analysis-validation_dataset-discovery.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import pingouin as pg\n",
    "from scipy import stats\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib.lines import Line2D\n",
    "import seaborn as sns\n",
    "from IPython.display import display\n",
    "\n",
    "from dual_data_utils import make_clean_concat_data\n",
    "from stopsignalmetrics import StopData, SSRTmodel"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Read in and Compute Metrics on Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset='discovery'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "OUTLIER_THRESH  = 3\n",
    "SSD_THRESH = 200\n",
    "\n",
    "dual_dict = {\n",
    "    'stop_signal_with_cued_task_switching': {\n",
    "        'dual_col': 'cue_task_switch',\n",
    "        'DC': 'cue_stay_task_stay',\n",
    "        'DE': 'cue_switch_task_switch',\n",
    "        'OTHER': ['cue_switch_task_stay']\n",
    "    },\n",
    "    'stop_signal_with_directed_forgetting': {\n",
    "        'dual_col': 'directed_forgetting_condition',\n",
    "        'DC': 'con',\n",
    "        'DE': 'neg',\n",
    "        'OTHER': ['pos']\n",
    "    },\n",
    "    'stop_signal_with_flanker': {\n",
    "        'dual_col': 'flanker_condition',\n",
    "        'DC': 'congruent',\n",
    "        'DE': 'incongruent'\n",
    "    },\n",
    "    'stop_signal_with_go_no_go': {\n",
    "        'dual_col': 'go_nogo_condition',\n",
    "        'DC': 'go',\n",
    "        'DE': 'nogo'\n",
    "    },\n",
    "    'stop_signal_with_n_back': {\n",
    "        'dual_col': 'delay_condition',\n",
    "        'DC': 1.,\n",
    "        'DE': 2.,\n",
    "        'OTHER': [3.]\n",
    "    },\n",
    "    'stop_signal_with_predictable_task_switching': {\n",
    "        'dual_col': 'predictable_condition',\n",
    "        'DC': 'stay',\n",
    "        'DE': 'switch'\n",
    "    },\n",
    "    'stop_signal_with_shape_matching': {\n",
    "        'dual_col': 'shape_matching_condition',\n",
    "        'DC': 'CONTROL',\n",
    "        'DE': 'DISTRACTOR',\n",
    "        'OTHER': ['DSD', 'SSS']\n",
    "    },\n",
    "}\n",
    "\n",
    "stopmetrics_var_dict = {\n",
    "    'columns': {\n",
    "        'ID': 'worker_id',\n",
    "        'block': 'current_block',\n",
    "        'condition': 'SS_trial_type',\n",
    "        'SSD': 'SS_delay',\n",
    "        'goRT': 'rt',\n",
    "        'stopRT': 'rt',\n",
    "        'response': 'key_press',\n",
    "        'correct_response': 'choice_correct_response',\n",
    "        'choice_accuracy': 'choice_accuracy'},\n",
    "    'key_codes': {\n",
    "        'go': 'go',\n",
    "        'stop': 'stop',\n",
    "        'correct': 1,\n",
    "        'incorrect': 0,\n",
    "        'noResponse': -1}}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_query_str(col, condition):\n",
    "    if type(condition)==str:\n",
    "        return \"%s=='%s'\" % (col, condition)\n",
    "    elif type(condition) in [float, int]:\n",
    "        return \"%s==%s\" % (col, condition)\n",
    "    elif type(condition)==list:\n",
    "        return \"%s in %s\" % (col, condition)\n",
    "\n",
    "def stop_summarize(curr_data, thresh=SSD_THRESH, query_str=None):\n",
    "    data_df = curr_data.query(query_str) if query_str is not None else curr_data\n",
    "    \n",
    "    sum_df = SSRTmodel().fit_transform(data_df, level='group')\n",
    "    sum_df_threshSSDs = SSRTmodel().fit_transform(data_df.query(f'SSD>={thresh} or condition==\"go\"'), level='group').add_suffix('_wThresh_SSDs')\n",
    "    sum_df_threshSubs = sum_df.query(f\"mean_SSD >= {thresh}\").add_suffix('_wThresh_subs')\n",
    "    return pd.concat([sum_df, sum_df_threshSSDs, sum_df_threshSubs],\n",
    "                       1,\n",
    "                       sort=True\n",
    "                      )\n",
    "\n",
    "def get_inhib_func(curr_data, cond):\n",
    "    inhib_df = pd.DataFrame(curr_data.groupby(['ID', 'SSD']).apply(lambda x: x.stopRT.notnull().sum()/len(x))).reset_index()\n",
    "    inhib_df['condition'] = cond\n",
    "    return inhib_df\n",
    "\n",
    "def get_gng_presp(curr_data):\n",
    "    curr_data = curr_data.copy()\n",
    "    stop_trials = curr_data.query(\"stop_signal_condition=='stop'\")\n",
    "    out={}\n",
    "    out['p_resp'] = (stop_trials.rt != -1).sum()/len(stop_trials)\n",
    "    out['p_resp_go'] = (stop_trials.query(\"go_nogo_condition=='go'\").rt != -1).sum()/len(stop_trials.query(\"go_nogo_condition=='go'\"))\n",
    "    out['p_resp_nogo'] = (stop_trials.query(\"go_nogo_condition=='nogo'\").rt != -1).sum()/len(stop_trials.query(\"go_nogo_condition=='nogo'\"))\n",
    "    return out"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "stop_data_dict = make_clean_concat_data(stop_subset=True, dataset=dataset)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Check P(resp|signal) in Go/NoGo "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>p_resp</th>\n",
       "      <th>p_resp_go</th>\n",
       "      <th>p_resp_nogo</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>33.000000</td>\n",
       "      <td>33.000000</td>\n",
       "      <td>33.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.431818</td>\n",
       "      <td>0.501263</td>\n",
       "      <td>0.015152</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.013957</td>\n",
       "      <td>0.014896</td>\n",
       "      <td>0.038497</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.378571</td>\n",
       "      <td>0.441667</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.428571</td>\n",
       "      <td>0.491667</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.428571</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.442857</td>\n",
       "      <td>0.508333</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>0.457143</td>\n",
       "      <td>0.525000</td>\n",
       "      <td>0.200000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          p_resp  p_resp_go  p_resp_nogo\n",
       "count  33.000000  33.000000    33.000000\n",
       "mean    0.431818   0.501263     0.015152\n",
       "std     0.013957   0.014896     0.038497\n",
       "min     0.378571   0.441667     0.000000\n",
       "25%     0.428571   0.491667     0.000000\n",
       "50%     0.428571   0.500000     0.000000\n",
       "75%     0.442857   0.508333     0.000000\n",
       "max     0.457143   0.525000     0.200000"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gng_presp_data = pd.DataFrame(list(stop_data_dict['stop_signal_with_go_no_go'].groupby('worker_id').apply(get_gng_presp)))\n",
    "gng_presp_data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "del stop_data_dict['stop_signal_with_go_no_go']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Get SSRT metrics for remaining tasks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# build dict\n",
    "ssrtc_out = {}\n",
    "for task_name in stop_data_dict.keys():  # [k for k in stop_data_dict.keys()][:1]:  # development loop using just 1st task\n",
    "    curr_data = StopData(stopmetrics_var_dict).fit_transform(stop_data_dict[task_name].drop(columns=['correct_response']))\n",
    "    short_name = task_name.split('_with_')[-1]\n",
    "    ssrtc_out[short_name] = stop_summarize(curr_data)\n",
    "    \n",
    "    if 'with' in task_name:\n",
    "        dual_col = dual_dict[task_name]['dual_col']\n",
    "        for key in [k for k in dual_dict[task_name] if k!='dual_col']:\n",
    "            query_str = get_query_str(dual_col, dual_dict[task_name][key])\n",
    "            ssrtc_out['%s_%s' % (short_name,key)] = stop_summarize(\n",
    "                curr_data,\n",
    "                query_str=query_str\n",
    "            )\n",
    "\n",
    "ssrtc_out['SE'] = ssrtc_out.pop('stop_signal_single_task_network')\n",
    "metrics = [c for c in ssrtc_out['SE'].columns if 'max_RT' not in c]\n",
    "\n",
    "#flatten data, remove outliers w/ values > 3 SDs from the mean\n",
    "flattened_data = pd.concat([ssrtc_out[k].add_prefix(k+'_') for k in ssrtc_out], axis=1, sort=True)\n",
    "flattened_data = flattened_data.filter(regex='SE|DC|DE', axis=1)\n",
