├── .gitignore
├── .github
    └── ISSUE_TEMPLATE
    │   ├── feature_request.md
    │   └── bug_report.md
├── README.md
└── Review-Supplemental-Materials
    └── Researcher-argreement-analysis.ipynb


/.gitignore:
--------------------------------------------------------------------------------
1 | **/.ipynb_checkpoints
2 | **/flask-dashboard-volt-master/*


--------------------------------------------------------------------------------
/.github/ISSUE_TEMPLATE/feature_request.md:
--------------------------------------------------------------------------------
 1 | ---
 2 | name: Feature request
 3 | about: Suggest an idea for this project
 4 | title: ''
 5 | labels: ''
 6 | assignees: ''
 7 | 
 8 | ---
 9 | 
10 | **Is your feature request related to a problem? Please describe.**
11 | A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
12 | 
13 | **Describe the solution you'd like**
14 | A clear and concise description of what you want to happen.
15 | 
16 | **Describe alternatives you've considered**
17 | A clear and concise description of any alternative solutions or features you've considered.
18 | 
19 | **Additional context**
20 | Add any other context or screenshots about the feature request here.
21 | 


--------------------------------------------------------------------------------
/.github/ISSUE_TEMPLATE/bug_report.md:
--------------------------------------------------------------------------------
 1 | ---
 2 | name: Bug report
 3 | about: Create a report to help us improve
 4 | title: ''
 5 | labels: ''
 6 | assignees: ''
 7 | 
 8 | ---
 9 | 
10 | **Describe the bug**
11 | A clear and concise description of what the bug is.
12 | 
13 | **To Reproduce**
14 | Steps to reproduce the behavior:
15 | 1. Go to '...'
16 | 2. Click on '....'
17 | 3. Scroll down to '....'
18 | 4. See error
19 | 
20 | **Expected behavior**
21 | A clear and concise description of what you expected to happen.
22 | 
23 | **Screenshots**
24 | If applicable, add screenshots to help explain your problem.
25 | 
26 | **Desktop (please complete the following information):**
27 |  - OS: [e.g. iOS]
28 |  - Browser [e.g. chrome, safari]
29 |  - Version [e.g. 22]
30 | 
31 | **Smartphone (please complete the following information):**
32 |  - Device: [e.g. iPhone6]
33 |  - OS: [e.g. iOS8.1]
34 |  - Browser [e.g. stock browser, safari]
35 |  - Version [e.g. 22]
36 | 
37 | **Additional context**
38 | Add any other context about the problem here.
39 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | neuro-symbolic-ai-systematic-review materials
 2 | =============================================
 3 | 
 4 | Authors: Kyle Hamilton & Aparna Nayak
 5 | 
 6 | 
 7 | 
 8 | This Repo Organization
 9 | ----------------------
10 | 
11 | -   **Review-Supplemental-Materials** - notebooks documenting the review process
12 |     
13 | -   **Data** - where all the CSV files live, as well the ACL data
14 | 
15 | -   **Other-Working-Files** - notebooks for analyzing the data extracted from the studies
16 | 
17 |     -   **utils.py** - some functions used in the notebooks so the notebooks
18 |         don’t get too cluttered
19 |     -   **EDA-working-files** - these are intermediate files generated by EDA
20 |         functions - nothing to see here
21 | 
22 | 
23 | Google docs:
24 | ------------
25 | 
26 | -   [The Final 59 Papers for inclusion in the
27 |     Review](https://docs.google.com/spreadsheets/d/13P8V0L5SypFlSmETEFDfc1omGjuIntw_oiQGlIdgHSA/edit?usp=sharing).
28 | 
29 | -   [The protocol and all papers
30 |     screened/reviewed.](https://docs.google.com/spreadsheets/d/1mMiZ5twurucBnW_EScDh9GT5-io9Q7XlKVY_nIOH6rA/edit#gid=1747218129)
31 | 
32 | -   [Glossary - Referenced by the
33 |     protocol.](https://docs.google.com/spreadsheets/d/1VzW2_ytt7A-f4IG0iVJdowr2s-9A7oQmYTkCghmcWk0/edit#gid=0)
34 | 
35 | 


--------------------------------------------------------------------------------
/Review-Supplemental-Materials/Researcher-argreement-analysis.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "markdown",
   5 |    "metadata": {},
   6 |    "source": [
   7 |     "# Researcher argreement analysis"
   8 |    ]
   9 |   },
  10 |   {
  11 |    "cell_type": "code",
  12 |    "execution_count": 6,
  13 |    "metadata": {},
  14 |    "outputs": [],
  15 |    "source": [
  16 |     "# some_file.py\n",
  17 |     "import sys\n",
  18 |     "# insert at 1, 0 is the script path (or '' in REPL)\n",
  19 |     "sys.path.insert(1, '../')\n",
  20 |     "\n",
  21 |     "# import file"
  22 |    ]
  23 |   },
  24 |   {
  25 |    "cell_type": "code",
  26 |    "execution_count": 7,
  27 |    "metadata": {},
  28 |    "outputs": [
  29 |     {
  30 |      "data": {
  31 |       "text/plain": [
  32 |        "<module 'utils' from '../utils.py'>"
  33 |       ]
  34 |      },
  35 |      "execution_count": 7,
  36 |      "metadata": {},
  37 |      "output_type": "execute_result"
  38 |     }
  39 |    ],
  40 |    "source": [
  41 |     "%matplotlib inline \n",
  42 |     "import matplotlib.pyplot as plt\n",
  43 |     "import pandas as pd\n",
  44 |     "pd.set_option('display.max_colwidth', None)\n",
  45 |     "import numpy as np\n",
  46 |     "from wordcloud import WordCloud\n",
  47 |     "import utils\n",
  48 |     "import umap\n",
  49 |     "import hdbscan\n",
  50 |     "import importlib\n",
  51 |     "importlib.reload(utils)"
  52 |    ]
  53 |   },
  54 |   {
  55 |    "cell_type": "code",
  56 |    "execution_count": 10,
  57 |    "metadata": {},
  58 |    "outputs": [
  59 |     {
  60 |      "data": {
  61 |       "text/plain": [
  62 |        "'/Users/kylehamilton/anaconda3/lib/python3.7/site-packages/matplotlib/mpl-data/matplotlibrc'"
  63 |       ]
  64 |      },
  65 |      "execution_count": 10,
  66 |      "metadata": {},
  67 |      "output_type": "execute_result"
  68 |     }
  69 |    ],
  70 |    "source": [
  71 |     "import matplotlib as mpl\n",
  72 |     "plt.style.use('../presentation.mplstyle')\n",
  73 |     "mpl.matplotlib_fname()"
  74 |    ]
  75 |   },
  76 |   {
  77 |    "cell_type": "code",
  78 |    "execution_count": 11,
  79 |    "metadata": {},
  80 |    "outputs": [],
  81 |    "source": [
  82 |     "a=pd.read_csv(\"../Data/scopus-filtered-by-top-publication - Aparna.csv\")"
  83 |    ]
  84 |   },
  85 |   {
  86 |    "cell_type": "code",
  87 |    "execution_count": 12,
  88 |    "metadata": {},
  89 |    "outputs": [
  90 |     {
  91 |      "data": {
  92 |       "text/plain": [
  93 |        "Index(['Key', 'Item Type', 'Publication Year', 'Author', 'Title',\n",
  94 |        "       'Abstract Note', 'include', 'relavance', 'Unnamed: 8',\n",
  95 |        "       'Publication Title', 'DOI', 'Url', 'Date', 'Date Added',\n",
  96 |        "       'Date Modified', 'Include (0,1)', 'Notes/Criteria'],\n",
  97 |        "      dtype='object')"
  98 |       ]
  99 |      },
 100 |      "execution_count": 12,
 101 |      "metadata": {},
 102 |      "output_type": "execute_result"
 103 |     }
 104 |    ],
 105 |    "source": [
 106 |     "a.columns"
 107 |    ]
 108 |   },
 109 |   {
 110 |    "cell_type": "code",
 111 |    "execution_count": 13,
 112 |    "metadata": {},
 113 |    "outputs": [],
 114 |    "source": [
 115 |     "a=a[['Key','Title','Abstract Note','include']]"
 116 |    ]
 117 |   },
 118 |   {
 119 |    "cell_type": "code",
 120 |    "execution_count": 14,
 121 |    "metadata": {},
 122 |    "outputs": [],
 123 |    "source": [
 124 |     "k=pd.read_csv(\"../Data/scopus-filtered-by-top-publication - Kyle.csv\")"
 125 |    ]
 126 |   },
 127 |   {
 128 |    "cell_type": "code",
 129 |    "execution_count": 15,
 130 |    "metadata": {},
 131 |    "outputs": [
 132 |     {
 133 |      "data": {
 134 |       "text/plain": [
 135 |        "Index(['Key', 'Item Type', 'Publication Year', 'Author', 'Title',\n",
 136 |        "       'Include (01)', 'Notes/Criteria', 'Input data', 'Abstract Note',\n",
 137 |        "       'Publication Title', 'DOI', 'Url', 'Date', 'Date Added',\n",
 138 |        "       'Date Modified', 'Scopus relevance order'],\n",
 139 |        "      dtype='object')"
 140 |       ]
 141 |      },
 142 |      "execution_count": 15,
 143 |      "metadata": {},
 144 |      "output_type": "execute_result"
 145 |     }
 146 |    ],
 147 |    "source": [
 148 |     "k.columns"
 149 |    ]
 150 |   },
 151 |   {
 152 |    "cell_type": "code",
 153 |    "execution_count": 16,
 154 |    "metadata": {},
 155 |    "outputs": [],
 156 |    "source": [
 157 |     "k=k[['Key','Title','Include (01)','Abstract Note']]\n",
 158 |     "k=k.rename(columns = {'Include (01)':'include'})"
 159 |    ]
 160 |   },
 161 |   {
 162 |    "cell_type": "code",
 163 |    "execution_count": 17,
 164 |    "metadata": {},
 165 |    "outputs": [],
 166 |    "source": [
 167 |     "b = pd.merge(a, k, on=[\"Key\"], indicator=\"merge_indicator\")"
 168 |    ]
 169 |   },
 170 |   {
 171 |    "cell_type": "code",
 172 |    "execution_count": 18,
 173 |    "metadata": {},
 174 |    "outputs": [],
 175 |    "source": [
 176 |     "b=b.rename(columns = {'Title_x':'Title', 'Abstract Note_x':'Abstract','include_x':'include_aparna', 'include_y':'include_kyle'})\n",
 177 |     "b=b[['Key','Title','Abstract','include_aparna','include_kyle']]"
 178 |    ]
 179 |   },
 180 |   {
 181 |    "cell_type": "code",
 182 |    "execution_count": 19,
 183 |    "metadata": {},
 184 |    "outputs": [
 185 |     {
 186 |      "data": {
 187 |       "text/plain": [
 188 |        "Index(['Key', 'Title', 'Abstract', 'include_aparna', 'include_kyle'], dtype='object')"
 189 |       ]
 190 |      },
 191 |      "execution_count": 19,
 192 |      "metadata": {},
 193 |      "output_type": "execute_result"
 194 |     }
 195 |    ],
 196 |    "source": [
 197 |     "b.columns"
 198 |    ]
 199 |   },
 200 |   {
 201 |    "cell_type": "code",
 202 |    "execution_count": 20,
 203 |    "metadata": {},
 204 |    "outputs": [],
 205 |    "source": [
 206 |     "b.to_csv('include_comparison.csv',index=False)"
 207 |    ]
 208 |   },
 209 |   {
 210 |    "cell_type": "code",
 211 |    "execution_count": 21,
 212 |    "metadata": {},
 213 |    "outputs": [],
 214 |    "source": [
 215 |     "both=len(b[(b['include_aparna']==1) & (b['include_kyle']==1)])\n",
 216 |     "aparna=len(b[(b['include_aparna']==1) & (b['include_kyle']==0)])\n",
 217 |     "kyle=len(b[(b['include_aparna']==0) & (b['include_kyle']==1)])"
 218 |    ]
 219 |   },
 220 |   {
 221 |    "cell_type": "code",
 222 |    "execution_count": 22,
 223 |    "metadata": {},
 224 |    "outputs": [],
 225 |    "source": [
 226 |     "union_ak=b[(b['include_aparna']==1) | (b['include_kyle']==1)].sort_values(by=['include_aparna','include_kyle'],ascending=False)"
 227 |    ]
 228 |   },
 229 |   {
 230 |    "cell_type": "code",
 231 |    "execution_count": 23,
 232 |    "metadata": {},
 233 |    "outputs": [],
 234 |    "source": [
 235 |     "union_ak.to_csv('include_union.csv',index=False)"
 236 |    ]
 237 |   },
 238 |   {
 239 |    "cell_type": "code",
 240 |    "execution_count": 42,
 241 |    "metadata": {},
 242 |    "outputs": [
 243 |     {
 244 |      "data": {
 245 |       "image/png": "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\n",
 246 |       "text/plain": [
 247 |        "<Figure size 432x288 with 1 Axes>"
 248 |       ]
 249 |      },
 250 |      "metadata": {},
 251 |      "output_type": "display_data"
 252 |     }
 253 |    ],
 254 |    "source": [
 255 |     "from matplotlib_venn import venn2\n",
 256 |     "venn2(subsets = (kyle, aparna, both), set_labels = ('Researcher 1', 'Researcher 2'), alpha=1, set_colors=('#89b79f', '#6aaed6'))\n",
 257 |     "# plt.title(\"Researcher Inclusion Agreement\")\n",
 258 |     "plt.savefig('../images/researcher_agreement.svg', format=\"svg\",  bbox_inches='tight')"
 259 |    ]
 260 |   },
 261 |   {
 262 |    "cell_type": "markdown",
 263 |    "metadata": {},
 264 |    "source": [
 265 |     "#### According to Kitchenham, agreement between researchers can be measured using the Cohen Kappa statistic.\n",
 266 |     "- https://www.inf.ufsc.br/~aldo.vw/kitchenham.pdf\n",
 267 |     "- Kappa values range from [-1,1], where 0 represents the exapected kappa score had the labels been assigned randomly.\n",
 268 |     "$$\n",
 269 |     "\\kappa = (p_o - p_e) / (1 - p_e)\n",
 270 |     "$$\n",
 271 |     "\n",
 272 |     "- However, the meaning and usefulness of this score is disputed. "
 273 |    ]
 274 |   },
 275 |   {
 276 |    "cell_type": "code",
 277 |    "execution_count": 20,
 278 |    "metadata": {},
 279 |    "outputs": [
 280 |     {
 281 |      "data": {
 282 |       "text/plain": [
 283 |        "0.33119677355467125"
 284 |       ]
 285 |      },
 286 |      "execution_count": 20,
 287 |      "metadata": {},
 288 |      "output_type": "execute_result"
 289 |     }
 290 |    ],
 291 |    "source": [
 292 |     "from sklearn.metrics import cohen_kappa_score\n",
 293 |     "'''\n",
 294 |     "y1 - array of shape (n_samples,)\n",
 295 |     "Labels assigned by the first annotator.\n",
 296 |     "\n",
 297 |     "y2 - array of shape (n_samples,)\n",
 298 |     "Labels assigned by the second annotator. The kappa statistic is symmetric, so swapping y1 and y2 doesn’t change the value.\n",
 299 |     "'''\n",
 300 |     "y1=b['include_kyle']\n",
