1uR4LZuRYlI1ACLNl26co4S4q9Gho8vDhkxAEBHcgQjyut8ykDfPn2hYfxkARmLiuEQ9mDnDMPardz/SpfZOkyoCogvBHYgQHV3dvS5MvY3+dgAB9vVbbIbbjZc7tHXncZOqAaILwR2IENXHGtTcapz1un3RZJOqARCp5k8ep3WLjb9bSt+oVUdXt0kVAdGD4A5EiJcPnjPcXjp9gqZMSDKpGgCRLO8246z7SfdlPfP+SZOqAaIHwR2IEP7B/c7FzLYDGB2rM9KUPSfVMPbjV2vU1e3p5xEAAoHgDkSAj+ou6ci5i4YxgjuA0WKxWPSNO+cbxmovtOiFfadNqgiIDgR3IAK8fPCs4Xb62AStmGk1pxgAUeH2hZO0dPoEw9iPXqmRx8OsOzBaCO5ABHj5kHE1mY8tmqQYloEEMIosFou+cYdx1v2D002q/OBcP48AMFIEdyDMtbR16t2aOsPYusVTTKoGQDS5Z+lUzZs01jD27xWH1U2vOzAqCO5AmHvryAW191iGLS7GolsXsn47gNEXE2PRn/v1uh843aQX958xqSIgshHcgTD3yiHjx9LZc1M1ISnepGoARJv7VszQ/MnjDGP/XnGYFWaAUUBwB8KYx+PRKweN/e2sJgMgmGJjLPor+0LD2IfnLuq53adMqgiIXAR3IIwdON2kM02thrE76W8HEGT3LpuqJdOMK8z8oPIwu6kCAUZwB8LYy36rN8xOS+51oRgAjLaYGIu+lWOcdT9ad0lbdh43qSIgMhHcgTD28qHeu6VaLCwDCSD47Esma8XMFMPYDyoP62Jbp0kVAZGH4A6EqbqLbdp13G0Yo78dgFksFosK711sGLtwsV0lr9WYVBEQeQjuQJh69dB59dygMDkhVmtsaeYVBCDq3TRvotb5TSCUvOHSmcbWfh4BYCgI7kCY8m+TuXn+RCXGxZpUDQBc8b/vXayeGze3dnTr3yoOmVcQEEEI7kAY6ujq1uuHWQYSQOhZMGW81q+abRgrqz6hPSfc5hQERBCCOxCGqo81qLnVeMHXHYsI7gBCw1/lLFBywtVPAD0e6f/9z351sykTMCIEdyAMVRw4a7i9dPoETU1JMqkaADCaPD5J37hjvmFs13G3yqtPmFQREBkI7kCY8Xg82nbgjGFs3RI2XQIQWh6+NUMZE437Sjz+4kE1XuowqSIg/BHcgTBz8EyzjtdfNozdvZTgDiC0JMbF6u/uW2oYq29p1/e3caEqMFwEdyDMbNtvbJOZYR2j6/y2GgeAUPCxhZN6TSz86r1jqj5Wb1JFQHgjuANhxr9N5q6lU9gtFUDI+r+fvE5J8VfjhscjFZTvUWtHl4lVAeGJ4A6EkRMNl7T/VJNh7O6lU02qBgCubWZqsr6Vs9AwVnO+RT965YhJFQHhi+AOhBH/1WRSk+OVPSfVpGoAYHC+dnOGls9MMYz9+NUaHfCbiAAwMII7EEb8+9vXLZmiuFj+GQMIbXGxMSp6cLniemyp2tnt0be27lJbJy0zwGDxig+EiYaWdu04aryg667rWE0GQHhYMm2CHr19nmHs4Jlm/eu2wyZVBIQfgjsQJio+OKuuHrsOJsXH6NYFk0ysCACG5s/vnK9FU8YbxkrfcOntIxdMqggILwR3IEy8uM+4mszHFk7SmB5bigNAqEuMi9UPPnuDEmKNq8x8u2y33JfaTawMCA9RFdxLSkqUk5Oj/Px8ORwOORwOOZ3OgJ3f6XRq3rx5crvdATsnIElNrR1648PzhrGPXz/NpGoAYPiWTJuggnsWGcZON7bqO2W71d3jU0UAvcWZXUCwOBwOuVwubd++XVarVZLkcrmUlZWloqIi5eXlDfvcTqdTxcXFKikpCVC1gNH2D86qo+vqC1pCbIzuXDzZxIoAYPi+dnOGXj10Xm/2aJGp/OCcil939eqDB3BVVMy4l5SUqLy83BDaJclms6m0tFT5+fnDmnnfvHmzsrKyVFxcLIfDYTg3EEjP7zW2ydy2cKLGJ8WbVA0AjExMjEXfd6xQ+tgEw/j3Xjqod2rqTKoKCH0Wj8cT8Z9LpaamKjs7WxUVFX0et1gsstvt/R4fyvO43W41NDSMaog/ceKEZs2aJUk6fvy4Zs6cOWrPBfNdbOtU5j9WqL2z2zf2r44VejCLnzuA8Pbmhxf0Z//9nnomkYnjEvXcN2/WtJQx5hUGBMBo5LWIn3F3Op1yu93KzMzs9z6ZmZmqrKykNx0h6eWD5wyhPT7WIvsSloEEEP5uWTBR37Ibd1W9cLFND/+8SpfaO02qCghdER/ct2zZIklKT0/v9z5paWmSpMrKyqDUBAzFC3tPG27fPH+iUpJpkwEQGb5xx3zdvsi4tO3+U0361hYuVgX8RXxw94bxgVpXvMd27twZhIqAwbvU3qlXDp0zjN27bKpJ1QBA4MXEWPSD9TdobnqyYfzF/Wf0vW2HTKoKCE0Rv6qMt/3FO6veF++xUGmVOXHixIDHT58+PeBxRI7KD86pteNqm0xsjEU51xHcAUQWa3KCfvKVVfrMj95SU+vVFpkfv1qjaSlJ+tKNc80rDgghER/c6+vrr32nYdx3NHkvZACe3XXKcPvm+ROV5rcKAwBEgnmTxunHX8zSl/57h2GX6L99dr+syQm6b8V0E6sDQkPEt8oA4arxUodeO2xsk/nUcjZdAhC5bp4/Uf90/zLDmMcjfXvrLr12+Hw/jwKiR8TPuIej48ePD3j89OnTWr16dZCqgVleOnCm16ZLdy2lTQZAZPvc6tk619Smf6887Bvr6PIo/5dV+smXV+nm+RNNrA4wV8QH97S0NLnd7kG1wQzUBx9MrMsOSXput7FN5vZFk5QyhtVkAES+v1g3X/Utbfr5O8d8Y60d3fr6z3fqv7+8SjcR3hGlIr5VZjAbIXlDPTufIlRcuNimt/12D/wU/Z0AooTFYtHffmqpPn2D8fdea0e3vvbznXrryAWTKgPMFfHBPTs7W5JUU1PT731cLpckadWqVUGpCbiWF/aeNlycNSY+VuuWTDaxIgAIrpgYi/7VsUKf8Lu2p7WjW1/96U69uI8V1hB9Ij645+TkSBp4qUfvsdzc3CBUBFzbs35tMvbrpig5IeI72wDAIC42Rv+x/oZe4b29q1uP/dqpLTs/MqkywBwRH9y9Yby/XVHdbrdcLpcyMzODWRbQr+P1l7TzaINhjNVkAEQrb3j/pN/vwW6PVPjUXv2g8rA8HnZYRXSI+OAuSUVFRXK5XL6WmJ62bt0qSSotLe11zOVyKSsrS/n5+aNeI+D1P7tOGm6njInXx/y2AweAaBIXG6P/+OxKfW717F7HflD5of7id7vU2tFlQmVAcEVFcC8oKFBubq5ycnIMLTNOp1OFhYUqKirqc8a9uLhYTqdTJSUlcjqdAz6Hy+XynbuqqiqQ5SOKeDwePf2+Mbh/Yvk0JcbFmlQRAISG2BiL/uUzy/TY7fN6HXtu9ymtL35H55paTagMCJ6oaZotKytTSUmJHA6HbDab6uvr5Xa7VVZWJrvd3udj1q9fr/Lyctlstj6DfXl5uTZt2uRbbtK7Ko3D4VBaWpqsVqvWr1+vgoKC0fyrIYLsOdEo1/kWw9gDK2eYVA0AhBaLxaKCexZr0vhE/eMfDqjHNfzafaJRn/7RWyr9UraWzUgxr0hgFFk8NIaFnRMnTmjWrFmSrmzWxLrvkePvnt2vn7191Hd7dlqyXvvu7bJYLOYVBQAh6NVD5/TN37yv5rZOw/iY+Fj9+/obdM8yNqyDuUYjr0VFqwwQDjq6unttunT/yhmEdgDow+2LJuvpx27S7LRkw/jlji498qtqPf7CQXV2dZtUHTA6CO5AiHj98HnVtbQbxj5DmwwA9GvBlPH6/Tdu1uq5vXc+f+K1Gn3+yffoe0dEIbgDIcL/otSVs63KmDjWpGoAIDykjU3QLx9eLUdW7zaEHbX1+vgP39TbNey0ishAcAdCQENLuyr2nzWMcVEqAAxOYlysNucu19/ft1Txscb2wgsX2/TFJ9/Tj145ou5uLutDeCO4AyHg97tOqr1HL2ZCXIw+tWK6iRUBQHixWCz68k1zVfbITZphHWM41u2RvvfSIX3t5ztV79eSCIQTgjtgMo/Hoy07jxvG7l46VdbkBJMqAoDwdcMsq/7wzVt0Rx8b17166Lw+8cM3VHW03oTKgJEjuAMm23eySQfPNBvGHspmiU8AGK7UsQn6yZdX6bt3L1KM38Jcpxtbtb7kXRW/VkPrDMIOwR0w2dYq42z7DOsY3TxvoknVAEBkiImx6Bt3zNevHl6jieMSDce6uj3a9MJBbfhFldyXaJ1B+CC4AyZq7ejS73cZV5PJzZqpGP8pIgDAsNw0b6Ke/8tbdKMtvdex7QfP6RM/fFPOjxpMqAwYOoI7YKKX9p9Rc+vVXf8slivBHQAQOJPHJ+lXD6/RX6xbIP897U66L+uhJ97Rk2+4xGbyCHUEd8BEv37vI8Ptm+dN1Cy/XQABACMXG2PRt3IW6pdfW6OJ44wX/3d2e/RPf/xAeb+sVuOlDpMqBK6N4A6Y5PDZZu2oNa5s8NCqWSZVAwDR4ZYFE/XHv7hVazJ677ZaceCsPv7DN7TruDv4hQGDQHAHTPIbv9n2ieMSdM/SqSZVAwDRY8qEJP364TX68zvm99k643jibf30rVpaZxByCO6ACS61d+qp6hOGsYeyZykhjn+SABAMcbEx+s7di/Szr65W2lhj60xHl0d//9wBfadsj1o7ukyqEOiNlACY4Lndp9TcZrwo9XOrZ5tYEQBEp48tnKTn/+JWrZ7bu3XmKecJfa70XZ1rajWhMqA3gjtggl+9a2yTuX3hJC5KBQCTTE1J0m82rNFjt8/rdez9j9y67z/f0p4T7uAXBvghuANBtvu4W3tPNhrGvrh2jknVAACkK60zBfcs1hNfzFJyQqzh2JmmVjmeeEf/47fvBhBsBHcgyH729lHD7RnWMbp90WRzigEAGNyzbKqefuwmzUwdYxhv6+zWX/5ul77/0iEuWoVpCO5AEJ1ratUf9pwyjH1+zWzFslMqAISMxVMn6Nk/v0Vrbb373v/zlSP6dtludXR1m1AZoh3BHQiiX717TB1dV2dqEuNi9HkuSgWAkJM2NkG//Poa/VkfrYxPO0/q6z+v0sUeiwwAwUBwB4KktaOr106pD2TOUKrfMmQAgNAQHxujf7x/mf7p/mXy/2D09cPn9bmSd3W+uc2c4hCVCO5AkDy7+5TqWtoNY1+9OcOkagAAg/XFtXNU+qVsJcUbY9Pek4164MdvqfZCi0mVIdoQ3IEg8Hg8+u83aw1jt8yfqIVTxptUEQBgKNYtmaLfbljba7Om4/WX9eCP32a5SAQFwR0IgreO1OngmWbD2NdumWtOMQCAYVk5O1Xlj9yoWWnGFWfqW9r1hdL3VH2s3qTKEC0I7kAQPPFajeF2xsSxun0hS0ACQLixTRqnpx+9WctmTDCMN7d16s9+skPv1NSZVBmiAcEdGGV7TzTqzSMXDGMP35qhGJaABICwNGl8on6Xd6NuXTDRMH6pvUtf+ekOvXb4vEmVIdIR3IFR5j/bPnFcoh7MnGlSNQCAQBiXGKfSL2XLvsT46WlbZ7c2/LxK2/afMakyRDKCOzCKai+06Pl9pw1jX7tlrpLiY/t5BAAgXCTFx+q/vpClj18/1TDe3tWtx37t1B/3nO7nkcDwENyBUVTyeo167ow9PjFOX+xjMw8AQHhKiIvRDz+7Up9ZOcMw3tnt0Td/6+y1WzYwEgR3YJSccl/WU9UnDWNfWDtHE5LiTaoIADAa4mJj9H3HCn121SzDeLdH+svf7dKL+5h5R2AQ3IFR8l+vHlF7V7fvdkJsjL5281zzCgIAjJrYGIv+5TPX68s3Gj9V7er26M9/874qD5w1qTJEEoI7MApOui9ry87jhrHPrp6lyROSTKoIADDaYmIs+rv7luorN801jHd2e/TYr5165dA5cwpDxCC4A6PgR68cUUfX1eb2hLgYPXb7fBMrAgAEg8Vi0d9+6jp9Yc1sw3h7V7fyf1mtNz5kqUgMH8EdCLATDZdUVmWcbf/86tmamsJsOwBEA4vFon/89DKtzzb2vLd3duvhn1fp7ZoL/TwSGBjBHQiwvmbbH719nokVAQCCLSbGok0PXK8HMo2rzbT9KbxXH6s3qTKEM4I7EEA15y9qa9UJw9jnV8/WFHrbASDqxMRY9L3cFbpvxXTD+JUdVndq38lGkypDuCK4AwG0+cWD6uq+OtueFB+jx5htB4CoFRtj0b89tKLXJk3NrZ36s5+8p8Nnm02qDOGI4A4ESPWxer2037jc19duzmAlGQCIcnGxMfrB+pW6c/Fkw3jDpQ594cn3dPRCi0mVIdwQ3IEA8Hg82vT8QcNYanK8HmG2HQCgK9c7/dcXMnXTvHTD+PnmNn3hyfd00n3ZpMoQTgjuQABUHDirqmMNhrE/v3MBu6QCAHyS4mNV+qVsZc1JNYyfdF/WF0rf1bmmVpMqQ7gguAMj1NrRpX9+/gPD2MzUMfri2tn9PAIAEK3GJsbpp19dpWUzJhjGj9Zd0hd/8p7qW9pNqgzhgOAOjNBP3qzVsbpLhrHv3r1IiXGxJlUEAAhlE5Li9YuvrdHCKeMM44fPXtSX/vs9NV7uMKkyhDqCOzACp9yX9Z8vHzGMZc1J1aeWT+/nEQAASGljE/Srr6/R3PRkw/i+k0362s92qqWt06TKEMoI7sAI/PPzH+hyR5fvtsUi/f19SxUTYzGxKgBAOJg8IUm/3rBWM6xjDOPVxxq04RdVau3x+gJIBHdg2N46ckF/3HPaMPb51bO1bEaKSRUBAMLNDOsY/frhNZo0PtEw/nZNnR77tVPtnd0mVYZQRHAHhuFye5c2Pr3XMGZNjtd37lpkUkUAgHA1d+JY/frhNUpNNq5E9vLBc/qrLbvU2UV4xxUEd2AY/r3ysD6qN16Q+u27Fil1bIJJFQEAwtnCKeP1y6+v0fikOMP4H/eeVsFTe9TdY1duRC+COzBEe0649eQbLsNY9pxUfWE1yz8CAIZv2YwU/eyrq5ScYFyV7GnnSf2/Z/fJ4yG8RzuCOzAE7Z3dKijfo54THwmxMXr8weVckAoAGLGsOWl68kvZSogzRrRfvfuR/uX5DwjvUY7gDgzBDyoP6+CZZsPYX6ybr/mTx/XzCAAAhuam+RP1xBczFR9rnBAqfaNW//xHwns0I7gDg/Seq04/fq3GMLZ46njlf2yeSRUBACLVnYun6D8+u1L+H+Y++Wat/v65A4T3KEVwBwah8XKH/mrLLvX8PRkfa9H3HSsUH8s/IwBA4H38+mn6vmOFLH7h/WdvH9X//Z99XLAahUgcwDV4PB79n2f26lRjq2H8O3ctYs12AMCoeiBzpv7toRW9Zt5/9e5H+j+/30t4jzIEd+AafvHOMf3Bb6Olm+ala8OtNpMqAgBEk8+snKkffHalYv3S+293HFfhU3vURXiPGgR3YABVR+v1j384YBhLGROvf31oBavIAACC5r4V0/X/fW6l4vxee8qqT+gvf/e+2jq7TKoMwURwB/pxrrlVj/3aqU6/mYzNucs1LWWMSVUBAKLVx6+fpv/8fO/VZv6w57S++tOdam7tMKkyBAvBHehDa0eXHv2VU+ea2wzjj90+T3cvnWpSVQCAaHfPsqn68ReylOC3MMLbNXVaX/yuzjW19vNIRAKCO+Cnu9ujb2/drepjDYbxWxdM1LfvWmRSVQAAXGG/boqe/HJ2rx1WD5xu0gM/fluu8xdNqgyjjeAO+Hn8xYP6417jxagzrGP0H31cGAQAgBluWzhJv8tbq/SxCYbxEw2XlfvEO9p13G1OYRhVBHegh/9+s1Ylr7sMY+MT4/STr2Qrze+XIwAAZlo+06qnHr1Jc9KTDeP1Le36XMm7esFvEgrhj+AO/Mmv3j2mf/BbQSYuxqIffzFLi6dOMKkqAAD6N3fiWJU/cpOu99tX5HJHlx79tVM/qDzMWu8RhOAOSNq687j+5vf7eo1veuB63bJgogkVAQAwOJPGJ+q3eWt1ax+vVz+o/FCP/drJijMRguCOqPeb9z5S4dN7eo1/9+5FcmTPMqEiAACGZlxinH7y5VV6KHtmr2Mv7j+j+/7zLX1wusmEyhBIBHdELY/Hox9u/1B//cxeefw+Rfxf9gX6xh3zzSkMAIBhSIiLUdGDy/X/Pnmd/NdSqL3Qovt/9Ja27PxIHv8XPYQNgjuiUle3R3/37H79W8XhXse+ccc8/eW6BSZUBQDAyFgsFn3tlgz97KurlTIm3nCsrbNbhU/t1WO/dqqhpd2kCjESBHdEHfeldn3lpzv083eO9Tr2F3fO13fuWiSLhWUfAQDh67aFk/SHb96i5TNTeh17Yd8Z3fMfr+vVQ+dMqAwjQXBHVPngdJM+9Z9v6o0PLxjGLRbp7+9bqm8R2gEAEWJWWrLKHrlRf7Z2Tq9jZ5va9JWf7tS3tuxi9j2MENwRFTwej37+9lHd/6O3dLz+suFYfKxFP/zsSn35prnmFAcAwChJjIvVP96/TE98MUvW5Phex59+/6Ts//aayqqOs2xkGCC4I+Kda2rVV366U3/77H61dXYbjk0an6jf5a3Vp1ZMN6k6AABG3z3Lpuql/3Vbn0tG1rW067vle/TAj9/WbnZcDWkEd0Ssrm6PfvHOUa37t9f02uHzvY7fMMuqP3zzFmXNSTOhOgAAgmvKhCT94murtemB6zU+Ka7X8V3H3fr0j97SN37jVM35iyZUiGvp/VMDIsDOo/X6h+cOaO/Jxj6Pf+Wmudr48cVKjIsNcmUAAJjHYrHoc6tn687Fk/V/f79P2w6c7XWfP+45rRf3ndEDK2fokdvnad6kcSZUir4Q3BFRDpxq0ve3HdLLB/u+Un7y+ER937FCty2cFOTKAAAIHVMmJKnkS9l65eA5/cMfDqj2QovheFe3R2XVJ1TuPKF7lk5V3m023TDLygIOJouq4F5SUqKysjLZbDbV19dLkjZu3KjMzMyQPC8Gx+Px6F1XvUrfcPUb2CXpgZUz9DefvE5pYxOCWB0AAKHrjsWTdfP8ifrpW7X60StH1NTaaTju8VxZPvKFfWd0/YwU/dnaOfrkimlKToiqCBkyLJ4o2T7L4XDI5XJp+/btslqtkiSXy6WsrCwVFRUpLy8vpM47kBMnTmjWrFmSpOPHj2vmzN7bG0eDxssdenbXSf1u53HtP9X/Ns7zJ4/TP92/TGtt6UGsDgCA8NJ4qUPFr9fop28d1eWOrn7vl5wQq3uXTdMDmTO0JiNNcbFcMtmX0chrURHcS0pKlJ+fr4aGBl+49iovL5fD4VB1dfWQZ8hH67zXEs3B/VJ7p149dF7P7z2tigNne60S09PEcYn65p3z9bnVs5UQxy8VAAAG43xzm/77rVr96p1jam7rHPC+qcnxsi+ZopzrpmiNLb3Xbq3RjOA+TKmpqcrOzlZFRUWfxy0Wi+x2e7/Hg33ea4mm4O7xeOS60KI3Dp/XGx9e0Ns1dQPOAkiSNTleD9+Soa/enKGxiXyUBwDAcDS1dujX736kX717TCfdl695/xiLtGxGim6cl64bbelaNTctql+HRyOvRfx30+l0yu12DzjrnZmZqcrKSrnd7l4z58E+b7Q719yqPccbtfuEW7uOu7XnRKMaL3cM6rGz05L18K0Zys2aSe8dAAAjNCEpXo/ePk95t9n0ysFz+tV7x/T64fPqb5+mbo+050Sj9pxoVPFrLsXFWLRwyngtmTZBS6aN13XTJ+i6aRNkTeZas+GK+HSzZcsWSVJ6ev/9zWlpV9bxrqysVG5urqnnjXRd3R7VtbTpbGObjta16Fhdi47WXdKxuhbVXrikCxfbhnS++FiL7Eum6KFVs3TbgkmKjeFqdwAAAik2xiL7dVNkv26KzjW16tndp/T7XSe172T/15dJUme3RwdON+nAaeP9pk5I0uy0ZM1MG6NZqcmalZasWaljNN06RhPHJWpMAks19yfig3tlZaUkDTjj7T22c+fOQQfs0TpvKOrq9qits0ttHd1q6+xWW2eXWjuu/NnW2a22jm61dnTpUkeXmls71NzaqebWDjVdvvJnXUu7zje36cLFNtW1tGukzVmxMRbdaEvXvddP1T1Lpyp9XGJg/qIAAGBAkyck6eFbbXr4VpuO11/SS/vPaPsH51T9UYPaB7jurKczTa0609SqHUf7Pp6cEKuJ4xKVPi5B6WMTNSEpTuOS4jQ2MU7j/vR15b9jNTYxTskJsYqPjfF9JcTGKD7OYrwda1FsjCXsl7OM+ODudrslXZ397ov3mPe+Zp5XutITNZDjx4/7/vv06dNDOvdQ/W7HR/pB5Yej+hyDMWl8glZnpGt1RqrWZKT7Pma77D6vE25zawMAIBpZJN2TkaB7MmaqtWOa9p1sVPWxBlUfa9CBU03q7K+n5hqaJDVdkFwBrVayWKS42BglxFr0yMfmyZE9K8DPYNQzo3V2DnyR72BFfHD3rqseLveV5LuQYTBWr149pHOHq5OSdkkqMbkOAAAQ/r71A+lbQXy+8+fPa+7cuSM+D2vkAQAAAGEg4mfcw1HPVpi+tLa26uDBg5oyZYomTZqkuDh+jKPl9OnTvk81duzYoWnTpplcEXri5xPa+PmENn4+oY2fT2gbzM+ns7NT58+flyRdf/31AXneiE98aWlpcrvdg2pXGahfPVjnlTSodT7nz58/pHNi5KZNmxbRa+aHO34+oY2fT2jj5xPa+PmEtoF+PoFoj+kp4ltlBrN+ujd8D2Wt9dE6LwAAANCXiA/u2dnZkqSampp+7+NyXbluedWqVaafFwAAAOhLxAf3nJwcSQMvyeg9NpS11kfrvAAAAEBfIj64e0Ozd8Mkf263Wy6XS5mZmSFxXgAAAKAvER/cJamoqEgul8vXutLT1q1bJUmlpaW9jrlcLmVlZSk/Pz+g5wUAAACGKiqCe0FBgXJzc5WTk2NobXE6nSosLFRRUVGfM+PFxcVyOp0qKSmR0+kM2HkBAACAoYr45SC9ysrKVFJSIofDIZvNpvr6erndbpWVlclut/f5mPXr16u8vFw2m63fAD6c8wIAAABDZfF4PB6ziwAAAAAwsKholQEAAADCHcEdAAAACAMEdwAAACAMENwBAACAMEBwBwAAAMIAwR0AAAAIAwR3AAAAIAwQ3AEAAIAwQHAHAAAAwkCc2QUA4SQrK0ulpaXKzMw0u5So5HK5lJ+fL4fDIbvdLpvN5ht3Op3asmWLioqKfOMwj8vlUlFRkaqqqpSWliZJcjgcysvLM7my6OVwOGSz2bR+/XpZrVZJ8v1s/HmPI/jKy8u1ZcsWSZLb7ZYk5efnKzc318Sq4FVSUqKysjLfbavVqo0bNwYvF3gADEpBQYFHkqe6utrsUqJWdXW1R1K/X0VFRWaXCI/HU1xc7LFarZ6ysjLDeEFBgae4uNikqpCZmTngv5+eXxUVFWaXG5Vyc3N7/RtpaGjw2O12T25urklVwctut3tsNpunpqbGN1ZWVuaR1Ov33WghuAOD0DMwEtzN019wz8zM5OcSIoqLi/sMfhUVFR6r1erJzMw0qTIMNrQTEM1RVFQ04OSDzWbjja+J8vLy+n1Tm5ub65HkaWhoGPU66HEHBqGwsJD2mBCRm5urmpoaVVRUqLq6Wh6PR9XV1fx8QoC3lSk3N1d2u91wzOl0yu12+z76R3C53W5lZmaqoaFBniuTdr2+GhoalJmZqdLSUrPLjUrFxcUDtsPk5+cbWjQQPE6nUyUlJbJarb1+t0lXfjbSlaww2gjuwDUUFhaqsLCw315QBJ/NZpPdbieshxjvi9fGjRt7HSsoKFBxcbEqKiqCXRYkVVVVGXrb++JwOFRaWkp/u0m81+r0x2q1qr6+PogVwau4uFiSlJ2d3edx7/jWrVtHvRaCOzAAl8slt9vd5ztsAFe5XC5VVlZKUr9vqPLy8rhw2EQDzeZu3rxZmZmZvBk22YYNG/oN7xUVFbwWmaSqqkpS/xdte8fdbveAb74CgVVlgAHk5+czQwgMQnl5uaSrod3lcvlmqXJycggcJhvo++9dkam6ujqIFcFfbm6uysvLlZWVpYKCAhUVFfmOVVZWqrKyUrW1tSZWiMGoqqoa1TfABHegH5s3bw5KvxqGzul0+kKhJNXX12v9+vUsl2ainTt3SrqyvGBlZaUqKiqUn5+vtLQ0lZSUyOFwaPv27czohiCHw8EERQgoLS1VZWWl3G63Nm/erPLychUXF/veBNfW1tLGZBKbzTbomfSamppRrYXgDvTB5XKppqZGBQUFZpcCP5WVlVq1apUhuLtcLs2bN095eXmGcQSPy+Xy/XdFRYVhtrCgoEB1dXXKysriQuIQs3nzZsOeCDCP1WpVbW2tHA6HKisr5XK5lJOTI5vNpurqakK7iVatWqXy8vJ+L67vOT7aF+DT4w70IT8/3xA8EBpsNptKS0t7vaGy2WwqKChQSUmJSkpKTKouunlfrCorK30XqfbkHduwYUMwy8IA3G63Nm3a1OfPC+awWq3KyckxvLl1uVzKyMjwXUOC4PNuHNffzyAYF6V6EdwBP94WGWY3Qo/Vau23HWb9+vWSgrMcF3rz/nux2Wx9zt56x5xO56hfvIXB2bRpk2+ZSJjP7XYrKytLklRdXa2Ghgbf7zu3262cnBzftSQILqvV6vs0t6+fQXV1te933GhnB4I70IO3RYYL6cKP95dmMK7qR2/e5VIHarnwvqB5V2iAuUpKSvhdF0LWrVsnu93u+0TRarWqrKxMFRUVvn87fGJlHm8r5oYNG3zh3el0yuFwqLCw0LdUZ3p6+qjWQXAHeqBFJnR5N/cZzIxTz35rBMdgeqS94Z7VS8znvQiSTxZDQ0lJiVwuV5+vP3a7XbW1tcrMzJTb7aYd0ER5eXmqra1VfX298vPzVVlZqdLSUtlsNl+74Gi/GebiVOBPnE6nqqqqfB9V+vOGwXXr1vkCyGhfPY6riouLfT3sHo9nwPtyoV3w9ffvpifvjNS8efNGuxxcg3cVGTaWCw3XWqPdarVq+/btSk1N5Y2vyaxWq6/n3cubD6xW66i3nhHcgT/xbgfen9TUVLndbpa0M4n340f/X5hePWfZ+fkEnzd0DKYNhp+P+bwX2THjHhpcLle/u3J6Wa1W2Ww23viaxLvST1+vQd5/T8H4xJ5WGQBhITMzUwUFBf0u9+j9xcla7uaw2Wy+j/L7Wg7Nuwux1WqlrzoEeK8DIQSGBrvdPqhVY1wuF/9+TOC9ONjbHuOvuLi4z5n40UBwB4bI+3E/gstut8vlcvXbv+79xVlaWhrkyuDlnW3qa2k077UJ/HyA3vLz8+VyuQbsXy8pKVFubi6fWJnA+8mU1Wrt9clIeXm5nE5n0H63EdyBQeg5i8iFj+YpKirqNePhXUKtvr5e27dv56N/E9nt9j5/RpWVlSosLFRBQQGfiISAnp+I0OMeGmw2myoqKlRYWKjNmzcbjrndbhUWFqqsrExlZWUmVYi8vDxt3LjR8Brj3RW6rKwsaL/bLJ5rXeUFRLHNmzeruLjYMMvudrtls9lktVq5SMgkhYWFcjqdqq+vV1pamjIzM1kNKIRUVlaqqKjI9+/GZrMpPz+fj/hDSFZWllwul2H9aZjPuymW942v941Vfn4+b3pDwObNm7VlyxZJV35WdrtdhYWFQf03RHAHAAAAwgCtMgAAAEAYILgDAAAAYYDgDgAAAIQBgjsAAAAQBgjuAAAAQBgguAMAAABhgOAOAAAAhAGCOwAAABAGCO4AAABAGCC4AwAAAGGA4A4AAACEAYI7AAAAEAYI7gAAAEAYILgDAAAAYYDgDgAAAIQBgjsAYFjcbrdycnKUlZWl1NRUzZs3z9TzhIto+/sCCByCOwBgWKxWq4qKipSfny+32636+npTzxMuvH/f9evXy+12m10OgDBi8Xg8HrOLAACEN4vFIqvVqoaGhpA4j9lycnJUUVFxzftZLBbZbDbV1NQEoSoA4Y4ZdwDAiFmt1pA6j5mi4VMDAOYguAMAEEBbt241uwQAEYrgDgBAABUXF5tdAoAIRXAHAGAYnE6nXC6X77bb7ZbD4ZDT6TSxKgCRLM7sAgAg2lRWVqqsrMzXz+12u5WVlaWysjIVFRUpMzPTcH+3263CwkLV19crLS3NN15UVOQ7h8vlUn5+vlwul+rr65Wdna2KigoVFhbK5XL5+q6zs7MNj/NXUlKi6upq322Xy6WcnBwVFBQE9HswXIP5XngDtP/3wvt9l6SqqiqlpaWpuLhYNputz+dyuVwqLCz0rfxSX1+vjRs3SpIqKiqUlZWl/Px81dTUyOl0+uqSroT6nss82u32a87EO51O330GUx+AKOQBAARNUVGRJzc3t9d4RUWFR5Knurq617jVavUUFBQYxgsKCjxWq9Vw/+rqak9RUZFHksdms3kyMzM9FRUVhsfZ7XaPJE9ZWVmvGgoKCjx2u73XeGZmpsdqtXpqamr6/XtZrVaP1Wrt9/hgDXSeoX4viouLPZI8mZmZnrKyMk9RUZHhcd7vRUNDQ5/PJclTXFxsOKck3/eooaHBk5mZafi+1NTU+J5zMLw/q6HWByA6EdwBIIgk9QrTXrm5uYbw2dDQYAiK/rzhvCfvY/p6E9DzcZJ6BXHv43qGVY/namDt6w2H12gH9+F8Lzyeq8E4Ly+v1zFvsPcPzAPVkZubO+D3djjB3Wq1Drk+ANGJHncACLKioqI+x3Nycgy3N2zYIEnKz8/v8/52u11Op7PPnmqbzdar5carsLBQkuRwOAzjubm5stlsstvthnHveczs3R7J98LbRuTP24Liv4a60+mU2+1WdnZ2r8esWrVK0pV2p0Bxu91Dqg9A9CK4A0AQ5ebmqrKyUqmpqXI4HCopKfFd4JiXl2cI2+Xl5ZLUbwDPysqSJMMFkoPx0EMPSboaUL3KyspUU1PTb0+1mWuTj/R70d/jQkWo1wcgNHBxKgAEUVlZmRwOh8rLy31f0pXZ1eLiYt9sd88A2t8MvXQl7A/14sWeF6ZWVVX1mmF3uVwqLy/Xzp07DReAmmWk34uhbuqUmZkpq9WqqqqqXsd27twpSb2+ZyMRCZtOAQgOgjsABFlZWZlcLpcqKytVXV2tyspK3+otFRUVstvt/a6YEmg9Z9ydTqc2bNggl8uloqIi3wos0pXVZswSrO9FT2VlZcrJyVFJSYny8vIkXfn+lJeXq6CggBlyAKagVQYAgsgbgG02m/Ly8lRcXKyamhpVVFRIujqjbLVaDUs9BlLP8/XsX8/KypLL5VJtba0vrIaC0fxe9Me7NGNFRYVycnLkcDhUWFjoW7JzqLzLcgLASBDcASBIvGuQ98Vut6ugoMDQnuHtRe+rZcPL6XQO+UJJ7/0zMzN9rSWbNm2SJG3cuLHXjHbPWXnv7f4uEh0to/W96E9FRYXy8vJUVlamiooK35+5ubkDPi4UWosARC6COwAEkdvt9vW1+0tPTzesZOLdfGegGd7CwsI+Vz/xbrrU32MkGVphvPftq0d8oLDs//iR6u88I/leDKc2byvTUHk/HfB/TpfL1e+1CIH63gGIfAR3AAiyDRs29Fq20OVyqbi4uNfumt4WmqysrF4BLz8/X/n5+X32fFutVt/uoV7eHVq95+0ZJL0z6P7P73a7VVZWpoKCArndbrndblVVVfnO471Pzz97slgs1/wazHmG8724ViD2fm/6amHJzc31tch4z11YWKjCwsJ+33h55eXlGYJ/fy0yI6kPQHSyeDwej9lFAEA0cLvdWrdunbZv365NmzbJ5XL5Wivq6+tVVFTU76zs5s2bVVFRIavV6ntMYWFhr/u73W6lpqbKZrOpurra9zzeY5mZmf3OWjudTm3atElut1s5OTmqq6uTdKXv3lu7y+XSQw89pOLiYt8bAf9lItPS0nxrj/cM5v1paGi45nmG8r0YqC7vxcDennPv7Lh33XvvpxBut1sZGRkDhmvvNQp98QZ8m80mq9Wq0tJS35uKQNQHIDoR3AEggvQM7mzcMzyVlZVyOBwqLS3t1dPu/cShqKhIlZWVKioqUkFBgUmVAog2BHcAiCAE95FLTU3Vxo0brxnIva1I1dXVQaoMQLSjxx0AgD/xXtQ7mHXaV61aRf85gKAiuAMA8Cc2m002m21QveRbtmzxLVMJAMFAcAeACOKdAfa/8BGDV1FRocrKSuXn5/d5carT6VROTo7S0tL6vTgVAEYDPe4AEAGcTqccDsegV2bBtZWXl2vLli19HsvPz5fdbg9yRQCiHcEdAAAACAO0ygAAAABhgOAOAAAAhAGCOwAAABAGCO4AAABAGCC4AwAAAGGA4A4AAACEAYI7AAAAEAYI7gAAAEAYILgDAAAAYYDgDgAAAIQBgjsAAAAQBgjuAAAAQBgguAMAAABhgOAOAAAAhAGCOwAAABAGCO4AAABAGCC4AwAAAGGA4A4AAACEAYI7AAAAEAb+fyGyTOrvE/DrAAAAAElFTkSuQmCC", "text/plain": [ "
" ] }, "metadata": { "image/png": { - "height": 236, - "width": 366 + "height": 250, + "width": 375 } }, "output_type": "display_data" @@ -308,39 +299,30 @@ }, { "cell_type": "code", - "execution_count": 64, + "execution_count": 6, "metadata": {}, "outputs": [ { - "ename": "ValueError", - "evalue": "Multi-dimensional indexing (e.g. `obj[:, None]`) is no longer supported. Convert to a numpy array before indexing instead.", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", - "Input \u001b[0;32mIn [64]\u001b[0m, in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43msns\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdisplot\u001b[49m\u001b[43m(\u001b[49m\u001b[43miris\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msepal_length\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkind\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mkde\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/seaborn/distributions.py:2218\u001b[0m, in \u001b[0;36mdisplot\u001b[0;34m(data, x, y, hue, row, col, weights, kind, rug, rug_kws, log_scale, legend, palette, hue_order, hue_norm, color, col_wrap, row_order, col_order, height, aspect, facet_kws, **kwargs)\u001b[0m\n\u001b[1;32m 2215\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m p\u001b[38;5;241m.\u001b[39munivariate:\n\u001b[1;32m 2217\u001b[0m _assign_default_kwargs(kde_kws, p\u001b[38;5;241m.\u001b[39mplot_univariate_density, kdeplot)\n\u001b[0;32m-> 2218\u001b[0m \u001b[43mp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplot_univariate_density\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkde_kws\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2220\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 2222\u001b[0m _assign_default_kwargs(kde_kws, p\u001b[38;5;241m.