    "z_df = flattened_data.apply(stats.zscore).apply(np.abs)\n",
    "flattened_data[z_df>OUTLIER_THRESH] = None\n",
    "flattened_data.index.name='ID'\n",
    "\n",
    "\n",
    "\n",
    "SSRTs = flattened_data.loc[:, ~flattened_data.columns.str.contains(\"wThresh\")].filter(regex='SSRT')\n",
    "SSRTs_ThreshSSDs = flattened_data.loc[:, flattened_data.columns.str.contains(\"wThresh_SSDs\")].filter(regex='SSRT')\n",
    "SSRTs_ThreshSubs = flattened_data.loc[:, flattened_data.columns.str.contains(\"wThresh_subs\")].filter(regex='SSRT')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Validation Analyses"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2 subs dropped for nan cell\n"
     ]
    }
   ],
   "source": [
    "def filter_out_nans(SSRTs):\n",
    "    old_nSubs = len(SSRTs)\n",
    "    SSRTs = SSRTs.dropna()\n",
    "    new_nSubs = len(SSRTs)\n",
    "    print(f'{old_nSubs-new_nSubs} subs dropped for nan cell')\n",
    "    return SSRTs\n",
    "SSRTs = filter_out_nans(SSRTs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# One-way Anova"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>predictable_task_switching</th>\n",
       "      <th>n_back</th>\n",
       "      <th>flanker</th>\n",
       "      <th>shape_matching</th>\n",
       "      <th>cued_task_switching</th>\n",
       "      <th>SE</th>\n",
       "      <th>directed_forgetting</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ID</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>s005</th>\n",
       "      <td>209.25</td>\n",
       "      <td>196.016129</td>\n",
       "      <td>205.00</td>\n",
       "      <td>189.666667</td>\n",
       "      <td>205.25</td>\n",
       "      <td>170.166667</td>\n",
       "      <td>316.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>s010</th>\n",
       "      <td>257.75</td>\n",
       "      <td>267.629032</td>\n",
       "      <td>267.50</td>\n",
       "      <td>317.250000</td>\n",
       "      <td>271.25</td>\n",
       "      <td>254.083333</td>\n",
       "      <td>351.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>s025</th>\n",
       "      <td>301.50</td>\n",
       "      <td>307.663306</td>\n",
       "      <td>295.50</td>\n",
       "      <td>316.583333</td>\n",
       "      <td>325.25</td>\n",
       "      <td>247.500000</td>\n",
       "      <td>392.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>s044</th>\n",
       "      <td>267.50</td>\n",
       "      <td>279.854839</td>\n",
       "      <td>211.75</td>\n",
       "      <td>299.083333</td>\n",
       "      <td>284.00</td>\n",
       "      <td>254.833333</td>\n",
       "      <td>349.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>s066</th>\n",
       "      <td>192.00</td>\n",
       "      <td>249.377016</td>\n",
       "      <td>262.25</td>\n",
       "      <td>217.416667</td>\n",
       "      <td>254.00</td>\n",
       "      <td>347.583333</td>\n",
       "      <td>271.50</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      predictable_task_switching      n_back  flanker  shape_matching  \\\n",
       "ID                                                                      \n",
       "s005                      209.25  196.016129   205.00      189.666667   \n",
       "s010                      257.75  267.629032   267.50      317.250000   \n",
       "s025                      301.50  307.663306   295.50      316.583333   \n",
       "s044                      267.50  279.854839   211.75      299.083333   \n",
       "s066                      192.00  249.377016   262.25      217.416667   \n",
       "\n",
       "      cued_task_switching          SE  directed_forgetting  \n",
       "ID                                                          \n",
       "s005               205.25  170.166667               316.25  \n",
       "s010               271.25  254.083333               351.75  \n",
       "s025               325.25  247.500000               392.00  \n",
       "s044               284.00  254.833333               349.25  \n",
       "s066               254.00  347.583333               271.50  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def mean_SSRTs_within_task(SSRTs):\n",
    "    SSRTs_taskMeaned = pd.DataFrame()\n",
    "    for task_name in stop_data_dict.keys():\n",
    "        short_name = task_name.split('_with_')[-1]\n",
    "        if short_name == 'stop_signal_single_task_network':\n",
    "            SSRTs_taskMeaned['SE'] = SSRTs.filter(regex='SE')\n",
    "        else:\n",
    "            SSRTs_taskMeaned[short_name] = SSRTs.filter(regex=short_name).mean(1)\n",
    "    return SSRTs_taskMeaned\n",
    "SSRTs_taskMeaned = mean_SSRTs_within_task(SSRTs)\n",
    "SSRTs_taskMeaned.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ID</th>\n",
       "      <th>variable</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>s005</td>\n",
       "      <td>predictable_task_switching</td>\n",
       "      <td>209.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>s010</td>\n",
       "      <td>predictable_task_switching</td>\n",
       "      <td>257.75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>s025</td>\n",
       "      <td>predictable_task_switching</td>\n",
       "      <td>301.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>s044</td>\n",
       "      <td>predictable_task_switching</td>\n",
       "      <td>267.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>s066</td>\n",
       "      <td>predictable_task_switching</td>\n",
       "      <td>192.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>212</th>\n",
       "      <td>s429</td>\n",
       "      <td>directed_forgetting</td>\n",
       "      <td>286.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>213</th>\n",
       "      <td>s441</td>\n",
       "      <td>directed_forgetting</td>\n",
       "      <td>293.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>214</th>\n",
       "      <td>s454</td>\n",
       "      <td>directed_forgetting</td>\n",
       "      <td>463.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>215</th>\n",
       "      <td>s490</td>\n",
       "      <td>directed_forgetting</td>\n",
       "      <td>376.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>216</th>\n",
       "      <td>s539</td>\n",
       "      <td>directed_forgetting</td>\n",
       "      <td>379.50</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>217 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       ID                    variable   value\n",
       "0    s005  predictable_task_switching  209.25\n",
       "1    s010  predictable_task_switching  257.75\n",
       "2    s025  predictable_task_switching  301.50\n",
       "3    s044  predictable_task_switching  267.50\n",
       "4    s066  predictable_task_switching  192.00\n",
       "..    ...                         ...     ...\n",
       "212  s429         directed_forgetting  286.00\n",
       "213  s441         directed_forgetting  293.50\n",
       "214  s454         directed_forgetting  463.25\n",
       "215  s490         directed_forgetting  376.50\n",
       "216  s539         directed_forgetting  379.50\n",
       "\n",
       "[217 rows x 3 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def melt_taskMeaned_SSRTs(SSRTs_taskMeaned):\n",
    "    return SSRTs_taskMeaned.reset_index().melt(id_vars='ID')\n",
    "melted_SSRTs = melt_taskMeaned_SSRTs(SSRTs_taskMeaned)\n",
    "melted_SSRTs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Source</th>\n",
       "      <th>SS</th>\n",
       "      <th>DF</th>\n",
       "      <th>MS</th>\n",
       "      <th>F</th>\n",
       "      <th>p-unc</th>\n",
       "      <th>p-GG-corr</th>\n",
       "      <th>np2</th>\n",
       "      <th>eps</th>\n",
       "      <th>sphericity</th>\n",
       "      <th>W-spher</th>\n",
       "      <th>p-spher</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>variable</td>\n",
       "      <td>256719.517784</td>\n",
       "      <td>6</td>\n",
       "      <td>42786.586297</td>\n",
       "      <td>27.577007</td>\n",
       "      <td>3.245425e-23</td>\n",