 301 |     "y2=b['include_aparna']\n",
 302 |     "\n",
 303 |     "cohen_kappa_score(y1, y2)\n"
 304 |    ]
 305 |   },
 306 |   {
 307 |    "cell_type": "markdown",
 308 |    "metadata": {},
 309 |    "source": [
 310 |     "## TF-IDF\n",
 311 |     "Even though the Kappa score is slightly higher than 0, it is clear that there is a lot of disagreement as between researchers as to which articles qualify for inclusion. Let's see if there is a clear difference in our choices.\n",
 312 |     "\n",
 313 |     "* vectorizer = TfidfVectorizer(stop_words='english',min_df=0.2,max_df=maxdf,ngram_range=(1,3),strip_accents='unicode')\n",
 314 |     "* Count only words occurring in at least 20% of the documents (min_df)."
 315 |    ]
 316 |   },
 317 |   {
 318 |    "cell_type": "code",
 319 |    "execution_count": 52,
 320 |    "metadata": {},
 321 |    "outputs": [
 322 |     {
 323 |      "data": {
 324 |       "text/plain": [
 325 |        "<module 'utils' from '../utils.py'>"
 326 |       ]
 327 |      },
 328 |      "execution_count": 52,
 329 |      "metadata": {},
 330 |      "output_type": "execute_result"
 331 |     }
 332 |    ],
 333 |    "source": [
 334 |     "\n",
 335 |     "importlib.reload(utils)"
 336 |    ]
 337 |   },
 338 |   {
 339 |    "cell_type": "code",
 340 |    "execution_count": 53,
 341 |    "metadata": {},
 342 |    "outputs": [
 343 |     {
 344 |      "data": {
 345 |       "text/plain": [
 346 |        "<matplotlib.image.AxesImage at 0x7fb0803c9048>"
 347 |       ]
 348 |      },
 349 |      "execution_count": 53,
 350 |      "metadata": {},
 351 |      "output_type": "execute_result"
 352 |     },
 353 |     {
 354 |      "data": {
 355 |       "image/png": "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\n",
 356 |       "text/plain": [
 357 |        "<Figure size 360x720 with 1 Axes>"
 358 |       ]
 359 |      },
 360 |      "metadata": {
 361 |       "needs_background": "light"
 362 |      },
 363 |      "output_type": "display_data"
 364 |     }
 365 |    ],
 366 |    "source": [
 367 |     "# Aparna's TfIdf tri-grams\n",
 368 |     "ap=b[(b['include_aparna']==1) & (b['include_kyle']==0)]\n",
 369 |     "a_abstracts=list(ap['Abstract'])\n",
 370 |     "text=utils.getTFIDF(a_abstracts,top_n=100,maxdf=1.0)\n",
 371 |     "utils.drawCloud(text,max_words=100,figsize=(5,10),raw=False, title=\"Researcher 2's TF-IDF\\n----------\\n\",save=True,path='../images/R2_cloud.svg')"
 372 |    ]
 373 |   },
 374 |   {
 375 |    "cell_type": "code",
 376 |    "execution_count": 54,
 377 |    "metadata": {},
 378 |    "outputs": [
 379 |     {
 380 |      "data": {
 381 |       "text/plain": [
 382 |        "<matplotlib.image.AxesImage at 0x7fb08135a470>"
 383 |       ]
 384 |      },
 385 |      "execution_count": 54,
 386 |      "metadata": {},
 387 |      "output_type": "execute_result"
 388 |     },
 389 |     {
 390 |      "data": {
 391 |       "image/png": "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\n",
 392 |       "text/plain": [
 393 |        "<Figure size 360x720 with 1 Axes>"
 394 |       ]
 395 |      },
 396 |      "metadata": {
 397 |       "needs_background": "light"
 398 |      },
 399 |      "output_type": "display_data"
 400 |     }
 401 |    ],
 402 |    "source": [
 403 |     "# Kyle's TfIdf\n",
 404 |     "kp=b[(b['include_aparna']==0) & (b['include_kyle']==1)]\n",
 405 |     "k_abstracts=list(kp['Abstract'])\n",
 406 |     "text=utils.getTFIDF(k_abstracts,top_n=100,maxdf=1.0)\n",
 407 |     "utils.drawCloud(text,max_words=100,figsize=(5,10),raw=False, title=\"Researcher 1's TF-IDF\\n----------\\n\",save=True,path='../images/R1_cloud.svg')"
 408 |    ]
 409 |   },
 410 |   {
 411 |    "cell_type": "code",
 412 |    "execution_count": 55,
 413 |    "metadata": {},
 414 |    "outputs": [
 415 |     {
 416 |      "data": {
 417 |       "text/plain": [
 418 |        "<matplotlib.image.AxesImage at 0x7fb080fd6208>"
 419 |       ]
 420 |      },
 421 |      "execution_count": 55,
 422 |      "metadata": {},
 423 |      "output_type": "execute_result"
 424 |     },
 425 |     {
 426 |      "data": {
 427 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAASUAAAC1CAYAAAAZdumAAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/d3fzzAAAACXBIWXMAAAsTAAALEwEAmpwYAACneElEQVR4nOyddXgdx7n/P7N7mMTMsmTLlpkhpjhOHGZqGygkhV/x9vaWb2/b2/QW0pRSTFMIp03D6MSOY2a2DLLFjEeHYXd+fxzp2IrQ7LT+Po/8+OzODuzOvPPOi0JKyUVcxEVcxIUC5Xx34CIu4iIu4kRcJEoXcREXcUHhIlG6iIu4iAsKF4nSRVzERVxQuEiULuIiLuKCgmGE+xdVcxdxERdxNiCGujESUfq3gKbr9HiCmM0GbBbT+e7OBQFPxMeBnkpSTImMceQjxJBz6AMHfzTI/p4jaFKLXyuw5ZBlTTuPvTp30KXOMW8dQgiK7HkoF9i3vXh8A6rrO/nEt57ghZW7z3dXLhg0Blv56aE/8UrT6vPdlTMOd6SHx6pf4OHKJ3jw0J/50cE/sr1r3/nu1jlDV7iH/zv4B35y8BHcEc/57s4A/NtzSlJK9h5uoLmth0Aocr67c8HhX/H8nmFJ5X8nfYmQHubtlg38ve71892lcwqLaqLYnodJMWJRLryTwUWiJGHH/jouGrb/+0ARCi6jA4AEo5NhxBv/krCpVr5S9nFAYBDq+e7OAJw0UZJSomk6Hl8IXyCErkuMBhW7zYTNakJVlAHyB12PPSMBVRUoQgwro5BSEtV0pARFgKoOrLOvXDAUpccbJBSOIITAbDLgtJsxm4wIwZDtSCmRUtLlDlBxtCXWT00SjmgDyg7Xh3hdQCAYxu0JEo1qmEwGEp1WzCbDkH2PajoABlVBSuhy+wmEIiQn2LBajAghkFLS4w3S4w3isJlJcFpRlOHfXSSi0eMNxjk/o1HFYTNjNRtRlIHvXpc6PREvfi2IWTGRaHIOWX+871LDHfEQ0sNYFDMJRgeqUIccq0TiifjwaQFUoZJodGJSjP3KSynRZOydqEJBkxrdEQ9hPYLdYMVpsKOI8ydx0KWON+rHG/WjCIUEowOLYh76+0oNb9RHQAshENgNVhwGG4LBv4Em9dg7BKIySnfYQ0RGsapmnAYHqlDicyIqNRShoCAI6WHcEQ+a1HEYbDgMtgHvSUqJjo4e333FkKQ4VlaiSx2DUGPfLurDFw1gECoJg3y7E58NaiF6ol50KXEZ7ZhO4MYUoaCO8A1HTZSkjC3YtdsqeW3NAarq2/H6Qmi6xGRUcdrN5GUlMWtSAZfOG0d6siPe6Zb2Hr7/mzfw+UNctqCMj1w3a9i22jq9fPfXr+H1hVg0u5SP3Tx3QF9aOjy89M5eNuw8RluHl2AoRpQsZgNJCTbKijNYOLOEuVMLMRmPD1PXdbbvr+NAZTPHats5Vt9OU5sbgBff2cPa7UcH9Gf6hDw+f/cSBqNJUkqa2np4YeXuWF86fUSiGhaTgaz0BC6bP46rFpfjclj6fUSfP8x3f/0aUkq+9ZkVrFx/kCdf3obXH6IwN4Uv3LOUCWMyeWfjIf70jw20d3pJcNm4/crp3HTFFAyqOqAfHl+IN9YeYNXGwzS0duMPhAEwGw0kOK0U56cyb2oRS2aX4rCbkVLii/r5e/2bbGjfgTfqx2qwMC1xPHOSpwxKAKSUHPZW84+6N6j01hDUwlhUM+OcRdyWdyVF9twBhKYj3M1z9W+yvWs/nogPg6KSY83guuxlzEmZjNq7W+voPFr1D7xRP7fmreDZutfZ6z5MSAuTYHSwOH0ON+QsG5IQnC1IKemJenmx4R02duzEHfGgoJBhSeXKrEUsTpuNUTk+xyJ6lDVtW1jXtp26QDMBLQAIXAYH05MmcFvelSQYnf3GUNFzlL9UP88nim7BoBh4svYVKj01hPUINoOFFZmLuCX3CgA6w25+dvjPLEidToYllb/XvUFDoBlNargMDhakTuem3CuwGSz9SM9Tta+wvWt//He6OYUvjb0Xi2oeMOa3mtexvn079xXfzrttm9nQvpOeqBeDMJBrzeC2vCuZmji+3xgiepTVrZt4o3kt7aEuJBKnwY5ZjRElgWB5xgKuzFo07PseNVEKhaP8+vE1vLRqL9GojsGgYDEbMakKoXAUjy9EQ4ubrXtryU5PID25JP5sapIDu9XErop6QpEo1y6dRKLLOmg7Ukq27KlhV0U9qqJw320LBtw/VtfOd375KsfqOhAituhMJgOaptPjC9Lp9nO0tp0Dlc1MHZ/bjyiFIxq/eeI9jtV1xOvT9dju0e0J4PGFBvQpNyNxyL7uPFDPj/7wFnXN3XGiaDKq+INhKo42c/BYM+t3HOMbn7qCrDRX/CNquk51QwddPQFWrj/IH5/dAEAgFGH/kSYe+vMq7rttPg/9eRXhSBRNlzS1uvn9M+sYk5/K9PK8fhOiy+3new+/zta9tUgZ2ygsZiO6LvEFwnR7AtQ0drJ9Xy0Tx2bhsJuJSo2/1rzAqpaNlDoLWZG1iKgeZWvXXg72HDthVz0+3gM9lTx4+M+oKCxMm0WaOYl6fwvrO3ZQfbCer43/JAW27PiO3hVx8+ChR6nxNzA7eQrF9jx6ol42tO/gV0ceI6TfxpK0ObGxSGgOtnPYU0Wdvwmn0c612ZeiSY1NHbv4R90bhLQQdxVej8q5O3b4tAC/OvIYe92HmZFUzjhnEQEtxKaOXfzh6DP4ogGuzV4aJ+ISycb2nXRHPMxOnkyWJZWgHmZTxy7eaF5LREb51Jg7+o3BrwWp8tWzrWsfWzr34jI6uDRjLlJKqnz1pJmT4mWjUqPW34i7yUNQC1Fsz2Nu7uUEtTDr23fwfMPbqELlzvxr+p1My12lGIWRzrCbte3biOhR5BBSw+5IDxU9x3i48gm6Iz3MS5lKqjmJal8D69t38KvKx/lu+efIs2XFxiwla9u28UjVPyh3lXBH3tWYVCObO3azsmUDGeYUlmfOZ7xrzIjve1RESUrJpl3VvLxqL7omuXxBGddfNpn0lBi19/pCHKtrZ+veGlraPUwp679bGgwKKxZOYNOuKhqau9m+v5ZL544ddLeLajrvbj6MlJCXlcTkspx+5aKazp/+vpFjdR0kuqzcc8McZkzMx24zEdV02ju97D/SxKbd1cwoz8Np778LmIwGvvGpKwiGowC0dnh44HdvEghGuHrJRK5ZOnFAn1x2ywAuSUpJdUMnD/zuTRpb3RRkJ3PnNTOZNC4bs8lAd4+ftzcc4oW3d7Njfx0P/XkV3/3C1QNMDgLBMI+/tJVP3DqfedOLeHv9QR79x0YOV7fy4KPvMHVCLh+/ZR5ub5D/ffgNmtt7WLO1kunlef368s+3drNlTw1mk4Fbr5zG0jljSXBaY4Shx8/hqlY2767GbjWTk5GIlJIjnmrWtm2j2JHPV8vuJ9EYO7Ytz5jPAxW/Iyqj/foa1EM8UfMSutT46vj7GOsoRAiBLnXGOQv5zdGneK7+Tb449h5UVCTwcuNqKr01fKzoFi7PXIDSq/BdkDqd7+9/mL/XvcG0xAkkmlzxdnxagPHmJL449l5sqgWAxWmz+f6Bh3m7dSNL0+dQYM8Z8J3OBqSUrGrZxK7uCm7JXcHNuVfE5TBL0ufw/f0P80LD28xKnkSWNQ2BwCgM/L/Sj2BRTFhVS4wwSFiYOpP/3v8LdnYdwB3xkmxKGNDWa01ruCV3BVdlLcakGIEYERIMFEU0Blq4LnsZHyq4FqOILeU5KVP4n32/Yn37Dq7LWYbDYIPeZ6clTWBq4ng8UR+7uytGHLuOTluok6+P/ySljgKEEGi6hsvo4MWGt9nauZdcayZCCKJS453WjVgVM58ovpVsSzpCCMqcxVT5GugIdbEwdRYp5sQR2x01p7Rjfy2RqE5OegJfvHcpCU5rv5dUWpjG5ZeMJxiKYLUY+z0rhGDmpHxys5KoaejkrXUVLJpVgtEwcLerb+5m3+EmABbNKhlAVDzeIAcqY/evWTKR266a3q8feZlJTB2fy21XTe8VXvf/kIoiKC1Mj/+ua+pCVWILJT3FwaSx2aN6H5qm89fnN9HY6iYzzcUP/uNainJT4n3JSnMxtigDq8XIX/65iU27q9mw4xjL5o173/EG8rOSuGH5ZExGAzddPpU33jtAXXM3Hl+I+29fQEF2MgDzpxfxz7d2c6yunaimx99fJKqzfX8tANPL87jvtgUYTpCB5WQkUl6SxXXLJhOJaBjU2Hh3dB8grEdYkj6bxBOOE0mmBBamzeKor67fmI9566j01nJJ2oz4JIWYnGBm8iRS6l5nv/sI7rCHZHMi3qiPTR27yLCksjBtZvyYBlBgy2aCq4SNHbuo9NYyM/n4ZiAQLEmfg009fuRNNyezIHU6z9a9zh73IfJ7ubGzjZAeZm37VlxGJ5dlzOt3TMswpzA9qZxXm1az332ELEsa9Mox309wEJBuSabQlsM+92EC0SC8vwyQZU1nRdbC+JEHiBOc98NpcLAicyFGcVxumWfNJMeWQZ2/CU/EGydK8W6c5DubnTyJkhPs1BShMD2pnJcbV9EYaI2XC+sROsPdJJicJBkT4uXNiolsSxrHfHV0R3rOLFHqY/Kiuj6oMFgIgRBgsw6uYnQ5LFw6Zyx//ucmdlXUU9vYRXFeyvsWqGTDjmP0+ILYrCaWzC4d8BLlCX0JhqPoUqK+r4wQot+R7WygvqWbjTurgBhxPJEg9fXBoAquWlzOP9/ajdsTYPXmIyydMxZV7d/fccUZcQLjsJnJzkikrrmb3IxEstKOf+Ds9EQAejwBolFtUKIeDkfRND1OeN7fn77rutSp8zehCIUiW+6AvufbslDo/22O+eqJyCgRPcratm396o/0clV+LUh3JEaU2kJddIbdZFrS2Nq5t199sbIBdHRaQx39rpsUI5mW1AHfvtCei4Kg3t88YNxnC+6Ih+ZgO1bVwu7uQwO0Vd2RHiTQEmzvd11KSUgP0xHupjPUTUALEdLD9ES8SGJcyGAotudiUQbKeAZDqjmJRJOr33tShIJZMaFLnagcuE5PFsWOvH5yKSEEVsWMQBDWI0gkoleLZzfY6Aq78WsBbIYYhxuVGh3hbiyKKc71joRRr9zJ43J44e09tHZ4+PEjb/PRm+YytjAdg2FordSJEEJw6bxx/OPNnXh8Id7dfJjivHn9yoTCUdZsrQSgvCSLoryUAfW47BZKC9Np6/Ty+pr9pCTYuGpJOSlJjkFZ3LOFfYeb8PhCGAwKM3qPUoMFzEtKsJGW7MDtCVBd30EwFMFu6z/p0pId8f8risDeS9jTUhwYDMeJSx8HGo5q6Cc0ZTQoTBqbze6DDew+1MCvHlvDbVdNJzcjcVBtG8QIuy8aQBUKVsPAyWJVLYj3Cbp7eg3tNnbsYkvnnkHfi0kxxhecL+onqmvU+5v43dGnhi4v+y/QvoV1IoQQvZyTgl8LxhfD2UZACxHWI/iiAf5w7JlBy8TGfPyDRHWNde3bea1pDY3BVhQERsWAURhGNFa0qoPLWgeDRTX34z7PNAQCu2od1ZoyKUYWpc7kbzUv8kTNS6zIXIRJMbCtaz+HPFXMS5lKmjl5VO2OiigJIVgwvZgls0tZvfkwG3YcY9eBOiaX5bB8QRmzJhWQnGAfVgUPUJCdxPTyfNZsOcLqzYe57arpOO3HF8TR2nYqa1oRQnDZ/HGDcgIGg8K9N87hWG07ze09/OHZ9bzwzh4WzhjDpfPGMa4oA4t5cDX8mYKUkqr6XkG5LvnTcxvjhOT90HVJS3tsIvoCYULh6ACi9H45U5/K32YxvW+X6utA/zaEENx0+VS276+j4mgzz6/czerNh5k9uZDl88cxuSwHh62/xkoQU7tLKQcQhVgTAwls3wK4LvtS5qdMG3S8QghyrBm95RWEgAmuUu4quH5IIpJyghAX+kwDBu7ysWvyrC7E90MRCgJBoT2H+4tvH9Kup08mJqVkbfs2fnf0KTItqdxffBtjHPmxxY3gV5WPs899eMj2TmbWnguiPNp1JITg8sxLaAl18EbzWrZ27kUVKibFyKXpc7kt78pRf7dRc0pWi5Gv3r+c8WMy+Odbu2lqc7NpVzVbdteQnurk0rljuX7ZZHIzE4cciKoqXLloAuu3H6W2sYtdFfVcMmNMXFPz3tZKgqEoackO5kwpHLQeIQTlpVn85Ks38LcXtrB+xzFa2j38481dvLx6H2OL0rlh2WQWzS7FZhncluJ0IQG3JwCApku27a0d3XO6HKDRgqFtoFR19DY5GalOfvjl63jqlW28ua6C7p4Ab62rYNXGQxRkJ3Pl4nJWLBpPksvW25Yg2ZSIJjU6w26KpYz3QUqJO+IZQKwyLKkIBBI5Kn+4RJMLi2ImqIXJt2X3k5MMh4iM4o54+12TUtIe6kaTOsmmhHOyIAGcvXY/QS1EjjUDp9E+bPlor1pcSsnHim5hcsJxGWJUjxLR/3W9BkJ6hFp/E9MTJ3B73lUYFSMuox2X0TmibdKJGDVREiJ2rLjzmplcfsl43ttayVvrD3L4WAvNbT08+fI2Vq4/yP23L2DFwgmDLighBNMm5FKQk8zR2nbeWlfBvGnFGFSBxxdiXa+N0JwphaQmOQY8f2I9xXmpfPszKzhS08abaytYt/0oze097D3UyIEjTby+9gBf/ugy8rOTzjxhksePahazkZuvmDpAID8YbBbToBzVmeidEIK0ZAefu2sxNy6fwtsbDrF682FqGjo5WtfOw0+s4Y339vPFey9l2oRcBFDmKmJN2xZ2dVcwI6k8vtAlkv3uyn7cUkyTUoTL6GB75z6uy76URGN/ecaJx1chBGnmZIrsuVR6aznirabcNYiMsPeZE69rUmN/zxEmJRzX0GpSZ3d3BQoK45xF5+yY7jI6KHMVs7ljN3vdh5iXMm3YMehIfNEAJsVIujm5H6FvC3VRdw7lYecaB3uOUtFTyRdK72GMIx84NXHKSUmD+xpITXJw4/IpXLW4nMNVrby8ei+rNx+hrdPLz/+ymvRkJzMnDb6TOmxmls0bx9Hadrbvq6OhpZv8rCQOVDZR39yF0ahy2fxxgxoqvr8vBoPK+DGZjCvK4O4bZrNpdzXPr9xNRWUz2/bW8uNHVvKjr9yAwzY6weHo3wPxY6eqxITZRbkD5V/nGqLXUj4/O5mP3jyXW6+cxu6DDTy/cjfb9tZQWdvOA797k1986xZyMhKZnlROhiWFNW1bGecsYmrieAB2dx9kffv2AcQyw5LK8owFPN/wFr+pfJKbc68gw5IKQE/EyzFfHUZhYEHqdCCmNbo+5zJ+dvjP/P7oM3yo4FrGOgpQhUpAC1EfaKYp0MqVWYswiv4a27dbNlBgy2FiQikSyYb2nWzv2k+hPYcJrhJOFVJKgnqIiB6NW1zTa7HcGe5GFQaMQu2VqQkUFK7NvpR97sP8ufqfhPUI5Qkxe5+QHqIx0Eq1r4ErMhdiM1gwCJVsazrVvga2de1jmXE+ihC0hjp4rPpFvFHfebFKj+hRglqo10q+J2Y5LzU6Qt04DDZUoWJRzf20iyeLRJMLs2LiydpX2Nl9oFdrGLNkH+ssZGrieMyKaURCdco9iBkKGpk0Lpvy0iwWzSrhew+/js8f5tU1+5kxMX9QwiKEYOncsTzz2g66PQHWbTvKndfM5N0tR4hEdcYVpVNeknVSFFZRBMmJdq5cNIGFM8fw68ff4+VVe2NcU2UTsyYVnNGdVQgRJ0KBUIT65i4Kc5LP2e49GgghcNotLJhezKxJBfzjjZ387ul1NLa6WbvtKLdfNZ1UUxL3FN7I748+za+OPEayKRGJJKJHuDprCa82vdu/TgQ35S4nrIdZ2bKePfsPxexwoHfC69yYs5wFJ/RhWtIEPlF0K0/WvsyDhx7FplpQhUpIDxPRI4x3jeGKzIX92rGrVmYnT+a3R5/srV/SGe4hxZTIx4puHqDmPhmE9DAPHnqUal8DYT1CUA8jgefrV/J603uYFCMZlhS+WnY/LmPMK2Gso5BPj/kQf6l+nl9XPoFVNWMUBkJ6hLAeJs+WxfKM+fF3dG32Ug56jvFY9YusbNmAKhQ6Q27GOgu5LmcZrzSe+8gLGzt28WTNS4T0MGE9QkCLGQl/dc9PMSkGzIqJ2/Ku5NKMeSPUNDh0qRPWwqSZk2kNdbCj6wBwXAv5UuMqLkmdwafH3DniMf609eZCCFRVMG9qEaUF6eyqqKe5zY2u6yjK4IKtnIxEZk3K5+0Nh1i7rZLL5o9j+76YTcySOWOHNCsYTV8cNjM3XDaZN9YeIBLRaO3wjvhMHy2JRHTkCbKV4TBpXDZOuxmPL8SqTYeZN7UIwyCC+fONPn/AKxeX88xr22nv8tHU6o7fm5M8hUxLGps6dtEa6iTZ5GJO8hQK7TkU2HP6EQAhBBbFzF0FN7AgdQa7uytoCXYghCDVlESps5BxzsJ+7atCYWn6HCa4xrCj+wA1vkaiMkqC0UmRPZfxrjFxI8E+SCRXZS1mfup0tnfuwxP1kW1NZ17KNLIsaadF/A3CwBWZC/FHA0OWMaumfq4XQghmJ09mjCOfnV0HOOarI6SHcRrsFNpzGO8qwX6CkaL0OZgWWcbGzl3U6G6Wl43lhpxSZiZNJKSHKLTlkGxK7NdmsT2XL4y9O64kGA4JRgefGnMndoO1n6xG03W2VtczyzabZenz+rVR4siLWXgPg+LeIxfAvJSpZFvSKXUUDiiXYUnhc6V3kWZOjskYpWRL5x5+U/kkC1Kn859ZH+/lNPtcdHw8XvMSG9p3sDxjPuUJpcP2Y1RESdclnW4fiS4b6iAq5j6n0S63H4BElw0xjNOoqghWLJrAu1uOcLSunfe2VtLS0YPTbmbRzDHDTjp/IExU0+MynMHK1jV3oWs6iiJIcA6vYrXbTFgtJjy+EJU1rUSi2qhsnPKzklgwfQxvrD3Ami1HmDWpgMsvGT/g/cQcf6Hb48dmMWExG4ep9dQQjkTx+kMkOm2DakCllLS29xAIxoSsSQn9CU2hPYfCQSykZyVPGnBNiJhNylhnIWPfR4CGghCCTGsaV1kXj6q8JMZxTEoYy6SEsaN6ZrQwKOqg4xoJQghSzUksz1wwYtlmt5eq+gBdTckEIy4+tOwGku2xd27HyiVpMwY8k2JOYlHa8D6hfbCo5vgR+UR0+4N858V3uHryOD536ax+8yDbmkH2KAge9M2JXArtuYPedxod/fqqSY23WzaiCoWbc68g9X3a1GRTIrOTJ7Ojaz8d4e4R2x8VUQpHonz3169jsxiZPbmQsYVpJCfaURWFcCRKTUMn/1y5m9qmTgyqwtI5Y4eNZieEYMq4HIrzUjlS3cqL78T86SZPySE3K2nI5wD2Vzbx87+sZsbEfKaNzyU/OynOWXm8IXYcqOOpV7ah6ZKCnGQmlGQOS+ScdgsTxmTS2uFh275a/vrPzVy2oAyr2UhU0/D6Q5iMhgHGkaqq8NGb53KwqoXq+g4efPQddh6oY+HMEjJSnb2EOkR9cxd7DjVwuKqV733hGkoKznx0w7ZOL19/8CVKC9KYOTGforxUXA4LihD4g2EOHmvh6Ve24wuEcTkszJt27gTF/45YNLaQhWML+ev6HTyxedc5azfRZuH/br6C7MThozycaUgpCWhBBAKlVzt7otJEkxrHvLUYhEqi0TVCbSdxfPN4g2zfV8vabUcxGlTMJgOqqhCJaoRCETRdYjSq3HjZFJbMGahleT9sVhPL55dxpKqVY3XtKIrgsvllAyyRB7wAXVLX1EVVfQf/fGtXvC8QM74MR6JICRkpTr5w9xKSE4aXP6iK4EPXzmTfkSbau7z85flNPPPadoxGA9GoRiSqsWLRBL563/J+zwkhyM1M5DufvZKfPPI2FUebefXd/bz+3oH4GLTekC3AkHZMZwptHR4qa9p4Y+2B3ncSC1MSCkcJ91q+O+xm7r99AaVngTBexHEIIXoNeYcvJ6UkFNUIhCMYDQo2k2mAAbCUkqiu4w9FYoa1JlO/evvMaQAUIZialxW/PlSbYS3WJoDFaMBsOD27PlWolLtKOOQ5xhO1L3NF5kISjA40qdEe6mZDx07ebdvCOGcxJSccEYfCqIiSyajyidvm89a6Cipr2nB7AgTDUSK9rg7pKU5KCtK5ekn5gFAhQ0OweHYJT76yjS63n8xUFzMnjmz7Mq44g/tuX8DmXdU0trnx+UOEI1FAYDUbyc1MZNakAq5fNon87JGFz312Tz/88nU88fJWDlQ24/EFCYWjWEwGUpMdcd+zwZ4dW5jOT796EyvXV7Bq02Hqm7vxB2MhQ+xWI0kJNsYVp7NoZgl5J3CBqqJQkJ2MzWLC6ehvUZ2R6qKkII30FCdaVAODiqIIXA4rJQVpZKW5+nGiqUkOPvPhRazZcoSaxi68viChiAZSYjIZSE9xMLE0m+uXTWZCaSaKcjEK8vlGVNN5fd8hntq8m1aPD5vJyPLyUu6dPx2nJSaakFJyuKWdX6/aSF2XG6OikmizxOaCxcJXr1xEqsOONxTmR6+vod3rR5eSG6dN4MpJ4wa0GdE0Xt97mL9v20ujO2bQm2K38vll87mktPC0xnNN9lI6w242dexiQ/tOVEXtjfsUxayYmJsylTvzr4krRoaDGMw14gTEb8YsfyXBYASvP0QooiF1iaoqOGxmHHbzoPKm4dDR7eO+bz5Jc3sPt6yYxhfvWTpsALMT+xLVdHz+EP5AhIgWs/41mwy4HBYsZuNJB0OXUqLpkh5PAG8gHF/QTpsZi8U4qsB0kaiG2xMkEAyDEJiNsYBzFvPAgHPHA9lJDKoSJxSxfuixwHhRnYe/8zxX3j6H8hmFaLqOpum9fmzKgPo0XeIPhPEFQkQiGlLGAry57BZsVmPcZOBChS51dnZV0B3pYU7KlNPSsl0I+Mv67Ty+aRfPfurOuEwJYt/qzf1H+N9XVvOhOVOYPyaf+q4efvPuJhaUFPDVFYswqCr+cJhPPvYCyTYrX7xsARJ48K111HR08a1rljI9PweTQSWiaeysbaK+y81DK9dx19xp3L94dr++SCn5+7Z9PPjWWq6cNJYl44pRhOBwSzvLxo+hKHV0LiBDQSLRdI2mYBt1/mZ8UT+qUEgwOsmxZZBqSo4HqevFkBPxpIwnVSGw28wD3CROBVJKtu6pobXTg9lkYNm8caMiSH19MRpUEl02Ekc+oo66ToMaMy1IThzeaneo501GQz8/tpHKD+ZGE+uHCipois70BaWkZcW8yVVFiUc0GKr/LocFl2N0jo8XGhShMCO5/Hx346wjGIny1w07WFhayP2LZmNQFabkZaEqgu+9soqbZ0ykLDONDq+fo60d3HP9cgpTY1z2VZPG8X+vv0tRajKm3vljVFVmF+VSlpnGH97bMmib7kCQv23cwfIJJXzjqqUYe0UMC0+TQ+qDQGBQDOTZsuIxlk4V5y1Gdygc5dV396HrstcAMn3kh04Dmqbj7vSSkOzA6w4QCoZxJtqwWE3xc7m3J0DAF8LutGJzmOPXpd57zx/GYjXiTLT142zCoSg9XT6Q4EiwYrEdr1PXdNydPnRdkpBsx2CMhYwN+sOEQxHMVhM9XT6MJgOupOP1+r1Berr8TJhRSMIJhE5KSXe7F0eCFb83RCgYwZVkw3xC+FwtqtPd4SXaG81BKILkdCfGsxw54SJGh3avn9rObm6dOQm1dyMWQjA5N7aYDzS2Mi4jFavJiN1sorqjC63XA7umowuH2YzlJL9lY7eHJreHL1++EOMwoZ0vBJyTWXqiGX5fpMfX1+xn98EGDKrCTZdPiQurzxa83X5++p/PMHfZBDa+vZ+AP8SCKyZxyycWo2s6q17aycrntiIUBV3Tue3+JcxYFDuXv/rkRt57fQ+qqhDwhVh63XSuu3s+iqLQXNfJHx54mYAvhKbp2B0WvvjDW0lItuPzBPnbQ29SdagJIQTJaU4+9l9XkZaVyK6Nlbzx7GbsTiudbT14uv1cefscrrxjLooiOFbRxMuPb+Dgrhr+40e3MWVuzIo5GtH4xbf+QU5RGjWHmwn4QtgcFj7//ZtJy04k4AvxyP+9Sle7h1AwwrGKRmYtLuOjX7mS5LQzxFZexGkhGIkQjmo4Lf2dpM1GFZOq0hMIApBst3Hvghn8fs0WdtQ0IgQca+/ik4tn47Kc3GnFGwohpSTRZrmgCRKcI6IUDEVYs7USo0ElEtHYdbCet9cfJKrpLJpVEnfKPZuQQHN9J61N3Xz1oQ/FDB175TxVR5p5+fENfOmHt5KVl8yO9Uf460NvUjo5D1eijTnLylmwYhJ2p5X926t55Icvc+n103Al2dn23iGMJgP/+ZPbEYpCT5cPZ2JMfvDa05voavfwzV/dhdFk4B9/fJfHf7mSL/zvLWiaTsXOGr76sw8xYUYhuzYc4W8PvcWiq6fgTLBRPrOQkok5fOOeP6Jrx+V+UoLHHaC9yc1XfnoniiL4yX8+zYaV+7ju7gXs21pFQ3Ub3/ndvUgJ/3P/n1l09RSSUs+tmvgihobNZMRsMOAOBPsZ6wYjUUJRjQRb7PgtgDFpKWS6HKyYWEqizUpxWjLZia6TXi92c4x77/b3b/NCxDkhSr5AmF/+7V3cniAQMyYUwMSx2XzursVnnUvqg9GosviqKSSm9D8OVeyoxtPt582/b0EIQcAforWxm87WHlyJNowmld0bK2mq66S7w0vAHyYcigU1mzC9gLef384jP3qVxVdNZfz0fBRFoEV1dm86ymU3zCAh2Y4QgktWTOYn//kUvt4IAzmFaZTPLMJsMVI4Ngtd1wn6wzgTYp78ygnW5idCEYL5y8txJcWIX0FpBp294VGiEQ3VoGIwxMLRqkYFqQ89CYdSdFzIk3YwjKCwieNMjuv9bY627lSHnZL0FDYfq+X6qeMxqjFN1c7aGDc0ISs9fqp4c/9hUhw2ZhXmYe49+kc0DZM6eOaYoZCd6CLT5eSdikoWlBTEj3CDOUSfb5wTamA2GZg/rZjapk7CEY0kl41Zk/JZsWjCCaE0zj4Ug4LZOtCiOhyKkpBsZ/y0gvi1GZeMIy0rkZ4uHz/8whOUTMxh+oKxBP1hdqw7TJ9isnh8Nv/923vY9M4Bnv7dKlyJNj73vZuw2ExoEQ3jCQTXYFTj6aYAzFZjPJqCiEUTGR0E2JyW+KQSiqAvcd3E2cW88ewWfvTlpzCZDaRlJTJhRuGQVUXDGn/4xlM0HoulmZqyaDy3fOHKC2qSjgY7Vu3n+YffHJI4KYrCh792PWWzRg5cPxpIKfF0+fjnr9+k5kA9E+eP5Zr7lqEbBFur6nEHguyua8IXCvPqnkOkOe0UpiQxLjMVk0Hl45fM5JsvvMWvVm3kkpIC6rt6+P2azVwzuYwxaTFNmATKMtN4cecBbvv9k6iKgiIE+cmJfPGy+UzptUmqau/iSEs7HT4/nmCIvQ3NvLSrAqfVzKyCHBwWM4lWC3fPn8aDb61DEYKFY4tQhKCqvZNJOZnMKc4bZrTnFueEKDlsZr7+qcvR9RiXpCjipM0HziaKxmXyzgvbmTC9kJQMF1JCJBzFZDZwZG89nW0ebv/kpbiSbOxcf4RI+HgAskg4SlKKg6vumMP85eV8+xOPUn24mYmziiguy6ZiZw3zLpuAUBQO760jNTMBu/PsacdUVUFRFVbcNpucwlRSMhIwmYf+zLqus3/jYY7uicWEcibZP5BpcdsbOtm6cs+QfReK4OpPXHpG21z5+Fqe/snLMd+vN3eTU5JJ6aJxvL7vMP5QGF3CzMIctlbXx/znCnMZlxkL8zu/JJ/vXncZf9u4gzf2HcZhNnHDtHLumjsVVYkF33v30DGe2bKHr125hMLUJIQAXyjME5t28bOV6/nj3TdiMqjsa2jhnYNHkVIyPT8bELxTUYnJYKAkLQVHr+zqpunl2ExG/rF9H5veeC/m/pPgYFr+6OLSnyucE6LUZ05wEjHLzhmEEEyYUcjUeSX83xefIL80g6A/jM1h5pPfvI70nCRciTYe/clrJCTbaWnowuY4LmR87anNHNxVQ2pmAp1tHhxOCzmFsXAe1909n19+6zke+vrfsVhNHK1o5N4vX9mPexoMmqaz+Z0DNNS0097s5r3XdtNY087MReNIGkFYHY1E6Wzr4enfrsJqM2G1m7nsxhnMXjJ+WH/EDzqyitOZf/V0ejq9+HoCBH1BvN1+PF2+s9Zm3eGmOGcWjWg0HmthzpVTeeDGy0d8VlUUlowrYkFJAaFoFIOiYDEet6zWdcnzO/YzPjudW2ZOjNvdSSlpdnv564bthKJRzEYD104p49opZSO2aVRVrplcxhXlYwlFY+IHs8EQNw+4UPBvoyO2Ocx89MtXkpIxMIOE0WTgni+voPpQM001HZitJorKsjAYVRKS7Xz9Fx/m8J46TGYjN388l9rKVhy97itLr5tKbnEaXrcfu8vK2Em5uJJiMqSM3GS+9vMPc3B3LdGwxq2fXEp6diwy59iJudz2yaUovRPClWzno1++Mi4kN5kNpKS7uOc/VgCxnV4oCgaDwp2fWUZB6XHnykVXTUGI2ET++x/XMHPROGYtLkNRBLVHW3nsF28xfloBrqSTt7/6oGDSgnFMnDcWXZdEI1HCwQi736vghx/9LdogiS7OBHLGZPZ6woPRbCD3JEPuCCEwGdS4vVH/mzHhdF2nm3aPj2S7FU2XNHT38Ma+w5Smx0wG+uo5I21eIPi3IUoms5HZS8cPek8IgdFooHRiLqUTB3pGp2UlkpaVGP89afZxQXlCsoOZiwaa9PfV60qyM3vJwHbTshNJyz5ep9VmZs6lE+K/Zy4eeuebfslxz3khBCXlMQ//UDBCxc4a7vrC5Yybko/UdSIR7V+aQ+qDEAKhChQ1Jruz2My4kh1nNWju5XddQmerm9qKBmZePpmpSyeM/NAoIYC7503nOy++zb1//geJNgsRTafLH6AwJYkvLl+A4V/UXejfhij9O8BkMnDZjTN4/JcrSU7bhKbpeLr93PjRhThHcEy+iJODEAJXipP7H7gjpt08w4RfCMH4rDQeufcmKls76PYHMKoqWQlO8pITMRtOTvv2QcJFovQvBKEIrrh1FrOXjqeny4eqKiSlOXG4Rpcm5yJODn3vVKhn590KIUiwWphRcG6yAQ8HKSU9wRBVHV10+QNo+uB56xKsFmbk55y07+mJuEiU/sWgKAop6S5S0k/Vevsi8bqI/pBSsqm6jv9buYZj7V1ENG1IBe30vGweu/vWi0TpVCClJBQI09Xipr2hE19PAF3XMZqNOJPspGQm4kpxYrIMLUyUUuLt9hMKxEKVqKpCQprzpEKDaJqOu70nbrVtsZmw9xpPSilxt3uIRjTMVhOOXiG4z+3n2N46gr4QGQWp5JRkoPay81JKohGNukONtNZ1YHVYyC/LITHNOSpuSVUV6A1jquuS7lY3TVVteLt9KKpCckYCmUXp2E+D+5JSEvSFaGvopL2xi5A/hMFoIDkjgfSCVBwuW9za/kKAlJKAN4jfExyyjBCQkOrEcAb8C2PRSiW+ngAdjV10tbgJ+mMxtS02MwmpTpIzE3Ek2uLf/Wyiwx/g+2+spr7bzbyiPMamp8acxgdBtst5WgQJ/g2JkpSSzuZu3n5yPete3Ebj0RaC/hBaNBZGRFEEBqMBi8NMZkEa5fPGMu/qaYyfXRInUCfi9b+8yzMPvoKUYHdZ+d/nv0xB2ejZ7ap9dXzn1ocI+EIIIfjI12/ghs/EAspFQhEeuPc3VO6qYebySfzXI5/k6K4afv0ff+PY3lo0TcfmsLDklrl87Hu3Yk+w4W738MdvPsP6l7YR9IVQDAoZeSnc9c0bWXLL3Li2bygYzQaQUF1Rz3O/fIPt7+yjp9OLFomCEJjMRjLyU7n0jvlc9dEluFIco14UUko6mrp46/F1rHthK41VrYQDYTRNRxECo9lIak4y866axlUfW0L2mIwLhjC99Pt3ePahV4e8b7Ya+cHz/0nxpJGDmA2Fvg2lYvMRVj65nn0bDtPZ3E0kFIkb3KqqgsFkwJFoJ29sFtOWlHPFXQtJGkSrfKZQ0dxKbVc3982fxacXzsF4lgXs/1ZESUrJgU1H+OUX/0rNgXoGM/7VdUk4FCEcitDT4eXwjirefnIdP37tawMmnBCCWZdP5pkHX8Hn9uNz+1n3wjbyv5o9qsUkpWTDK9tpb+wCwJFoY9oJGhwpIeAJ4nP7qd5fT1NVKw999lGqepMsAPh6Arz2l3exJ1j58Ndv4A/feJp3nl4fNyLUIhqNx1p5+MuPk5GfyoS5w0cFNVlNbHlzN7/60t9ob+h8f4cJBcLUHmrkr997ju1v7+VLv/k42cXpI45X13W2v7OP33/tSeoPNw1493pv3Q2Vzfzjl6/z3vNb+Oh3b2XxTbNRLwD1dSQUwdfjH9I4MxIyxgnHqSBGsLv56/ef473nNhP0hwctp0V1tGiYkD9MR2MXR3fXMO+aaWeVKHX6Yundl5YWYxqCQzqT+LciSs3VbTz46UdoqIy5VKgGlezidPLGZpGQ6oxlvm330FLTRkttB/4eP1JC0cQ8ckoyB60zb2wWUxaOZ/3L2wFY+/wWrvvUZThHEZMp4A2y6dWd8d/lc8eSM0RM8c7mbp7+ycs0VbUya/lkXKlOdq85QHtjF1KXrHxyPcmZiaz95xZSs5KYuGAcQV+Ine/uJ+QP4+328dqf36VsdgnqMILZ+sNNrHtxGx2NXdhdVgrL88gqSsNgVGmp7aByVzWeLh9SSvauP8RD/+9PfPvxz+JKGfp4KKVk8+u7+Nln/kRPb3YZRVXILk6ncEIuzmQHAW+QukON1B5qIhKK0FrXwS8//2eCvhAr7l40Iod3tnHJDTNJyUqkp9Mb++vwUlPRwOEdVaddt5SSltp2fvyJ37N/45H4dSHAnmAnLScJe4INKWNH947mLnzdfnRdMmnBOHKKR5cQ4FTh6rUIj+hnx97r/fi3IUpSSt5+cn2cINldVu7/4Z1ccv1MbM7j8hFJbMfuaOxi38YjbHxlBwtvnDXo0Q1ihG3Zhxaw6Y1daBGNusNN7Ft/iLlXDcyk+n4c3lFF7aFGILZIF98yB4Nx8J3I0+Xjvee38skH7uCKexajGhQqNlfyndt/jqfTR1erm7/+7z9Jy0vm2098joLxOeiazrM/e5W//e/zvVxiJT63H9cwgeh2rNoPSGYsm8hH/+dWCifkxOUkmqZRU9HII998mh2r9wOwb/1hXvjtSu765o1Dyt3qDzfxm688HidIyRkJ3P3tm7nkuhnYE229qcAh5A+xd/0hHv3O36naV0fAG+LR/36WnDEZTF5Ydt6OckIIisrzKCrPO+5bJ2H13zfx4/t+j9RPzy8n6Avx26880Y8gZRamccOnlzN7xVSSMxLi8y8cjODu8FC5q4Ytb+5mwXUzUIeYM2cKE7LSSXfYeauiksnZmRiUsxuP6d+GKGlRnQObj3/0OVdOZfmHLxlwNBAIrHYLuaVZ5JRkctmdCwaEsu1XXgimLCwjf2wWVfvriUY0Vj2zkdlXTBn22KHrOute3EakN9pAem4y05ZMGPZj54/N4tI75sfdVMpmjWHqogmsfWEryBjnde23b6ZwQm4syoCisPCGWfzjl2/gc/vpbnPT3eoelihJKSmZUsCXf3cfyZkJ/fpjUAwUT8rjP373Cb5904NU7a9HSslbj61lxT2LychPHVCfFtV59qHXaK3tAMDmsvLFX3+M2Sum9KtbAFaHhVmXTyazMI3v3PZzGo+24Ony8dgPnud7//gSthHSZZ0LxPt8hgTxUkree34LW9/aHb82bkYx//mH+8gbO9BC3OpQsTosZBakMf+a6WdFIeAOBPGG+h8fPzZvBr9cs5FAJMJV5ePIdDowDnKUMxlUUu2n52R/RohSdWcX7x2r5rLSMWQnXJiBxPo0Pn2wOiwjasmEEENyLifCnmBj8S1zqDpQDxJ2rTlAU1UruaVDhwV1t3vYtnJv/PfsFVNJHEGNP3ZGEdYTQt0qqsLY6UUxokTMKnzqovH9JkRSRgKuZDs+t59wMEJP5wjJORXBtfcvG0CQ4veFIDU7iRs/ewU//+yj6FpMFrL9nX1cee/iAXHDG442s/HVHfFrS2+dy8zlk4Yl8nljs7j9P67mF5//C7qmU7Glkt3vVYyK+/ygIegL8dqj76JFY/IoV4qDzz5096AE6f04W0faP23cztPbd/e7JoTAGwrzzI69PLdrPxajAXWQ/k3OyeL3d1w/6L3R4oyM6mBrOz985z2qOrvPRHVnBYqqkJ6XEv+9/e29VFfUjzoOz0i45PpZJCTHAqn1dHpZ//L2IeuWUrJvw2Fa69oBMFmMLLpp9oiTMPt9sgMhBCnZSXHTIleqk6TM/gJPo8kQJ2Qx1XaI4eBItI14VBJCMH1pOYlpCfF6d717YNBjzM7VB+JOsSazkaW3zRtxMQkhmL1iCmk5sRAe0YjGuhe3nbFvdaFASkntoUaq9h9XXFxy3UxKppzZNPMniwynnbKMtH5/49JTmZGXzZyCXGbkZVOemT6gTFlGGgXJiafd/r/N8U1RBAuum8m6F7cRjWg017Tzndt+zvWfXM6im2eTkpV4yqmHhBBkF6cz/dJyVv99E0hY89wWrvnEpdhdA907dE3nvee3xHfH4kn5lE4tHJEQJAwSPdJ8gqzL7rJheX9SByHiMiEpiaVsGgapWUmj0uQkprnIKcmgs7kbgLpDjYQC4X6cnJSy35E5OTOBgvE5o1pwCSlOiifl01IbI9yHd1QR8AYHfZ8fZBzZUUWoV9OmGhTmXTP9vPsq3jFjMrdNP/kswkA8OOHp4JRWYV+CPE3Xh929+ozANF0nquvoUg5pCdqXwmm09faVjcVoGnkH7dt9l9wyN541paWmnT9+82m+tOz7PPwfj7F7bQV+b/CUdmRFVVh25wIMvfKemooGDmyqHLSutoZO9q491NsxWHjDLMy24ZNVCgEWu3nggj7ht8lqHHjcfF/xkYaWlJGA0TRyanHVqPaTIXW3ewj4+hsXRkJRmqvb4r/TclP6Ea3hoKgKOSdEQuhs7j6rYUjOF2oPN8X/b3NayS09uUgDZwOqomBU1VP6OxNC8JPilKSUdAeCPLVzDxtr6jAoCktLikiwWAaEbZVS0uLx8uzufWyvbyCqS8oz0rlt6kTGpPRPEqnpOlvrGnh+7wFqurpxmc0sKSniuvKy3oygAk3X+cee/WQ6HSTZrDyxfTc1Xd1ku5zcPnUSs/JzR6TQZquJz/z0I2QUpPLyH9+hp8OLlJK2+k5eeWQVbz62lsIJOSy9dR4Lb5wVOz6MUpAohKB8XilF5bkc2VlNNBxl1TMbmH5peT+Bt5SS7e/so7utB4hxBKOSlZzA8QyFWBTLkfo6PFWyu2yj2qmFELGAcL0I+UOEA5F+ZbSohucEGZYj0RaLjT4KCCH6xY6KhKJ4unxk/otl9+1qccf/b3VYcCZdeJxgX07B4QIz9jEKQogBWX5PFifFKQWjUf77zXf44+ZtpDvsjEtL5aX9B3l0y45+O7CUkgZ3D5/558u8euAQJSkpTMhIY+2xaj759xepaGmLcxBSSl7cV8EXXniVNq+PGbk5OC1mfrZmPd99azXB3mBUem+5H69ey7defxtFCKZkZ3G4rYPPPf8qm2rqRuRwhBDYE2x85Os38OPXvsa1913aK9CN3Y+EIhzZWc0fv/kUX778Bzz1k5fihGs0sDosLL1tXvyD7Fi1P3786EMkHGXdC1vjdU6+pIzMwtEttJE/9OnvsKpRHVUtQog4Vwi93PP7joa6psfTPAEYzcaT6qLRfJxj03UZ11T+q0BKSSR0nJAbzQaUc2CceLLoCYb4xstv8WbFEfQh1kJ3IMjXXnqLJ7buOu32Rk2UpJRsrK5l9ZFjfHrebH50zRV89dKF/Pbm61CE6NdZXUp+v2kr7mCQ391yPd9avoRvLFvMwzdfS1TX+d3GLfE8Vo09Hn6xdiNXlo3lNzdfy38uWcCPr7mCzy+cx+sHj7C+qrYfUajq7OaTc2fxg6uW87VLF/Kbm6/DZTHzh01bCWujM+5SVIXCCbl85qd38dDb3+b+H36I8XOOu5FICa11HfztB8/zP3f8grpDTaM+Is6/ZjpJvVo0d3sPG1/d2e/Z+iNNHNp2DIjJEBbfMgfVcOHExdGiQztbnggpZf/gaULE4433QVGVflxi9CSDrZ1YXiij04R+kCAQ/YT+fa5OFxpqOrt5s+IIB5pbh9xT7CYjzT0ent9zgGDk9DaPk1oNa6tqsJlMrCgrRRUxVi7VbmP52P7B2LsCAdYcrWZBYQGZLgehaJRQNEqG08GEjHR2NTbTHYxl9NhUU0enP8BV42OBy0LRKBFNY3ZeLmZVZWNNbb+6M50OFhQVxNNo5yW6WDymkP1NrbR4Ri9zECI2ITIKUrnx/13O/738X/zwpa9wxd2L4scSqcfcUn7+uT/j7R5d3en5qcy6YkrseQlr/rEpboogpWTTa7vw9cTGnlmYfl6NAgeDvycwsuCJWBFvtz/+22wxYrL0l4upBrXfEc/n9o8oaD9ev6SnwxP/bTCq2P/VYkIJcJxg+R/0hQj6hnb6PV9odPcQ1XWm5Awt7zKqKsUpSbR4vHhCw2t4R8KoZUqalNR395BotZBk6+8hnpvo6ifPafX66A4EePPQEbbU1verp9XrQ1UE/nAE7HCkvYOQpvH1V9/qZ4wV1XV8kTAdvkC/nTvVbsN6gmxFCEFhUhL+SIR2n4/8pJPzAeobh8VmZuL8cYyfXcK19y3jD19/ij3rDgJQsaWSzW/sZtkd80ckIKqqsOyO+ax+diPhYIRj++o5tP0YUxaNJ+gLsfGV4zY7c6+aiitpdGm+zxW6WnuIhKMj+ptpUY3W+o74b1eKE4u9v+bPaDKQUZAad8Vob+wk6AvhSBx52kld0nisNf47IcXRj8D9qyDrhMzQvp4ArbUdpGYnn8ceDUSfCMVhHl4ZYzebCUc1okPEWhotRi/olhDRNFRFoIrjDJYQAqPSfwJHNA1Nl8zIzWZewUCvaZNBJckas84NRqKYVZUbJ00gwTJQM1OQlNiPZRzMKMuoKkg47ZcBsd29ZGoBX3z4Y3zlyh/S0diFrunsW3+IS2+fP0CgPxjGzSimZGohBzYdIRKKsPb5rUxeWEbV/jpqKhqAmCZt0Y2zL7jwRR2NXXS39owo5/J0+Wg82hL/nT0mYwBREopgwpwS1j6/tbfubhqPtTJ2etGI/fD1+Dm29ziXXDA+F7vr/Ft0n2mUTC1ANahoUY1IKMLOdw8wfk7JBcU99xGjFo93yESWEmjzemOJCJTTO2aPmigJAYlWC9Vd3QSjEWymPvmLxNObErgPTrMZi8FAXmIiH5kxZdgXnOaI7X5LS4oozxzZsdATCveLeielpMMfwKAouMwnl8p4KAghyMhLIbckk45eD35f/Fgz8mQx20xcevs8KrZUInXJjlX76en0sm3l3njspdJphRRNzDsPk2/49jxdXvZvPExGQeqwmpYDm47Q0dQdr3LyJePiphYnYtrSiTgSbXi7/QT9Ida9uI2SqQXD2oTFnH0Px80JhCKYs2LKeXfKPdMQQlAypYC03OT4WFc9u5EV9ywiJSvpPPfuOMakJmM3m3hl30EuHTsGu8k4wHK/prOLLTX15Ccl4LKe3joc9VdWhKA8M4MOn5/K9s4TtGewu6m53xEr0+VkTGoyG6pr6Ar0t/vps13qw4zcWM6p1ZVVMTumE7Ry7y8L0OTxUO/uid8Laxo76hvJcNrJdA19FNI1nWg4OmpBot8ToKPXMBBi9jujNWoTQjD3yqmkZscmVmt9Bwe3HmVnrxOrELD4pjlDOvmeXQw/fl2XvPLIKry9kQAGPC0l/p4AL/5uZVw+5EpyMHP55AFELOYyksmcFVPj1956fC2Vu2qGtXZ3t3t49mevxAXdWUXpzLly6gXFPZwpJKQ6WXzz7Pjv+iNN/PV7z+H3BEacq0OtkTON3MQElpYWse5YDd9+9W121TfR2Zv4stXjZfWRY3zlhTdo9/q5YfKE0w5vMmqiJIRg+dgxJFotPPTeBvY0tVDX7eb5fQd472h1v/3XajDwsdkzqO/u4b/feJutdQ0c6+hkT2Mzf9+9j1crDsfLTs3J4rKxY/jL1p38afN2DrW1c7S9gw3Vtfx24xYa3D39+hGIRPjZmvXsb26lrtvN37btYmtdPddOKMM1yPGvD03VrfzvXQ/z5t/eo/FYC+FgBPk+w8tYtEWdzhY3jz3wPI2VzUBMyDp10eCZUIZCSnYSc6+aBkA0HGXt81upPRQzlEtMT2DWFQMX8YWCiq1H+e1/PUF7Q2c/49Q+gvHIt59l3/pD8fKX3DCLnDGDc7mqQeW2/7g6TqC7Wtz89FN/ZO+6Q/02CSkluqbTUNnCQ//vUQ5uPQrE3v2tX7iS5MzEszji8wdFUbjmE8vIG9ebEFLCyifX86OP/46DW48S9IfQe42J++ZnJByls6Wbnav389SPX+qncDgbMCgKX1gyn+m5Obxx4DD3PP4c1//hca7/4+Pc8Mcn+NzfX+FgSzu3TZvItZNOX3FzUsaT+UmJfOOyxfxk9Truffo5LAYDGQ4Hn184j99u2BJPaieE4LKxYwhGlvK7jVu5/+8vAhKBwG428el5x3cGs6ryrcuW8PO1G/jT5m08vH4TAKpQyEtM4Jrx/dMXTcrMJMVm4/5/vEhUiwnVrhhXyj0zpw1rPBkNa+xYtY9Nr+/EmWgnpzSTwgm5ZBak4kiM5WnzdPuoP9zEvo2Haa46bks1dckEpi0tP6mXLYTg0tvmsfLxdQT9ITa8soOAN6ZZmbZkAmm5KSPUcH4wdfF4Dm49xjvPbGD/piNMX1pOflk2RpOB5pp2tr61m5qKxvi7yR+XzW1fumrIo5UQgoLxOdz3wJ388vN/xtcToOZAA9+57SEmLhjH+FljSEh1EfAFObanlp3vHoi7riiK4Iq7F7HszgVDHyV1Sd2RJjydXoL+EH5PEH9PAF+Pn6r99ei9gdeklLz79000HGnC5rJhd1mxOi1YbGZsTmt8jO+HFo2Fo/F2+wn6Qvg9AXw9Afw9fiq2HI2/By2q8cZf1rC35BA2lxW7y4rNYcFsN+NIsJE/LnvId5SWm8xnfvoRfvyJ39PV4kbXdDa9totdayrIH5dNflk2ziQ7Upd4un201HTQXNNKd2sPrhQnV9y9CDh7SgAhBFkuJ7+69Rpe3neQVYeP0uj2EIpGSbBamJabxbUTy1hSWoz5DATkOymipAjBinGlTM/JpqqzC1UISlJTcFnMXFY6pp903qAoXD9xPEtKiqjq7MIbCmM3mchJcJFqP67aFUKQbLPyncsv5b45M2lw96BLSYrNRm6iC7upv8TfoCh847LF3DNrGq1eHyk2K2NSkgcNo9APIvYndRkL0rW5korNlcM/osTCknz2Z3cPEOKOBCEEY6YUMG5WMbvXVMRU7cR2/hNdXS4kmG0mPvo/t7J/42H+9oPnaa5u47U/vztk+eziDL748MfILEwb0W9v0Y2zEAL+8PWnaG/swu8JsuWN3Wx5Y/egz5itJq762BLu/tZNwx5zI5EoP/v0nziyqypm5zNUbCMJq5/dyOpnN/brl2pQSEpP4MGV3xw09IrP7ecHdz9M49GWYe2ItKjOK4+s6j9uJWa7lTMmg5+v/u8hQ68IIZi2eAJfe/RT/Pa/nohHRQ36QhzeUTWKQHJnfy4JIUiyWblr1lTunDGZYCSKJnUMioLVaIyb6JwJnLRDrhCCDKeDDGd/+U2SbeALF0KQaLUyLWd4rYkQAoMQ5Cclkp+UOGxZicSoqIxNS2Vs2sBJNBTSclL40H9dx9oXYnG5A77goBNYCDBZTLFYSh9awOUfuSTOSZ0sTBYjy+6Yz961B9F728otzRwxJG2//igCoQgURQyq+RMidgToiy8+4P6AOgYpoygIRZCRn0ru2CxKpxWSPSaDZx58hcrdtf2sjoWIuaLMumIKH/rqdaMKsQExQ8pFN86mYHwOz/3yDba8uRt3h6ffN4j591kYN6OYGz5zOTOXT8JgHCEwvoxZyfc5N5+sM6umxY5DQ8u4euvX9FOKXdRX/0gQimDKovE88OJXeOtv7/HuPzbHxAyhyAAxoBACkzUWK33BdTOwJ5w7raQQIu7ndtbaGEFIdsGYl0Y0jXueeg6Av9xx80mnHe4bZ8gfpq2+g6bqNtrqO/B0+Xo1YgKrw0xaTjJ5Y7PIHpMRdx49nR2g4WgLn1/8P/Fz/4e+eh13f+umUdWpazpH99YS8ARBQOH4HFwp/SMFuNs9cTMDu8tK8aT8fgtT13WO7hm6Dl3TqdxTQ9Abwp5go3hiHkIR8fhTVfvqOLq3lu7WHlSDQkZBWoxoFWegGk7e+bIvS0p7fQdH99TScLSFgDeIyWIkPT+V4vI8ssdkYDQbRveOdJ3K3bH+nypUo0rp1IIBxp8A0UiUyl01hIORQZ4cHUwWI6XTCkcVa7xvnvo9QRoqm6k71Eh7YxdBfwhFUbAn2EjLSSZ7TAaZhalx7utClU8OgyE7/IEiSh99+p8IIfjTbTde0LnQ+9Anx/jxfX9A13RsTis/eePrjJmc/0GcRBfxb4y+ZJS1XW68odCQhMFlNlOeNXIiCYYhSh+YeEoGReF/rrg09v8PiL1KNKKx+tlNcWFr2awx5JeNLtPJRVzEhQIpJeuO1fCjle9R2+UeMjuuAGYV5PLIh248rciTHxiiJHqF6h8USCmpOVDPvg0x1bmiCi69fd6gGp6LuIgLGZ3+AA+8tYb6LjdzCnMZk5rChmM16MC8wjyae7xsqamjLDONry5fdDEZ5YUKLarx0h/eiTvf5ozJZNblF65t0kVc+JBS4ouGCWlDC86tBiNW1XhG59nh1nbqu9x8dO50/t+iuZhUle+89g7+cIRvXLEEXUq21tTzrVfe5khbB+PSR6+AGgwXidJZgBbVeOfpjbz795jNlaIqXHPfskHD2V7ERZwMHty7mtfqDwx5/yMlM/ns+IVntM02rw9FCJaNG4PZECMZFoOBNq8PpMSgKMwpzGNJaRF/27yTy8aOwTqK6KVD4SJROk0017TReKwVu9OKUARdrW42v76LVc9sjPu5lc8t5bI7R44wcBEXMRL80TBdIf+QgmZ/9NS1hENBiJg5yonHMpfVQntDExFdx6woKEJQlpHKa/sP0RMMXSRK5xO711Twi8//Oa7ujUa0uGAbIKMglU/96EP/erGALuK84L6y+VyWM46ukJ+ucIDOkI9Xaw/QEvSM/PApItPpQJeSms5uJmXHMkUXJifyeKeb2s5uStJist4ufxBdSvTTVNpfJEpnALH87v01EoqqUDKlgE//5MOMOc8pcy7iXwNCCEpcqZS4YjIbKSURXWNfV/NZJUpFKUmkOey8d7SaKyeMRVUUJmVnoiiC77/5Lh+ZNRV/b064LJcT52lG6/jAEKVQtAV/tAajkoTdeOHEmymZWsi19y+jraGTgCeIwRTL8jFl0XimXzoRZ9KpWYMPBl2G6AnF0mo7TeWoyugyg1zEvybO1RpIttm4bfoknGZznAfKTXRx+/RJ/GH9VrbW1CMBi0HlU5fMxn4aRzf4ABGlNv/bHO78X9Jsy5mY9nMulOhoxZPy+H8P3hWzxO39YkKIs5JOOax1srf1MwDMyHoGm1JwRuu/iIsYDELAJ+bN7OffpgjBJxfMpiglic3VdZgNBpaUFjO/6PQNgz8wRCm24vXevwsHfR/gXO1a8gIb/0X860MIMcAYUgiBxWjg2ollXDuxLH7tTOADRJQu4mxASklU6nSHA7jDQTRdw6QaSDLbcBrN/UIfnwx0qeONhOkK+wlqUVQhcBktJJpsGM9AwsKzDSkl/miEzpCPgBZBEQKHwUyi2YpZGZ1fXl8uNL8WpjsUIKBFkFJiVA24jGZcRgtGZQSH4wsQfXngJBJFiDMaIQAuEqV/G7QEPPzx4AZCepQZqXlcnz+JiK6xtuUYzx7byYHuZnoiQTRdYlJVkkw2ZqTmckfxDKakZI+KOEkp0aRkT2cjz1XvZlt7Le1BHyEtiiIETqOZMa5Urs6bwIrcCbiMg2T8PQFrmip5uzFmEZ9jS+Tj4+aOGP/5QHczTx/dgUTiNFr4VNkCXKbBZW+H3a08XrkNCVyRU8aCjFjs8OaAh2erdvJ2w2GaAz0xooTAbjSRbUvgkoxiPjFuHk7jQIGulLHF2uT3sKG1irXNRznobqUr5CeoRZASjIqKw2iiwJHM0qxSrs0vJ83iuKCJk5SSiKazs76RVYePUdXRSTCqkWAxMyEzneVlJRSnJp92Ikr4QBKl2OLQdD/BaCOaDGBQXFgMWQiGtmSN7VoBQlobUT2mqTAoLsxqGoqwDPsipdSJ6j2EtDZ0GUQIA0YlAaOSjCKGXlhSSnTChKLNRPUehDBiVtMxKomIYRZ5bHF7CUYb0WUEk5qMWU0fsvxo0BMO8o/q3fiiYaq9XSzNKuWX+9/jmWM7Cen9LYRDehRPJEStr4t3Go/wpYlLuLN4OuoIcbV90TC/qVjHU0e3442GB5QJaBFag142t9bwfM1evjNtBWUJQztvHuhu5uljOwGYlJTNR8fOGXGcDT43z1TtRJeSdIuDe0pn42JwotTk74mXdRrNLMgoYldnA9/c9ipHetoGlA9oEdqDPoLRCJ8YN2/QOnUkvz+4gScqt9EW9A6qHA/pUbzREM0BD1vaavhnzR4emHk1k5MuXL9ITyjET95ey0t7DxLWNEyqihCg6ZKVByv525adfGbhHO6cMQWD+m9GlIQw0BXcyLHuX+ELH0aXYVTFRoJ5OsVJX8RhHDcgqHkw2kCj9xk6AmtjhEyPhRFRFRs2YxH5ro+RZrsMIfrvwjGVayd17r/Q6n+TsNaGLiMIoaAKO1ZjAVmO68l23DbIsxqdwY3Uuv+IJ1yBpvsRQsWkppFhv5p810cxKAkDJqEuo7T6XqfW/Uf80VqkjGJUXKTYlpLjvBOBAcnpJfur9nTy0L53efrYDnQpybK6GJ+YQarFTlCLcqSnjSPuNqJSpycS5MG9qylyJjM/vWjIRRPQIvxg11v8s2YPupQoCHLtiYxLTCfZZMOvRTja005lTxthXWN7ex1f2vRPfjXvFkpcQycpOFdoDvRwyN3KV7a8SI23C7NqIMvqIsPqRBGCzpCfJn8PnkiQWWn5OAyDpxtSEBiFEidIJkUl3eqk0JFMusWBIhTagh4OdLfEyxx2t/Kd7a/zp4V3kmK58NJIRXWdX6/ZxAt7KlhcUsS1k8rIT0rAZDDgCYY40NzKMzv28uCq9aQ7HVxednra8Q8cUfKFj3Cg/auYlBTS7VchgO7gNjoCqwlEa5ic/lushv52Qb5IJXU9f8WgJOAyTcJqzEVKnZ7QbnpCu6lo/waGdAdJlv5W17oMcajju7T538JqyCXNdhkGJYGI3o0vUokvfIhApI73hzqXUtLie43Dnd9DyigJ5mlYjYVEdTfdwW3UuH+PL1LJ+NQfYsAZb1NKSavvVQ51fAddRkmwTMduLCWiddDhfxdvuALJyWWZHQzNgR6eOroDo6pyb+lsPlIykzSzI26x64uGebl2Hz/e8w7eaBhvNMRfj2xhdloBRjHw+KRLyZNHt/N8zV50KXEYTHxm/EJuKpxMotmK0qsp9UcjrGmu5IHdK2kJeDjq6eD/9rzNr+bdjG2IRX6ucLSng+/veot6n5tl2WP52Ng5lCVkYDEYEUBE12gJeNjcWsO4xKG5ViEEV+eXs7LxMJOSslieM45xCek4jGYMvdyxJiWNfjc/27ea1+oOIIGK7hZWNx3h5sLhs/+cD9R0dvPi3gqum1TGt1YsxWLoL1ObkpPJopJCPvnUCzy+dRdLSovi7iingg8eUYocIctxIyVJX8OguABJSGvlQNtX6A5todb9CONSvgvEFo8QgiTLbMrTHsJpKsekpiJ670X0bg62f4P2wCqavM+TZJnHiaYGvshROgLvYTXkMiXjT1gNeb33JboM4o9UY1QHJg4MRKs52vUTAMan/ohU21IEBkDij1Sxr+1LtPtX0eR5jjzXvfHnwlobVd0Po8kQRYmfJd/1cRRhBnQ84QPsa/siUb0bg3JyCTcHgwQ+WjqHz5cvGiCncRjN3FY8jVpfF48civnv7epopNnfQ55jYOqfOm8Xfz68GU3qqELhC+WLuat0FopQ+hlu2I0mrswdjwD+c8uLhHWNDS1VrGs5xvLsced1MVZ0NyOE4ENjZvCVSZcOcGo1KipFzhQKHbHvPVxfs6wuHl14JzaDaVAZi0EI8uyJfGvq5Rxyt1HZ04aOZENrFTcVTrlAjF2O40hrO4FIlOsnjR9AkCA2vpwEF0vHjuH53ftxB4KkO089yeoHIzDRCTAoLvJd92FQXb0+OQpmNYOCxPsQGGkPrCGstfd7RlVspNmWYTFkoghD73MCo5JIluNmQCEQqUGX/eUgmvQhZQSD4sSkpgAi3qaq2HCaJ2AxZA44LjZ7XyKktZBuu4o02zIUYYw/ZzMWk+u8E5C0+F5Bl4H4c13BzQSiddiMReQ6P4SqWHqfU3GaJpLtuO2Mvcd8RyJ3l84aUnCsILgqdwIWNbZv9USC1PvdA8pJKXmt/gCtQS8A4xMzuLloCur7CFIfhBAsziphQmLMXSEqdV6tO4B+ltMEjQQJjEtI53MTFg3rZd83d4aDEAKH0TysVkoIQYrZzuLM4ynvG3xuIvrpc8JnGmFNQxFgM5mGHbvDbCSi6WhDxUkfJT5wRMlqyOsVah9/OUKIOBcU0TrxR4YOtB4TeEfRZRidMAbFgUDtJUj9bYBshgLMhgy84cNUdv4IX6QSXQ6fO04nTFdwIyBItMxElxE0PRj/02UIm7EIgYFAtJ6w3hV/tie0C9BJME8ZwA0JEatPcGaOOQsyikk1Dy2/EEKQYXWSYIqFW9WlTldoYCqfkB7l3abjCRgWZ47BYRjezcCqGpmakhP/vb+rCU/k9PLPnwlclz+RJJP1nHJsfZwXQFCLBeO/0JDlciIl7GlsHnLuhzWNXfXNpDlsI6b3HgkfuOObSU1BEQPN2FVhw6QmE9KaCGmt/e7FBNYddAY24g5tJxhtIKp70WWIiO5GMrhntUlNpzjxP6js+j8avc/S6n+TJMscMuzXkGSZh0FxDpjAmu4jFG0BJEe7HqTa/ZsB9eoyhCSKlBE03dd3lWA0lhfOYshlMIv12NhPPwuwACYnZ49YzqiomE7gpMKD7OKdQT813hhhVYSgLDEDycgJEjOtruN1hPy4wwESzecvLbdJUZmWknvWCFK//IInXD+RU5UXTvTpfijLSGNseiq/X7eFJJuV+UX5OMwxrknTddq9fp7avocNVbV8Yv5M7P9uREkII4MxeEIo8QWry+O7rpSSzuA6jnQ+gD9Sg1FJxGrMw6ymoSoOoloPwWjDEG0JMuxX4TSV0eB5ijb/Str8K2n3v4PdNJYC1ydIs1/Rj0jGOLAIsaOeIS6/OhGqsGE3lqAKK4qIfUCJjPdbFYPv1oowDWtKMFqoQiHT6jqFBThw0bSHfHgisXx2UkoePrCWxyq3jlhTS+C4A2lY1/BrZz7kxsnArBpIt5y6HGQwRHWd9qCXyp52jnnaaQ54cIdjRpQhLUpQi9LgG3gkvtDgMJv4r8sW8pUX3uArz79OTqKLDJcTs6riCYWo7+6h0+9nSUkxd8+eetoysQ8cUZIyQuyY9X6Nlx5f1Io4bpcSjDZwqOM7BKNN5DjvIN/1McyGjF5iIegObqUj8O6Q7cXkQGMoTf4m+Qkfp8O/hibv83jC+6jo+AZhvYtc50dO8AmKESKBgXHJ/02CZcbQdSPifY39P0agdBlCSjmAaEipESMMp/fZFSGwGc5MyvCeSBCtL8stcNDdOvwDg0Fy3o8tihAjGmaOFlFdZ0dHHU8e3c6Wtlo6Q/7zPr7TgRCCmfk5/O6O63l043a21NSzp6EZTdcxGwzkJDi5d850bps+Ead5eIPY0eADR5TCWju6jKCK/l3XpJ+w1onAgFlNi1/vDm0jGG3EZiymOPELGNXE+L2Yi4VvRH+y2EsWWAzZZDvvIMNxLXU9f6Gq+zfU9zxOpv3aeL2qcGBS0whpzYS0VlRhG+VHUjAbYqmvg9FGBiM+Eb0LXYb6Ed1TxenGUe5DVNc5kYNKMtkwDGNkORjMqiGuLj9dnOoRSDB4Xr2TRUiL8sdDG3nk0EZ8vQakihAkm21kWl2kWuwkGC3YDCasBiNHe9pZ23Ls9Bs+yxBCUJaRxg+vu5zuQJAOn5+IpmMzGUl32LGZzlwI3g8cUQpE6whGG7AZx/Sz7/GEKwhrHRjVZGzGwnj5qOYGJGY1HVV5v2BX0h3czMlkkoolznSQ5biF+p4niOhdRPSeOFFShJkky1w84b20+d8iw34N6iiJiMs8hQbP07hDu4nqXozqcbmLlJKe0J4zRpTOFKyqoVfpEEsS+tDcGxiXkHFSdQggYQhXkJNFVNfPW2IwKSXP1+zhNxXriOgaApiUnM09pbOZmZpHksmGWY1x6H3L96ljOz4QRKkPqqKQYreRYj97QQs/cEQpqvdQ2/MnSpO/jkos5nVY76DW/QiSMCnWRZhO4JTMhixAIRCtJaS1YlH7BLwaHYG1NHtfHLItb/gwEh2boaAfIZBouEM7iOpeLIZsjMpx4iGEIMtxIy2+l+gMbKC254/kOu/GoDjps3HSZIBApBohTDhMpfHnkixzsRiy8UcqafQ+S57rbgSxY5Y/UkWD5+kz8g7PJJLMNkyqgWg0jC4lUV0nxTxa7vDMQkqJOxw4bwLjnkiQvx3ZElfrT0vJ5Vfzbh7Sr63PYfdChy4lmq7HOeCz/W0/cEQp0TyLdv+7eMNHSLBMBwldwU34IoexGgrJT/g4J8qbEi0zcBjH4o0cYl/rF0izLUMIA57QfjqDG0g0z6A7tH3QtjoD66nq/hU2YxF2YwkmNQ2Jhj9yjO7gNgBynHcOUN/bjMWUJH+Nwx3fo6r7N7T4XsdhHIuiWIhqbgLReoLROoqTvhQnSgBmNZOChPs50vkAVd2/pDu4JWbRrXfSFdiEyZCGWc1Ak8Ez/2JPEekWJ2kWOzXeMJrUOdDdwqITbG9OByceMXWpj2oBV3s7z5sOq8bbRa23G4j1/a6SWSM62nYEfUPeu1DQ0N3D999YxbWTxnNN+biz3t5ZI0pSSqSMBYgaapfok5qMRHljQl8rJiWLgoRPo8sQ1e5f0+h5ple+ZCHJMo8xSV/GZihCyl4VrACjkkxZ6v9S2fljPOF9HOs+gEDFpKaQ6/wIua67ONj+TTQZ4P0yHKdpPHZTCf5ITS/XFEWgoAgLNmMhua4Pk2G/ZkB/hRCk21ZgVjOodT+CO7STtsjbSHQUYcSguEi0zCXBPG3AczFjTkGt+1G6AhvpDKxDVRykWBdTnPh5jnX/HG/44KBavfMBp8nM9JS8uFnA6qYj3F0yC7vx9O2p7CfYO/VEggS1CNZhBPRBLcrOjsE1qecCXSF/nEsyCpUiZ/Kwczuia+zqPH/9HS2OtLWz7lgtS0qLz0l7Z40o7a5q4revbuCz1y5gUmFWv3u6Lnny3Z00dLj5/PWXDJv5QNN01h2o5s0dRpq778FubmFeWRG3XPJXQno9mu7DqCRiMeTS45f85b1t7DrWSCAcIcVp465LZzA+byJTMv5AIFpPVHejCBNmQzYmJRkQlKf9tJdg9JdrJFrmMC3jb4S1diJ6J7oMIVAxqIlY1EyUIVT3ENPaJZinMzH9l4S0VsLRNiTRmD2VIQ2jkjQoYREYyHbcRrrtcgLRenQZxqSmYjFkIzBQlvL93nrOrPr6VKEguL5gEq/XHyCoRdnb2ciLtXu5o3j6qITpffY7g73HXHsiqhBoUtIa8HDI3cqctMHjnUsp2dpeS0V38+kP6hRhVntdMHqD53sj4UG1qBDr75b2WnZ01J2Hnp4cPMEQglis7nNxLD9rRKnbG2B7ZQNu38Cjhi4lO481UNPaTSgcHZIoSSnZfKiWb/z1dYoykplUVEgoHI3FpFEdmAzj42Wjms4vXnibt3Ye5pLyInJTEuj2B+MpvlXF2u+odCJUMbjQLhZxz4JVycVK7sm+gphLAkashhyshpyRH+D44jSqSUSjDrYfrWf2uFyUXkfYofp6viCEYGZqHstzyni5dh9RqfOzvauBmIW03dDfNaGPQw5pUWq8nWxqrebq3nhC78fYhDRSzHZag15CusbvDq6nxJVKitneT8kRc2ht5ke73yY4TKLGs41sWwIuo5mucICIrrGy4SDTU3P7OTH39XdPZyPf3/nmWUmJdKaRYrehKoJg5Ny82/MiU1IVwdduvZRQJEqCfXity9r9VZiNKg/cs4K8tEQABhMt9PiDbDpUy5LJY/jeRy5HVZRRHw8vVBxubOOn/1zDX//jDkyGC+O4NhhMisqXJy6lxtvJns5G3JEg39/5Jv+o2sW89EIKnSlYVSMhLUp7yEu1p5OK7haqvZ2oQmFJVilpg0yDDKuTy3PKePxoTH63oaWK+9c9w82FUxibkI4qBG1BH5vbqnm9voL2oI+yhHSOejrOiw9Zls3F7LQC3mw4CMAzVTtjUQPyykkx29CkpCnQw6rGw7xUu4+ukJ9JSVkc7G4hMoIdk94rxPdHIwS12F9Ai9ATDvZz/6nxdrK+pQqbwYhFNWIxGLGoBmwGEwnG4eOGDYXyrAyKU5J572g1C0sKT9rk42RxRoiSlJJgJEpHjw8hBKmuwX2qpJREtVhWqAS7ZUgTwD6tRFTT6fT4sZtNOKxmIr351AxqLJxq366j6xK3P0ggHCEj0YmuS3SpI3rLvr9ubzBMlzeAIgQpThsWk2HAbt7nVKgqgnBUo73Hh6ZLEmwWXDbzgPKx8fvRpSTJbsVh7c8h6HqvBkNV+tWXaLfgtA6sT9Ml24/UE4pEiWga4WhskSlCoCpnNvzo6UIIQbbNxc9m38D/7HyDDa1VRKXO3q4m9nY19fvO799PXEbLkPZBCoL7y+axt6uR3Z2NSIjX2efwq8njWcZmpOTyzamX8+kNf+9nMX6uYBAK/2/CQvZ3N1Pv6yaoRfnLkS08dXQHFoMhHmI3KnUUBFfkjueL5Yv5xLqnqfd1D1t3Z8jHve89SUvAQ1TXiUqNiB4T/p+obVzZcIi3Gw6jCoFBUTEqCgahUORM4ZGFd+A0nrzpRaLVwn9feSnfe30Vf960nesnjSfBahn0eC44/fl52kRJSsn+2hZ+/sJajjS0o6oK4/PSmVc28Ozv9gf55l/foL3HBxJyUhP4wd0rsJr7H992HWvksVXbaXf7OdbSSSgS5ZO/ei4WD1gRfPP2ZUwszESXkkff2srOow20dHvx+EO8tGk/Gw5UA1CYkcT377oCkzE2zEhU45UtFTz57k5a3V4Egvz0RO5fMYf5Ewr7veTfvraRSETj2rkTeOj5teyvbUbTdHJTE/nFJ68jIylmjqBLyaaDNfzx9c1Ut3ah65LUBDt3Lp7K9XPLMfZyOJsP1fLoyq187PJZ/O3t7RxqaCOqaaQlOPjY8llcObMMRRGEI1EeW72DnZUN7KttwRsI8alfPxcPRztzbC7/ceOiAYHcR4M+6xgx5HZw6s8IIch3JPGLuTfxYs1enq3aRZWnnZCuDSBECjEv+lJXGlfmjSfdMng6cyEEmVYXP597E7/c/x7vNB7GEwkiOW4BLoBEk5Urcsv47PiFJJltZNtctAQ8vcfn4fp8XLUhTvj3VCGEoCwhnV/OvYmf7F3FjvZ6Qno09heOxseeaXVyW9E07h07G6tqYlxCOvW+7mFb16SkM+SjOxwYsR8SSbR3Uw/2MowJIf8pmx+4g0HWVFZhNRp4aPV6Htuyi2S7dVAL+HEZqXz3qmWnND/7cNpEqdPj57tPriQUjvK125aSluBg3f4q/vL2NjS9P0tqN5v42OWzaHP7eGzVdqpbOgd9UUkOGwsmFKFLyYsb99PY6eaG+ROxGFUEgvTEmPxBIBibk0ay00qXN8if3tzC+PwMlkwujhnk2a3xEK5SSl7ZUsHPX1jLDfPLWVheRDAc5en3dvPfj7/Fz++/jkmFx8OQNHf2UFHXSkVdC+UFmdyxeAqBcISmjp74kVNKya6jjXz7sTeZPTaP+66cg0FVeWvHIX72/HuYjQaumT0eIQSeQIgdlfXUt3ezbEopH7t8Fr5QmEfe2MJP/7mGsrx0xmSlIIQgNzWBBJsFbzBMVXMnN8ybiNUU+1RZyafisxaTd/xq/s1ouo4iBEWOlBGfcRjNPDDrGoK9co+yxOGNImPRGix8pGQmNxROprKnjYPdrTQF3ASjUUyqSrLZToEjiWJnClm2BMwjuHYIIcixJfDAzKup8c5nb1cTNd5O/NEwVtVIgSOZKSk55NuT4gvhv6etoCPow6Qa4lEOBsPEpCz+cMkdsWD+ikriMGVHCyEEE5Oy+P2C2znQ3czezkZagl6klCSarIxxpTIpKYv03oiWUkr+c9JS7iyejsNoxqwMviQTTVYenH3DoE7Ro4HVYDzlQHqeYJjX9h/CH46QZLWi6TptnsFNGVLPgFHlaRElKSVr91dR3dLFA/es4LKppQghmFKURWNnDyt3Hu5X3mhQmVGSi6brrNpdSWVj+6D1FmYkUZiRhK7r7Kisp8cf5Po5E3BY+3vIK4pg8aSYmrK+3c3jq7YzPi+Nm+dPGrBwu31B/vbONhZPKuaz1yzAaFCRUlKYkcy9P3uaf6zbw8TCzH67VU1rF7ctnMJtCyejKMoAz/eopvPXd7aRleTiG7ctw2mL9a88P4ND9W08vWYXl00tjXOCmi6ZVpzD56+/BFNv+yaDyhd+/xK7qxoZk5WC0aByxfRx6FKyr6aZlm4P186eMKLsbSTYjSYuyTg5la5RUZmTdnK55QSAiCUJmJaSy7SUk1cQDKhTCAxCZYwrlTG92WGHw8SkrBHLACSb7WfMpupECCGwGozMSM1jRmreiGVLXGmUuNKGLWdWDczrTWxwrpGV4OSJe24bVJb7fhhV5bRdmE6PKAG7jzWRYLMwuTArTggMqsLssXm8vfPIaXXuTOJoUzsNHT1cPn0cFXXHnUYjUQ2XzcKRxnZCkf6aQJfNwpLJY1CGsGTt8PjZX9PMzNI8qlo649clkiSHlT1VzXR6/eSYE+LPL5xYhFE9Xl9mkhOzQaXbe+EYRF7ERZwIg6KcViTJk27vdB6WUtLh8WG3mLCfwMUIIUh22s6Y0+eZQGu3l4im8diq7Ty9Zle/e5rUyU9LQn9fxDy7xYTNPLQNldsXxBsM8+6eo2ysqOl3T5cSm9lINHr8CKsqgiRHfxcM0SvYGCn+0EV88CClRNcliiLQdRnTBJ8gBI4ZGEukHrNl6rs3mucAdE0ilP7RMHVdh17nYl2TMbnZBaYYGQmnLVPqe4nv5+0utEUWE3oKvnjDQmaVDmSpjQZlgL3UyGFPY8eV6+eVc/uiqQPuK4ogK/kEv7jeaxfx7wFvT5A/P/QmE6YVsPndgwgB1354HhOnx47Ee7ZWsfKFHXR3+nC4LFx7x1wmTMunu9PHY79+h7LJuWxecwiDQeXGu+czblLsKNzd6eOFxzZQdbgZV6KNa++cy9iJOQghWP3KbjRNx93lZ8+WY6Sku/jEV67E4Tx9h+e+NR3VdUJRDSklqqJgNqhnNCHlaRElIWJC573VzfT4Q3GZj5Qyrh6/UJCV5MRoUPCHIhRmnBnL1CSHFafNgtsfJD89cdi8aBfx7wctqrFjQyUmi5GPfHYZh/bU8fsfvsp3f3MXyWlOzGYjl14zlfTsRLatPcyjD73JD/5wL9GIxpY1B3G6LNzzucvYu62K3z7wCt/77d3Y7Gb+9OAbZOUlc99/Xsnh/Q08/L8v8Z1ffYSUdBcdbR5WvbKL6z80j3u/eDl+bxCL5fRjZ0kpqenq5uW9B9laU0+r10dE07CZTOQnJXDp2DEsLyvBaR4+jvdocFqrSAAzSnLxBEJsOlgTZ0dDEY31FdUDvLXjPmknXusNnXq2Oasx2amMyUrl9a0Haen2HmedpSQS1QidgrVqksPGrNI8Nh+q40BtS786NV0nED51a10B2MwmQhENXzDUr+4LjQu9iKGhGlWWXz+NgjHpLL5yMmarkaMHY2GPS8tzyM5PprvTi8NlpafbTzgUm4cms4HLbphO/ph0Lr12KlJKqo+00Nbs5sDOWrLzUmhp6MJqM+H3hjh2KFYnEnILU7n8xumMKcti0swiDMbTM7yVUrLuWA0fffyfPPzeJvY0ttATDBHRdFo9XtZUVvHtV1byxedeodnjPe35edqc0oLxBUwuzOThVzbQ5vaRkeRgy+E6Gtrd/TgHKSXbjtRzsK4VTyDE4YY2urwB/vjGFpLsVtITHSyfVhq36znTcFhMfPaa+Xz7sTf5/O9e5NIpY3DZLHT0+Nhf28IN8yayYsbJeUCriuATV8zmYH0r//XoqyyfNpasJCc9gRAH61opzU7lM9fMP+U+zyzN5bn1e3nw+fdYMmkMUU0n1WXjkvLzo4W5iJOHqghsjtgJQjUo2J0WvO4A0YjG3379NjVHWhkzPgtN09GienxBqwYVa68212BQsdrNeHuC2OxmAv4Qu7ccxWAygIRp88aQlHJcEJ2c6kRRzxzX3u7z88Cb7+ILh/n8knlcOnYMaQ47ihCEolFqOrt5dsde3qg4wsPvbTr/dkoOq5n/+fDl/OH1Tbyy5QCqojCnLJ8f3LOCx1btIMV13G6hsqmDncdiXtHFmbEsDnVtXdS1dZHmcnDplDEYT3RSFYLy/EycVgvqCC/ZajKwsLyI4szB7W+EEMwdX8BD91/Hk+/u5PVthwhForhsZspy0ynN7q9qnpCfgd1iwqgOTSSFEBRmJPHQfdfy5Ls72XCgGk8whM1sojgjmeklx/3d0hMdLJk8hiRHf1sYu9nEoonFFGQkDaj7kgmFfO7aBbyytYLfvroRq9nIVTPLWFBedMHlBruIwRGN6nS2e8nMTSYSiuLu9JGU6qCt2c2Gdyr4/m/vJisvmaMVTaxfuT/+XCQUpbvTS0q6k1AwgtcdICnFjivRhjPBxq0fW0R2wRC2Zmd4cuxvaqGuy81/LlvI3XOmDVBgZTgdTMrOpCcUYt3RGroDwdMKAndGBN25qQn8z0cuJxCKxGw0TEaEgO/fdUW/cncsmsIdi6aMvm7gw0unjVgOINlp43sntDcYFCGYVJjJD+5ZQTAcRdclBlXBbDL0+45CCD60ZHTtCiHIS0vkv25dSjAcRdN0VFVgNhr6fbwpRVlMKbp6wPNpCXZ+cPeKQes2GQ18eOk0brlkEhFNR1Vi9V4kSB8c6JrOi49vxOcJcnBPHUaTgZIJ2UQiGkajyu4tx2hp6OLtF3f2O/ZEoxrP/20DS66axJ6t1biSbBSWZmC2mpizpIw//OR1Lr12KgCtjd1cddss7I6zE5HUHQhhUBVm5ucM7loiBFajgZl5Oeyub4q7RJ0qzojvW8ybXgwwbhys3MnWe6bL9vXVbhneuvVk247JgIYWKA6XlHCkui0mIxdOANyLOBlYbCYWLC9n58ZKjCYDX/zuDThcMW75M9+8lrVv7aOhup2rbptN4dgMjCYD4VAUu9PC3CVlbFt3BKvNzOe/cwNWe8xH8iOfXsqGVRXs2XIMoQjGT87D1GvxX1CSTnLa4G47p4rsBCeqUPCEBk9o0YcOv59Uhx37MOtgNPjARZ68iDOLkYSSHyT7lgsRUpeMm5jL4hWTBtybPKuIybOOywfLe00FfJ4gUsKE6fksvGLigOfMVhNLr57C0qsHnjrmLCkbvB8nIXx+/zcvz0pnRn42z+7YS1lGGonW/lukLiX7m1pZdegYt06fiMNsHrS90c6li0TpAoGUkk6vn23HGohqOtMKs8lKGpjs8ky25/YHqWho5UB9Kw2dbnoCsZ3QajKS6rKTn5pISUYKxRkpOEbgLAdDVNPYU9tMbXs3uckJTCnIOmuKjHMBKSUtbi87qhpQhGBGcQ6pTvsHgnCvP1TDc5v3Dhsq2KiqfPaKeRSkJQ24fuOUcv73jdXc/dg/mJWfQ1aCE6Oq4g2FONLWyZbqOpJtVsyqgce37Or3fKrDxorxY0edLeYiUbpA4AuF+eoTr7P1aD0SSWlmKr/9xI2kJ5xZ834pJRFN4+XtFTz23g5q2ruJaoPH8hGA2Wjgu7cu56rpg+/Aw7Xzyo6DPPD8agLhCBajga9ct5hb5w70S/ygoNMb4At/eYmKhlZAMK0wm1999DpctsEP11a7mVs/vghnwsk5+tqdFm77+CLsp+nveCLqO7p5e2/lsGXMBgN3LxooS21ye/if197BHQjS7vNzuHVwn9Uuf4Afrlwz4PqUnEyWl5WgjDKE80WidIGgrsPN7pqmuMFpZXMHBxvbzjhR0qXkT6u28sd3thLRhhdISmIpdUqzRnaCHfCslKzadzRuqxWMRFm9/yg3z5l4Wuri84kjTe0camzvdV6Q7Ktrprq9i8n5gzsAmy1GLrt+dAqTE2Gzm0/pueFgt5hJd9nxhyOEoxp6ryvLaAyck2xWvrZ8UW+Ov5NHss12UobFF4nSMOjxB2nt8WJUVfJSEs+qi0gsQuYJv0XMxuVMQkrJnppm/rpmRz+ClOq0U56XQXaSE4OqEghHaO/x0dDZQ7LDSm5KwjC1DgXB+7t/psdzrnFi/KXYbxGPc3Wh4/LJpcwpzSMUjuILhekJhOjyBXjknS0cbGwb9lmnxcyNU8rPUU8vEqUhIaXkyfW7eHT1NgrTkvjzZ27Fbj79DB1DIS81kRnFuWw4FHPsnV6UQ3nuySV1HAlSwsvbD+ALhePX5o3N51s3LSMn2dVP3SslBCMRgpEoFuPJTxMhYPnksWw6Uoc/FMZls3DtjAkXlJP2yWJsdhrleRnsrW1GCFgwroDC9KSRH7wAYDYaSDf257qjms7L2ytGJErnGheJ0hCIaBpbKusIhCMEI5GznnXVZjLywztXsLumCSklUwqzSRhCVnGqCEQi7K5piv+2mox89or55KUkDJDzCBFzc7GdIiEWQnDFlLEUpCVS3+GmMD2Z0syUD6w8CSDRZuHn91zLntomjKrK1MJsbMNk4vlXgpSSsKZR0dzKjrom6rvdhDUNp9lMSVoKM/NzyEtMGDKl2sngIlEaAm09PiqbO85Ze0IIEu1WFk84e7m1PIEQHd7jQeazkpwUZwyfm+x0YFAVJuZlMjEv86zUf67RF3/+0okl57sr5xRSSpp6PPzfW++x5mgVwUg0npBDl7HQKsl2G3fNnspH58w4Jc76RFwkSoNASsmB+lbc/n+twGvhqEYwfNzxOMFqOe0JdBH/+ghEovzPa6tYd6yGablZLC0tJj85AZOq4gmFqWhu5a2DlTy8ZhMWg4F750w/v4kD/lWx7Wj9BRV65UxAf1+EgZhG5IN7nLqIc4MDza1sqq7jxsnj+frlS7CbjP2IzjXl47ht2iQ++/eXeW7Xfm6ZOhGnZXjvjuFwRrKZSCAcidITCOENholqGooiMBsMOK1m7BYTBkU5Jeqp65JwNLa7CyEwGdRB0xF5giHc/iDhqIZBUXBYTLhsFsy9xnqjabuvLrc/wI6q4+mUdRlTaQ+rPRJgUg0jauj60ky9P6nCgOoGGevJou/baLqOpul4AsF+4WR0KQlFokS1IdoQAvMo+qBLGfN3GoGIG1T1rKSH6htHTyCELxgmqmsIBGajit1sxmExYTSoo84BGLPl0nujOA6NM/GNTmyzbxxufxB/OIKm6SiKgtVkwGW1YDUZz0t6rUZ3DyC5aUr5AIIEsfdQkJzIZeNKeHLbLryh8LknSn2TvcPjY/uxBjYerqWioZW2Hh/+cJioFsuYYTKoOK1m8lMTmT+2gOWTS8lOOrlsHBUNrXzrmTfRdJ1Up50H776GJLu1N25TlHWHqnllewUVDW24/UGimoaqKNjNJjISHUwpyOLq6eOZmJcxoF0pJT2BEHUd3VS3dnG4qZ3Klg5q2rqo73DHyzV2urnnN88OUHGfCIOq8sAdV1CWkz7imP64agtv7Do0bJkku41f3HstifaTM7zTdJ2Nh2upau2k1e2lzeOjw+Onw+vH7Qv0O74dqG/hjl88OaSlbYLNwoN3XTOirVR1axdffeI1QtHhY1J9/NLZXDdj/LBlRgspJYFwhO1VDazed5R9dS209XjxhyNENT1GMFQVu8VImsvBuOw0Zo3JZUZxDukux7BzUJeSn778HpuO1AxZBiAnOYGf3X3NsGnnRxqDLiWNXT1sqaxj85E6Dje10+XzEwhH45lnLEYDCTYLYzJTWDy+mCXlxSTZh04Zf6bhMJtRFSWeb3EoqErMGf90E6eeElGq73Tz2Hs7Wb3/KK1u75DHnGDv7tXQ2cPGw7U8sW4Xn758LtfNmDAgSeRQCEYiVLd2EdV12nt8eIMhEm0Wmru9/Pild3n3wLFBLJI1/OEIbR4f++paSHM5mJg3UL0uJfzy9fW8uHU/oWE8myOaTk1b17D9NKrKqNIax4i5n6rW4evzOMNop3B8jGo6v3x9fa/V8fAIRqJUDzOuJLs1ngB0OISjsXpGGv+ZktFpus7myjp+v3ITe2ubh+xjKBLFEwzR3O1lb20zz23ey02zJ/Ltm0eO99Pq9oz4jaTklI/4Ukr21bXw+NodbDxcS7cvMKSCNxiJ0u0PUtPezer9RylZm8JXrlvMnNL8c2JiMSkrg0yng3VHa5iYlTHAEFJKiTsQZP2xGuYW5pFgPT2t8akRpQ43z23eOyBEQR93ZDKo6FLGqX0fmrs9/N8L72JSVa6eXnbSlD4U1ej2BTEZVL7+5OtsP+GIdWLiwT5ODsBiNDBrTO6QbYWjUXTo75PVy76fCKOqDit+MY6wi8T7CRSlJzM5PxNPIIQ/HCEUjRKKaATDkTNieWBUlcF9zN43LiHAoAw9rtjRZOT27BYT04tyaPf48IXCBCNRwpEogUh0SBeWU0UkqvHk+l38buUmvMHwgPvK+472st89hUvKikZcyALB2Kw0Wnt89ARCBMIRwpEooWiUQPjkI5QOhd3Vjby+69CAU6/aK/owqApRXY+F2ektJCUcae7gG0+9yc/vvZbJ+ZlnnWNKcdj44tIF/PCtNXT5AywuKSLNacegKPjDEao6unh+z366A0E+P2kCNZ3d/Z63GFSyE0Z/QjolojS1MJvJ+ZlsO9aAw2KiLDuNWWPyKM/LIDPRidVkJKrrtHZ7WX3gKK9sr6AnEAIgEI7w+7c3M29sPinOwdN7DwVN16nvdPPXNdvZXtWAqghKM1NZUFZIWXYaiXYrEU2jucvDvroWdlQ1YDEZKM5IHrQ+IeBTy+dyx4Kp/a57AiH+6/HX6PLFspFmJ7l44M4rsAzDpgsEhWmJoxrHnQumcOvcSWi9Adj9oVga8a88/hr1ne6RKxgGRoPK92+/nMAgXEtTl4evPfl6PPRvWXY637552ZByMIOikDqKb5SbnMCvP3Z9LJ20FgsD7A9H+Ofmffz53W2nNZ4ToeuSv2/ayy9fX99vQ7SaDEzOz2JOaR6Facm4rOZYwsRes47dNU1UNreTluBgZnHOqBJCfHL5HD5+6Sw0XScYieIPR2ju8vDlv71Cp2/kLLUjQQjBZZNLeWztTpq6eki0W5mUn8nMMbmUZaeR5rJjMhgIRzXqOrp5fdchVu2tjHP07R4fv1+5iYfuuRbzWdagtni8/GH9Vtp9Ph7buosnt+/BqCixjCm98kQJWAwGPvf3l+PZi/swKTuTRz9807ABE0/EKY3GYjRwz5KZzByTy/JJpRSmJ8UbPPGDF6UlMasklwVjC/jG02/G2ffa9m62Hq3niiljT4rKa7rkr+9u51BjGwk2C59ePpfrZk6Ie7CfmILm5rmT8ARCtPX4hrTEFkKQk5xATnJ/N4our7/f8dJsVCnLTh8xBtNo0BfPqY8Ftpljx6REuxXTacZShhinUJwxeERCu9nU79hiN5sYn5M+6qP0UBBCYDSo8aihzt64WmfSb09Kyd66Zn771sZ+BKk8N4MvXX0J04qyMaoDlSAQM4Wo73DT7Q+MyiB14DcykQxYjUYMo1xYo0F6goN7l8wgquksKS8mK9E1qCB7TEYyl4wr5O8F2Tz4ynvx8e+oaqS6rYtx2cMnsjxdqEKQl5RA+kkyEX0oTEk6qWPmKRElIQSLxxexeHzRsESl7+NeUlbEDbPK+eua7UCMuu6uaeKKKWNPuu399S1YTQa+ceNSVkwZN+gu33eUS7BZzrhV9EWcH0Q1nT+v3kb3CXKpiXkZ/PSuq4dUnvRdMxsNjBkiTPL5hABunz9lRK1gH9G/ec5E1h6sYt3BagD8oTAVDa1nnSilOew8eOOVpyxaEHBSROmUt8gTE+CNXBaWlBfHM8MCNHb2nPIgr5xaxuWTSy/mUPs3wtGWDjYdqY3/tptNfPnaRSetzb2QIIQ4qXxpJoPaz+Jf0ruOzrI9nejlGg2n+KeepDnQOTGeFEKQ7nJgNRmJ9MmWIpHYyzzJCWUxGrhxdvnFHGv/RpBSsvFIbT9H4tkleUwpyPrAEqRTgRCC3OQEDIoSDyPiP400XieLPuI3HAns+xofCItug6q8L+XSiLZ2gyIrycWYjA+2Y+dFnBx0KdlV3Rj/LYAlE4ox/BtuTO/XiJ4rr4NgJMp7lVVsrW3A/T4j3BNRmJzEpy6ZfX5TLMFxS2hfKIwvGMYTDOEPxVTd4ahGOKrR6vaedpYDgOwk5ykbq13EBxOhSLSfMavJaGBcTtq/3MbUZ+3vDYbxhkJ4A2EC4f7r6FBj2zl3f4pqOr94dwOPbdmJJiVGVSWqxTRufVybLiUJFguOiaduyd2HUyZKslcVeKipjXUHq9lV3Uh9Rw9ufyAW2a43qp1Eog+SGfdU4bCY/3977x0lV3Xl+3/ODZVT5xzULXUrRxQQCBBJCIMJNmnw8J5ncPZzWG/Gfva8ZzNjPGP757HH9vP4Z2AcZpzBYLIIAoEQCJRQTi211Dl3V3fluvee90dVl7rUrdBIAgnqs5a0VnfXrXvOPffue84+e3/3BS8WlmNyRBNGJqQEwG3XyZ9kpPv5ipSSSCLJjqOdbNh/lJ0tXXQNjTAcjaVTXWQm8jtVTfrdb2PL4BB/3r6bioCfz1+2lPqiAn766kYsKfncimV0j4T4/ZbthBNJPnXJ4jMO6HxHRsmSkh1HO3lg7VtsPtR6yoCyUVXFs3FBcwbpg4dhmpn8R0hpSZ9pKsP5gGGavLq3mf94aRN723tOGT2f0io6O8/RZDjcN0AkkeC+1VeyemYqjKfY62EwEmVmWTGzyopZUFXOp//wF/7jjS187ZrL3l2fkiUlz27bz3cfX5cJLoSUsSjwuKkuClCZ76fQ58brsOO0aThtOqFonB+veT2j2Zwjx+kiOe5BFJn/LliShskvXt7Ef7y0KSvQVVcVSvxeqgsDVOT7yPe48Ix5jg73DPDLlze/q0u4UCKBpqjUFuRljI1T12iJparfKIpCntPB1Y31PLxtF5+7bCkB5zufyU7KKEkp2dXSlWWQBDCnupS/vmwhi+oqCbgd4xyQQgiO9g7ysxc2cuaxsDk+aKiKkhVOkjTMUxY9OJ+RUvLcjgM8sPatjJ9VVVLxfH91yTxmVpbgddqPWwYJhID1e5v51bot7+p0yaXrWFISGrP7WeRxs+5gM+FEEp8jVSQz3+UiGI0RTRgEzmB1PSmjZFqS36zfljVDurihhn++axX5HtdJp2xSnnNF2RzvUxy6hsdhp2c4DEA4nmQ4Gqc0cHYrwb5bhGIJ/vOVrRmDJIDbls3lyx+6NF3y/uQKBu/2k1SdH0BTFHZ1drO4OpWm01BcSNfwCK8dOsKqGdMwLIvt7Z3Y0jl7Z8KkjNJgOJqVBOu06Xzm2mWnNEiQyvZPnoXdtxwfPJw2ndI8L4d7BoDUbtyhrr4LVvO7uWeAw90DmZ9LA17uvXLxKQ2SlKkd7nd79606L0BDcQGbjrbx14vno6sqs8tKqM4L8M1n1vLkrn1EkwZbWtpZUV87roLuZJmUSesfCTMyZhek2O+h/jRuDCklR/uGzkpIwLuDyPJY5GZ57y2qIpgzRufbkpL1+45csMqgbQPBrOXntLJCCn2nV2n3UFf/u+7oduoaX191BV+75vKMa8bnsPPVay6jwO3i1aYjbGlpZ2ZpMV9cufyM48cmNVNKmlbWjeDQtdNqgGlJ1u0+dMHcRIoiUMb0K24Yp1SKzHHuEEKwvKGGX72yJaNwsH7fEZq6+mkoK7zgZktJw8wKPnTZ9dPaRg/Hk2w4cHLhuXOBEIK55aXjfrestorf3HMbRweG0DWVKfl5eOy2Mx6PSZk0j8OW5XAcCkcJT6BpMxYpJZsPtbFuz+F31sL3AJumEhiTyBuMxOgYHH5PYkRypJhRWczc6mMPxlA4yr89/RpDkdg5z/062/hdjiwj1BMMkTiF496yJE9v3cv+9vOnRpsQgkKPm0XVFcwtL8WbdnifKZMySoVed5YcRd9ImJf3TDwDkumywFub2/nWo2snFOQ6X7Fr2VnlkXiSRzbuJGEYF9wD8H7BoWt8/IqLsqL5Nxw4wtd/v4YDnX2YljXh2Mh0sYRQLMH2o53nReHFmqK8LDmd/R197DjadcL2J02TNW/v5/+uef0dl86+kJjU8s3jsHHFzLqMk860JD9+dgPxpMnKWXXkeVwopITcWvuDrNl+gCc27yEYiZHvSe0RDoTO/6AAIeCq2VN5bvuBjHLiY2/tIp40uHnxLEoDXlRFkDQtYokkg+EowUiMixtqMlpCE5E0TfpHIsSTqbSBSCJJOJYgHE8wGI4yHDnmr4slkzy7bR9FPg9uuw23w4bLpmPXVGy6RsDleMeFIs8WUkqGIjHCsQQJwyCWNNKpRknC8QTbj3ZkfX7H0U6e8Thx2W2pPtltOHQNm67itOnke1wnXMYIIbi4oYaPrVjAL17ehGmloptf23eEXS1dLGuoZnF9FVUFflx2G4ZpEYxEaR8YZl9HL3vaumntD/KF65Yz/SRSH/GkwUAoQsIwiRsGkXgykz7VMxzOirMbicV5eute8twuXHYdtz01RjZdw66p5LmdEwoDVuT7WTClnFf2NAMQjie47+EX+Pyq5VxUX4EnLbofiiU41N3P45t28+LOJmJJg/I8H0Ph6Gkn4pqWxUAopfmdSCtnjk0H6xwczvrsy7sP0zYwnBkfl11PjZGm4nHY8TnPzmzoZEw6ePKOi+fxyp7DHEobpqFwjP/viVd44MU3CbgdKEIhEk8wEI5m1v/5bif33XYN6/c28/DGnWe3B+cAIQSXNNawvKGGV/embpykafH45j08s20/bruOoggMM6UcaZgWHoeN333hzpMapaaufj7/i8eJxpMkTDPzdpdyvHRrKJbge4+/kpaIOSZzoaspueFPX7OUv7p0wTm+EidHAt9+9CU2HmxJxw6l+0M6LeK4F/9z2w/w/I4DCEYlO1IFF2yqSnVRgAc/+ZGTCulpqsInrlpCPGnwh9e3ZzZOhiIx1rx9gOfePoCSVkQkrZ99/Cz+VPPcbc0dKXVOwyBpmJjpmdZEY9Q/EuH+P7+UNUZqWvvIpml87eYruG5+47hz6KrC365cwo6jXZnwmpa+Ib72+zXke5ype0hCKBZnMBzNRHpPKcrj/jtX8YOn17PlcPu4752I/pEIn3rw0UzuqWlZmbSv49NWDMviwbVvZcZGIFAUgaYq2FSV6+Y38rWbV05W2GPSTMooCSEoy/PyrTtWcd/DL3Cwsw9JavAHw9Gs+CVIxV/UleTz1ZuuYOm0amIJgz+/ueuCcHg7bTpfv2UlScPkzabWTJuTpslQZPz6/3SWdYZpMTASOe0puBz9Xjn6U0pFMRxPOT3fc2TK3zaZggCp7sgx19MiSpLBUPS07guHrvHF6y9lekUxD619iyO9g8f0q+GkGxKaqpwymTtuGFlVhE/ZH7LHyIC0ZG3ihIUUhBDMqy3j/3zkKr77+Dq6gyFIt713OExvOh5rFEUIFtZV8PWbVzK1tICFUypO2yiZlmQgFM3KHTwV1th7zkrdcxGSDEdj6R6fZzMlIQSzq0r42b238Nim3azd2UTH4DDRRBJLSrR0eaPKAj8rZ9Vzw6IZFKe3OxdMKeemxTNJGCZTSwtOy+Lme1xcv3B65mabX1s+6U6+E4QQlOf5+Nd7bmDN9v08u20/zT0D6bp26RI+moLTZqPQ52JWZQlex8njMwIuR1Zf3nHbgKkTKClKKbFIvdlVMV5Yy223cd38xkwppLri/DN76wlYOq2KAq/rDL4kRYHHlbWJcsJTpotT3LBwOssbali/r5l1uw9zoLOXoUiMeNLAsmTmcy67Tonfw+yqUlbMmMKiuoqTfn+J38MNC6efcQiIACoL/Cf8uyIEV8+ZSn1JAQ9v3MGG/UfpHQ5lVhe6quJx2KgrKWDVvAaunTct40heOauezsERJJJZlScv6eW0aVwzdxqh2OkbpRMxv6Z80vpn7wRxijf8yf8oJbGkQV86fsm0JDZNxe9ykOd2nrVCfe81o8UJB8NRhsIpFQRFCBw2DZ/Tjtdhx6Zr70q5m5ORsAz+ZddTNId6+eqsDzHD/+4Y8PeS0Qz6cCzllwvHE+l6aQoOm4bf6cDjtJ9WUc33itH2j1aDgZSEb57Lid/lOGW9tQuUE3bojPSUhEgVn6sqCJzJ15z3jL51S/weSs6iGP7ZRkrJoZEe9gQ7CBln/ma8EBj14/hcDnwXqB67IgRep/2k/sgPEh886b4cOXKc1+SMUo4cOc4rzolGd6belmUQMRIY0kQTKm7Njq6MX9uP3Wod/UvUTBAxEqhCwas7JnTcjm5rjmaqSSQjyTgJy8Charg1xwnL14w9VgiRqk1vJokYcYQQuDU7diV1eSY6b1KahJIxTClxqjouzX7SUjlSSkwpiZhx4qaBEOBUbThV2ylL7GT8JmOOdSg6Ts2GwomrYUgpiVtJQkYcgcCl2nCop076TFgGISOllePUbLjU7Lp6E7YPScRItQ8BdkXHdYr25cgxEWfdKFlScnC4izWdO9nc30x3bJi4mcSu6lQ481hdMZcPVy7AoR7bmk1YBv+y+2mklHxpxrU83b6dJ9u20R0bxqZozPSX8/H6FcwNVGXd4M2hXr635xmuKp3J8qJp/OLQq2zsO0QoGcdvc7KiuIH/XreCQrtn3IOxeeAIDx5cxz11l7Awv4ZHWjbzdPvb9MSGUVAocfr41LSVXFacHWcSM5M837GTx9u20RLuJ2mZ5NlcLCuayt21F1Physs6l5SSgUSYtV17eLV7P0fCvYSScRQhyLe7WVJQx91TllPuDEz48CYsg9d7D/J46zYOjnQxkj7Wrzup9RRy95TlXJRfm3WsEGBYJo+0bOIvrVvpjA4BUOLwcV35XG6rWYxLG++/CBtxnmp7m6fbt9MeHcSUFgU2DyuKG7irdhnFjvHljCxpsX2wlT8ceZO9wQ6Gk1GEEPh0B7XuQq4qncnqinnoyoWvFJnj3eGsGyUpJb8+vIHnO3dS7PBR5ynCoznojgXZFWxjx1Arg4kwn5h6RWa3ypKSvUPtdMWCJC2DDb0HmeYtpSq/gJZwP6/27Gf3UDvfXXg7C/JqMg9G2IizdeAoUTPBE23b6I2N0OBL1VbfG+zgd81v0DTSzXcX3E7All3dczAeZnN/Mwvza3ilex/PdOyg3BlgqreEoUSE9sggNiX78sTMJD/Yu4ZHW7bg1e3M8JfjVG20hPt5+OhbvNl3iH+efxuNvuz67m8PtPD9Pc/iVG3UuAto9JURNRPsCXbwuyMb2RPs4EcX3Y3flr21HjeT/HT/Wv549E1MaVHmDDDNV4JpmXRFg7zVd5g7apaOGwMB/PHom7zZd5hadyEL8msYSkTYE2znR/ufZzAR5n9MvwZVKJkxCxtx/mX3UzzXsZMih5dZ/gpUoXBopIf/PLyBzQNH+O6C27OMp5SSjX2H+Pq2R4hZSab7ymj0lRK3DNoiA7zZfxghBKsr5p3ZTZXjA8VZN0qKENxTt5xry2czN1CFT09FecetJH86+hY/3vcCT7Ru47bqxeTbs3eygskob/U3850Ft7OooBZNqISMGD878BJ/OLKRn+5fy08W/zUuLTvqd8dgK0sL6/nOxbdT6vCDgNZwP197+xHe6mvm0ZYtfLx+xfhlGPB421Y8moPvL7yTeXnV6IpK0jLpjA6NewCfbn+bR1s2U+cp5p/m3cpUbzGKUAgbcX7b/AYPNa3je7uf5keL78arp9JqhBAsKazjG3NuYm5eFSUOH7qiYUmLvcEO/m7rH9g51Mqm/mauLpt1rG1S8nT7dn53ZCNe3c6Xpq/iipLpuDR7KpfLiNMS7mO6f3zts4RlsrHvEF+afm1mVmpYFs937uJbOx/nibZt3FazhApXXuaYh1veYk3HDi4vns7fz7qeYocPgKFEhO/veZY1HTv4+cGX+cacm9BEatZjIXn46CaGk1G+OutD3Fy1EF3R0kvhBM3hPuyKhiZyrsscp89Zv1uEEDT6yri8uJF8uxtNUVGEwKnauLFiAaVOP/3xEP3x8ITHry6fy9LCemxKKu7Hqzn4eP0KSp1+dg21cWB4fOKirmj8bf1llDsDqIqCKhRq3IX8Tf0KFCF4rnMnEXPihOCBeJgvz1jFssJ6XJoNXVFxaTbqvcU4xxi/iJngkaObAPhMw5U0+kozffNodu6pu4S5eVVsH2rl9d6mrDZ6NDsfqphHtbsAu5qSqdAUlVmBSi4rbsSUksOh3qxjwkacPx19C0tafGraSm6sXIDf5kJXVGyqRr7dzfz8GhzqxGkZy4umcWv1Rbg0O4pQsKkaV5XNZKq3hGAySnPoWGLqYCLCoy1b8GhOPt94NaUOP6pIXcd8m5u/qV+BW3Owvmc/XbFjpY4sKRlORlGFQq2nMDNmqqLg0R3MCVRmZq45zm+iiSTNPQN0DY2850nn5+QVNlrSezRDe/SfW7Ph052YWCTl+FQNgWBhfk1WEKIQggKbh+m+cuKWwb7hjnHHBWwu6r0lx/lVBLMDlfh1J+2RQXpjIxO2tdpdwLy86lM+OO2RQY6E+ylyeJmXVzXuXE5VZ3nRNExp8UZf02ldDwGUOlNRv3EzO22kLTLA0XAfBXYPK0tnTjow89Kiaegi249jExrFDh+WlIwkj6WGHBrppjM6RKUrD5dmZzARYSAeZiAeZjARwaHq+HQHw8kYreFjiomaUJiXV