\u001b[39mplot_bivariate_density, kdeplot)\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/seaborn/distributions.py:991\u001b[0m, in \u001b[0;36m_DistributionPlotter.plot_univariate_density\u001b[0;34m(self, multiple, common_norm, common_grid, warn_singular, fill, color, legend, estimate_kws, **plot_kws)\u001b[0m\n\u001b[1;32m 988\u001b[0m artist \u001b[38;5;241m=\u001b[39m ax\u001b[38;5;241m.\u001b[39mfill_between(support, fill_from, density, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39martist_kws)\n\u001b[1;32m 990\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 991\u001b[0m artist, \u001b[38;5;241m=\u001b[39m \u001b[43max\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplot\u001b[49m\u001b[43m(\u001b[49m\u001b[43msupport\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdensity\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[43martist_kws\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 993\u001b[0m artist\u001b[38;5;241m.\u001b[39msticky_edges\u001b[38;5;241m.\u001b[39mx[:] \u001b[38;5;241m=\u001b[39m sticky_support\n\u001b[1;32m 994\u001b[0m artist\u001b[38;5;241m.\u001b[39msticky_edges\u001b[38;5;241m.\u001b[39my[:] \u001b[38;5;241m=\u001b[39m sticky_density\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/axes/_axes.py:1632\u001b[0m, in \u001b[0;36mAxes.plot\u001b[0;34m(self, scalex, scaley, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1390\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 1391\u001b[0m \u001b[38;5;124;03mPlot y versus x as lines and/or markers.\u001b[39;00m\n\u001b[1;32m 1392\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1629\u001b[0m \u001b[38;5;124;03m(``'green'``) or hex strings (``'#008000'``).\u001b[39;00m\n\u001b[1;32m 1630\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 1631\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m cbook\u001b[38;5;241m.\u001b[39mnormalize_kwargs(kwargs, mlines\u001b[38;5;241m.\u001b[39mLine2D)\n\u001b[0;32m-> 1632\u001b[0m lines \u001b[38;5;241m=\u001b[39m [\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_lines(\u001b[38;5;241m*\u001b[39margs, data\u001b[38;5;241m=\u001b[39mdata, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)]\n\u001b[1;32m 1633\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m line \u001b[38;5;129;01min\u001b[39;00m lines:\n\u001b[1;32m 1634\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39madd_line(line)\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/axes/_base.py:312\u001b[0m, in \u001b[0;36m_process_plot_var_args.__call__\u001b[0;34m(self, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m 310\u001b[0m this \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m args[\u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m 311\u001b[0m args \u001b[38;5;241m=\u001b[39m args[\u001b[38;5;241m1\u001b[39m:]\n\u001b[0;32m--> 312\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_plot_args\u001b[49m\u001b[43m(\u001b[49m\u001b[43mthis\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/axes/_base.py:487\u001b[0m, in \u001b[0;36m_process_plot_var_args._plot_args\u001b[0;34m(self, tup, kwargs, return_kwargs)\u001b[0m\n\u001b[1;32m 484\u001b[0m kw[prop_name] \u001b[38;5;241m=\u001b[39m val\n\u001b[1;32m 486\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(xy) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m2\u001b[39m:\n\u001b[0;32m--> 487\u001b[0m x \u001b[38;5;241m=\u001b[39m \u001b[43m_check_1d\u001b[49m\u001b[43m(\u001b[49m\u001b[43mxy\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 488\u001b[0m y \u001b[38;5;241m=\u001b[39m _check_1d(xy[\u001b[38;5;241m1\u001b[39m])\n\u001b[1;32m 489\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/cbook/__init__.py:1327\u001b[0m, in \u001b[0;36m_check_1d\u001b[0;34m(x)\u001b[0m\n\u001b[1;32m 1321\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m warnings\u001b[38;5;241m.\u001b[39mcatch_warnings(record\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m w:\n\u001b[1;32m 1322\u001b[0m warnings\u001b[38;5;241m.\u001b[39mfilterwarnings(\n\u001b[1;32m 1323\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124malways\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 1324\u001b[0m category\u001b[38;5;241m=\u001b[39m\u001b[38;5;167;01mWarning\u001b[39;00m,\n\u001b[1;32m 1325\u001b[0m message\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mSupport for multi-dimensional indexing\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m-> 1327\u001b[0m ndim \u001b[38;5;241m=\u001b[39m \u001b[43mx\u001b[49m\u001b[43m[\u001b[49m\u001b[43m:\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m]\u001b[49m\u001b[38;5;241m.