       "      <td>3.859356e-16</td>\n",
       "      <td>0.478959</td>\n",
       "      <td>0.661857</td>\n",
       "      <td>False</td>\n",
       "      <td>0.205375</td>\n",
       "      <td>0.001602</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Error</td>\n",
       "      <td>279275.609783</td>\n",
       "      <td>180</td>\n",
       "      <td>1551.531165</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Source             SS   DF            MS          F         p-unc  \\\n",
       "0  variable  256719.517784    6  42786.586297  27.577007  3.245425e-23   \n",
       "1     Error  279275.609783  180   1551.531165        NaN           NaN   \n",
       "\n",
       "      p-GG-corr       np2       eps sphericity   W-spher   p-spher  \n",
       "0  3.859356e-16  0.478959  0.661857      False  0.205375  0.001602  \n",
       "1           NaN       NaN       NaN        NaN       NaN       NaN  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def run_anova_on_melted_SSRTs(melted_SSRTs):\n",
    "    return pg.rm_anova(data=melted_SSRTs, dv='value', within='variable', subject='ID', detailed=True)\n",
    "anova_res = run_anova_on_melted_SSRTs(melted_SSRTs)\n",
    "anova_res"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Planned Contrasts\n",
    "\n",
    "Guidelines from [here](http://web.pdx.edu/~newsomj/uvclass/ho_planned%20contrasts.pdf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_degOfFree(anova_res):\n",
    "    return anova_res.loc[anova_res.Source=='Error', 'DF'].values[0]\n",
    "\n",
    "df = get_degOfFree(anova_res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_standardError(anova_res):\n",
    "    MS = anova_res.loc[anova_res.Source=='Error', 'MS'].values[0]\n",
    "    return np.sqrt(MS * (2/len(SSRTs)))\n",
    "std_err = get_standardError(anova_res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "directed_forgetting: Mean=108.87, t=10.882, p=0.000000, d=1.44\n",
      "n_back: Mean=37.68, t=3.766, p=0.000112, d=0.76\n",
      "cued_task_switching: Mean=29.84, t=2.983, p=0.001627, d=0.53\n",
      "shape_matching: Mean=28.56, t=2.855, p=0.002408, d=0.59\n"
     ]
    }
   ],
   "source": [
    "def run_planned_contrasts(SSRTs_taskMeaned, std_err, df):\n",
    "    planned_tasks = ['directed_forgetting', 'n_back', 'cued_task_switching', 'shape_matching']\n",
    "    test_res_df = pd.DataFrame(index=planned_tasks, columns=['mean', 't', 'p', 'd'])\n",
    "    for task in planned_tasks:\n",
    "        diffs = (SSRTs_taskMeaned.filter(regex=task).values - SSRTs_taskMeaned.filter(regex='SE').values)\n",
    "        t = np.mean(diffs)/std_err\n",
    "        pval = stats.t.sf(t, df) \n",
    "        print(f'{task}: Mean={np.mean(diffs):.2f}, t={t:.3f}, p={pval:.6f}, d={np.mean(diffs)/np.std(diffs):.2f}')\n",
    "        test_res_df.loc[task, ['mean', 't', 'p', 'd']] = np.mean(diffs), t, pval, np.mean(diffs)/np.std(diffs)\n",
    "    return test_res_df\n",
    "\n",
    "test_res_df = run_planned_contrasts(SSRTs_taskMeaned, std_err, df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Planned related-samples t-test for n-Back load"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "def subtract_SE_SSRTs(SSRTs):\n",
    "    diff_SSRTs = SSRTs.sub(SSRTs.filter(regex='SE').values)\n",
    "    del diff_SSRTs['SE_SSRT']\n",
    "    return diff_SSRTs\n",
    "diff_SSRTs = subtract_SE_SSRTs(SSRTs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "n-Back DE > DC: Mean=32.95, t=2.654, p=0.006297, d=0.48\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>mean</th>\n",
       "      <th>t</th>\n",
       "      <th>p</th>\n",
       "      <th>d</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>directed_forgetting</th>\n",
       "      <td>108.873656</td>\n",
       "      <td>10.881992</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.441481</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>n_back</th>\n",
       "      <td>37.680346</td>\n",
       "      <td>3.766175</td>\n",
       "      <td>0.000112</td>\n",
       "      <td>0.755162</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cued_task_switching</th>\n",
       "      <td>29.841398</td>\n",
       "      <td>2.982667</td>\n",
       "      <td>0.001627</td>\n",
       "      <td>0.532571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shape_matching</th>\n",
       "      <td>28.55914</td>\n",
       "      <td>2.854504</td>\n",
       "      <td>0.002408</td>\n",
       "      <td>0.589404</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>n_back: DE &gt; DC</th>\n",
       "      <td>32.946974</td>\n",
       "      <td>2.65422</td>\n",
       "      <td>0.006297</td>\n",
       "      <td>0.484592</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                           mean          t         p         d\n",
       "directed_forgetting  108.873656  10.881992       0.0  1.441481\n",
       "n_back                37.680346   3.766175  0.000112  0.755162\n",
       "cued_task_switching   29.841398   2.982667  0.001627  0.532571\n",
       "shape_matching         28.55914   2.854504  0.002408  0.589404\n",
       "n_back: DE > DC       32.946974    2.65422  0.006297  0.484592"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def compare_nBack_load(diff_SSRTs, test_res_df):\n",
    "    diffs = (diff_SSRTs.n_back_DE_SSRT.values - diff_SSRTs.n_back_DC_SSRT.values)\n",
    "    t, pval = stats.ttest_rel(diff_SSRTs.n_back_DE_SSRT.values, diff_SSRTs.n_back_DC_SSRT.values, nan_policy='raise', alternative='greater')\n",
    "    print(f'n-Back DE > DC: Mean={np.mean(diffs):.2f}, t={t:.3f}, p={pval:.6f}, d={np.mean(diffs)/np.std(diffs):.2f}')\n",
    "    test_res_df.loc['n_back: DE > DC', ['mean', 't', 'p', 'd']] = np.mean(diffs), t, pval, np.mean(diffs)/np.std(diffs)\n",
    "    return test_res_df\n",
    "\n",
    "test_res_df = compare_nBack_load(diff_SSRTs, test_res_df)\n",
    "test_res_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Visualize"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "formal_tasks = {\n",
    "    'All': 'All',\n",
    "    'SE': 'Single Task',\n",
    "    'single_task': 'Single Task',\n",
    "    'go_no_go': 'Go/No-Go',\n",
    "    'predictable_task_switching': 'Predictable Task Switching',\n",
    "    'cued_task_switching': 'Cued Task Switching',\n",
    "    'flanker': 'Flanker',\n",
    "    'shape_matching': 'Shape Matching',\n",
    "    'n_back': 'n-Back',\n",
    "    'directed_forgetting': 'Directed Forgetting' \n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.set(style=\"whitegrid\", palette=\"colorblind\", color_codes=True)\n",
    "palette ={\"DC\":\"C0\", \"DE\":\"C1\", \"SE\":\"C2\",\n",
    "         \"Dual Low Demand\":\"C0\", \"Dual High Demand\":\"C1\", \"Simple Stop\":\"C2\"}\n",
    "\n",
    "task_order_dict = {\n",
    "    'SE': 'aa',\n",
    "    'go_no_go': 'ab',\n",
    "    'predictable_task_switching': 'ba',\n",
    "    'cued_task_switching': 'bb',\n",
    "    'flanker': 'ca',\n",
    "    'shape_matching': 'cb',\n",
    "    'n_back': 'da',\n",
    "    'directed_forgetting': 'db'\n",
    "}\n",
    "\n",
    "trial_order_dict = {\n",
    "    'Simple Stop': 'aa',\n",
    "    'Dual Low Demand': 'ab',\n",
    "    'Dual High Demand': 'ba',\n",
    "}\n",
    "\n",
    "def context_str(string):\n",
    "    if 'DC' in string:\n",
    "        return 'Dual Low Demand'\n",
    "    elif 'DE' in string:\n",
    "        return 'Dual High Demand'\n",
    "    elif 'SE' in string:\n",
    "        return 'Simple Stop'\n",
    "    elif 'OTHER' in string:\n",
    "        return 'POS/3BACK/DSD|SSS/CUE_SWITCH'\n",
    "    else:\n",
    "        return 'COMBINE'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ID</th>\n",
       "      <th>variable</th>\n",
       "      <th>SSRT</th>\n",
       "      <th>Task</th>\n",
       "      <th>Trial Type</th>\n",
       "      <th>task_order</th>\n",
       "      <th>trial_order</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>372</th>\n",
       "      <td>s005</td>\n",
       "      <td>SE_SSRT</td>\n",
       "      <td>170.166667</td>\n",
       "      <td>Single Task</td>\n",
       "      <td>Simple Stop</td>\n",
