Minor word smithing.

02-Discrete-Bayes.ipynb

@@ -399,7 +399,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlwAAACeCAYAAADno9QmAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ed1f2a58>"
+       "<matplotlib.figure.Figure at 0x242232f4b38>"
       ]
      },
      "metadata": {},
@@ -506,7 +506,7 @@
     "\n",
     "Lets say we get a reading of **door**, and suppose that testing shows that the sensor is 3 times more likely to be right than wrong. We should scale the probability distribution by 3 where there is a door. If we do that the result will no longer be a probability distribution, but we will learn how to correct that in a moment.\n",
     "\n",
-    "Let's look at that in Python code. Here I use the variable `z` to denote the measurement as that is a customary choice in the literature. I try to write this book from the perspective of a programmer who uses meaningful names, not a mathematician that uses one letter variables, but one goal I have is to have you reading the literature, so you need to become familiar with the naming conventions."
+    "Let's look at that in Python code. Here I use the variable `z` to denote the measurement. `z` or `y` are customary choices in the literature for the measurement."
    ]
   },
   {
@@ -528,7 +528,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlwAAACeCAYAAADno9QmAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ed645940>"
+       "<matplotlib.figure.Figure at 0x24223436518>"
       ]
      },
      "metadata": {},
@@ -586,15 +586,16 @@
     "\n",
     "```Python\n",
     "from filterpy.discrete_bayes import normalize\n",
+    "normalize(belief)\n",
     "```\n",
     "\n",
-    "It is a bit odd to be talking about \"3 times as likely to be right as wrong\". We are working in probabilities, so let's specify the probability of the sensor being correct, and computing the scale factor from that. The equation for that is\n",
+    "It is a bit odd to say \"3 times as likely to be right as wrong\". We are working in probabilities, so let's specify the probability of the sensor being correct, and compute the scale factor from that. The equation for that is\n",
     "\n",
     "$$scale =  \\frac{prob_{correct}}{prob_{incorrect}} = \\frac{prob_{correct}} {1-prob_{correct}}$$\n",
     "\n",
     "\n",
     "\n",
-    "Also, the `for` loop is cumbersome. NumPy lets you index arrays with boolean arrays. You create a boolean array with logical operators:"
+    "Also, the `for` loop is cumbersome. NumPy lets you index arrays with boolean arrays. You create a boolean array with logical operators. We can find all the doors in the hallway with:"
    ]
   },
   {
@@ -655,7 +656,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmUAAACeCAYAAABzRX3UAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3X9UVHX+P/DnMEAOah5cdPhlIiqoYGQMkQx+1owfR9Fd\nq5WoNkXWbMpIoINK4TlbymorJxSSwU0XRbcjnVXLbaGYjB8isuugcFJBc5WMnJmzrIVoJjjM94++\nze4IOgPOdO+Mz8c5c07zntd939frDKd5+b6/JCaTyQQiIiIiEpSb0AkQEREREZsyIiIiIlFgU0ZE\nREQkAmzKiIiIiESATRkRERGRCLApIyIiIhIBNmVEREREImBzU1ZcXIzg4GDIZDIoFArU19ffNra1\ntRVz5syBr68vZDIZJk6ciDfeeAO9vb0WcbW1tVAoFJDJZJg0aRK2bds29EqIiIiInJhNTVl5eTky\nMjKQm5uL5uZmxMTEYO7cuejo6Bgw3tPTE6mpqdBoNDh79iy2bNmCHTt2YO3ateaY9vZ2JCUlITY2\nFs3NzVizZg3S09Nx4MAB+1RGRERE5EQkttzR/9FHH8VDDz2EkpIS81hISAgWLVqEvLw8m3b02muv\nobGxEUeOHAEArF69Gh9++CHOnDljjnnhhRdw+vRpcwwRERHRvcLqSllvby+ampoQHx9vMZ6QkICG\nhgabdnLu3Dl88sknmD17tnmssbERCQkJFnGJiYnQarUwGo02zUtERETkKtytBXR2dsJoNEIul1uM\ny+VyHDp06I7bKpVKHD9+HD09PXjhhRcsVtX0en2/Rk8ul+PmzZvo7Oy02F9XV5dNxRARERE5g1Gj\nRvUbc+jVlx988AFOnDiB999/H3//+9+xceNGR+6OiIiIyGlZXSnz8fGBVCqFwWCwGDcYDPD19b3j\ntgEBAQCAKVOm4ObNm1i2bBlWrVoFNzc3+Pr6Djinu7s7fHx8BlsHERERkVOz2pR5eHggMjISGo0G\nTz31lHlco9Fg0aJFNu/IaDSaX25ubpg5cyY+/PBDi5iqqiooFApIpdLbzjPQct/d0Gq1AACFQmHX\necXC1esDXL9G1uf8XL1GV68PcP0aWd/Pw9rpWFabMgDIysrC4sWLERUVBaVSCbVaDZ1OB5VKBQDI\nycnBsWPH8NlnnwEA9uzZg2HDhmH69Onw9PTEsWPH8Prrr2PRokXw8PAAAKhUKmzduhWZmZl48cUX\nUV9fj7KyMuzdu/du6iUiIiJySjY1ZcnJybh8+TLy8vKg0+kQHh6OyspKBAYGAvjxpP0LFy78d1J3\nd2zYsAHnzp2DyWTC+PHjkZ6ejoyMDHNMUFAQKioqkJmZiZKSEvj7+6OoqAgLFy60c4lERERE4mdT\nUwb8uLL108rYrUpLSy3ep6SkICUlxeqcs2bNMi8pEhEREd3L+OxLIiIiIhFgU0ZEREQkAmzKiIiI\niESATRkRERGRCLApIyIiIhIBNmVEREREIsCmjIiIiEgE2JQRERERiQCbMiIiIiIRsLkpKy4uRnBw\nMGQyGRQKBerr628bW1tbi4ULF8Lf3x/Dhw9HREREv7v+19bWws3NzeIllUpx9uzZoVdDRERE5KRs\nasrKy8uRkZGB3NxcNDc3IyYmBnPnzkVHR8eA8Q0NDXjwwQexb98+nDp1Ci+99BKWL1/e72HjEokE\nra2t0Ov10Ov10Ol0mDx58t1XRURERORkbHr2ZUFBAdLS0pCWlgYAKCwsxCeffAK1Wo28vLx+8Tk5\nORbvVSoVqqursW/fvn7PxBwzZgxGjx491PyJiIiIXILVlbLe3l40NTUhPj7eYjwhIQENDQ027+jK\nlSvw9va2GDOZTFAoFPD390dcXBxqampsno+IiIjIlUhMJpPpTgE6nQ4BAQGoq6tDbGyseXzdunV4\n//330draanUnH3/8MZ566ik0NDQgMjISAHD27FnU1NQgKioKPT09KCsrQ0lJCerq6qBUKi227+rq\nMv/3l19+OagCiYiIiMTgf0/RGjVqVL/PbTp8eTeOHDmC5557DkVFReaGDABCQkIQEhJifh8dHY32\n9nZs2rSpX1NGRERE5OqsNmU+Pj6QSqUwGAwW4waDAb6+vnfctr6+HklJSVi/fj2WL19uNZno6GiU\nl5ffMUahUFidZzC0Wq1D5hULV68PcP0aWZ/zc/UaXb0+wPVrZH0/j/898jcQq+eUeXh4IDIyEhqN\nxmJco9HccUWrrq4O8+bNw1tvvYX09HSbkj1x4gT8/PxsiiUiIiJyJTYdvszKysLixYsRFRUFpVIJ\ntVoNnU4HlUoF4MerLY8dO4bPPvsMAFBTU4P58+djxYoVSElJMa+ySaVS+Pj4AAC2bNmCoKAghIWF\noaenB7t378bBgwexf/9+R9RJREREJGo2NWXJycm4fPky8vLyoNPpEB4ejsrKSgQGBgIA9Ho9Lly4\nYI7ftWsXrl+/jvz8fOTn55vHx48fj/PnzwMAenp6sGrVKnR0dEAmkyEsLAwVFRVITEy0Z31ERERE\nTsHmE/1VKpV5ZexWt96tv7S0tN/YrbKzs5GdnW3r7omIiIhcGp99SURERCQCbMqIiIiIRIBNGRER\nEZEIsCkjIiIiEgE2ZUREREQiwKaMiIiISATYlBERERGJAJsyIiIiIhFgU0ZEREQkAjY3ZcXFxQgO\nDoZMJoNCoUB9ff1tY2tra7Fw4UL4+/tj+PDhiIiIGPAO/7W1tVAoFJDJZJg0aRK2bds2tCqIiIiI\nnJxNTVl5eTkyMjKQm5uL5uZmxMTEYO7cuejo6BgwvqGhAQ8++CD27duHU6dO4aWXXsLy5cuxd+9e\nc0x7ezuSkpIQGxuL5uZmrFmzBunp6Thw4IB9KiMiIiJyIjY9+7KgoABpaWlIS0sDABQWFuKTTz6B\nWq1GXl5ev/icnByL9yqVCtXV1di3bx9SUlIAAGq1GgEBAdi8eTMAIDQ0FP/4xz+Qn5+PJ5544q6K\nIiIiInI2VlfKent70dTUhPj4eIvxhIQENDQ02LyjK1euwNvb2/y+sbERCQkJFjGJiYnQarUwGo02\nz0tERETkCqyulHV2dsJoNEIul1uMy+VyHDp0yKadfPzxx/j8888tmji9Xt+v0ZPL5bh58yY6Ozv7\n7e8nWq3Wpn0OlqPmFQtXrw9w/RpZn/Nz9RpdvT7A9WtkfY41efLkO37u8Ksvjxw5gueeew5FRUWI\njIx09O6IiIiInJLVlTIfHx9IpVIYDAaLcYPBAF9f3ztuW19fj6SkJKxfvx7Lly+3+MzX13fAOd3d\n3eHj43PbORUKhbWUB+Wnrtne84qFq9cHuH6NrM/5uXqNrl4f4Po1sr6fR1dX1x0/t7pS5uHhgcjI\nSGg0GotxjUYDpVJ52+3q6uowb948vPXWW0hPT+/3+cyZM/vNWVVVBYVCAalUai0tIiIiIpdi0+HL\nrKws7Ny5Ezt27EBbWxtWrlwJnU4HlUoF4MerLePi4szxNTU1mDdvHl566SWkpKTAYDDAYDCgs7PT\nHKNSqfDNN98gMzMTbW1t2L59O8rKypCdnW3nEomIiIjEz6ZbYiQnJ+Py5cvIy8uDTqdDeHg4Kisr\nERgYCODHk/YvXLhgjt+1axeuX7+O/Px85Ofnm8fHjx+P8+fPAwCCgoJQUVGBzMxMlJSUwN/fH0VF\nRVi4cKE96yMiIiJyCjY1ZcCPK1s/rYzd6ta79ZeWlg54B/9bzZo1a9BXQtR/9e2g4q3pHjbWIfMC\ngN9wd0z0GWlz/L86u6G7dtOuOTiyPmDwNRIR0dA54ncCENdv4b3M5qZMLNLrOq0HDckNu89Y9H8+\nmHj7axb60V276VT1AYOvkYiIhs6xvxOAGH4L72V8IDkRERGRCLApIyIiIhIBNmVEREREIsCmjIiI\niEgE2JQRERERiQCbMiIiIiIRYFNGREREJAJsyoiIiIhEwOamrLi4GMHBwZDJZFAoFKivr79t7I0b\nN7B06VJERETA09MTc+bM6RdTW1sLNzc3i5dUKsXZs2eHVgkRERGRE7OpKSsvL0dGRgZyc3PR3NyM\nmJgYzJ07Fx0dHQPGG41GyGQypKenY/78+bedVyKRoLW1FXq9Hnq9HjqdDpMnTx5aJUREREROzKam\nrKCgAGlpaUhLS0NoaCgKCwvh5+cHtVo9YLyXlxeKi4uxbNkyBAQE3HHuMWPGYOzYseaXRCIZfBVE\nRERETs5qU9bb24umpibEx8dbjCckJKChoeGudm4ymaBQKODv74+4uDjU1NTc1XxEREREzsrqA8k7\nOzthNBohl8stxuVyOQ4dOjTkHfv5+aGkpARRUVHo6elBWVkZHn/8cdTV1UGpVA55XjHp7u6GVvsv\n2+OHjXVgNo4x2BodSavVCp2CQ7E+5+fqNbp6fYDwNfJ34u4I/f1ZO0XLalPmKCEhIQgJCTG/j46O\nRnt7OzZt2uQyTRkRERGRraw2ZT4+PpBKpTAYDBbjBoMBvr6+dk0mOjoa5eXldp1TSCNHjoQi/AGb\n4+u/+hbADccl5ACDrdERfvqXj0KhEDQPR2F9zs/Va3T1+gDx1MjfiaERy/fX1dV1x8+tnlPm4eGB\nyMhIaDQai3GNRmP3Fa0TJ07Az8/PrnMSEREROQObDl9mZWVh8eLFiIqKglKphFqthk6ng0qlAgDk\n5OTg2LFj+Oyzz8zbtLa24saNG+js7MTVq1fR0tICAIiIiAAAbNmyBUFBQQgLC0NPTw92796NgwcP\nYv/+/faukYiIiEj0bGrKkpOTcfnyZeTl5UGn0yE8PByVlZUIDAwEAOj1ely4cMFim3nz5uHixYvm\n9zNmzIBEIoHRaAQA9PT0YNWqVejo6IBMJkNYWBgqKiqQmJhor9qIiIiInIbNJ/qrVLine truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283edb5fda0>"
+       "<matplotlib.figure.Figure at 0x24223c60ef0>"
       ]
      },
      "metadata": {},
@@ -687,7 +688,7 @@
     " \n",
     "This result is called the [*posterior*](https://en.wikipedia.org/wiki/Posterior_probability), which is short for *posterior probability distribution*. All this means is a probability distribution *after* incorporating the measurement information (posterior means 'after' in this context). To review, the *prior* is the probability distribution before including the measurement's information. \n",
     "\n",
-    "Another term is the [*likelihood*](https://en.wikipedia.org/wiki/Likelihood_function). When we computed `belief[hall==z] *= scale` we were computing how *likely* each position was given the measurement. This is not a probability distribution because it does not sum to one. Likelihoods are not probability distributions. \n",
+    "Another term is the [*likelihood*](https://en.wikipedia.org/wiki/Likelihood_function). When we computed `belief[hall==z] *= scale` we were computing how *likely* each position was given the measurement. The likelihood is not a probability distribution because it does not sum to one.\n",
     "\n",
     "The combination of these gives us the equation\n",
     "\n",
@@ -782,7 +783,7 @@
     "\n",
     "First let's deal with the simple case - assume the movement sensor is perfect, and it reports that the dog has moved one space to the right. How would we alter our `belief` array?\n",
     "\n",
-    "I hope after a moment's thought it is clear that we should shift all the values one space to the right. If we previously thought there was a 50% chance of Simon being at position 3, then after he moved one position to the right we should believe that there is a 50% chance he is at position 4. The hallway is circular, so we will use modulo arithmetic to perform the shift."
+    "I hope that after a moment's thought it is clear that we should shift all the values one space to the right. If we previously thought there was a 50% chance of Simon being at position 3, then after he moved one position to the right we should believe that there is a 50% chance he is at position 4. The hallway is circular, so we will use modulo arithmetic to perform the shift."