40hTX649zle7t5LKBnL9C/HhcOu1i7+6se/5zt/eRnTem/H7pzsvllS0hUdYvtgK00j3fTHQ0TNBFEzSWu4P/2p8R3XFIW843w/kFoSjj68XdHguL/7dGeW43zs7726g47oEAOJELUUjvtMod2Lc4Jjj6cn7bAvsBfjnsBJLISg2pVK/WiPDGJIK2MURpdbu4fa2BPsoDMaJGzEiFkGzSM9E56vOzZMzDSY6vUT0Cenwq6mr9c4QytIVy6VWSJjbZGUU3v/cBd3vfbvHB9sK5EMJ6JIUr6nsdw95WKOhvt4tXs/X9n6R+o8xVxdNpNrymZT7S7I+K3ejyQNk63NHTSUFZDnOfNUm/cSy0plZ5wP6rBn3SglTIPfHnmD3zW/wVAyQkB3UezwZcIBToZATFzuV4AtfWzCGp/kqAoxYcy6gkATamoL/wT5Zqk2nXoWEjfTOUlCRTnBg2ZXtcxnLWkBqXNvGTjCD/c+x8GRLhyqjWKHF7/uwq7qJ8zjiZlJJBKHenqqhGMRKOjK6Q9t1EwggYDNySx/5Ym/V6SM+LGfBfk2N/fP/wiv9zbx55ZNbB9s5WcHXuL3R97kxsr5/E39Cvz6qTXcL0Ra+4N85TdP892PXc+yadXvdXPeN5xVoySl5PnOXfz7/rUEbC7+ce4tLC2sx63Z0YRCwjL5+BsPcTg08ezAkhbxCYwOEiJGyic00VZ23DSwJni8DWkRt5KpPCj1zLrq0VPJkDEziSFNdMYb2NFZhEuzZWYIXbEg9+14jK5okDtrl3F7zRIK7V70tD/qoaZX+NmBl8Z9l1NNxfhEjESqVPIZtf7kuNMxVlO9JfzrojsnNbsRaX/hlSUzWFHcwOGRXp7t2MFT7W/zX4c30BcLcd/cm7Gd4fU/35BSsrOlk2D0wlO+PN85q3eKJSVru/aQlCa31yxhdfncrDdk2EgQPYHDGVJGpCM6lPK3jDnOkBZtkZQvo3LMjtEowWSE4WR03LJqIBFiOBnDqepZb/h3QpkzgEez0xMfJpiI4nRmO5illDSll2K17sLMg71t4CjtkUFm+iv4bMOVWUZVSkkwMbHoXZnTj0PV6YwO0R8PZe2UnW2q3QXoikZbZICRZIw8+/gl9KkQQmATGo2+Uhp8pVxZOoMvb/4dr/bsoy0yQJ335NnsZ0I8nRTuczrwOGz0jYQ50NHHcDSOz2VnWmlKmP9EM07TsmgfGOZwdz+RRJICj4uGskICbue4mDNJatkWjMQyxQv6RsK09R9zKyiKoMTvQRGCvpEwhmlR7PegpnXfk4ZJz3AoVWnW58mUJDJMi55gCIdNIy99biklpiVpHwzS3D1ANGFQ4E21z+9yTDgDTZomvcEwbocNn9NO0jQ51DVAa/8QAOV5PqaU5OM6RfWUUUb7mEiauB02Ased17IseobDHO4eIBiJoaqCQq+bqoIA+R5nWp/p9GfKZ9coITNGp8SZLdsgpWRXsI3uCXxCY9nQc5DV5XOz/DGt4X72DXfi0ezM8leM62AwGWVr/xGur5iXHUPTe4iRZIwF+dUU2s8skbbU6WdOoJLXe5tY37Ofj1YvzjrXYCLC+p792BSVS4sbMsdFjNTSKM+WWq6NvR7BZJTN/c0Tnq/Slc80Xwk7Blt5sm0bn5h2xbjo6NE39JkujaZ6S6jzFHFwpJuXuvdwS9VF4x7gsbOBsf0+/ncivZRu9JVS4vTTNNJN1Dy32k8HOvv47EOPccfyedQU5fHT596ga2gEy7JQFIViv5tPX72MmxbPzBiG0fYHIzH+/xc28sy2/QTTet+qqlCZ7+eTVy9l9YLGrOIYf3x9O09s3kPXUIjBcAQp4R8fWZtVTt7vcvCbz99JodfND55+jc2H2vjFpz9KVWEAKSXbj3bypV8/iaYo/PyTt9KYVsJs6urjUw8+yq1LZvOF1ZekAm9DEX76/EZe2H6A4Wgqyl5TFaoLA3zq6mVcO29aVp8A2geG+dufPcx18xu557KFfP+pV3l1T3NGNdOua3zt5pXcsmQWp0JKyfq9zdz/6Es4dI1vfvTqLPmXcDzBQy9t4vFNuxkMRVOyPAI0RSXf4+SO5fO498rFkxrPs2qUNKEwxVPExr5DvNS1h+VF0/DrTpKWwY7BVn6wZ01KQOokz9D6nv38tvl1bqiYj0uz0xML8sN9zzGYiLCqbA61nvHOaiT8/OA6AnY3cwKVKAi2D7Xyy0PrUYXCzVWLxgVCThZdqNxTdynbh1p54OA6/LqLpYV16IpGT2yYBw6+zKGRHi4vmc6igmMR1qmtcpV9w13sGmpLyYlI6IwN8cDBdRzNOP6zcag6fz3lEv738J/59eENmNJidflcAjY3FhbBRJR9wQ5qPIXMDpzYD3Q6eDQ7/71+BffteIyf7HuRmGlwWXEjHs2OIU0GExF2DbWRtExuq1mSGb6QEePXhzcwP6+aqd4SvLoDBUHIiLO2aw/NoV5KHf7MJsW5wrQsIokkT2zZQzxhsLCugs9csxS7rvHGgRae2rqX7z/1KlNLC5hTfSxEIZowuP/Rl1i7s4nFUyu5dm4DfpeDfR29PPrmTr7157VoiuC6+Y2ZY0r9Xi6fWYeU8NTWvbT0DbFqXgNVY7STHHpKGleIlFrkmm37aRsIUlUYAGBnaxeRdP22/R29GaPU3DPIUDhGXUl+6vrGEtz38Iu8ureZRXUVXL9gOgGXgwNdfTz21i7ue/gFkqbJjYtmZM9cpCSSSHKgs4/7H32J1v4gd106n/I8HwOhCLtau5lRWXzKl5mVNkjf/NMLaKrC12+5kkV1FVkvpT+9voNfvryJ6eXF3HvlEkr8HkLxBPs7etl6uP0dqWqcVaMkhODWqot4tXs/r3Tv5+DIAxTbfYwYUTqjQS4vns7sQCXPdGyf8HiXamN1xVwebHqF3x/ZiFuzM5AIE0xEmO4r47ONV2UC98bS4Cul0O7h77b8gUK7B1Uo6ehwk5urFnJt2ewznk0IIVhUUMv/nLGaH+17jn/Y/gglDh82RaM/HiZkRLmoYAp/P3M1DuXYjGh2oJKVJTN5oXMXX9j0G2rcBVhS0h4dIs/m4gvTr+ZH+56f8HxXlEznfzRezQMH1/FQ+pp4dSemtAglY8Qtg2/MuemMjZIQgqtLZzIQD/Hzgy/zr3ue5YGDL+PS7BiWyYgRI2Ea3Fi5gLHKg0nL4sm2bfzq0Hp8uhOf7kQVCiNGjP54CJ/u5LMNV5E/wY7quaBzcIQ7ls/j7268LKOfdNXsqVhS8pdNu3lp9yHmpCuiSClZu6uJtTubuGzGFL5916q0IUmJr82sKOYrv32GB9duYnljbWaptHJ2PStn12NaFjtaOmntH+KGhdO5uKFmwjY1lhchgcPdAyybVp32RXXRWF6cMRA3LpoBwIHOXmyaSn1Jahf3mW37WL+vmWXTqvnux1bjd6bacNWcqSydWs2XfvUE//78G1xUX0l5nm/cuTcfamPx1Ep+/olbKPZ7MstBw7JO6Dcca3Be25cySHZd4/47r+Wiuspst4plseHAEXRV5X/dfAXzasqyjo8mkmjq5HWszrr3caq3mB8tvptHWjazN9hB3EpS6crnY1OWc23ZHA6NdOO3Ocm3jbegFpKbKxeysmQGT7a9TWuknzpPEYvyp/CR6osomSD3CkAVCt+cewsvdO5ifc8BhhIRlhTUcVXpTK4tn51JrB1LtbuAu6dcTJ2n6LTFPVWh8OHKBTT6SnmybRu7hw4TtwwW5Fexong615TNwqtlr7ftisY/zLmROYFKNvSm2ubRHdxavYhbqhbh050MJaLMmcCwaIrKXbXLWJQ/hec7d7I72EEwEUFXVGb7K5gdKOXioqlZ7VtVPpt5edWUOMbfpALBiuJGSpx+at3ZM05NUbmzdimL8mtZ07mT3UPtDCej2FWdcmeAeXnVXFbckFWm06c7+N9zbuK1ngMcCfcxnEz5x+odxdxYMZ9V5XOYelz82LnE67Bz5/J5WYJumqpwSWMNT2zeQ0vfMX+lYVo8vXUvQsAdy+dlDBKkHsyl06qoLgxwpHeAA529LK6vekdtqi3Kw23XaerqAyAUT3Cws48VM6ZwpGeQfe09JAwTVVFo6uqnwOOiLOAlYZg8+/Z+QHDXpfMzBmm0ffNry1gxYwpPbdnL+r3N3LF8fCqPogjuvXJJxiCNHqurJ94Ft+upZ2X93ma+8fALuOw6377rOubXjM8cUITAqeskTYumrn5mVZWgKUomLu+dFrY460ZJCEG9p5ivzLweU1pIJCpKxtk1J6+KOXkTD7CUEoTgkqJpXFw0FVNaCATaBAoBYzGlhUezc1d6d8tCoqCkQgVOcNx0fxnT/WWT7p8iBDP85Uz16HQNvUY0uZuKvO/gss2Y8Fyp5FQnd0+5mDtrl6bbJrJUDz7XeNVJzqcw3Z/KKTOlhUUq6NKyBugf/h4FtmPrdU1RuXvK8pO2/aaqhSc9V6O/jIasc4l0yMX4a6kpKiuKG7g0HTQ6ugN6fP/eLYr9HsoC3nGBrR5HaikVSxiZPdrhaJzD3QNoqkpr/xCRXdl+L0taSJmaDbQPDLO4/p21qdDnptjn4XDPIEnTonNwhN7hMDMrinHoGo+9tZvBcBSPw8bRvkGqCwN4nXYGwzGO9g7iddhoKB1fcFNVFObVlPHklr3sONrJ7RfPHfeZfI8rLTt9+uPgtOlsPtzGNx9+Abfdxnf+ajWzqyZ+sShCcMOiGbzZ1Mr3nniFjQdbuGnxTObXlKev+Tsb/3OyTzvq7FQmWGqd7vFq+sae7HETLe/OBZpSSEXe/6Gt/9MoJE45AGfatuOPlyKPAu8nUcTZD9qbbFvfzet+MjwOW2YnK5vRsRmTxhNPlbaKJpJ8+9HxIRmjnxZCnFFAoVPXqCvJZ0dLF6FYnH0dqXSi+tICHDaN/3xlC0f7hijxe+gbiXD5zDpURSEUixNLGngcdlyOiQNCRrXRB0JRTEuiqdn3oMumY9MmNy4dA8P84yMv0jcS4ZLyYqYU55/w3h5dHitC8NBLb/HizibW7mpiSnE+NyyczocvmkmBZ/Ixau+v4JF3kdSF1jk+U0dKi0j8DUaiL6IIO373rdi0aUiSDEeeJJZ4G9DwuT6E07YIkAyF/4BdbyAUW4dlDZPvvRdFuAlGHkVV8okmtmLT6shz34miuIkmdhIMP4wQOkW+v0cIFSlNBkK/xKbVEo5tQBEOAp670dUKpIwSjDxGPNmEaQ2iKn7yvX+LTXt/BfypSqo00GTwOe188fpL8Z1EinZmZck7bpMQgukVxazfd4Te4TC7Wroo9LkpC3hx6Bp2XWNvWzdJwySWSDKjojhznECMqZQyntFskBP1+Z1MVLYdaWdWVSkBl4ONB4/y4No3+fyq5egnMG6aqnD1nKksm1bNxoMtPL11H28dauXfnnmNZ7ft51t3XEtjedF7FxLwQSfl3NtK/8hDFPo+g2H20DX4DSoK/h1FcSOEDb/rVpJmOz1D/0xV0S9RhIdwfAPh+AYC7jvSNdHcWDLMwMiD5HvvJeC+jb7hn6Aqfvyuj2DXp+F330rX4DeQJAEHYDESfRabNoU898cIxdbSN/xvlOV9j5HoGqKJtyn0fpb+0H+gKn50dfJL1/cTHocNj8PGcDTO4vpKphTnn7NzNZYXYZgWR3oHOdDZx9TSArxOO7qmUuL3sqe9B1VR0NNObiEEPqcdl10nmkgyHI0TcGenGkkp6UmXZir0ubNCEs6E2VWl/ORvbiIYifGlXz3Jb9dvoyLfz0eXzkE5wTmESGmMXz1nKitn1dHU1c/PXtjIy7sO8ZM1r/Nv/+3GExq1iThvEpM0RU2pUk7iGCEEuqKmpDHOkyyGkegLKIqTeLIJwxrEsHpIGIcQ6Dht8zCsHkwriCUjWFbqpkJa+JzX47avwO1Ygaamdl9UtZCA6zYc+jzcjstIGKmYJkU40NQyGBdVrhFw347TPh+v60MkzQ4kBobVi02rQdeqsWvTABDiXMaIn//4nHYayooIx5NsPtQ26ajslHsiddOdLIFVCEFtUR5Om8aetm46BoeZU1WachLbdKaVFdLcM8CBzj4KPC5KA95M+6aXFxGKJdjd2j2ufaZlseVwG0Kkyo6dLf/daHWemsIA3/joVXiddn787AZeP3DklNdICIGmqjSWF/GVD19OwO1kf0cvkcSJA6Yn4rwwSnZV49vzP8ovLr6X+klE/tZ7ivnlxfdy//yPYlfOj4fMkhEU4UAIDUXYKfB+Bl2rJprYQufAVzHMQVQlH7J8MAJVGa88qQgXQtjTU3kVOHm9OCFUFOFLf6OSqvyIxOO4hlDsZbqGvkE0sRmf68az2+kLEFVRuHXpbGyqwq9e2cLutu4xFYtT8sMj0ThHegYmLJIphKDA60JK2NPejWVlK0CMfYALvCljs+1IByPROLPSjmMBzK4qoWsoxN72nvROnS3TvpuXzEJTFf5r/Va6gqFjbbMk6/cd4Y0DLVQXBLi0sfasXx8hBAtqy/n7D19O0jD59qMvc7CrL6tfScOkuWeAeNIY1++e4TBxw8DrtKOdZLdvIs6L5ZuS1uOZLE7NRoOv9By06NRIaSExSeXQm0hpAgou+yJC0bV4HFehCCemNYSmFDCSeAabXo/ffTOxxB6kdXwV1hO96cb/XkoLZOrcSDP180kx0dRSCjyfQFUCKMqZpdy8HxBCcGljLXevWMB/vbqVzz70F5ZMraKqwI9hpXbJDnb2UVXo54f/7UaUCR6sK2bW8czWffx63RYGRqJUF/qJJgySpsk9ly3MbIk70s7uF3c24Xc5spaKMyqKicYTNHX1s2L6lMwyTAjBZTOmcNuyOfzx9R189sHHuHLOVPLcDpq6+nlxZxOqIvji9ZdS5Ds3cWBCCFbNa6BzcIT/+9zr/NMja/nBPTdQlC4uG4on+MIvn8DvcjCrqoTyPB+KELT2B1m3+xBJw+Smi2biOkVV4uM5L4zShUg4/hrDkadImh30j/wcu95AofczeB3XkTTa6Bj4MiDRtRpK/F/H7biccPBVOgb+Dl0txWGbm5ktqYofIbJjOgQqqpLHqFESwokiPIDFYPi3ROObsawgXcF/wmVbgt99K6qShxCjQ6qhqqnjTWuYePIAnUP/AIBTn0Oh74soyuQkUc5XdE2lyOdO+13GG3GbplLk8xBwZfdXUxU+e+3F1BTm8fvX32b93mbihpFKMtZ1yvO9XNJYO6FyhRCCS6dP4XOrlvO7DW/zpzd2YEkLXVWpLc7jrkvmZz6rCMH8mnK2Hm5nRmUJ+Z5jqqQ1RQFqi/MZCkczgZ3H2q3xhdWXUhrw8vAbO/nVus2YloVD12koL+STVy1heUPNuBm2pigUet3kT2LnS9dUin1u/Mf5rhShcPeKBXQHR3hp1yF+uW4zX/7QCmyail3TmFNdysaDLezv6CVppnYp7ZpGeb6Pj6+8iFuWzJ5wTE7GGVXI/SBjyRhSjtUWEijiWNSslFEkJopwMmr7JXGkTKAIF1ImEcIOCKSMIoRtjEFJzYZSS8HUW8mSCcBCYEfKSLpq/eiZNYRwIWUEIRyZ3TgpY4CgfeDzFPq+jE2rQcoY7f1foDTvfuz6VN4PGKZFJJFAVZQJk0wN0ySSSKIpCs4J/i7TaRmdg8MEI3FURZDndlLkc+NMv+UnerhTG2OSgZEInUMjJAwTl12n2Och35OdzJtI765panYbpJSE0yknLps+bqkz+nwORWK0DwRJJE38bgcVeT7sujZhu0zLIhJPIgRZQaGncw0nukZSSgzTIppIIoTA7bChiGPJwkPhKL0j4cw5fU47pQHvqc594j/kjNL7G0vGaO//HG77Jdi0OuJGE+HYa1Tk/zA9k8qR4z0hZ5Q+qKTecp2EYq9gyWE0pQiX4xI05dQJmTlynENyRilHjhznFSc0SudFSECOHDlyjHKq3bfc/D5HjhzvKrmZUo4cOc4rckYpR44c5xU5o5QjR47zipxRypEjx3lFzijlyJHjvCJnlHLkyHFe8f8ATVoihE1fyX0AAAAASUVORK5CYII=\n",
 428 |       "text/plain": [
 429 |        "<Figure size 360x360 with 1 Axes>"
 430 |       ]
 431 |      },
 432 |      "metadata": {
 433 |       "needs_background": "light"
 434 |      },
 435 |      "output_type": "display_data"
 436 |     }
 437 |    ],
 438 |    "source": [
 439 |     "# Intersection TfIdf\n",
 440 |     "ab=b[(b['include_aparna']==1) & (b['include_kyle']==1)]\n",
 441 |     "a_abstracts=list(ab['Abstract'])\n",
 442 |     "text=utils.getTFIDF(a_abstracts,top_n=100,maxdf=1.0)\n",
 443 |     "utils.drawCloud(text,max_words=100,figsize=(5,5),raw=False, title=\"Intersection TF-IDF\\n----------\\n\",save=True,path='../images/R12_cloud.svg')"
 444 |    ]
 445 |   },
 446 |   {
 447 |    "cell_type": "code",
 448 |    "execution_count": 4,
 449 |    "metadata": {},
 450 |    "outputs": [],
 451 |    "source": [
 452 |     "a75=pd.read_csv(\"scopus (75).csv\")"
 453 |    ]
 454 |   },
 455 |   {
 456 |    "cell_type": "code",
 457 |    "execution_count": 6,
 458 |    "metadata": {},
 459 |    "outputs": [
 460 |     {
 461 |      "data": {
 462 |       "text/plain": [
 463 |        "339"
 464 |       ]
 465 |      },
 466 |      "execution_count": 6,
 467 |      "metadata": {},
 468 |      "output_type": "execute_result"
 469 |     }
 470 |    ],
 471 |    "source": [
 472 |     "len(a75)"
 473 |    ]
 474 |   },
 475 |   {
 476 |    "cell_type": "code",
 477 |    "execution_count": 7,
 478 |    "metadata": {},
 479 |    "outputs": [
 480 |     {
 481 |      "data": {
 482 |       "text/plain": [
 483 |        "Index(['Key', 'Title', 'Abstract', 'include_aparna', 'include_kyle',\n",
 484 |        "       'inclusion', 'disagreement', 'symbolic', 'NN', 'comments', 'input data',\n",
 485 |        "       'IMPORTANT but doesn't meet criteria', 'kyle wants to read anyway ;)',\n",
 486 |        "       'save for later'],\n",
 487 |        "      dtype='object')"
 488 |       ]
 489 |      },
 490 |      "execution_count": 7,
 491 |      "metadata": {},
 492 |      "output_type": "execute_result"
 493 |     }
 494 |    ],
 495 |    "source": [
 496 |     "a75.columns"
 497 |    ]
 498 |   },
 499 |   {
 500 |    "cell_type": "code",
 501 |    "execution_count": 9,
 502 |    "metadata": {},
 503 |    "outputs": [],
 504 |    "source": [
 505 |     "a75=a75[['Key', 'Title', 'include_aparna', 'include_kyle',\n",
 506 |     "       'inclusion', 'disagreement', 'symbolic', 'NN', 'comments', 'input data']]"
 507 |    ]
 508 |   },
 509 |   {
 510 |    "cell_type": "code",
 511 |    "execution_count": 12,
 512 |    "metadata": {},
 513 |    "outputs": [
 514 |     {
 515 |      "name": "stdout",
 516 |      "output_type": "stream",
 517 |      "text": [
 518 |       "Index(['Key', 'Item Type', 'Publication Year', 'Author', 'Title',\n",
 519 |       "       'Abstract Note', 'include', 'relavance', 'Unnamed: 8',\n",
 520 |       "       'Publication Title', 'DOI', 'Url', 'Date', 'Date Added',\n",
 521 |       "       'Date Modified', 'Include (0,1)', 'Notes/Criteria'],\n",
 522 |       "      dtype='object')\n"
 523 |      ]
 524 |     }
 525 |    ],
 526 |    "source": [
 527 |     "orig=pd.read_csv(\"scopus-filtered-by-top-publication - Aparna.csv\")\n",
 528 |     "print(orig.columns)\n",
 529 |     "orig=orig[['Key','DOI','Publication Title', 'Publication Year', 'Title']]"
 530 |    ]
 531 |   },
 532 |   {
 533 |    "cell_type": "code",
 534 |    "execution_count": 13,
 535 |    "metadata": {},
 536 |    "outputs": [
 537 |     {
 538 |      "data": {
 539 |       "text/html": [
 540 |        "<div>\n",
 541 |        "<style scoped>\n",
 542 |        "    .dataframe tbody tr th:only-of-type {\n",
 543 |        "        vertical-align: middle;\n",
 544 |        "    }\n",
 545 |        "\n",
 546 |        "    .dataframe tbody tr th {\n",
 547 |        "        vertical-align: top;\n",
 548 |        "    }\n",
 549 |        "\n",
 550 |        "    .dataframe thead th {\n",
 551 |        "        text-align: right;\n",
 552 |        "    }\n",
 553 |        "</style>\n",
 554 |        "<table border=\"1\" class=\"dataframe\">\n",
 555 |        "  <thead>\n",
 556 |        "    <tr style=\"text-align: right;\">\n",
 557 |        "      <th></th>\n",
 558 |        "      <th>Key</th>\n",
 559 |        "      <th>DOI</th>\n",
 560 |        "      <th>Publication Title</th>\n",
 561 |        "      <th>Publication Year</th>\n",
 562 |        "      <th>Title</th>\n",
 563 |        "    </tr>\n",
 564 |        "  </thead>\n",
 565 |        "  <tbody>\n",
 566 |        "    <tr>\n",
 567 |        "      <th>0</th>\n",
 568 |        "      <td>WLW49ADY</td>\n",
 569 |        "      <td>10.3233/SW-190368</td>\n",
 570 |        "      <td>Semantic Web</td>\n",
 571 |        "      <td>2020</td>\n",
 572 |        "      <td>Neural-symbolic integration and the Semantic Web</td>\n",
 573 |        "    </tr>\n",
 574 |        "    <tr>\n",
 575 |        "      <th>1</th>\n",
 576 |        "      <td>YXUZIQIU</td>\n",
 577 |        "      <td>10.1007/s10489-020-02165-6</td>\n",
 578 |        "      <td>Applied Intelligence</td>\n",
 579 |        "      <td>2021</td>\n",
 580 |        "      <td>Towards bridging the neuro-symbolic gap: deep deductive reasoners</td>\n",
 581 |        "    </tr>\n",
 582 |        "    <tr>\n",