\u001b[39mndim\n\u001b[1;32m 1328\u001b[0m \u001b[38;5;66;03m# we have definitely hit a pandas index or series object\u001b[39;00m\n\u001b[1;32m 1329\u001b[0m \u001b[38;5;66;03m# cast to a numpy array.\u001b[39;00m\n\u001b[1;32m 1330\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(w) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/pandas/core/indexes/base.py:5385\u001b[0m, in \u001b[0;36mIndex.__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m 5383\u001b[0m \u001b[38;5;66;03m# Because we ruled out integer above, we always get an arraylike here\u001b[39;00m\n\u001b[1;32m 5384\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m result\u001b[38;5;241m.\u001b[39mndim \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m-> 5385\u001b[0m \u001b[43mdisallow_ndim_indexing\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresult\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 5387\u001b[0m \u001b[38;5;66;03m# NB: Using _constructor._simple_new would break if MultiIndex\u001b[39;00m\n\u001b[1;32m 5388\u001b[0m \u001b[38;5;66;03m# didn't override __getitem__\u001b[39;00m\n\u001b[1;32m 5389\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_constructor\u001b[38;5;241m.\u001b[39m_simple_new(result, name\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_name)\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/pandas/core/indexers/utils.py:341\u001b[0m, in \u001b[0;36mdisallow_ndim_indexing\u001b[0;34m(result)\u001b[0m\n\u001b[1;32m 333\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 334\u001b[0m \u001b[38;5;124;03mHelper function to disallow multi-dimensional indexing on 1D Series/Index.\u001b[39;00m\n\u001b[1;32m 335\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 338\u001b[0m \u001b[38;5;124;03min GH#30588.\u001b[39;00m\n\u001b[1;32m 339\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 340\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m np\u001b[38;5;241m.\u001b[39mndim(result) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m--> 341\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 342\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMulti-dimensional indexing (e.g. `obj[:, None]`) is no longer \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 343\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msupported. Convert to a numpy array before indexing instead.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 344\u001b[0m )\n", - "\u001b[0;31mValueError\u001b[0m: Multi-dimensional indexing (e.g. `obj[:, None]`) is no longer supported. Convert to a numpy array before indexing instead." - ] + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "image/png": { - "height": 490, - "width": 489 + "height": 489, + "width": 490 } }, "output_type": "display_data" @@ -352,39 +334,30 @@ }, { "cell_type": "code", - "execution_count": 62, + "execution_count": 7, "metadata": {}, "outputs": [ { - "ename": "ValueError", - "evalue": "Multi-dimensional indexing (e.g. `obj[:, None]`) is no longer supported. Convert to a numpy array before indexing instead.", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", - "Input \u001b[0;32mIn [62]\u001b[0m, in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43msns\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdisplot\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43miris\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msepal_length\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkind\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mkde\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/seaborn/distributions.py:2218\u001b[0m, in \u001b[0;36mdisplot\u001b[0;34m(data, x, y, hue, row, col, weights, kind, rug, rug_kws, log_scale, legend, palette, hue_order, hue_norm, color, col_wrap, row_order, col_order, height, aspect, facet_kws, **kwargs)\u001b[0m\n\u001b[1;32m 2215\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m p\u001b[38;5;241m.\u001b[39munivariate:\n\u001b[1;32m 2217\u001b[0m _assign_default_kwargs(kde_kws, p\u001b[38;5;241m.\u001b[39mplot_univariate_density, kdeplot)\n\u001b[0;32m-> 2218\u001b[0m \u001b[43mp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplot_univariate_density\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkde_kws\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2220\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 2222\u001b[0m _assign_default_kwargs(kde_kws, p\u001b[38;5;241m.\u001b[39mplot_bivariate_density, kdeplot)\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/seaborn/distributions.py:991\u001b[0m, in \u001b[0;36m_DistributionPlotter.plot_univariate_density\u001b[0;34m(self, multiple, common_norm, common_grid, warn_singular, fill, color, legend, estimate_kws, **plot_kws)\u001b[0m\n\u001b[1;32m 988\u001b[0m artist \u001b[38;5;241m=\u001b[39m ax\u001b[38;5;241m.