    ]
   },
   {
@@ -796,7 +797,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmUAAACrCAYAAAAn8uvKAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283edf71160>"
+       "<matplotlib.figure.Figure at 0x24223cb52e8>"
       ]
      },
      "metadata": {},
@@ -812,13 +813,13 @@
     "    result = np.zeros(n)\n",
     "    for i in range(n):\n",
     "        result[i] = belief[(i-move) % n]\n",
-    "    belief[:] = result # copy back to original array\n",
+    "    return result\n",
     "        \n",
     "belief = np.array([.35, .1, .2, .3, 0, 0, 0, 0, 0, .05])\n",
     "plt.subplot(121)\n",
     "book_plots.bar_plot(belief, title='Before prediction', ylim=(0, .4))\n",
     "\n",
-    "perfect_predict(belief, 1)\n",
+    "belief = perfect_predict(belief, 1)\n",
     "plt.subplot(122)\n",
     "book_plots.bar_plot(belief, title='After prediction', ylim=(0, .4))"
    ]
@@ -1623,7 +1624,8 @@
     "set_figsize(y=2)\n",
     "fig = plt.figure()\n",
     "for _ in range(50):\n",
-    "    perfect_predict(belief, 1) # Simon takes one step to the right\n",
+    "    # Simon takes one step to the right\n",
+    "    belief = perfect_predict(belief, 1)\n",
     "    plt.cla()\n",
     "    book_plots.bar_plot(belief, ylim=(0, .4))\n",
     "    fig.canvas.draw()\n",
@@ -1676,7 +1678,7 @@
    "source": [
     "## Adding Uncertainty to the Prediction\n",
     "\n",
-    "We want to solve real world problems, and we have already stated that all sensors have noise. Therefore the code above is incorrect since it assumes we have perfect measurements for the movement. What if the sensor reported that our dog moved one space, but he actually moved two spaces, or zero? Once again this may initially sound like an insurmountable problem, but let's model it and see what happens. We will create a simple noise model for the sensor. Later we will handle more complicated error models.\n",
+    "`perfect_sensor()` assumes perfect measurements, but all sensors have noise. What if the sensor reported that our dog moved one space, but he actually moved two spaces, or zero? This may sound like an insurmountable problem, but let's model it and see what happens.\n",
     "\n",
     "Assume that the sensor's movement measurement is 80% likely to be correct, 10% likely to overshoot one position to the right, and 10% likely to undershoot to the left. That is, if the movement measurement is 4 (meaning 4 spaces to the right), the dog is 80% likely to have moved 4 spaces to the right, 10% to have moved 3 spaces, and 10% to have moved 5 spaces.\n",
     "\n",
@@ -1694,7 +1696,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAACcCAYAAAC9SeXkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283edb3d940>"
+       "<matplotlib.figure.Figure at 0x2422406fdd8>"
       ]
      },
      "metadata": {},
@@ -1736,7 +1738,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAACcCAYAAAC9SeXkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283edf71eb8>"
+       "<matplotlib.figure.Figure at 0x24224010518>"
       ]
      },
      "metadata": {},
@@ -1755,7 +1757,7 @@
    "source": [
     "Here the results are more complicated, but you should still be able to work it out in your head. The 0.04 is due to the possibility that the 0.4 belief undershot by 1. The 0.38 is due to the following: the 80% chance that we moved 2 positions (0.4 $\\times$ 0.8) and the 10% chance that we undershot (0.6 $\\times$ 0.1). Overshooting plays no role here because if we overshot both 0.4 and 0.6 would be past this position. **I strongly suggest working some examples until all of this is very clear, as so much of what follows depends on understanding this step.**\n",