 583 |        "      <th>2</th>\n",
 584 |        "      <td>EX5ZGV3N</td>\n",
 585 |        "      <td>10.1016/j.artint.2021.103504</td>\n",
 586 |        "      <td>Artificial Intelligence</td>\n",
 587 |        "      <td>2021</td>\n",
 588 |        "      <td>Neural probabilistic logic programming in DeepProbLog</td>\n",
 589 |        "    </tr>\n",
 590 |        "    <tr>\n",
 591 |        "      <th>3</th>\n",
 592 |        "      <td>YCQKU49S</td>\n",
 593 |        "      <td>10.1016/j.cogsys.2017.07.004</td>\n",
 594 |        "      <td>Cognitive Systems Research</td>\n",
 595 |        "      <td>2018</td>\n",
 596 |        "      <td>Learning Łukasiewicz logic</td>\n",
 597 |        "    </tr>\n",
 598 |        "    <tr>\n",
 599 |        "      <th>4</th>\n",
 600 |        "      <td>NPTPCDHQ</td>\n",
 601 |        "      <td>10.1109/TNNLS.2016.2603784</td>\n",
 602 |        "      <td>IEEE Transactions on Neural Networks and Learning Systems</td>\n",
 603 |        "      <td>2018</td>\n",
 604 |        "      <td>Deep Logic Networks: Inserting and Extracting Knowledge from Deep Belief Networks</td>\n",
 605 |        "    </tr>\n",
 606 |        "    <tr>\n",
 607 |        "      <th>...</th>\n",
 608 |        "      <td>...</td>\n",
 609 |        "      <td>...</td>\n",
 610 |        "      <td>...</td>\n",
 611 |        "      <td>...</td>\n",
 612 |        "      <td>...</td>\n",
 613 |        "    </tr>\n",
 614 |        "    <tr>\n",
 615 |        "      <th>1505</th>\n",
 616 |        "      <td>44UQWM7C</td>\n",
 617 |        "      <td>10.1109/TITS.2020.3046885</td>\n",
 618 |        "      <td>IEEE Transactions on Intelligent Transportation Systems</td>\n",
 619 |        "      <td>2021</td>\n",
 620 |        "      <td>Optimizing Locations and Qualities of Multiple Facilities With Competition via Intelligent Search</td>\n",
 621 |        "    </tr>\n",
 622 |        "    <tr>\n",
 623 |        "      <th>1506</th>\n",
 624 |        "      <td>28FVD3B5</td>\n",
 625 |        "      <td>10.1007/s00521-019-04509-x</td>\n",
 626 |        "      <td>Neural Computing and Applications</td>\n",
 627 |        "      <td>2020</td>\n",
 628 |        "      <td>Knowledge-based reinforcement learning controller with fuzzy-rule network: experimental validation</td>\n",
 629 |        "    </tr>\n",
 630 |        "    <tr>\n",
 631 |        "      <th>1507</th>\n",
 632 |        "      <td>C3XUFTES</td>\n",
 633 |        "      <td>10.1109/TCAD.2020.3025508</td>\n",
 634 |        "      <td>IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems</td>\n",
 635 |        "      <td>2020</td>\n",
 636 |        "      <td>A Data-Driven Asynchronous Neural Network Accelerator</td>\n",
 637 |        "    </tr>\n",
 638 |        "    <tr>\n",
 639 |        "      <th>1508</th>\n",
 640 |        "      <td>5HARP4V6</td>\n",
 641 |        "      <td>10.1016/j.artmed.2019.101722</td>\n",
 642 |        "      <td>Artificial Intelligence in Medicine</td>\n",
 643 |        "      <td>2019</td>\n",
 644 |        "      <td>Multi-criterion mammographic risk analysis supported with multi-label fuzzy-rough feature selection</td>\n",
 645 |        "    </tr>\n",
 646 |        "    <tr>\n",
 647 |        "      <th>1509</th>\n",
 648 |        "      <td>NKEYVKMC</td>\n",
 649 |        "      <td>10.1109/TIFS.2018.2868221</td>\n",
 650 |        "      <td>IEEE Transactions on Information Forensics and Security</td>\n",
 651 |        "      <td>2019</td>\n",
 652 |        "      <td>MEG: Memory and energy efficient garbled circuit evaluation on smartphones</td>\n",
 653 |        "    </tr>\n",
 654 |        "  </tbody>\n",
 655 |        "</table>\n",
 656 |        "<p>1510 rows × 5 columns</p>\n",
 657 |        "</div>"
 658 |       ],
 659 |       "text/plain": [
 660 |        "           Key                           DOI  \\\n",
 661 |        "0     WLW49ADY             10.3233/SW-190368   \n",
 662 |        "1     YXUZIQIU    10.1007/s10489-020-02165-6   \n",
 663 |        "2     EX5ZGV3N  10.1016/j.artint.2021.103504   \n",
 664 |        "3     YCQKU49S  10.1016/j.cogsys.2017.07.004   \n",
 665 |        "4     NPTPCDHQ    10.1109/TNNLS.2016.2603784   \n",
 666 |        "...        ...                           ...   \n",
 667 |        "1505  44UQWM7C     10.1109/TITS.2020.3046885   \n",
 668 |        "1506  28FVD3B5    10.1007/s00521-019-04509-x   \n",
 669 |        "1507  C3XUFTES     10.1109/TCAD.2020.3025508   \n",
 670 |        "1508  5HARP4V6  10.1016/j.artmed.2019.101722   \n",
 671 |        "1509  NKEYVKMC     10.1109/TIFS.2018.2868221   \n",
 672 |        "\n",
 673 |        "                                                                  Publication Title  \\\n",
 674 |        "0                                                                      Semantic Web   \n",
 675 |        "1                                                              Applied Intelligence   \n",
 676 |        "2                                                           Artificial Intelligence   \n",
 677 |        "3                                                        Cognitive Systems Research   \n",
 678 |        "4                         IEEE Transactions on Neural Networks and Learning Systems   \n",
 679 |        "...                                                                             ...   \n",
 680 |        "1505                        IEEE Transactions on Intelligent Transportation Systems   \n",
 681 |        "1506                                              Neural Computing and Applications   \n",
 682 |        "1507  IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems   \n",
 683 |        "1508                                            Artificial Intelligence in Medicine   \n",
 684 |        "1509                        IEEE Transactions on Information Forensics and Security   \n",
 685 |        "\n",
 686 |        "      Publication Year  \\\n",
 687 |        "0                 2020   \n",
 688 |        "1                 2021   \n",
 689 |        "2                 2021   \n",
 690 |        "3                 2018   \n",
 691 |        "4                 2018   \n",
 692 |        "...                ...   \n",
 693 |        "1505              2021   \n",
 694 |        "1506              2020   \n",
 695 |        "1507              2020   \n",
 696 |        "1508              2019   \n",
 697 |        "1509              2019   \n",
 698 |        "\n",
 699 |        "                                                                                                    Title  \n",
 700 |        "0                                                        Neural-symbolic integration and the Semantic Web  \n",
 701 |        "1                                       Towards bridging the neuro-symbolic gap: deep deductive reasoners  \n",
 702 |        "2                                                   Neural probabilistic logic programming in DeepProbLog  \n",
 703 |        "3                                                                              Learning Łukasiewicz logic  \n",
 704 |        "4                       Deep Logic Networks: Inserting and Extracting Knowledge from Deep Belief Networks  \n",
 705 |        "...                                                                                                   ...  \n",
 706 |        "1505    Optimizing Locations and Qualities of Multiple Facilities With Competition via Intelligent Search  \n",
 707 |        "1506   Knowledge-based reinforcement learning controller with fuzzy-rule network: experimental validation  \n",
 708 |        "1507                                                A Data-Driven Asynchronous Neural Network Accelerator  \n",
 709 |        "1508  Multi-criterion mammographic risk analysis supported with multi-label fuzzy-rough feature selection  \n",
 710 |        "1509                           MEG: Memory and energy efficient garbled circuit evaluation on smartphones  \n",
 711 |        "\n",
 712 |        "[1510 rows x 5 columns]"
 713 |       ]
 714 |      },
 715 |      "execution_count": 13,
 716 |      "metadata": {},
 717 |      "output_type": "execute_result"
 718 |     }
 719 |    ],
 720 |    "source": [
 721 |     "orig"
 722 |    ]
 723 |   },
 724 |   {
 725 |    "cell_type": "code",
 726 |    "execution_count": 21,
 727 |    "metadata": {},
 728 |    "outputs": [
 729 |     {
 730 |      "data": {
 731 |       "text/html": [
 732 |        "<div>\n",
 733 |        "<style scoped>\n",
 734 |        "    .dataframe tbody tr th:only-of-type {\n",
 735 |        "        vertical-align: middle;\n",
 736 |        "    }\n",
 737 |        "\n",
 738 |        "    .dataframe tbody tr th {\n",
 739 |        "        vertical-align: top;\n",
 740 |        "    }\n",
 741 |        "\n",
 742 |        "    .dataframe thead th {\n",
 743 |        "        text-align: right;\n",
 744 |        "    }\n",
 745 |        "</style>\n",
 746 |        "<table border=\"1\" class=\"dataframe\">\n",
 747 |        "  <thead>\n",
 748 |        "    <tr style=\"text-align: right;\">\n",
 749 |        "      <th></th>\n",
 750 |        "      <th>Key</th>\n",
 751 |        "      <th>Title</th>\n",
 752 |        "      <th>include_aparna</th>\n",
 753 |        "      <th>include_kyle</th>\n",
 754 |        "      <th>inclusion</th>\n",
 755 |        "      <th>disagreement</th>\n",
 756 |        "      <th>symbolic</th>\n",
 757 |        "      <th>NN</th>\n",
 758 |        "      <th>comments</th>\n",
 759 |        "      <th>input data</th>\n",
 760 |        "    </tr>\n",
 761 |        "  </thead>\n",
 762 |        "  <tbody>\n",
 763 |        "    <tr>\n",
 764 |        "      <th>0</th>\n",
 765 |        "      <td>WLW49ADY</td>\n",
 766 |        "      <td>Neural-symbolic integration and the Semantic Web</td>\n",
 767 |        "      <td>1.0</td>\n",
 768 |        "      <td>0</td>\n",
 769 |        "      <td>0.0</td>\n",
 770 |        "      <td>0.0</td>\n",
 771 |        "      <td>NaN</td>\n",
 772 |        "      <td>NaN</td>\n",
 773 |        "      <td>position paper</td>\n",
 774 |        "      <td>NaN</td>\n",
 775 |        "    </tr>\n",
 776 |        "    <tr>\n",
 777 |        "      <th>1</th>\n",
 778 |        "      <td>YXUZIQIU</td>\n",
 779 |        "      <td>Towards bridging the neuro-symbolic gap: deep deductive reasoners</td>\n",
 780 |        "      <td>1.0</td>\n",
 781 |        "      <td>0</td>\n",
 782 |        "      <td>0.0</td>\n",
 783 |        "      <td>0.0</td>\n",
 784 |        "      <td>NaN</td>\n",
 785 |        "      <td>NaN</td>\n",
 786 |        "      <td>position paper</td>\n",
 787 |        "      <td>NaN</td>\n",
 788 |        "    </tr>\n",
 789 |        "    <tr>\n",
 790 |        "      <th>2</th>\n",
 791 |        "      <td>EX5ZGV3N</td>\n",
 792 |        "      <td>Neural probabilistic logic programming in DeepProbLog</td>\n",
 793 |        "      <td>1.0</td>\n",
 794 |        "      <td>0</td>\n",
 795 |        "      <td>0.0</td>\n",
 796 |        "      <td>0.0</td>\n",
 797 |        "      <td>NaN</td>\n",
 798 |        "      <td>NaN</td>\n",
 799 |        "      <td>This paper is important because it is refenced a lot in the literature, but it does not meet our specific criteria for text as input.</td>\n",
 800 |        "      <td>MNIST</td>\n",
 801 |        "    </tr>\n",
 802 |        "    <tr>\n",
 803 |        "      <th>3</th>\n",
 804 |        "      <td>YCQKU49S</td>\n",
 805 |        "      <td>Learning Łukasiewicz logic</td>\n",
 806 |        "      <td>1.0</td>\n",
 807 |        "      <td>0</td>\n",
 808 |        "      <td>0.0</td>\n",
 809 |        "      <td>0.0</td>\n",
 810 |        "      <td>NaN</td>\n",
 811 |        "      <td>NaN</td>\n",
 812 |        "      <td>not text input</td>\n",
 813 |        "      <td>NaN</td>\n",
 814 |        "    </tr>\n",
 815 |        "    <tr>\n",
 816 |        "      <th>4</th>\n",
 817 |        "      <td>NPTPCDHQ</td>\n",
 818 |        "      <td>Deep Logic Networks: Inserting and Extracting Knowledge from Deep Belief Networks</td>\n",
 819 |        "      <td>1.0</td>\n",
 820 |        "      <td>0</td>\n",
 821 |        "      <td>0.0</td>\n",
 822 |        "      <td>0.0</td>\n",
 823 |        "      <td>rule based</td>\n",
 824 |        "      <td>deep belief network (DBN),\\nrestricted boltzman machine (RBM)</td>\n",
 825 |        "      <td>NaN</td>\n",
 826 |        "      <td>DNA,\\nMNIST</td>\n",
 827 |        "    </tr>\n",
 828 |        "    <tr>\n",
 829 |        "      <th>...</th>\n",
 830 |        "      <td>...</td>\n",
 831 |        "      <td>...</td>\n",
 832 |        "      <td>...</td>\n",
 833 |        "      <td>...</td>\n",
 834 |        "      <td>...</td>\n",
 835 |        "      <td>...</td>\n",
 836 |        "      <td>...</td>\n",
 837 |        "      <td>...</td>\n",
 838 |        "      <td>...</td>\n",
 839 |        "      <td>...</td>\n",
 840 |        "    </tr>\n",
 841 |        "    <tr>\n",
 842 |        "      <th>334</th>\n",
 843 |        "      <td>LVJ8NGHX</td>\n",
 844 |        "      <td>A computational analysis of general intelligence tests for evaluating cognitive development</td>\n",
 845 |        "      <td>0.0</td>\n",
 846 |        "      <td>0</td>\n",
 847 |        "      <td>0.0</td>\n",