\u001b[39mfill_between(support, fill_from, density, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39martist_kws)\n\u001b[1;32m 990\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 991\u001b[0m artist, \u001b[38;5;241m=\u001b[39m \u001b[43max\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplot\u001b[49m\u001b[43m(\u001b[49m\u001b[43msupport\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdensity\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[43martist_kws\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 993\u001b[0m artist\u001b[38;5;241m.\u001b[39msticky_edges\u001b[38;5;241m.\u001b[39mx[:] \u001b[38;5;241m=\u001b[39m sticky_support\n\u001b[1;32m 994\u001b[0m artist\u001b[38;5;241m.\u001b[39msticky_edges\u001b[38;5;241m.\u001b[39my[:] \u001b[38;5;241m=\u001b[39m sticky_density\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/axes/_axes.py:1632\u001b[0m, in \u001b[0;36mAxes.plot\u001b[0;34m(self, scalex, scaley, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1390\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 1391\u001b[0m \u001b[38;5;124;03mPlot y versus x as lines and/or markers.\u001b[39;00m\n\u001b[1;32m 1392\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1629\u001b[0m \u001b[38;5;124;03m(``'green'``) or hex strings (``'#008000'``).\u001b[39;00m\n\u001b[1;32m 1630\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 1631\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m cbook\u001b[38;5;241m.\u001b[39mnormalize_kwargs(kwargs, mlines\u001b[38;5;241m.\u001b[39mLine2D)\n\u001b[0;32m-> 1632\u001b[0m lines \u001b[38;5;241m=\u001b[39m [\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_lines(\u001b[38;5;241m*\u001b[39margs, data\u001b[38;5;241m=\u001b[39mdata, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)]\n\u001b[1;32m 1633\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m line \u001b[38;5;129;01min\u001b[39;00m lines:\n\u001b[1;32m 1634\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39madd_line(line)\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/axes/_base.py:312\u001b[0m, in \u001b[0;36m_process_plot_var_args.__call__\u001b[0;34m(self, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m 310\u001b[0m this \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m args[\u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m 311\u001b[0m args \u001b[38;5;241m=\u001b[39m args[\u001b[38;5;241m1\u001b[39m:]\n\u001b[0;32m--> 312\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_plot_args\u001b[49m\u001b[43m(\u001b[49m\u001b[43mthis\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/axes/_base.py:487\u001b[0m, in \u001b[0;36m_process_plot_var_args._plot_args\u001b[0;34m(self, tup, kwargs, return_kwargs)\u001b[0m\n\u001b[1;32m 484\u001b[0m kw[prop_name] \u001b[38;5;241m=\u001b[39m val\n\u001b[1;32m 486\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(xy) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m2\u001b[39m:\n\u001b[0;32m--> 487\u001b[0m x \u001b[38;5;241m=\u001b[39m \u001b[43m_check_1d\u001b[49m\u001b[43m(\u001b[49m\u001b[43mxy\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 488\u001b[0m y \u001b[38;5;241m=\u001b[39m _check_1d(xy[\u001b[38;5;241m1\u001b[39m])\n\u001b[1;32m 489\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/matplotlib/cbook/__init__.py:1327\u001b[0m, in \u001b[0;36m_check_1d\u001b[0;34m(x)\u001b[0m\n\u001b[1;32m 1321\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m warnings\u001b[38;5;241m.\u001b[39mcatch_warnings(record\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m w:\n\u001b[1;32m 1322\u001b[0m warnings\u001b[38;5;241m.\u001b[39mfilterwarnings(\n\u001b[1;32m 1323\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124malways\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 1324\u001b[0m category\u001b[38;5;241m=\u001b[39m\u001b[38;5;167;01mWarning\u001b[39;00m,\n\u001b[1;32m 1325\u001b[0m message\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mSupport for multi-dimensional indexing\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m-> 1327\u001b[0m ndim \u001b[38;5;241m=\u001b[39m \u001b[43mx\u001b[49m\u001b[43m[\u001b[49m\u001b[43m:\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m]\u001b[49m\u001b[38;5;241m.\u001b[39mndim\n\u001b[1;32m 1328\u001b[0m \u001b[38;5;66;03m# we have definitely hit a pandas index or series object\u001b[39;00m\n\u001b[1;32m 1329\u001b[0m \u001b[38;5;66;03m# cast to a numpy array.