     "\n",
-    "If you look at the probabilities after performing the update you probably feel dismay. In the example above we started with probabilities of 0.4 and 0.6 in two positions; after performing the update the probabilities are not only lowered, but they are strewn out across the map.\n",
+    "If you look at the probabilities after performing the update you might be dismayed. In the example above we started with probabilities of 0.4 and 0.6 in two positions; after performing the update the probabilities are not only lowered, but they are strewn out across the map.\n",
     "\n",
     "This is not a coincidence, or the result of a carefully chosen example - it is always true of the evolution (predict step). If the sensor is noisy we lose some information on every prediction. Suppose we were to perform the prediction an infinite number of times - what would the result be? If we lose information on every step, we must eventually end up with no information at all, and our probabilities will be equally distributed across the `belief` array. Let's try this with 100 iterations. The plot is animated; recall that you put the cursor in the cell and press Ctrl-Enter to execute the code and see the animation."
    ]
@@ -2657,7 +2659,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAACcCAYAAAC9SeXkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ed636780>"
+       "<matplotlib.figure.Figure at 0x24224061e10>"
       ]
      },
      "metadata": {},
@@ -2692,7 +2694,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAACcCAYAAAC9SeXkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283edb7cfd0>"
+       "<matplotlib.figure.Figure at 0x242241b8828>"
       ]
      },
      "metadata": {},
@@ -2750,7 +2752,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAACcCAYAAAC9SeXkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283edb7c320>"
+       "<matplotlib.figure.Figure at 0x242241f7128>"
       ]
      },
      "metadata": {},
@@ -2785,7 +2787,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAACcCAYAAAC9SeXkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAFPVJREFUeJzt3X+05HV93/Hna1k0IHgTxVIFl1ZYUamt0c1qCyFGNGBy\nCjbYBtTYxgZILOBJe1IS+sMc9URj0uaHkMhGxGhISIKmYGoo0GApyVH2KoI/dmUFRH5pROGWX5pl\nefeP+e463LN7Z/bez3fu3bnPxzlz7sx3PvN9f753hxfv+Xxn5qaqkCRJ0tKtWe4JSJIkTQsbK0mS\npEZsrCRJkhqxsZIkSWrExkqSJKkRGytJkqRGbKy04iW5I8n5yz0PSUpyXZJNyz0PrVzxe6zUUpI3\nAh+pqmZNe5JnAo9W1WOt9ilJi5Hk+4HHq+rh5Z6LViZXrNRagCbdepL9AarqW0ttqnbuS5IWYyiP\nHlxqU2UeTTcbq1WmW8a+OMm7k3wzyVySi5I8pbt/bZL3JLk7yXeTfDHJ6fP28bNJvpTksSTfSvLJ\nJM9J8iPAh7sxTyTZkeSDQ487J8mW7nFfTnJ+kv2G7r8jyTuTXJjkfuD6bvtXh08FJjmom/PfJvlO\nks1JXjN0/xFd/Tck+Z9JHgbe0dOvVNI+aIwsvC7JB5K8I8m9wJ3d9k8OnwocMzOf6PLv0iQP0uWk\nptPa5Z6AlsXrgcuA44CjgA8CDwP/AXg38G+As4BbgH8J/GGSr1fVdUleCvxeN+Z64OnAy7v9/jVw\nNvA+4FAGq1ePAST5FeBfA28DbgZeCLwfeCrw9qG5nQP8d+AVfO/5OX8F7BLgZcAbgLuAnwf+IsmL\nq+rWoXHvAc4D3rpXvx1Jq8VCWQiD/LsUeBWw80Xg/DxaMDOHxv1XBln3n3FRY7pVlZdVdAGuA26n\ne39dt+0M4FHgQOA7wFnzHvMx4Nru+uuAB4CD9rD/NwI75m07AHgE+LF5238aeGDo9h3ANbvZ5x3A\n+d31I4EngBPnjfkM8IHu+hHdmPOX+/ftxYuXlXkZkYUHdPdv3cPjNnXXDxiVmd3tJ3Y+xsv0X+ya\nV6cbq/uvvfPXDFaOjgSeAvzfeeP/D3BMd/0aBo3OV5P8cZIzujeXL+QYBgH00SQP7bwAFwEHz3v8\njSP29SIGrxjnz/H6oTnutHnEviStbgtlIQxesC3kKGB/Fs7MncyjVcJTgRo28k3nVfVIkpcBxwKv\nBn4OeG+SV1XVTXt42M4G/vXAtt3c/+2h64/sxXxHabkvSavPOBmShvvSFHDFanX6oSTDYXAs8F3g\ntu7n8fPGvxL4ws4bNXBDVf1KVb0MuI/B+50A/g5g3v6/yGC5/Miqun03l735FOEXu5/z53j88Bwl\naQwLZeE4vsIYmanVxRWr1emZwIVJfofBkvc7gPdX1WPdtnd2n8q7mcEbMf85g9UpkpwMPI/Bqbdv\nAhuAw/lew3NH9/OUJDcAj3WrXL8K/GqXYdcyeO69GPjBqvqlcSdeVbcnuRz43SQ/x+CTOm9lsOx+\n2qJ+G5JWq4WycOSDx8lMrT42VqvT5cBDwA0M3h9wGfDL3X3/CdgB/CbwLAavyN5YVZ/s7n+AQWj8\nMnAwg0/lvbOqPgRQVbNJfpvBJ/6eBfwB8Jaqelf3keWzgd9g8GnBW4EPDc1rTytX87f/W+DXgY8w\n+FTi54GfqKptCzxGkuZbKAvHzaNRmbnQvjSFxvrm9SQnAb/F4NThxVX1a/Pu/xHgCgafsAD4WFW9\nq/Fc1UCS64BtVXXmcs9FmjSzTDuZherLyBWrJGuAC4ATgHuBzUmuqKqt84ZeX1Un9zBHSVoys0zS\nJIzz5vWNDLr6O6tqO4Ol0lN2M27cT0ZoebkkrdXKLNMws1C9GOc9VocxeB/NTnczCKj5/mmSzwH3\nAL9YVV9qMD81VlWvWu45SMvELNMuZqH60urN658B1lXVo0leC/wP4PnDA+bm5nx1IImZmZmVvCI0\nMsvAPJM0sLs8G+dU4D3AuqHbh3fbdqmqh6vq0e76XwL7J3nGEuYqSa2ZZZJ6N05jtRk4KskR3V/9\nPg24cnhAkkOHrm9k8GnDbyNJK4dZJql3I08FVtWOJGcDV/O9jyhvSXLW4O7aBLw+yc8D2xl8P9FP\nLbTPmZmZPd43OzsLwIYNG8Y9hkWZpjrTdCyTquOxTLbO3Nxc6+nstT6yDFZPnnksq7vONB3LUuuM\nyrOx3mNVVVcBR8/bdtHQ9QuBC/d6dpI0QWaZpL75twIlSZIasbGSJElqxMZKkiSpERsrSZKkRmys\nJEmSGrGxkiRJasTGSpIkqREbK0mSpEZsrCRJkhqxsZIkSWrExkqSJKkRGytJkqRGbKwkSZIasbGS\nJElqZKzGKslJSbYmuTXJeQuM+6Ek25P8ZLspSlIbZpmkvo1srJKsAS4ATgSOAU5P8oI9jHsP8L9a\nT1KSlsoskzQJ46xYbQS2VdWdVbUduAw4ZTfjzgEuB/624fwkqRWzTFLvxmmsDgPuGrp9d7dtlyTP\nAV5XVb8HpN30JKkZs0xS71JVCw9ITgVOrKozu9tvAjZW1blDY/4U+I2qujHJJcBfVNVHh/czNze3\nq9C2bdsaHoKklW79+vW7rs/MzCxLw9Iqy8A8k1azUXm2dox93AOsG7p9eLdt2AbgsiQBDgFem2R7\nVV251zOWpH6YZZJ6N86K1X7Al4ETgPuAG4HTq2rLHsZfAny8qj42vH34Fd7MzMwe683OzgKwYcOG\nsQ5gsaapzjQdy6TqeCyTrTM3N7fr+jKuWDXJMlideeaxrO4603QsS60zKs9GrlhV1Y4kZwNXM3hP\n1sVVtSXJWYO7a9P8h+z1LCWpZ2aZpEkY51QgVXUVcPS8bRftYexbGsxLkpozyyT1zW9elyRJasTG\nSpIkqREbK0mSpEZsrCRJkhqxsZIkSWrExkqSJKkRGytJkqRGbKwkSZIasbGSJElqxMZKkiSpERsr\nSZKkRmysJEmSGrGxkiRJamSsxirJSUm2Jrk1yXm7uf/kJDcnuSnJjUmObT9VSVoas0xS39aOGpBk\nDXABcAJwL7A5yRVVtXVo2LVVdWU3/sXAnwIv7GG+krQoZpmkSRhnxWojsK2q7qyq7cBlwCnDA6rq\n0aGbBwFPtJuiJDVhlknq3TiN1WHAXUO37+62PUmS1yXZAnwceEub6UlSM2aZpN6lqhYekJwKnFhV\nZ3a33wRsrKpz9zD+OODtVfWa4e1zc3O7Cm3btm2p85a0D1m/fv2u6zMzM1mOObTKMjDPpNVsVJ6N\ns2J1D7Bu6Pbh3bbdqqobgOclecb405Sk3pllkno38s3rwGbgqCRHAPcBpwGnDw9IcmRV3dZdfynw\nlKr69p52uGHDhj0Wm52dHTmmhWmqM03HMqk6Hstk68zNzbWezmI0zzJYPXnmsazuOtN0LEutMyrP\nRjZWVbUjydnA1QxWuC6uqi1JzhrcXZuAU5O8Gfg74DHgX+31TCWpR2aZpEkYZ8WKqroKOHretouG\nrr8XeG/bqUlSW2aZpL75zeuSJEmN2FhJkiQ1YmMlSZLUiI2VJElSIzZWkiRJjdhYSZIkNWJjJUmS\n1IiNlSRJUiM2VpIkSY3YWEmSJDViYyVJktSIjZUkSVIjNlaSJEmNjNVYJTkpydYktyY5bzf3vyHJ\nzd3lhiQvbj9VSVoas0xS30Y2VknWABcAJwLHAKcnecG8YbcDx1fVPwHeBfx+64lK0lKYZZImYZwV\nq43Atqq6s6q2A5cBpwwPqKpPVdVcd/NTwGFtpylJS2aWSerdOI3VYcBdQ7fvZuGw+VngL5cyKUnq\ngVkmqXepqoUHJKcCJ1bVmd3tNwEbq+rc3Yz9UQZL7cdV1QPD983Nze0qtG3btgZTl7SvWL9+/a7r\nMzMzWY45tMoyMM+k1WxUnq0dYx/3AOuGbh/ebXuSJP8Y2ASctLsgkqRlZpZJ6t04K1b7AV8GTgDu\nA24ETq+qLUNj1gH/G/jpqvrU7vYz/ApvZmZmj/VmZ2cB2LBhw7jHsCjTVGeajmVSdTyWydaZm5vb\ndX0ZV6yaZBmszjzzWFZ3nWk6lqXWGZVnI1esqmpHkrOBqxm8J+viqtqS5KzB3bUJ+C/AM4DfTRJg\ne1Vt3OvZSlJPzDJJkzDOqUCq6irg6HnbLhq6fgZwxrhFb7hzz6vrD33f3xs5Ztizn7aWIw85+Enb\nbrv/Ie575PEFH7c3dXZXQ5qE1s9lWN3P59ZZJknzjdVYtXbO9fePMeq7Y+3rfccfwpGHPHnbfY88\nPmaN8ersroY0Ca2fy+DzWZL65J+0kSRJamRZVqwkSaONcyoYlv7WBt8+IbVjYyVJK9TenQqGxb61\nwbdPSO14KlCSJKkRV6wkSdJUmNTp84XYWEmSpKkwqdPnC/FUoCRJUiM2VpIkSY3YWEmSJDViYyVJ\nktSIjZUkSVIjNlaSJEmNjNVYJTkpydYktyY5bzf3H53kb5J8J8m/bz9NSVo6s0xS30Z+j1WSNcAF\nwAnAvcDmJFdU1dahYd8CzgFe18ssJWmJzDJJkzDOitVGYFtV3VlV24HLgFOGB1TV/VX1GWD0151K\n0vIwyyT1bpzG6jDgrqHbd3fbJGlfYpZJ6t0+/ydtHnroIWZnb3vytu5vAPVZY2/Nzs42ms3y1pi2\nOiv9WFo/l2Hpz+fFHMv69esXXW+lG+f3sdL//c1M66ykGkupM4n/Zkbl2TgrVvcA64ZuH95tk6R9\niVkmqXfjrFhtBo5KcgRwH3AacPoC49NiYuM6+OCD2fCP1j1p2+CvVY/+w4pLqTGunV33hg0bms1n\nOWpMW5195VhaP5dh8c/npRzL3NzcXj+mB71k2UK/j33l39/MtM5KqNGiziT+mxmVZLine truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ee0d2a90>"