       "      <td>aa</td>\n",
       "      <td>aa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>373</th>\n",
       "      <td>s010</td>\n",
       "      <td>SE_SSRT</td>\n",
       "      <td>254.083333</td>\n",
       "      <td>Single Task</td>\n",
       "      <td>Simple Stop</td>\n",
       "      <td>aa</td>\n",
       "      <td>aa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>374</th>\n",
       "      <td>s025</td>\n",
       "      <td>SE_SSRT</td>\n",
       "      <td>247.500000</td>\n",
       "      <td>Single Task</td>\n",
       "      <td>Simple Stop</td>\n",
       "      <td>aa</td>\n",
       "      <td>aa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>375</th>\n",
       "      <td>s044</td>\n",
       "      <td>SE_SSRT</td>\n",
       "      <td>254.833333</td>\n",
       "      <td>Single Task</td>\n",
       "      <td>Simple Stop</td>\n",
       "      <td>aa</td>\n",
       "      <td>aa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>376</th>\n",
       "      <td>s066</td>\n",
       "      <td>SE_SSRT</td>\n",
       "      <td>347.583333</td>\n",
       "      <td>Single Task</td>\n",
       "      <td>Simple Stop</td>\n",
       "      <td>aa</td>\n",
       "      <td>aa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>367</th>\n",
       "      <td>s429</td>\n",
       "      <td>directed_forgetting_DE_SSRT</td>\n",
       "      <td>348.500000</td>\n",
       "      <td>Directed Forgetting</td>\n",
       "      <td>Dual High Demand</td>\n",
       "      <td>db</td>\n",
       "      <td>ba</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>368</th>\n",
       "      <td>s441</td>\n",
       "      <td>directed_forgetting_DE_SSRT</td>\n",
       "      <td>296.000000</td>\n",
       "      <td>Directed Forgetting</td>\n",
       "      <td>Dual High Demand</td>\n",
       "      <td>db</td>\n",
       "      <td>ba</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>369</th>\n",
       "      <td>s454</td>\n",
       "      <td>directed_forgetting_DE_SSRT</td>\n",
       "      <td>438.500000</td>\n",
       "      <td>Directed Forgetting</td>\n",
       "      <td>Dual High Demand</td>\n",
       "      <td>db</td>\n",
       "      <td>ba</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>370</th>\n",
       "      <td>s490</td>\n",
       "      <td>directed_forgetting_DE_SSRT</td>\n",
       "      <td>291.500000</td>\n",
       "      <td>Directed Forgetting</td>\n",
       "      <td>Dual High Demand</td>\n",
       "      <td>db</td>\n",
       "      <td>ba</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>371</th>\n",
       "      <td>s539</td>\n",
       "      <td>directed_forgetting_DE_SSRT</td>\n",
       "      <td>345.000000</td>\n",
       "      <td>Directed Forgetting</td>\n",
       "      <td>Dual High Demand</td>\n",
       "      <td>db</td>\n",
       "      <td>ba</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>403 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       ID                     variable        SSRT                 Task  \\\n",
       "372  s005                      SE_SSRT  170.166667          Single Task   \n",
       "373  s010                      SE_SSRT  254.083333          Single Task   \n",
       "374  s025                      SE_SSRT  247.500000          Single Task   \n",
       "375  s044                      SE_SSRT  254.833333          Single Task   \n",
       "376  s066                      SE_SSRT  347.583333          Single Task   \n",
       "..    ...                          ...         ...                  ...   \n",
       "367  s429  directed_forgetting_DE_SSRT  348.500000  Directed Forgetting   \n",
       "368  s441  directed_forgetting_DE_SSRT  296.000000  Directed Forgetting   \n",
       "369  s454  directed_forgetting_DE_SSRT  438.500000  Directed Forgetting   \n",
       "370  s490  directed_forgetting_DE_SSRT  291.500000  Directed Forgetting   \n",
       "371  s539  directed_forgetting_DE_SSRT  345.000000  Directed Forgetting   \n",
       "\n",
       "           Trial Type task_order trial_order  \n",
       "372       Simple Stop         aa          aa  \n",
       "373       Simple Stop         aa          aa  \n",
       "374       Simple Stop         aa          aa  \n",
       "375       Simple Stop         aa          aa  \n",
       "376       Simple Stop         aa          aa  \n",
       "..                ...        ...         ...  \n",
       "367  Dual High Demand         db          ba  \n",
       "368  Dual High Demand         db          ba  \n",
       "369  Dual High Demand         db          ba  \n",
       "370  Dual High Demand         db          ba  \n",
       "371  Dual High Demand         db          ba  \n",
       "\n",
       "[403 rows x 7 columns]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def clean_SSRTs_for_Barplots(SSRTs):\n",
    "    melted_SSRTs = SSRTs.reset_index().melt(id_vars='ID', value_name='SSRT')\n",
    "    melted_SSRTs['Task'] = [i.split('_SSRT')[0].replace('_DC', '').replace('_DE', '') for i in melted_SSRTs['variable']]\n",
    "    melted_SSRTs['Trial Type'] = [context_str(i) for i in melted_SSRTs['variable']]\n",
    "\n",
    "    melted_SSRTs['task_order'] = melted_SSRTs['Task'].map(task_order_dict)\n",
    "    melted_SSRTs['trial_order'] = melted_SSRTs['Trial Type'].map(trial_order_dict)\n",
    "\n",
    "    melted_SSRTs = melted_SSRTs.sort_values(['task_order', 'trial_order'])\n",
    "    melted_SSRTs['Task'] = melted_SSRTs['Task'].map(formal_tasks)\n",
    "    return melted_SSRTs\n",
    "melted_SSRTs = clean_SSRTs_for_Barplots(SSRTs)\n",
    "melted_SSRTs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "title_dataset = dataset if dataset != 'all' else 'combined'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x468 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_SSRTs_barplot(melted_SSRTs, save_fig=False):\n",
    "\n",
    "    f, (a0, a1) = plt.subplots(1, 2, gridspec_kw={'width_ratios': [1, 8]}, sharey=True, figsize=(12,6.5))\n",
    "\n",
    "    # Single Task\n",
    "    bar = sns.barplot(x='Task', y='SSRT', hue='Trial Type', data=melted_SSRTs[melted_SSRTs['Trial Type'].isin(['Simple Stop'])], palette=palette, errcolor='0', ax=a0)\n",
    "    a0.axhline(SSRTs['SE_SSRT'].mean()-3, color='k', linestyle=':', linewidth=4)\n",
    "    a0.set_ylabel('Stop Signal Reaction Time', fontweight='bold', fontsize=15)\n",
    "    a0.set_xlabel('')\n",
    "    a0.set_xticks([-.25])\n",
    "    a0.set_xticklabels(['Simple Stop'], rotation=31, fontweight='bold', fontsize='11')\n",
    "    a0.set_yticks(np.arange(0, 450, 50))\n",
    "    a0.set_ylim([0, 400.5])\n",
    "    a0.set_yticklabels(np.arange(0, 450, 50), fontdict={'fontweight':'bold', 'fontsize':'11'})\n",
    "\n",
    "\n",
    "    custom_lines = [Line2D([0], [0], color=sns.color_palette()[2], lw=6),\n",
    "                    Line2D([0], [0], color=sns.color_palette()[0], lw=6),\n",
    "                    Line2D([0], [0], color=sns.color_palette()[1], lw=6)]\n",
    "    a0.set_zorder(1)\n",
    "    a0.legend(custom_lines, ['Single Task', 'Dual Low Demand', 'Dual High Demand'], prop={'weight': 'bold', 'size':9.75}, loc=(1.1,.85), frameon=True)\n",
    "\n",
    "\n",
    "    # Dual Tasks\n",
    "    sns.barplot(x='Task', y='SSRT', hue='Trial Type', data=melted_SSRTs[melted_SSRTs['Trial Type'].isin(['Dual Low Demand', 'Dual High Demand'])], palette=palette, errcolor='0', ax=a1)\n",
    "    a1.axhline(SSRTs['SE_SSRT'].mean()-3, color='k', linestyle=':', linewidth=4)\n",
    "    a1.set_ylabel('')\n",
    "    a1.set_xlabel('')\n",
    "    a1.get_legend().remove()\n",
    "\n",
    "    # _ = plt.legend(prop={'weight': 'bold'})\n",
    "    _ = plt.xticks(rotation=31, ha='right', fontweight='bold', fontsize='11')\n",
    "    _ = plt.yticks(fontweight='bold', fontsize='12')\n",
    "\n",
    "\n",
    "\n",
    "    _ = f.text(0.5, 0.01, 'Task', ha='center', fontweight='bold', fontsize=13)\n",
    "    _ = plt.title(f'Interference of SSRTs in Dual Tasks in {title_dataset.capitalize()} Dataset', fontsize='18', fontweight='bold',  y=1.1, x=.44, pad=-20)\n",