\u001b[39;00m\n\u001b[1;32m 1330\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(w) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/pandas/core/indexes/base.py:5385\u001b[0m, in \u001b[0;36mIndex.__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m 5383\u001b[0m \u001b[38;5;66;03m# Because we ruled out integer above, we always get an arraylike here\u001b[39;00m\n\u001b[1;32m 5384\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m result\u001b[38;5;241m.\u001b[39mndim \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m-> 5385\u001b[0m \u001b[43mdisallow_ndim_indexing\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresult\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 5387\u001b[0m \u001b[38;5;66;03m# NB: Using _constructor._simple_new would break if MultiIndex\u001b[39;00m\n\u001b[1;32m 5388\u001b[0m \u001b[38;5;66;03m# didn't override __getitem__\u001b[39;00m\n\u001b[1;32m 5389\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_constructor\u001b[38;5;241m.\u001b[39m_simple_new(result, name\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_name)\n", - "File \u001b[0;32m~/miniforge3/lib/python3.9/site-packages/pandas/core/indexers/utils.py:341\u001b[0m, in \u001b[0;36mdisallow_ndim_indexing\u001b[0;34m(result)\u001b[0m\n\u001b[1;32m 333\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 334\u001b[0m \u001b[38;5;124;03mHelper function to disallow multi-dimensional indexing on 1D Series/Index.\u001b[39;00m\n\u001b[1;32m 335\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 338\u001b[0m \u001b[38;5;124;03min GH#30588.\u001b[39;00m\n\u001b[1;32m 339\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 340\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m np\u001b[38;5;241m.\u001b[39mndim(result) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m--> 341\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 342\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMulti-dimensional indexing (e.g. `obj[:, None]`) is no longer \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 343\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msupported. Convert to a numpy array before indexing instead.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 344\u001b[0m )\n", - "\u001b[0;31mValueError\u001b[0m: Multi-dimensional indexing (e.g. `obj[:, None]`) is no longer supported. Convert to a numpy array before indexing instead." - ] + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "image/png": { - "height": 490, - "width": 489 + "height": 489, + "width": 490 } }, "output_type": "display_data" @@ -1034,7 +1007,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.7" + "version": "3.11.4" } }, "nbformat": 4, diff --git a/slides/ensemble.pdf b/slides/ensemble.pdf index d8070e12..174abee0 100644 Binary files a/slides/ensemble.pdf and b/slides/ensemble.pdf differ diff --git a/slides/ensemble.tex b/slides/ensemble.tex index de748fd2..36cfd242 100644 --- a/slides/ensemble.tex +++ b/slides/ensemble.tex @@ -691,7 +691,7 @@ \begin{figure}[htp] \centering - \begin{notebookbox}{https://nipunbatra.github.io/ml-teaching/notebooks/boosting-explanation.ipynb} + \begin{notebookbox}{https://nipunbatra.github.io/ml-teaching/notebooks/boosting-explanation.html} % \includegraphics[scale=0.8]{../figures/decision-trees/entropy.pdf} \includegraphics[scale=0.55]{../figures/ensemble/alpha-boosting.pdf} \end{notebookbox} @@ -700,7 +700,7 @@ \pause \begin{column}{0.5\textwidth} \begin{figure}[htp] \centering - \begin{notebookbox}{https://nipunbatra.github.io/ml-teaching/notebooks/boosting-explanation.ipynb} + \begin{notebookbox}{https://nipunbatra.github.io/ml-teaching/notebooks/boosting-explanation.html} \includegraphics[scale=0.55]{../figures/ensemble/alpha-boosting-weight.pdf} \end{notebookbox} \end{figure} @@ -775,7 +775,7 @@ \begin{figure} % \includegraphics[scale=0.25]{../figures/ensemble/feature-imp-\thetree.pdf} \centering - \begin{notebookbox}{https://nipunbatra.github.io/ml-teaching/notebooks/ensemble-feature-importance.ipynb} + \begin{notebookbox}{https://nipunbatra.github.io/ml-teaching/notebooks/ensemble-feature-importance.html} \includegraphics[scale=0.25]{../figures/ensemble/feature-imp-\thetree.pdf} \end{notebookbox} @@ -804,7 +804,7 @@ \begin{frame}{Computed Feature Importance} \begin{figure}[htp] \centering - \begin{notebookbox}{https://nipunbatra.github.io/ml-teaching/notebooks/ensemble-feature-importance.ipynb} + \begin{notebookbox}{https://nipunbatra.github.io/ml-teaching/notebooks/ensemble-feature-importance.html} \includegraphics[scale=0.8]{../figures/ensemble/feature-imp-forest.pdf} \end{notebookbox} \end{figure}