+       "<matplotlib.figure.Figure at 0x2422420b160>"
       ]
      },
      "metadata": {},
@@ -2816,7 +2818,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAACcCAYAAAC9SeXkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ef341438>"
+       "<matplotlib.figure.Figure at 0x242244623c8>"
       ]
      },
      "metadata": {},
@@ -2847,7 +2849,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAACcCAYAAAC9SeXkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ee1e2278>"
+       "<matplotlib.figure.Figure at 0x2422434ec18>"
       ]
      },
      "metadata": {},
@@ -2880,7 +2882,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAACcCAYAAAC9SeXkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ed5ff780>"
+       "<matplotlib.figure.Figure at 0x24223c99048>"
       ]
      },
      "metadata": {},
@@ -2914,7 +2916,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAS4AAADmCAYAAABrjGguAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ee25e1d0>"
+       "<matplotlib.figure.Figure at 0x242242d2940>"
       ]
      },
      "metadata": {},
@@ -5429,7 +5431,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAoAAAAGGCAYAAADrfDCjAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ed5eb4e0>"
+       "<matplotlib.figure.Figure at 0x242240fdb38>"
       ]
      },
      "metadata": {},
@@ -5630,7 +5632,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAACRCAYAAAAB1/Y6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAADuZJREFUeJzt3X2snnV9x/H3p3aCaD1TeXBS200pMGEKeizGp8BkFlhi\nN/ljlKGZy4RlYo1ZJgvJ4j+GbYlumeIm3RiORcUJGnFDBKOZqZvYo0V8aMNBttIW5GGWe1EDq913\nf9wXzdlZzzk39Hd2P/T9Sk7O9fA91/395U7v8+nvuvprqgpJkiQdvhXDbkCSJGlSGKwkSZIaMVhJ\nkiQ1YrCSJElqxGAlSZLUiMFKkiSpkSWDVZJrkzyY5K5Faj6YZDbJnUnOaNuiJEnSeBhkxuo6YMNC\nJ5OcD7y4qtYBlwEfadSbJEnSWFkyWFXVVmDfIiUbgeu72juAqSQntGlPkiRpfLR4xupEYPec/b3d\nMUmSpCPKyv+vF+r1ev7fOZIkaWJMTU1l/rEWM1Z7gRfO2V/dHZMkSTqiDBqs0n0dys3AWwGSvAp4\ntKoebNCbJEnSWFnyVmCSjwNnA89Lch/wXuDpQFXVlqq6JckFSe4Bfgy8balrTk1NHV7X88zMzAAw\nPT3d9LqjYtLHB5M/Rsc3/kZljFt37eOdX3lkqD08FR96/bG8du1zhvb6o/L+LadJH+OojK/X6y16\nfslgVVUXD1Bz+ZPoSZIkaSK58rokSVIjBitJkqRGDFaSJEmNGKwkSZIaMVhJkiQ1YrCSJElqxGAl\nSZLUiMFKkiSpEYOVJElSIwYrSZKkRgxWkiRJjRisJEmSGjFYSZIkNWKwkiRJamSgYJXkvCQ7k9yd\n5IpDnH92kpuT3Jnk20l+q3mnkiRJI27JYJVkBXA1sAE4DdiU5NR5Ze8AvltVZwDnAB9IsrJ1s5Ik\nSaNskBmr9cBsVe2qqv3ADcDGeTUFrOq2VwH/UVU/bdemJEnS6BskWJ0I7J6zv6c7NtfVwEuS3A98\nC3hXm/YkSZLGR6pq8YLkQmBDVV3a7V8CrK+qzfNqXl1Vv5/kxcDtwEur6kdP1PR6vYMvNDs723YU\nknSEePjo47ly++PDbuNJu+rMozjusYeG3YZ02NatW3dwe2pqKvPPDzJjtRdYM2d/dXdsrrcBnwao\nqu8D/wbMfw5LkiRpog3ygPk24KQka4EHgIuATfNqdgHnAl9NcgJwMnDvQhecnp5+at0uYGZmZlmu\nOyomfXww+WN0fONvVMa4ddc+YPxmrFatWsX06WuWLlwmo/L+LadJH+OojK/X6y16fslgVVUHklwO\n3EZ/huvaqtqR5LL+6doCvA/4aJK7uh97T1X98PBalyRJGi8DLYlQVbcCp8w7ds2c7QfoL8cgSZJ0\nxHLldUmSpEYMVpIkSY0YrCRJkhoxWEmSJDVisJIkSWrEYCVJktSIwUqSJKkRg5UkSVIjBitJkqRG\nDFaSJEmNGKwkSZIaMVhJkiQ1YrCSJElqZKBgleS8JDuT3J3kigVqzk6yPcl3kny5bZuSJEmjb+VS\nBUlWAFcDbwDuB7Yl+WxV7ZxTMwV8GHhjVe1NcuxyNSxJkjSqBpmxWg/MVtWuqtoP3ABsnFdzMXBT\nVe0FqKpH2rYpSZI0+gYJVicCu+fs7+mOzXUy8NwkX06yLclbWjUoSZI0LlJVixckFwIbqurSbv8S\nYH1VbZ5T8yHgFcAvA88E/hW4oKrueaKm1+sdfKHZ2dmWY5CkI8bDRx/PldsfH3YbT9pVZx7FcY89\nNOw2pMO2bt26g9tTU1OZf37JZ6yAvcCaOfuru2Nz7QEeqarHgMeSfAV4GXAPkiRJR4hBgtU24KQk\na4EHgIuATfNqPgt8KMnTgKOAs4A/W+iC09PTT63bBczMzCzLdUfFpI8PJn+Mjm/8jcoYt+7aB4zf\njNWqVauYPn3N0oXLZFTev+U06WMclfH1er1Fzy8ZrKrqQJLLgdvoP5N1bVXtSHJZ/3RtqaqdSb4A\n3AUcALZU1fcOv31JkqTxMciMFVV1K3DKvGPXzNt/P/D+dq1JkiSNF1delyRJasRgJUmS1IjBSpIk\nqRGDlSRJUiMGK0mSpEYMVpIkSY0YrCRJkhoxWEmSJDVisJIkSWrEYCVJktSIwUqSJKkRg5UkSVIj\nBitJkqRGBgpWSc5LsjPJ3UmuWKTulUn2J3lzuxYlSZLGw5LBKskK4GpgA3AasCnJqQvU/QnwhdZN\nSpIkjYNBZqzWA7NVtauq9gM3ABsPUfdO4EbgoYb9SZIkjY1BgtWJwO45+3u6YwcleQHwa1X1V0Da\ntSdJkjQ+UlWLFyQXAhuq6tJu/xJgfVVtnlPzD8D7q+rrSa4D/rGqbpp7nV6vd/CFZmdnGw5Bko4c\nDx99PFduf3zYbTxpV515FMc95g0Njb9169Yd3J6amvo/k0krB7jGXmDNnP3V3bG5poEbkgQ4Fjg/\nyf6quvlJdyxJkjSmBglW24CTkqwFHgAuAjbNLaiqFz2x3c1YfW6xUDU9Pf3Uul3AzMzMslx3VEz6\n+GDyx+j4xt+ojHHrrn3A+M1YrVq1iunT1yxduExG5f1bTpM+xlEZX6/XW/T8ksGqqg4kuRy4jf4z\nWddW1Y4kl/VP15b5P/JUm5UkSRpng8xYUVW3AqfMO3bNArW/3aAvSZKksePK65IkSY0YrCRJkhox\nWEmSJDVisJIkSWrEYCVJktSIwUqSJKkRg5UkSVIjBitJkqRGDFaSJEmNGKwkSZIaMVhJkiQ1YrCS\nJElqxGAlSZLUyEDBKsl5SXYmuTvJFYc4f3GSb3VfW5P8UvtWJUmSRtuSwSrJCuBqYANwGrApyanz\nyu4FXl9VLwPeB/x160YlSZJG3SAzVuuB2araVVX7gRuAjXMLquprVdXrdr8GnNi2TUmSpNE3SLA6\nEdg9Z38Piwen3wE+fzhNSZIkjaNU1eIFyYXAhqq6tNu/BFhfVZsPUXsO/duGr62qfXPP9Xq9gy80\nOzvboHVJOvI8fPTxXLn98WG38aRddeZRHPfYQ8NuQzps69atO7g9NTWV+edXDnCNvcCaOfuru2P/\nS5KXAluA8+aHKkmSpCPBIMFqG3BSkrXAA8BFwKa5BUnWADcBb6mq7y91wenp6afQ6sJmZmaW5bqj\nYtLHB5M/Rsc3/kZljFt37QPGb8Zq1apVTJ++ZunCZTIq799ymvQxjsr4er3eoueXDFZVdSDJ5cBt\n9J/JuraqdiS5rH+6tgB/BDwX+MskAfZX1frD7l6SJGmMDDJjRVXdCpwy79g1c7bfDry9bWuSJEnj\nxZXXJUmSGjFYSZIkNWKwkiRJasRgJUmS1IjBSpIkqRGDlSRJUiMGK0mSpEYMVpIkSY0YrCRJkhox\nWEmSJDVisJIkSWrEYCVJktSIwUqSJKkRg5UkSVIjAwWrJOcl2Znk7iRXLFDzwSSzSe5MckbbNiVJ\nkkbfksEqyQrgamADcBqwKcmp82rOB15cVeuAy4CPLEOvkiRJI22QGav1wGxV7aqq/cANwMZ5NRuB\n6wGq6g5gKskJTTuVJEkacYMEqxOB3XP293THFqvZe4gaSZKkiZaqWrwguRDYUFWXdvuXAOuravOc\nms8Bf1xV/9LtfxF4T1V984maXq+3+AtJkiSNkampqcw/NsiM1V5gzZz91d2x+TUvXKJGkiRpog0S\nrLYBJyVZm+TpwEXAzfNqbgbeCpDkVcCjVfVg004lSZJG3MqlCqrqQJLLgdvoB7Frq2pHksv6p2tL\nVd2S5IIk9wA/Bt42/zqHmi6TJEmaJEs+YyVJkqTBjP3K64MsXjrOklyb5MEkdw27l+WQZHWSLyX5\nbpJvJ9m89E+NjyRHJbkjyfZufO8ddk/LJcmKJN9MMv9RgbGX5N+TfKt7H78+7H6WQ5KpJJ9KsqP7\n83jWsHtqJcnJ3Xv3ze57bwI/a96d5DtJ7kryse7RnYmS5F3d5+hI/64Y6xmrbvHSu4E3APfTfx7s\noqraOdTGGkryWuBHwPVV9dJh99NakucDz6+qO5M8C/gGsHHC3sNjquonSZ4GfBXYXFUT98s5ybuB\nVwDPrqo3DbuflpLcC7yiqvYNu5flkuSjwD9X1XVJVgLHVNV/Drmt5rrfG3uAs6pq91L14yDJC4Ct\nwKlV9V9JPgn8U1VdP+TWmklyGvAJ4JXAT4HPA79bVfcOtbFDGPcZq0EWLx1rVbUVmNgP86r6QVXd\n2W3/CNjBhK2BVlU/6TaPov9c4/j+bWYBSVYDFwB/M+xelkkY/8/LBSV5NvC6qroOoKp+OomhqnMu\n8P1JCVVzPA145hOhmP5kwyT5ReCOqnq8qg4AXwHePOSeDmncPygGWbxUYyLJzwNnAHcMt5O2ultk\n24EfALdX1bZh97QM/hz4AyYwNHYKuD3JtiRvH3Yzy+AXgEeSXNfdLtuS5BnDbmqZ/Ab9mY+JUVX3\nAx8A7qO/1NGjVfXF4XbV3HeA1yV5TpJj6P9F7oVL/MxQjHuw0oTobgPeCLyrm7maGFX131V1Jv31\n3c5K8pJh99RSkl8FHuxmHtN9TZrXVNXL6X+Yv6O7RT9JVgIvBz7cjfMnwB8Ot6X2kvwM8CbgU8Pu\npaUkP0v/bs1a4AXAs5JcPNyu2uoeD/lT4HbgFmA7cGCoTS1g3IPVIIuXasR1U9c3An9fVZ8ddj/L\npbu18mXgvGH30thrgDd1zyF9AjgnycQ82wFQVQ903x8GPkP/MYRJsgfYXVUz3f6N9IPWpDkf+Eb3\nPk6Sc4F7q+qH3W2yTwOvHnJPzVXVdVU1XVVnA4/Sf8Z65Ix7sBpk8dJJMKmzAE/4W+B7VfUXw26k\ntSTHJpnqtp8B/AowMQ/mA1TVlVW1pqpeRP/P4Jeq6q3D7quVJMd0M6okeSbwRvq3JLine truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ee16aac8>"
+       "<matplotlib.figure.Figure at 0x2422414a128>"
       ]
      },
      "metadata": {},
@@ -5681,7 +5683,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAACRCAYAAAAB1/Y6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ee2b1d68>"
+       "<matplotlib.figure.Figure at 0x242242ebe80>"
       ]
      },
      "metadata": {},
@@ -5715,7 +5717,7 @@
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAAFfCAYAAACMQoJKAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x283ee328a90>"
+       "<matplotlib.figure.Figure at 0x2422424eb38>"
       ]
      },
      "metadata": {},