    "    f.tight_layout()\n",
    "    plt.subplots_adjust(wspace=.01)\n",
    "    if save_fig:\n",
    "        plt.savefig(f'figures/dataset-{dataset}_metric-SSRT_barplot.png', dpi=300)\n",
    "    plt.show()\n",
    "    plt.close()\n",
    "    \n",
    "plot_SSRTs_barplot(melted_SSRTs, save_fig=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ID</th>\n",
       "      <th>variable</th>\n",
       "      <th>Dual Task SSRT - Simple Stop Task SSRT</th>\n",
       "      <th>Task</th>\n",
       "      <th>Trial Type</th>\n",
       "      <th>task_order</th>\n",
       "      <th>trial_order</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>s005</td>\n",
       "      <td>predictable_task_switching_DC_SSRT</td>\n",
       "      <td>41.833333</td>\n",
       "      <td>Predictable Task Switching</td>\n",
       "      <td>Dual Low Demand</td>\n",
       "      <td>ba</td>\n",
       "      <td>ab</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>s010</td>\n",
       "      <td>predictable_task_switching_DC_SSRT</td>\n",
       "      <td>8.416667</td>\n",
       "      <td>Predictable Task Switching</td>\n",
       "      <td>Dual Low Demand</td>\n",
       "      <td>ba</td>\n",
       "      <td>ab</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>s025</td>\n",
       "      <td>predictable_task_switching_DC_SSRT</td>\n",
       "      <td>25.500000</td>\n",
       "      <td>Predictable Task Switching</td>\n",
       "      <td>Dual Low Demand</td>\n",
       "      <td>ba</td>\n",
       "      <td>ab</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>s044</td>\n",
       "      <td>predictable_task_switching_DC_SSRT</td>\n",
       "      <td>18.666667</td>\n",
       "      <td>Predictable Task Switching</td>\n",
       "      <td>Dual Low Demand</td>\n",
       "      <td>ba</td>\n",
       "      <td>ab</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>s066</td>\n",
       "      <td>predictable_task_switching_DC_SSRT</td>\n",
       "      <td>-179.583333</td>\n",
       "      <td>Predictable Task Switching</td>\n",
       "      <td>Dual Low Demand</td>\n",
       "      <td>ba</td>\n",
       "      <td>ab</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>367</th>\n",
       "      <td>s429</td>\n",
       "      <td>directed_forgetting_DE_SSRT</td>\n",
       "      <td>159.166667</td>\n",
       "      <td>Directed Forgetting</td>\n",
       "      <td>Dual High Demand</td>\n",
       "      <td>db</td>\n",
       "      <td>ba</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>368</th>\n",
       "      <td>s441</td>\n",
       "      <td>directed_forgetting_DE_SSRT</td>\n",
       "      <td>40.500000</td>\n",
       "      <td>Directed Forgetting</td>\n",
       "      <td>Dual High Demand</td>\n",
       "      <td>db</td>\n",
       "      <td>ba</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>369</th>\n",
       "      <td>s454</td>\n",
       "      <td>directed_forgetting_DE_SSRT</td>\n",
       "      <td>206.833333</td>\n",
       "      <td>Directed Forgetting</td>\n",
       "      <td>Dual High Demand</td>\n",
       "      <td>db</td>\n",
       "      <td>ba</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>370</th>\n",
       "      <td>s490</td>\n",
       "      <td>directed_forgetting_DE_SSRT</td>\n",
       "      <td>44.500000</td>\n",
       "      <td>Directed Forgetting</td>\n",
       "      <td>Dual High Demand</td>\n",
       "      <td>db</td>\n",
       "      <td>ba</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>371</th>\n",
       "      <td>s539</td>\n",
       "      <td>directed_forgetting_DE_SSRT</td>\n",
       "      <td>135.833333</td>\n",
       "      <td>Directed Forgetting</td>\n",
       "      <td>Dual High Demand</td>\n",
       "      <td>db</td>\n",
       "      <td>ba</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>372 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       ID                            variable  \\\n",
       "0    s005  predictable_task_switching_DC_SSRT   \n",
       "1    s010  predictable_task_switching_DC_SSRT   \n",
       "2    s025  predictable_task_switching_DC_SSRT   \n",
       "3    s044  predictable_task_switching_DC_SSRT   \n",
       "4    s066  predictable_task_switching_DC_SSRT   \n",
       "..    ...                                 ...   \n",
       "367  s429         directed_forgetting_DE_SSRT   \n",
       "368  s441         directed_forgetting_DE_SSRT   \n",
       "369  s454         directed_forgetting_DE_SSRT   \n",
       "370  s490         directed_forgetting_DE_SSRT   \n",
       "371  s539         directed_forgetting_DE_SSRT   \n",
       "\n",
       "     Dual Task SSRT - Simple Stop Task SSRT                        Task  \\\n",
       "0                                 41.833333  Predictable Task Switching   \n",
       "1                                  8.416667  Predictable Task Switching   \n",
       "2                                 25.500000  Predictable Task Switching   \n",
       "3                                 18.666667  Predictable Task Switching   \n",
       "4                               -179.583333  Predictable Task Switching   \n",
       "..                                      ...                         ...   \n",
       "367                              159.166667         Directed Forgetting   \n",
       "368                               40.500000         Directed Forgetting   \n",
       "369                              206.833333         Directed Forgetting   \n",
       "370                               44.500000         Directed Forgetting   \n",
       "371                              135.833333         Directed Forgetting   \n",
       "\n",
       "           Trial Type task_order trial_order  \n",
       "0     Dual Low Demand         ba          ab  \n",
       "1     Dual Low Demand         ba          ab  \n",
       "2     Dual Low Demand         ba          ab  \n",
       "3     Dual Low Demand         ba          ab  \n",
       "4     Dual Low Demand         ba          ab  \n",
       "..                ...        ...         ...  \n",
       "367  Dual High Demand         db          ba  \n",
       "368  Dual High Demand         db          ba  \n",
       "369  Dual High Demand         db          ba  \n",
       "370  Dual High Demand         db          ba  \n",
       "371  Dual High Demand         db          ba  \n",
       "\n",
       "[372 rows x 7 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def clean_diffs_for_Seaborn(diff_SSRTs):\n",
    "    melted_diffs = diff_SSRTs.reset_index().melt(id_vars='ID', value_name='Dual Task SSRT - Simple Stop Task SSRT')\n",
    "    melted_diffs['Task'] = [i.split('_SSRT')[0].replace('_DC', '').replace('_DE', '') for i in melted_diffs['variable']]\n",
    "    melted_diffs['Trial Type'] = [context_str(i) for i in melted_diffs['variable']]\n",
    "\n",
    "    melted_diffs['task_order'] = melted_diffs['Task'].map(task_order_dict)\n",
    "    melted_diffs['trial_order'] = melted_diffs['Trial Type'].map(trial_order_dict)\n",
    "\n",
    "    melted_diffs = melted_diffs.sort_values(['task_order', 'trial_order'])\n",
    "    melted_diffs['Task'] = melted_diffs['Task'].map(formal_tasks)\n",
    "    return melted_diffs\n",
    "\n",
    "melted_diffs = clean_diffs_for_Seaborn(diff_SSRTs)\n",
    "melted_diffs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_diffs_barplot(melted_diffs, save_fig=False):\n",
    "\n",
    "    fig = plt.figure(figsize=(12,6))\n",
    "\n",
    "    bar = sns.barplot(x='Task', y='Dual Task SSRT - Simple Stop Task SSRT', hue='Trial Type', data=melted_diffs, palette=palette)\n",
    "    plt.legend(prop={'weight': 'bold'})\n",
    "\n",
    "    _ = plt.xticks(rotation=31, ha='right', fontweight='bold', fontsize='11')\n",
    "    _ = plt.yticks(fontweight='bold', fontsize='12')\n",
    "\n",
    "    bar.set_xlabel('Dual Task', fontsize = 18, fontweight='bold')\n",
    "    bar.set_ylabel('Dual Task SSRT - Stimple Stop Task SSRT', fontsize = 16, fontweight='bold')\n",
    "\n",
    "    lowx, highx = plt.xlim()\n",
    "    plt.plot([lowx, highx],[0,0],color='k',linestyle=':',linewidth=3)\n",