 848 |        "      <td>0.0</td>\n",
 849 |        "      <td>rule</td>\n",
 850 |        "      <td>0</td>\n",
 851 |        "      <td>No ML/DL</td>\n",
 852 |        "      <td>NaN</td>\n",
 853 |        "    </tr>\n",
 854 |        "    <tr>\n",
 855 |        "      <th>335</th>\n",
 856 |        "      <td>MPD5LQBT</td>\n",
 857 |        "      <td>Cost-optimal constrained correlation clustering via weighted partial Maximum Satisfiability</td>\n",
 858 |        "      <td>0.0</td>\n",
 859 |        "      <td>0</td>\n",
 860 |        "      <td>0.0</td>\n",
 861 |        "      <td>0.0</td>\n",
 862 |        "      <td>0</td>\n",
 863 |        "      <td>clustering</td>\n",
 864 |        "      <td>Optimization technique</td>\n",
 865 |        "      <td>NaN</td>\n",
 866 |        "    </tr>\n",
 867 |        "    <tr>\n",
 868 |        "      <th>336</th>\n",
 869 |        "      <td>7YX447XS</td>\n",
 870 |        "      <td>Concept generalization and fusion for abstractive sentence generation</td>\n",
 871 |        "      <td>0.0</td>\n",
 872 |        "      <td>1</td>\n",
 873 |        "      <td>1.0</td>\n",
 874 |        "      <td>0.0</td>\n",
 875 |        "      <td>semantic resources</td>\n",
 876 |        "      <td>ML</td>\n",
 877 |        "      <td>Uses external data sources to semantically enrich text summarization. It is the application text fusion.</td>\n",
 878 |        "      <td>text</td>\n",
 879 |        "    </tr>\n",
 880 |        "    <tr>\n",
 881 |        "      <th>337</th>\n",
 882 |        "      <td>NaN</td>\n",
 883 |        "      <td>NaN</td>\n",
 884 |        "      <td>NaN</td>\n",
 885 |        "      <td>NaN</td>\n",
 886 |        "      <td>NaN</td>\n",
 887 |        "      <td>NaN</td>\n",
 888 |        "      <td>NaN</td>\n",
 889 |        "      <td>NaN</td>\n",
 890 |        "      <td>NaN</td>\n",
 891 |        "      <td>NaN</td>\n",
 892 |        "    </tr>\n",
 893 |        "    <tr>\n",
 894 |        "      <th>338</th>\n",
 895 |        "      <td>NaN</td>\n",
 896 |        "      <td>NaN</td>\n",
 897 |        "      <td>195.0</td>\n",
 898 |        "      <td>76</td>\n",
 899 |        "      <td>75.0</td>\n",
 900 |        "      <td>1.0</td>\n",
 901 |        "      <td>NaN</td>\n",
 902 |        "      <td>NaN</td>\n",
 903 |        "      <td>NaN</td>\n",
 904 |        "      <td>NaN</td>\n",
 905 |        "    </tr>\n",
 906 |        "  </tbody>\n",
 907 |        "</table>\n",
 908 |        "<p>339 rows × 10 columns</p>\n",
 909 |        "</div>"
 910 |       ],
 911 |       "text/plain": [
 912 |        "          Key  \\\n",
 913 |        "0    WLW49ADY   \n",
 914 |        "1    YXUZIQIU   \n",
 915 |        "2    EX5ZGV3N   \n",
 916 |        "3    YCQKU49S   \n",
 917 |        "4    NPTPCDHQ   \n",
 918 |        "..        ...   \n",
 919 |        "334  LVJ8NGHX   \n",
 920 |        "335  MPD5LQBT   \n",
 921 |        "336  7YX447XS   \n",
 922 |        "337       NaN   \n",
 923 |        "338       NaN   \n",
 924 |        "\n",
 925 |        "                                                                                           Title  \\\n",
 926 |        "0                                               Neural-symbolic integration and the Semantic Web   \n",
 927 |        "1                              Towards bridging the neuro-symbolic gap: deep deductive reasoners   \n",
 928 |        "2                                          Neural probabilistic logic programming in DeepProbLog   \n",
 929 |        "3                                                                     Learning Łukasiewicz logic   \n",
 930 |        "4              Deep Logic Networks: Inserting and Extracting Knowledge from Deep Belief Networks   \n",
 931 |        "..                                                                                           ...   \n",
 932 |        "334  A computational analysis of general intelligence tests for evaluating cognitive development   \n",
 933 |        "335  Cost-optimal constrained correlation clustering via weighted partial Maximum Satisfiability   \n",
 934 |        "336                        Concept generalization and fusion for abstractive sentence generation   \n",
 935 |        "337                                                                                          NaN   \n",
 936 |        "338                                                                                          NaN   \n",
 937 |        "\n",
 938 |        "     include_aparna include_kyle  inclusion  disagreement            symbolic  \\\n",
 939 |        "0               1.0            0        0.0           0.0                 NaN   \n",
 940 |        "1               1.0            0        0.0           0.0                 NaN   \n",
 941 |        "2               1.0            0        0.0           0.0                 NaN   \n",
 942 |        "3               1.0            0        0.0           0.0                 NaN   \n",
 943 |        "4               1.0            0        0.0           0.0          rule based   \n",
 944 |        "..              ...          ...        ...           ...                 ...   \n",
 945 |        "334             0.0            0        0.0           0.0                rule   \n",
 946 |        "335             0.0            0        0.0           0.0                   0   \n",
 947 |        "336             0.0            1        1.0           0.0  semantic resources   \n",
 948 |        "337             NaN          NaN        NaN           NaN                 NaN   \n",
 949 |        "338           195.0           76       75.0           1.0                 NaN   \n",
 950 |        "\n",
 951 |        "                                                                NN  \\\n",
 952 |        "0                                                              NaN   \n",
 953 |        "1                                                              NaN   \n",
 954 |        "2                                                              NaN   \n",
 955 |        "3                                                              NaN   \n",
 956 |        "4    deep belief network (DBN),\\nrestricted boltzman machine (RBM)   \n",
 957 |        "..                                                             ...   \n",
 958 |        "334                                                              0   \n",
 959 |        "335                                                     clustering   \n",
 960 |        "336                                                             ML   \n",
 961 |        "337                                                            NaN   \n",
 962 |        "338                                                            NaN   \n",
 963 |        "\n",
 964 |        "                                                                                                                                  comments  \\\n",
 965 |        "0                                                                                                                           position paper   \n",
 966 |        "1                                                                                                                           position paper   \n",
 967 |        "2    This paper is important because it is refenced a lot in the literature, but it does not meet our specific criteria for text as input.   \n",
 968 |        "3                                                                                                                           not text input   \n",
 969 |        "4                                                                                                                                      NaN   \n",
 970 |        "..                                                                                                                                     ...   \n",
 971 |        "334                                                                                                                               No ML/DL   \n",
 972 |        "335                                                                                                                 Optimization technique   \n",
 973 |        "336                               Uses external data sources to semantically enrich text summarization. It is the application text fusion.   \n",
 974 |        "337                                                                                                                                    NaN   \n",
 975 |        "338                                                                                                                                    NaN   \n",
 976 |        "\n",
 977 |        "      input data  \n",
 978 |        "0            NaN  \n",
 979 |        "1            NaN  \n",
 980 |        "2          MNIST  \n",
 981 |        "3            NaN  \n",
 982 |        "4    DNA,\\nMNIST  \n",
 983 |        "..           ...  \n",
 984 |        "334          NaN  \n",
 985 |        "335          NaN  \n",
 986 |        "336         text  \n",
 987 |        "337          NaN  \n",
 988 |        "338          NaN  \n",
 989 |        "\n",
 990 |        "[339 rows x 10 columns]"
 991 |       ]
 992 |      },
 993 |      "execution_count": 21,
 994 |      "metadata": {},
 995 |      "output_type": "execute_result"
 996 |     }
 997 |    ],
 998 |    "source": [
 999 |     "a75"
1000 |    ]
1001 |   },
1002 |   {
1003 |    "cell_type": "code",
1004 |    "execution_count": 28,
1005 |    "metadata": {},
1006 |    "outputs": [
1007 |     {
1008 |      "name": "stdout",
1009 |      "output_type": "stream",
1010 |      "text": [
1011 |       "<class 'numpy.float64'>\n",
1012 |       "<class 'str'>\n"
1013 |      ]
1014 |     }
1015 |    ],
1016 |    "source": [
1017 |     "print(type(a75['inclusion'][0]))\n",
1018 |     "print(type(a75['include_kyle'][0]))"
1019 |    ]
1020 |   },
1021 |   {
1022 |    "cell_type": "code",
1023 |    "execution_count": 29,
1024 |    "metadata": {},
1025 |    "outputs": [],
1026 |    "source": [
1027 |     "agree=a75[(a75['include_kyle']==\"1\") & (a75['inclusion']==1.0)]"
1028 |    ]
1029 |   },
1030 |   {
1031 |    "cell_type": "code",
1032 |    "execution_count": 30,
1033 |    "metadata": {},
1034 |    "outputs": [
1035 |     {
1036 |      "data": {
1037 |       "text/plain": [
1038 |        "Index(['Key', 'Title', 'include_aparna', 'include_kyle', 'inclusion',\n",
1039 |        "       'disagreement', 'symbolic', 'NN', 'comments', 'input data'],\n",
1040 |        "      dtype='object')"
1041 |       ]
1042 |      },
1043 |      "execution_count": 30,
1044 |      "metadata": {},
1045 |      "output_type": "execute_result"
1046 |     }
1047 |    ],
1048 |    "source": [
1049 |     "agree.columns"
1050 |    ]
1051 |   },
1052 |   {
1053 |    "cell_type": "code",
1054 |    "execution_count": 31,
1055 |    "metadata": {},
1056 |    "outputs": [],
1057 |    "source": [
1058 |     "agree=agree[['Key', 'Title', 'symbolic', 'NN', 'comments', 'input data']]"
1059 |    ]
1060 |   },
1061 |   {
1062 |    "cell_type": "code",
1063 |    "execution_count": 33,
1064 |    "metadata": {},
1065 |    "outputs": [],
1066 |    "source": [
1067 |     "joined=pd.merge(agree,orig,on='Key')"
1068 |    ]
1069 |   },
1070 |   {
1071 |    "cell_type": "code",
1072 |    "execution_count": 35,
1073 |    "metadata": {},
1074 |    "outputs": [
1075 |     {
1076 |      "data": {
1077 |       "text/plain": [
1078 |        "Index(['Key', 'Title_x', 'symbolic', 'NN', 'comments', 'input data', 'DOI',\n",
1079 |        "       'Publication Title', 'Publication Year', 'Title_y'],\n",
1080 |        "      dtype='object')"
1081 |       ]
1082 |      },
1083 |      "execution_count": 35,
1084 |      "metadata": {},
1085 |      "output_type": "execute_result"
1086 |     }
1087 |    ],
1088 |    "source": [
1089 |     "joined.columns"
1090 |    ]
1091 |   },
1092 |   {
1093 |    "cell_type": "code",
1094 |    "execution_count": 36,
1095 |    "metadata": {},
1096 |    "outputs": [],
1097 |    "source": [
1098 |     "joined=joined[['Key','DOI','Publication Title', 'Publication Year','Title_x', 'symbolic', 'NN', 'comments']]"
1099 |    ]
1100 |   },
1101 |   {
1102 |    "cell_type": "code",
1103 |    "execution_count": 37,
1104 |    "metadata": {},
1105 |    "outputs": [],
1106 |    "source": [
1107 |     "joined.to_csv('agreed75.csv',index=False)"
1108 |    ]
1109 |   },
1110 |   {
1111 |    "cell_type": "code",
1112 |    "execution_count": null,
1113 |    "metadata": {},
1114 |    "outputs": [],
1115 |    "source": []
1116 |   }
1117 |  ],
1118 |  "metadata": {
1119 |   "kernelspec": {
1120 |    "display_name": "Python 3",
1121 |    "language": "python",
1122 |    "name": "python3"
1123 |   },
1124 |   "language_info": {
1125 |    "codemirror_mode": {
1126 |     "name": "ipython",
1127 |     "version": 3
1128 |    },
1129 |    "file_extension": ".py",
1130 |    "mimetype": "text/x-python",
1131 |    "name": "python",
1132 |    "nbconvert_exporter": "python",
1133 |    "pygments_lexer": "ipython3",
1134 |    "version": "3.7.3"
1135 |   }
1136 |  },
1137 |  "nbformat": 4,
1138 |  "nbformat_minor": 4
1139 | }
1140 | 


--------------------------------------------------------------------------------