    "    _ = plt.title(f'Interference of SSRTs in Dual Tasks in {title_dataset.capitalize()} Dataset', fontsize='18', fontweight='bold')\n",
    "    plt.tight_layout()\n",
    "    lowy, highy = plt.ylim()\n",
    "    _ = plt.axis([lowx, highx, lowy, highy])\n",
    "    if save_fig:\n",
    "        plt.savefig(f'figures/dataset-{dataset}_metric-SSRT_differences_barplot.png', dpi=300)\n",
    "    plt.show()\n",
    "    plt.close()\n",
    "    \n",
    "plot_diffs_barplot(melted_diffs, save_fig=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Repetitions with Exclusions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "def pipeline(SSRTs, strip_str=''):\n",
    "    SSRTs = SSRTs.copy()\n",
    "    SSRTs.columns = [c.replace(strip_str, '') for c in SSRTs.columns]\n",
    "    SSRTs = filter_out_nans(SSRTs)\n",
    "    \n",
    "    # One-way ANOVA\n",
    "    SSRTs_taskMeaned = mean_SSRTs_within_task(SSRTs)\n",
    "    melted_SSRTs = melt_taskMeaned_SSRTs(SSRTs_taskMeaned)\n",
    "    anova_res = run_anova_on_melted_SSRTs(melted_SSRTs)\n",
    "    display(anova_res)\n",
    "    \n",
    "    # Planned Contrasts\n",
    "    df = get_degOfFree(anova_res)\n",
    "    std_err = get_standardError(anova_res)\n",
    "    test_res_df = run_planned_contrasts(SSRTs_taskMeaned, std_err, df)\n",
    "    \n",
    "    # n-Back t-test\n",
    "    diff_SSRTs = subtract_SE_SSRTs(SSRTs)\n",
    "    test_res_df = compare_nBack_load(diff_SSRTs, test_res_df)\n",
    "\n",
    "    # Visualizations    \n",
    "    # All 7 tasks\n",
    "    melted_SSRTs = clean_SSRTs_for_Barplots(SSRTs)\n",
    "    plot_SSRTs_barplot(melted_SSRTs, save_fig=False)\n",
    "    # Diffs Dual SSRTs - Single SSRTs\n",
    "    melted_diffs = clean_diffs_for_Seaborn(diff_SSRTs)\n",
    "    plot_diffs_barplot(melted_diffs, save_fig=False)\n",
    "\n",
    "\n",
    "    return test_res_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Exclude Short SSD trials"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "7 subs dropped for nan cell\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Source</th>\n",
       "      <th>SS</th>\n",
       "      <th>DF</th>\n",
       "      <th>MS</th>\n",
       "      <th>F</th>\n",
       "      <th>p-unc</th>\n",
       "      <th>np2</th>\n",
       "      <th>eps</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>variable</td>\n",
       "      <td>39851.690167</td>\n",
       "      <td>6</td>\n",
       "      <td>6641.948361</td>\n",
       "      <td>4.499371</td>\n",
       "      <td>0.00032</td>\n",
       "      <td>0.152524</td>\n",
       "      <td>0.789274</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Error</td>\n",
       "      <td>221429.210679</td>\n",
       "      <td>150</td>\n",
       "      <td>1476.194738</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Source             SS   DF           MS         F    p-unc       np2  \\\n",
       "0  variable   39851.690167    6  6641.948361  4.499371  0.00032  0.152524   \n",
       "1     Error  221429.210679  150  1476.194738       NaN      NaN       NaN   \n",
       "\n",
       "        eps  \n",
       "0  0.789274  \n",
       "1       NaN  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "directed_forgetting: Mean=36.95, t=3.787, p=0.000110, d=0.60\n",
      "n_back: Mean=35.97, t=3.685, p=0.000159, d=0.71\n",
      "cued_task_switching: Mean=23.18, t=2.375, p=0.009410, d=0.41\n",
      "shape_matching: Mean=21.35, t=2.187, p=0.015132, d=0.44\n",
      "n-Back DE > DC: Mean=39.17, t=2.895, p=0.003877, d=0.58\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x468 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "thresh_SSD_tests = pipeline(SSRTs_ThreshSSDs, strip_str='_wThresh_SSDs')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "thresh_SSD_tests.to_csv(f'result_csvs/dataset-{dataset}_metric-SSRT_wThresh_SSDs_tests-validationContrasts.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Exclude Short SSD subjects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "16 subs dropped for nan cell\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Source</th>\n",
       "      <th>SS</th>\n",
       "      <th>DF</th>\n",
       "      <th>MS</th>\n",
       "      <th>F</th>\n",
       "      <th>p-unc</th>\n",
       "      <th>p-GG-corr</th>\n",
       "      <th>np2</th>\n",
       "      <th>eps</th>\n",
       "      <th>sphericity</th>\n",
       "      <th>W-spher</th>\n",
       "      <th>p-spher</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>variable</td>\n",
       "      <td>58986.719851</td>\n",
       "      <td>6</td>\n",
       "      <td>9831.119975</td>\n",
       "      <td>6.661342</td>\n",
       "      <td>0.000006</td>\n",
       "      <td>0.000112</td>\n",
       "      <td>0.293952</td>\n",
       "      <td>0.69828</td>\n",
       "      <td>False</td>\n",
       "      <td>0.091164</td>\n",
       "      <td>0.037585</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Error</td>\n",
       "      <td>141681.280530</td>\n",
       "      <td>96</td>\n",
       "      <td>1475.846672</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Source             SS  DF           MS         F     p-unc  p-GG-corr  \\\n",
       "0  variable   58986.719851   6  9831.119975  6.661342  0.000006   0.000112   \n",
       "1     Error  141681.280530  96  1475.846672       NaN       NaN        NaN   \n",
       "\n",
       "        np2      eps sphericity   W-spher   p-spher  \n",
       "0  0.293952  0.69828      False  0.091164  0.037585  \n",
       "1       NaN      NaN        NaN       NaN       NaN  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "directed_forgetting: Mean=61.50, t=6.303, p=0.000000, d=1.06\n",
      "n_back: Mean=32.12, t=3.292, p=0.000697, d=0.56\n",
      "cued_task_switching: Mean=21.81, t=2.236, p=0.013851, d=0.34\n",
      "shape_matching: Mean=11.35, t=1.163, p=0.123762, d=0.22\n",
      "n-Back DE > DC: Mean=32.44, t=1.915, p=0.036774, d=0.48\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x468 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA2AAAAGoCAYAAAAgtoZUAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAAC4CElEQVR4nOzdd3QUVRvH8e+GVFpCkV5FCAjSq/QggmIBBJQOCkpvSkdBBCJIkSJVMBQFonQFRDoIBIJKh1CkBUJLAul13j9i9s0SOruk8Pucw8nu3Nl57swOs/PMvXPHZBiGgYiIiIiIiNicXUpXQERERERE5HmhBExEREREROQZUQImIiIiIiLyjCgBExEREREReUaUgImIiIiIiDwjSsBERERERESeESVgIiIiIiIiz4jVErArV65w7do1ay1OREREREQk3TFZ60HMJUuWJG/evGzbts0aixMREREREUl3rNoF0Uq5nIiIiIiISLpkn9IVEHletG/fnv3791OuXDm8vb2feDmnT5+mePHiVqxZgtWrVzNr1iz8/f1xc3Oje/futG3b1upx0qtbt27x5Zdfsnv3buLj4ylatCg//vgjGTNmvOf8Pj4+eHl5cejQIW7fvk3mzJkpU6YMbdu2xcPD46nmd3d3T/Z5k8mEs7MzuXPnpkGDBvTo0YPMmTPfd/57WbRoEdWqVXukee82ffp0ZsyYAcDhw4dxcnJ6ouXcb5mJMmTIQObMmSlevDgtW7akadOmTx3ncepxv3VbuXIlQ4cOfeiy8ufPz9atW61aPw8PD/z9/XnzzTeZMmWKVZedyFrHt3stMykHBwfc3NwoV64cH374IZUqVbJ5PZ4HQ4YMYdWqVRbT7O3tyZIlC6VLl6Z9+/bUq1fvqWLY6rfrSaW2+sjzxaoJ2O3btx/pB8ZkMjFu3DhrhhZJ927evMnEiRM5cOAAW7Zsseqyz507x9ChQ4mPjwfgxo0b5tfyaMaNG8fvv/9ufn/lypX7Jl+rV69myJAhFr0GgoOD2b17N7t372bgwIF06dLliee/F8MwiIiI4Pz588yfP59jx46xcOHCJ13dVCsuLo7bt2/j6+uLr68vBw8e5KuvvkrpaomVxMTEcOPGDTZv3sy2bdsYN27cM0myn0exsbEEBQWZjzP9+/enW7duj72c0NBQZsyYweLFizl27JgNapq26yPPJ6smYJGRkcmuoCRlMpkwDEMJmMgTGDduHL/99hv58+e3+rKPHDliTrhGjRpFtWrVyJYtm9XjpGeHDx8GElqTpk6dSlxc3D3ni4yMxNPTE8MweOWVVxgwYAAFChTg33//ZfTo0Vy+fJmpU6fSvHlzsmfP/tjzJ9WmTRs++eQTICEBCw4OxtPTEx8fH/bt28f+/fupWrUqO3bsMH/m4sWLtG/fHoChQ4fSuHFjc9ndy38cnTt3pmXLlgBWaf262x9//IGDgwORkZGcPn2a6dOn4+fnh7e3N9WrV6dJkyZWj/k43njjDV599VXz+zlz5vDTTz8BWGz/DBkyPPO6WcPUqVOJjo7G0dHR6st++eWXmTVrFvHx8YSGhuLr68u3337L7du3GTlyJJUqVaJgwYI2r8fzIHv27KxatQrDMAgPD+fIkSN8++23XL16lalTp1K1alUqVqz4WMucM2cOP/zwg41q/PhSW33k+WTVBMzZ2dnix1pErMeW91hGRESYX9eqVct8MiOPLnEblipViqJFi953vjNnzhAcHAzAhx9+aD4pL1SoEIMGDaJPnz5ER0fzzz//4OHh8djzJ5UpUyby5Mljfp83b14+++wzcyJ07NgxqlatajFPWFiY+XXWrFktyp5G5syZzV0ebSF37tzmxK5o0aJUrFiRRo0aERoayrx581I8AXNxccHFxcX8PlOmTObX1trGKelpkvOHcXBwsNhGJUqUIH/+/Hz88cdERkayePFihg0bZvN6PA/s7OwstnWxYsUoXbo077zzDvHx8cyfP/+xE7DUNj5AaquPPJ+smoC5urri6elpzUWKpGuJ9yu0aNGC5s2b880333D8+HFy5sxJmzZtzN3Kkt4L4e/vj7u7O7169aJ3794AbN68mdmzZ+Pn54eLiwu1atViwIABFq1lifeBdO/enUuXLrFp0yZcXV3JmjUrZ8+eNc/32muvAXDq1CkA/Pz8mDx5Mvv37ze3wvTu3ZsqVaqYP5N4/0CNGjWoVasWs2fPBmDSpEnUrVuXK1euMGnSJHbv3k1kZCTu7u507dqVhg0bmpeReI9MhgwZ2LdvHxMmTGDTpk3ExsZSp04dhg8fzgsvvGCePyoqitmzZ/Pbb79x5coVcuTIQfXq1enduzcFChQwzxcUFMSUKVPYsmULd+7coWjRorRr145WrVo90ne0Y8cOvLy8OHbsGNHR0ZQoUYL27dvz9ttvAwn3ZnXo0ME8/+rVq1m9erXF95NU0ivzM2bMwNXVlRo1amBnZ8drr73G3r17AczJyuPO/zBJW1getyUqJiaGOXPmsG7dOvz9/XFxcaFgwYK8//77vP/++w/87L3uk0qcVqhQIZYsWcLYsWPZvXs3Dg4OvP766wwZMsQiUXkcOXPmxMPDg7Vr13LixAlu3LjBCy+8cN/7te43fceOHcydO5czZ84QHh5Ojhw5qF27Nv369SNHjhxPVLeHiY6ONu/bAQEBZMiQgUKFCtGyZUuL+zIvXLjApEmT8PX15c6dO2TLls38/7NUqVL3XX54eDgffPABp06dImPGjCxevJgyZcpw8+ZN8//ToKAgsmbNiru7O926dXvovX/3uvfqUY9vT6Ju3brkzZuXq1evsnPnTnMCdq96PM56nTlzhmnTpuHj40NUVBT58+fnvffeo2PHjhb/d+7cucPs2bP5448/CAgIwM3NjXr16tGrVy9y584NwEcffcTu3bspXLgwmzZtMn82Li6O2rVrc+vWLVq2bMmYMWMA8PX1ZerUqRw5cgR7e3sqV65M//79Le7RTFy/9957j8yZM+Pt7Y2zszPly5dn27ZtODg4sG/fPovjweuvv86FCxdo1KgR06ZNe+xtXbx4cSpUqMDBgwfZs2cPcXFx5m2xevVqFi9ezIULF4iOjiZXrlw0bNiQXr16kSlTpmT3lrm7u9OsWTO+/vprDMNg4cKFrFixgsuXL2MYBnnz5uXtt9+ma9euODg4PPb397Bt+KD6iDxLGoRDJBU4fvw4a9euJTo6GkhIsr755hvy5cvHm2+++cDP/vzzz4wYMcL8Pioqil9//RUfHx9WrFhhPhlItGTJEkJCQoCEq8Wurq4WCVhSJ0+epHXr1oSHh5un+fj4cPDgQWbPnk3t2rUt5j969Kg5IciQIQOvvPIK165do1WrVty4ccM836FDh+jVqxdjxowxt8YkMgyDDz/8kCNHjpinbdiwgbCwMObNmwck3JvQpUsXixv0AwICWL16Nfv37+fnn38mZ86chIWF0bZtW4v1O3XqFJ9//jlXr16lb9++D9iysGDBAsaPH28x7dChQxw6dIjjx48zePDgB37+XooXL86LL77IuXPnOHv2LB9++CHZsmWjVq1aeHh48Nprr1kkXY87//3ExMRw/fp1vvnmGyChS/jjXsmeOHEiXl5eFss8duwYX3zxBaGhoXz00UePtbxEYWFhtGnThsuXL5uneXt7kyFDBkaNGvVEywTLwUX8/PwsEvhHsW/fPrp3727RnfTq1at4e3tz5swZli5d+sR1e5CRI0eycuVKi2knTpxg9OjRODo60rJlS0JDQ+ncuTP+/v7mea5fv86WLVvYv38/K1eupFChQsmWbRgGgwYN4tSpU2TIkIHJkydTpkwZ4uPj+eSTTzh69Kh53lu3brFnzx4OHDjAokWLHnt/SfQ0x7cHKVGiBFevXuX8+fP37Xb4OOt14sQJ2rZta9EKfObMGcaPH8/58+cZPXo0AIGBgbRq1YpLly6Z57t+/Tre3t5s27aNH3/8kcKFC9O8eXN2797NhQsXOHLkCK+88gqQsF/dunULwHz/2q5du+jevTsxMTHmZW7btg0fHx+WLl1KyZIlLdZr06ZN5uO4k5MTXbp0Ydu2bcTExLBjxw5zi++ZM2e4cOECwFO1Aru7u3Pw4EHCw8O5dOkSRYoUYfXq1cmOgZcuXWLBggXcuHGDiRMnPnCZ3333HdOnT7eYdu7cOaZOnUpUVBT9+/d/rO/vcbehSEqy6jD0IvJkjh8/TqNGjfjtt98skqn169cDCfc1JHYvy5MnDzt27KBz586EhoaaW53r1q3LmjVr+PHHH3nxxRe5ceMG3377bbJYISEhfPrpp/z22298/vnnTJ06lU8//dRcvnz5cvM9KWPGjCE8PJzChQuzcOFC1q1bx2uvvUZsbCxffvllsq4cISEhNG7cmPXr1zNjxgyyZ8/O5MmTuXHjBtmyZWPWrFmsX7+eDz74AABPT09CQ0MtlhEfH09gYCBeXl4sW7bM3Iq3a9cu8wnHqlWrzMlX586dWb9+PVOmTMHR0ZErV66Y+/fPnz+fs2fP4uTkxDfffMOGDRvMrVJz5syxOIG629mzZ5k0aRIAZcqU4ccff2TFihXmpHPBggX8+eefVKhQgR07dpi7PjVu3Nj8/dyLyWRi0qRJFvfYBQUFsW7dOvr370/9+vUt7gl63PmTmjdvHu7u7ri7u1OmTBk8PDzMCXK7du0e+4Rk9erVALRt25aNGzeydu1a6tSpg52dHX/88ccTd+25desWrq6uLF++nAULFpAlSxbg//v/k0pcDiQMEvW4fvnlF+Li4ihevDgrVqxg48aNvPfeewD89ddfyfZdawgODja3lnTo0IE//viD5cuXW/w/ADhw4AD+/v7Y29szd+5cNm/ezNy5c3FzcyMuLu6+z+ScNm0af/zxBwAjRoygfv36QMKJeuJJrqenJ5s3b+bHH3+kQIEC5u/3ST3s+PakEr9fwzDMx4a7Pc56ffXVV4SFheHq6sq0adPYsGEDzZs3BxKOi2fOnAES7se9dOkS9vb2DBw4kPXr1zNmzBgyZszIjRs3zEnJa6+9RtasWZOt62+//QYkdCOuXLky8fHxjBo1ipiYGMqWLYu3tzcrV66kYsWKhIeHM3bs2GTrFRISQvv27Vm/fj0TJ06kcuXK5q7jSdcpccCmTJkyPdUohkn/L925c8e8TQCqVq3KunXr+PXXX80xEvfToUOH0qZNG/Nnd+zYwdChQ4mNjTVfZHjzzTfZuHEjq1atokyZMhaff9Tv71G34f3qI/KsWa0F7OTJk4887969e6lRo4a1QoukeZkyZWLs2LE4OTnx0ksvsWzZMs6cOUNgYCCQ0FLl7OwMJLQsJfbR37Rpk/lq7ccff4ybmxtubm60bt2asWPHsnHjRsaMGWPRdSZPnjx07doVk8lknpb0xzVnzpzkyZOHoKAgDhw4AEDLli0pUqQIAJ988gmbN2/m0qVLHD58mHLlylmsy4ABAyhcuDDFihUjPj7efALw1ltv8fLLL5vrumLFCsLCwti5c2eyq+D9+/c3HyPatGnDN998g2EYBAUFkSVLFvOPbsGCBRk8eDAmk4lixYoRERGBvb29uU6J89WuXZuqVasC0KJFC1auXIm/vz8bNmzg448/vud3smrVKmJjY3FwcGD69Onky5cPgG+//ZYGDRoQHByMt7c3NWvWJE+ePNjZJVzPcnFxeeg9PS+//DLr169n8eLFrF+/nvPnz5vLbt68Sa9evVi9ejXFihV7ovkfpEaNGnzwwQdPdL9u4j547Ngx/Pz8qFatGtOmTTMPcf80RowYQfny5QF4++23+emnn7h9+zaxsbHY2z/ZT1XSffxJRvWcOHEiw4YNIyYmhty5cxMSEkLhwoXN5SEhIVa/r83NzY0DBw5w/vx5ChYsiIODA4ZhkCdPHvz9/c2JZOL2jo2N5c8//8TV1ZWaNWvy+++/4+rqarHuiXx9fc2JQPPmzS1ORJN+f3v37iVfvnxUqFCBVatWkSlTpqcaHORhxzdruN+gN4+6XoGBgRw8eBBISHwbNWoEwLBhwyhUqBAvv/wyuXPnJjQ0lI0bNwLw3nvvmbtRFitWjMDAQCZPnszff//NmTNneOmll3jzzTdZtmwZGzZsYNCgQcTExLB582YA3n33XSCh5S2x9bdjx47mXgudO3fmr7/+4sCBA+YutIkcHR0ZMGAAGTNmNP+/f+utt5g1axY7d+40twgmHn8bNGjwVIPfJN2fErf10qVLuXbtGg4ODmTPnp3AwEBz9+/EJM3V1fW+9ztu3bqVS5cukS1bNjJnzkxAQAD58+fn6NGj5s8/6vf3ONswvd1/KWmTVbsgXrp0iTVr1hAcHEzJkiVp1qyZxUH76tWreHp68scff3DixAlrhhZJ0woUKGDx4+jq6goknFw9SGLXEuCez+xK2l0k0YsvvnjPk7O7JW0dmjhx4j27k5w6dcoiAXNwcLA4QQ0KCjJfmV68eDGLFy++5zLuTsCSJhKJ2wIwdy1JrNtLL71ksS6JrROJLl68CCTcI5d40nN37Ps5ffo0kPDdJCZfgPn5W7t37zZfEX8S2bNnp2/fvvTt25dLly6xa9cuvL29OXHiBNHR0Sxbtozhw4c/8fyQkLx++OGH+Pr6Mnr0aMLDw7l48eID7w96kMGDBzNo0CD++ecf+vTpg8lkwt3dnddff5127dpZfFeP637feVxc3BMnYElbqJJeZLiX+7XenTp1il9//ZW//vqL8+fPWyRy9zvpf1oRERHs3buX8ePHc/jwYYtEJTF+tWrVeP3119m0aRMLFy5k4cKFZMyYkapVq9K8eXNzApHU9evXza//+ecfi3t5ChUqRMeOHVm4cCFr165l7dq1ODo6UqFCBd55551kv+eP40mPbw9z94Ax9/Ko65X0eFeiRAnz6yxZstC9e3fz+yNHjpiPQ3fff5T0/enTp3nppZdo3rw5y5Yt4+rVqxw8eJA7d+5w+/ZtTCaTufth0uN40t4IiQzDSNaFNm/evMkec/H2228za9YswsLC2Lt3Ly+//LJ5dNanHYQm6f+lxG1tGAaHDh1i06ZN/P333xZdiB/lgkdMTAy+vr5s27aNv//+22L/TPz8o35/T7INRVKS1RKwv/76i48++ojIyEjztLVr1+Ll5YWdnR1eXl5MnTrVolxEEtzdevCoJzqPcmKaOIJeoicZrOFRl333gAmPsoygoKBk05KerN1rGYknyw87gXtY/Lvr/6ifTYz/KIns3dauXcv27du5ffs2c+fOJUOGDBQsWJA2bdrQokULXnvtNa5du2Zu5Xrc+ZPKlCkTBQsWpGDBguYr5v7+/nTr1o2VK1dajMr3KN58803KlSvHmjVr2LlzJ0ePHuXkyZOcPHmStWvXsnLlyiceNCPp/wFrDcWe9N6/ez1sOulJYuL9SUlNmTKF2bNn4+DgQMOGDWnfvj0mk+mp7kt7mNDQUFq1asXZs2fJmzcv77zzDhUrVmTNmjUWz/+zs7Nj+vTp7N27l/Xr17Nnzx4uX77M9u3b2b59Ox9//PE9T0SLFSvG2bNnOXfuHCtWrLAYjGbYsGG89dZbrFu3jj///JOzZ8/i4+ODj48Pe/bsYfLkyU+0Tk96fHuYxO+3UKFCD2yBfZT1SpqAP+i48qBjbtL9KfHYUK5cOV566SXOnDnD77//bm7BrFKlirm1yFrH8WLFivHyyy9z/Phx8+AghmHg5uZGzZo1HxrjQRK3tZOTk/newoEDB7Ju3ToyZsxI48aN6d69OwEBAcnu67qXuLg4OnfuzIEDB8iWLRuNGzemYsWKHDx4kGXLllnM+yjf35NsQ5GUZLUE7LvvviMiIoJMmTJRuHBh/Pz8OHDgABs3bmTLli2sX78ewzCwt7d/4hu1RZ5niT/oSU8Uko72t3nzZvM9AFeuXCE2NpaCBQsmSxIetTUh6bLHjRtnbl0KDQ3l8uXLvPjii8luer972W5ubmTOnJnQ0FB69uxJnz59gIQTnOPHj1O8ePHHTgIgoevhv//+i5+fn0UXtYkTJ3L69GkqV65M165dKVCgAKdOnaJp06YWg2kcPnyYF1988YHJaGKr4eXLl7l69Sp58+YFEq66Jz68M+mV8kcVEBBgvgdk165dFvdl2NnZmU/iEq8yP+7899OkSRPWrVvHtm3bOHfuHN999x2fffbZI9c7KiqKkydPcubMGZo3b06PHj2IiIhg5cqVjB49mvPnz7N//37zPUUpLSIigu3btwNQsmRJc1ejxJHVIOG7TNz/AgICkn1+/vz5QEK328R7BxO7n9nKhg0bzCe7S5YsMf8/vHtQjhs3bnDq1Clu3rxpftB0QEAAI0aMMLeO3p2AFSxYkCVLljBy5Eg2bdrE9OnTeeedd3B2diY4OJiTJ09y/vx5hg4dip2dHYGBgXzzzTesXLmS9evXM3r0aJs+SuBxHD161NzC/aB7mx51vZI+euPYsWPmVvmoqCjat29PoUKF+OCDD3B3d8fe3p7Y2Fh8fHwsWpYSu2yD5bGhadOmTJw4kW3btpm71jVr1sxcnvRYu3DhQqpXrw4k3BsZHBxM4cKFkx1b73ccf/vttzl+/Dhbt27l6tWrADRs2NBiv39c169fx9fXF0h4TImDgwMXLlxg3bp1AHz++efme+US/88klfQ3KPFZsD4+PubtNXXqVHPr4T///GPx2Uf9/h5nG96rPiLPmtUG4Th+/DgZMmRg1apVrFy5ku+++w7DMBg7dqw5+SpTpgy//PIL/fv3t1ZYkedGYrKT+IN04cIFatSoYe7OM2LECI4cOcJff/1Fjx49aNiwIW+++eYT3fsCmIc7h4QLLDt37uTkyZOMGjWKd999l4oVK1p0ObmfxHuNFi9ezMaNGzlz5gwTJ06kZcuW5iuej+v1118H4Nq1a4wePdp8dXnRokVs376da9euWcT+7bff+Pnnnzl79izz58+nZcuWVK5c2XwCcS9vv/02JpOJmJgY+vTpw8GDBzl69Cj9+/c3X0l91KHsk2rSpIn5ZGj48OGsXr2af//9l7///pv+/fubR4tMHHTlced/kC+++MLcbcnLy+uerWb3ExgYSOvWrRk2bBhDhgzh6NGjBAQEWHQbetKugtZw7do1AgICuHz5Mj4+PvTo0YObN28CWNznl7QL0rJly4iPj2fHjh3JBpmIiYkxdzX7888/8fPz488//2TKlCnmeWzRBTFpt7q1a9fy77//8sMPP5gHJUhsnVmxYgUfffQRgwcPZt68eVy4cIHr16+bW1judcL9yiuvkD17dvr164ednR3Xr19n0aJFQEJy37FjR0aOHMnXX3/NuXPnuHbtmrn7Y4YMGVLsRDUmJoaAgAACAgK4cOECv//+O/369QMSWteSPgbibo+6Xjly5DCPprd06VLWrVvHuXPnGDt2LIcOHTK39GTJksV8kWHFihUsWLCAs2fP8ssvv5gfv1GlShVefPFFcx3effddczfH27dv4+LiYtFFtGTJkuYLPl9//TW+vr4cPXqUgQMH8uabb1KzZs1HHvClSZMm2NnZcevWLXbv3m2e9qji4+PN2/rSpUvs2LGDbt26ERMTg8lkMt/zlnRk3K1bt3Lu3Dn++OMPFixYYJ6euK8mvVB38OBB8yMdEm3YsIHz58+zcuVK8xDxiZ991O/vcbbhveoj8qxZ7dcyJCSEbNmymZumE0/cAgMDcXBwoH///nTs2NF8o7qIPJ6XXnoJSPjhe/fdd2ndujWjRo2ib9++jB49mn379tGiRQvz/BkyZGDAgAFP9X9uwIABtG/fHn9/f7p27WpR1rZtW4urjvfTvXt3tmzZQlBQULJh3xs0aEClSpUeu17NmjVjzZo1HDhwgOXLl5tH44KEm6oTT7jbt2/P6tWruXDhgsXoawBly5a9530yiUqVKkWvXr2YPn06hw8fthiwABJaRRKvsj6O/PnzM3jwYMaMGcPNmzfvOZR9/fr1eeONN55o/gfJly8fvXv3Zvz48cTExDB+/HhmzZr1SPXOmzcvH3/8MbNmzWLv3r3J7rcrU6ZMig6ulPSZckm99957FiegtWrVImPGjISHh5uf/WUYBqVLlza3bEJCi2LlypXx9fXl77//Nj/3LanAwECLex6toXbt2kycOJGYmBimTp3K1KlTk8WEhPv7fvvtN/z8/O55j+bd/1+TKlasGO+88w6rV69m3rx5vP/++zRu3JhffvmFffv2me8pS6pt27ZP3L30aR0/fpy6desmm54hQwZGjhz5wAfHP856jRgxgnbt2hEWFpasdbhFixbmQYQ+//xzjh49ytWrVxk/frxF63quXLmSPQ81V65c1KpVyzxa6euvv26xLe3s7Bg0aBC9evUyD4WfVM+ePR+55TF37txUqVIFHx8fIOGCQ+IARI8iMDDwntsaoHfv3uYk9aWXXqJQoUJcvHiRP/74456jZAYGBpIrVy7zbxckbO86deowfvx43NzcCA4OZunSpcke6XD79m3i4+Mf6/t71G14r/okPuJE5FmxWjZ090hVSa8wTJ8+nc6dOyv5EnkKLVu2pH79+mTOnBk3Nzdy5swJJPyAfPvtt1SoUMF8hbZq1arMmzfvvielj6ps2bIsXboUDw8P3NzccHZ2pkSJEnzxxRcMGTLkkZZRoEABfv75Z9566y1y5MiBo6MjRYoUoV+/fk98T4m9vT3z5s2jW7du5pHi8uXLR7Nmzfjpp5/IlSsXkHAD/dKlS/nggw/InTs3Dg4O5M+fnw8//JAFCxY89PlZvXr1Ys6cOdSsWZOsWbPi7OxMuXLlmDx5MgMGDHiiukNCYujl5UX9+vXJnj079vb2uLq6UqFCBb744gu+++47i+Pl487/IB06dDAPwrF161bzsPSPol+/fkycOJEKFSrg5uaGg4MDBQsWpFOnTnh5eaVoC1giOzs7smbNStWqVZk0aRLjxo2zKM+dOzczZ86kdOnSODo6UrhwYb744guLgRYSTZkyhTfeeAM3NzeyZs1KhQoVmDt3rrk7Y2KrlDUVK1aM7777jtKlS+Ps7EyePHl46623mDBhAgDnz5/n0qVLZM2alUWLFtGlSxeKFCmCk5MTGTNmpHz58kyYMIGOHTs+ME6vXr1wcHAwP1DYwcGBWbNm0b9/f4oXL07GjBlxcnKiVKlSDB8+/JH/v9uavb09L7zwAo0aNWLp0qXmrm/38zjrVbp0aZYvX07Dhg1xdXXFxcWFEiVKMHToUIv7/nLnzs3q1av58MMPKVSoEA4ODrzwwgu8//77rFix4p4JYdJ6Ju1+mKhBgwYsWLCAGjVqkDlzZjJmzMgrr7zClClTHtjCdy9JLxY0btz4ie+5y5AhA9myZaN27drMmzePnj17msscHByYM2cOtWvXJkuWLLi5uVG9enW8vLzMx9XE/x8NGjTg3XffNXdJz5MnD9mzZ2fu3LlUqlSJjBkzkjNnTurXr8/cuXMBiIyMZP/+/Y/1/T3qNrxXfUSeNZPxpA9uuUtiH/vEPveJ09zc3Ni3b581QoiIiIjIA6xYsYJhw4YB8OOPP1K5cuUUrpGI3M2qlytDQ0OZMWOGxbTY2Nhk0yDh6puIiIiIPJ3o6GgCAwO5fv26eRTCfPnymbsMikjqYtUWsLtv0H3QUM16DpiIiIjI0wsMDEx2D+aXX37JBx98kEI1EpEHsVoLWJUqVay1KBERERF5RNmyZSN//vzcuHGDvHnz0qZNGyVfIqmY1VrARERERERE5MFsPmSVYRj4+vpy8+ZNSpYsSdGiRW0d8onFx8cTFhaGg4ODHswnIiIiIiKPzTAMYmJiyJQp0z1HKbZqArZ69Wq+++47Xn/9dQYOHMj169f56KOPLB5y16JFC7788stUOSR9WFgYfn5+KV0NERERERFJ40qUKEGWLFmSTbdaArZ582aGDBmCyWQyD77x1Vdfcfr0aQAyZcpEWFgYv/zyCyVKlKB9+/bWCm01Dg4OQMLGetjzgURERERERO4WHR2Nn5+fObe4m9USsMSnkzdo0ICWLVty48YNtmzZgslk4sMPP2TgwIH8+OOPfPXVV6xevTpVJmCJ3Q4dHR1xcnJK4dqIiIiIiEhadb9bmqzWD/DEiRM4OjoyceJEihYtyq5du4iPjwcwJ1tt2rTB2dmZ8+fPWyusiIiIiIhImmG1BCwyMpKMGTPi7OwMwO7duwEoUqQIefLkARKyQHt7ezTwooiIiIiIPI+s1gUxV65cXL16lYsXL5IlSxa2bduGyWSidu3a5nl2795NaGgoxYsXt1bYZyI+Pp6bN28SHBxMXFxcSldHUiFnZ2cKFChw376+IiIiIiJgxQSsTp06LFu2jDZt2mBvb09ERAQmk4nmzZsTFhbGt99+y88//4zJZMLDw8NaYZ+Jy5cvYzKZKFKkiIaol2QMw+DWrVtcvnw5VT9mQURERERSntW6IPbp04ciRYpw8+ZNAgICAPj4448pWbIkcXFxLF68mMjISIoVK0aXLl2sFfaZCAsLI3/+/Dg6Oir5kmRMJhM5cuQgMjIypasiIiIiIqmc1VrAsmfPzpo1a9i4cSPXr1+nSpUqlC9fHoCsWbNSvXp1atSoQceOHc33iaUlqfG5ZZJ6KDEXERERkUdh1QcxOzk58e67796zzMvLy5qhRERERERE0hyrN+v4+vpy9OhR8/t//vmHoUOH8vHHHzNlyhRu3bpl7ZApIjImNsWW6+Pjg7u7u/lfxYoV6dWr11Nt2+nTp+Pu7k5YWJjF9JUrV+Lu7o6fn98TL/tRY7u7u1OqVClq1KjBhAkTiI21zTZ+XGFhYbi7uzN9+vSUroqIiIiIpHFWawGLiIigW7du7N+/n86dO1OmTBm2bdtG7969iYuLwzAMdu3axZo1a1i+fDm5c+e2VugU4exgT54+862+3IBpHz3yvP369aNMmTKcPXuW6dOnM2zYMObMmWP1Oj0rs2bNIkOGDOzdu5f58+eTI0cOPvro0beHiIiIiDwf9u3bh7e3N61ataJ69eopXZ3HYrUWsNmzZ+Pj44NhGGTKlAmA8ePHExsbS7Zs2WjXrh158uTh2rVrfPfdd9YK+1wrWbIktWvXplOnTnTp0oXt27fj5+eXrNWqffv2NG/eHICTJ0/SvHlzXnnlFWrVqsWSJUueOH5oaChDhgyhYsWK1K5dmylTphAbG4unp6f58QN//PEH7u7u/PLLLwC89dZbfPbZZ/dcXrVq1ahbty5Dhgzh1VdfZd68eRiGQWBgID169KBixYo0adKEnTt3AjBkyBDefvtthg0bRpUqVejduzdr166lbt261K5dm7179wKwd+9eGjduTJkyZahfvz6///67xee/+OILypcvT4sWLbh8+TKQ8GDxZs2aUa1aNWbMmPHE20hERERErM/Ly4tDhw6lyducrJaA/f7775hMJiZNmkTPnj05evQo58+fx2QyMXLkSEaMGMHcuXMxDMP8kGaxnjJlygBw5syZB863atUqHB0dmTJlCsWLF2fq1KlPHHPs2LFs3LiRwYMH06FDB+bMmcMPP/yAh4cH169f5/Tp0/j4+AAJXVOvXbvG6dOnH+kxBGXKlCEoKIjAwEDGjh3LxYsX+eKLL6hUqRL9+/cnKCgIAD8/P7Jly0aLFi3YtGkTc+bMYdCgQURFRTF37lwAli1bRsGCBZk2bRpZsmRh1qxZ5jh+fn44ODjQv39/jhw5wk8//QTAoEGDCA4OZtSoUVy9evWJt5GIiIiIWF94eLjF37TEal0Qr1y5QpYsWWjSpAkAu3btAsDBwYF69eoBULx4cVxdXbl586a1wspd4uPjk00zDMP8+tNPP2XLli3s27ePixcvcufOnSeO9fvvv9O4cWPef/99AHbu3MmmTZvo3Lkzrq6u/Pnnn+zfv5+SJUty4MABdu3ahYODA3Xq1HnkGHFxcezevZvg4GAGDx5snp54n6GLiwsDBw7k5MmTLFiwgDZt2tCkSRN+/PFH87qNHTuWzZs3s337dgIDA3F0dDQvx8nJiREjRmAymZg2bRpBQUGEhITg5+dH//79eeONNyhXrhwbNmx44u0kIiIiIpLIai1g9vb2xMTEmN/v2LEDk8lEhQoVcHJyAiA6OpqwsDCyZs1qrbDyn7NnzwJQtGhR85DocXFxABbPp+rfvz8zZ86kWrVqvPHGG08V02QyWQy/bhgGJpMJe3t7ateuzYYNG/Dz86N3795cvnyZX375hapVq5I5c+aHLvvMmTNkyZKFnDlzEhsbS4MGDVi+fDmLFi1iyZIllC5dGsC8byU+JsDFxQWADBkymBPPdu3a8csvv9CgQQNeffVVizguLi7mdbC3tzevA/x/+2mIeRERERGxFqu1gBUtWpTjx4+zZMkSsmfPzj///IPJZDJ3N4uPj+frr78mNjaWokWLWivsc+3kyZM4OTnh7+/PvHnzKF++PKVLl+bGjRsAbNiwgbNnz3Ly5ElKlCgBJNywWLBgQaKioti+fTvw/0TjQbZv386JEyfM7xs2bEi9evXYuHEjFStW5M6dO/j6+jJkyBAAPDw8GDBgAFmyZMHDw4MCBQrw999/8/nnn983xv79+3FwcODQoUPs2LGDjz76CDs7O2rUqMGBAwe4ePEif/zxBzt37mTLli2PtI1u377NiRMnePXVVwkODmbv3r0PfaZb5syZKV26NN7e3hQtWpSNGzc+UiwRERERkYexWgLWsmVLRo0axdixY83T3NzcaN68Obdu3aJJkybcvn0bk8lEu3btrBX2ufbtt98CkClTJmrWrMmIESMAqFmzJm+++SaLFy+mWrVq1KpVi+vXrwPQp08fpk+fztixY6lcuTKnT5/m3LlzD401adIki/dbtmzhiy++AMDT05OMGTPSo0cPOnToAEDt2rVxcHCgcuXK2NnZUa1aNS5fvvzA+7+6deuGyWQiR44cdOzYkT59+gAwevRoRowYwejRo8mSJQtjxowhZ86cj7SNXF1d+fDDD1m2bBnnzp2jVKlS7Nmz56FdLydMmMCgQYP48ssvee+998iSJcsjxRMREREReRCTkfQGoac0depUfvjhByIjIylSpAgTJkygbNmyREVFUa5cOezs7OjRowe9evWyVkirioqK4ujRo5QpU8bctQ0SRsQrVaqUxbyRMbE4O1j1OdY2Xa7Y3r32ExERERGxvg4dOuDv70/+/PlZtGhRSlfHwv1yikRWPdPv27cvPXr04M6dO+TIkcM83cnJifHjx1OtWjXy5MljzZApxlZJkpIvEREREZH0y+pn+w4ODhbJV6J3333X2qFERERERETSFKuNgigiIiIiIiIPliYSsIiICN58802LVrSYmBjGjBlDtWrVqFu3rsVTsM+dO0fr1q2pUKECLVu25OTJkylQaxEREREREUupPgE7cuQIbdu2NT/nKtHSpUtZvHgxXbp0oU6dOnh6enLgwAEg4WHD165dY8yYMYSGhtK7d2+sONaIiIiIiIjIE0mRBCw8PPyR523RogX58uVLdl/Zli1byJEjB127dqV3794AbN26latXr3L8+HHeeOMNmjRpQtOmTbl48SKnT5+26jqIiIiIiIg8LpsMuTdy5EhGjhyZ7IG3sbGx/PTTT8ydO5fdu3c/0rJWrlxJ6dKlkz0/KiAggOzZswOY/169epWrV69aTEtalvgw4oc5evSoxXt7e3vCwsIspjk72pHBweWRlvc44mIiiIyOt/pyxfaio6M5ePBgSldDREREJN2Liooy/01r5182ScCWL19OQEAAU6ZMIWPGjACsWbOG6dOn4+/v/1jLKl269H3LTCbTfd8nvk7senj3vA9yr+eAZcqUKdl8u8cXfeRlPqpag/8lk8OD5/Hx8TE/8BgSHsT86quv8uWXX95zBMpHMX36dGbMmMFff/1lsa73mt68eXMyZcrE4sWLGTJkCNu2bcPHx+eBy2/fvj1hYWGsXLnygfO5u7ubXzs6OlKqVClGjBhB2bJln2i9rG38+PEsWLCAU6dOJStzdHSkXLlyKVArERERkedL4rm6k5MTlSpVSuHaWEp8Dtj92CQBy5IlCzt37qRdu3Z8+OGHzJ07l9OnT2MYBnnz5qV79+5PHSNXrlycO3cOgMDAQADy5MlD7ty5LaYFBQWZy9Kbfv36UaZMGc6ePcv06dMZNmwYc+bMeaZ16NKlC++9955Vl9m4cWNatWrFrVu3mDlzJj169GDjxo1kzpzZqnFERERERJ41m9wD9vPPP1O0aFGOHz/OwIED8fPzI0eOHIwYMYLff/+dVq1aPXWMevXqcfPmTebPn8+MGTMA8PDwIH/+/BQvXpz169ezfv161qxZQ6FChShevPhTx0xtSpYsSe3atenUqRNdunRh+/bt+Pn5sXLlStzd3fHz8wMSWp+aN28OwMmTJ2nevDmvvPIKtWrVYsmSJY8UKzo6mqioKHNzb6Lvv/+eXr16AXD79m169OhBhQoV6NatG23btqV9+/bmeWNiYhgyZAiVK1fmo48+IiQk5J6x8uXLR82aNXnnnXcYO3YsN27cYPXq1UBCS6qHhwdVq1Zl6NChhIeHc/nyZdzd3Rk/fjyNGjWiTp06/Prrr/Ts2ZMKFSrQt29f4uLiiImJYejQoVSsWJHy5cvTvXt3IiIizJ+fMGECjRo1omrVqsyePRtIaEEdP348VatWpXnz5ly4cOHRvyARERERkbvYJAErUqQIP//8M/Xr18cwDEwmE8OGDaNdu3Y4OjpaJUaHDh3o0KED8+bNY9u2bQwdOpQqVaoAMG3aNPLly8fw4cPJmDEj06ZNe6wuiGlRmTJlADhz5swD51u1ahWOjo5MmTKF4sWLM3Xq1EdafvXq1Slbtixly5bl2LFj95xnxowZ7Nixg0GDBvHyyy/j6+trUe7n50fhwoVp3749u3fv5tdff31o3FdeecW8XmfPnmXo0KG8+eabDBkyhD179li0+G3ZsoU+ffpgMpn49NNPKVmyJE2aNGHjxo38888//P333/j4+DBw4EB69OjB1q1b+fPPP82f37hxI7169aJo0aJMmzaN0NBQNm3axIIFC3jnnXfo0KHDQ7taioiIiIg8iNW6ICa9JymRYRhkyJCB+Ph4Bg4cyNKlSzGZTJhMJhYuXPhYy9+6davFewcHB4YPH87w4cOTzfviiy8+cstOehMfn3wAj6RD8H/66ads2bKFffv2cfHiRe7cufNIy124cCHOzs4ADB069J7z+Pr6UqVKFVq3bg1gbrVKVKRIEbp3786dO3eYOXMmt27deqTYkLBee/fuJS4ujnnz5pmn79u3j5YtWwLQsmVLmjRpwoYNG4iKiqJ3797s3buXn3/+mZCQEOrVq8fUqVPZuXOnOTlM2gr3/vvv8/bbb3Pr1i3++ecfbt++zcGDB3FycmLYsGHY2dnh4+Pz0PvYRERERETux2oJ2P79+x9YHhcXZ35OV3pvjUoJic9JK1q0qLnrYVxcHACRkZHm+fr378/Fixfp06cPzs7OFsnMg7zyyivmQThcXO49+mNcXJxFsnf395z4+QwZMgA80rPZElv0ihYtSmxsLACzZ88mW7ZshISEkDNnTvO8ifWys7MzD/6SOBKnYRj88ccf9OvXj4EDB9K9e3f27NljUYfE+tnb25s/YzKZMAyD+Ph47OzstO+KiIiIyFOxWgKWeB+QPDsnT57EyckJf39/5s2bR/ny5SldujQ3btwAYMOGDZw9e5aTJ0+ah+Dft28fBQsWJCoqiu3btwP/T9SeVrVq1fjpp59YtmwZAQEBXL58mXz58j32cq5cucKePXsICQlh7ty5ZMmShbfffpubN2+a1ytx1MdWrVpZ3Gf2ID4+PsTHx5MpUybWrVsHPHzdq1evjpeXF+PGjaNs2bJs3LjxsddHRERERCSRErAnFB8bRa3B/9pkuXb2Tg+fEfj222+BhJabmjVrMmLECABq1qzJm2++yeLFi6lWrRq1atXi+vXrAPTp04fp06czduxYKleuzOnTp82jST6tvn37cvnyZSZOnEjDhg0pUqQIDg4PGVP/HjZu3MjGjRtxdHSkdOnSzJ07l5w5c5IzZ07Gjx/PzJkz2bRpE9WrV6dnz56P3I3y/fffZ8+ePeZ1z5EjB+fOnaNGjRr3/Uz9+vXp1q0bS5cu5e+//6Zx48asWLHisddJRERERATAZDxKP7AndOvWLXLkyEFcXBy//PILQUFBvP7667z44ou2CvlUEsfsv9dzwEqVKpWCNUsb5s2bx9GjR2nYsCEAn3/+Oe+99545MUzvtJ+IiIiIPBsdOnTA39+f/Pnzs2jRopSujoX75RSJbPIcsKtXr/Lxxx9Tvnx5vvrqKwYPHsxvv/0GwJw5c1i4cGGqebCuWE+dOnXYsmULn3/+OXFxcVStWpVu3bqldLVERERERFINmyRg33zzDadPn8bNzY0bN26wfv16MmfOTLFixfjnn3+YMWMGc+fOtUVoSUHu7u4sW7YspashIiIiIpJq2eQ5YPv378fe3p6vv/6aP//8k/j4eNq1a8eiRYtwcnLi+PHjtghrUzbsqSnpgPYPEREREXkUNknA7ty5g6urK/nz58fHxweTyUSVKlVwdHTE2dmZsLAwW4S1GQcHByIiIlK6GpKKxcTEmIevFxERERG5H5skYLlz5yYoKIjNmzezbds2nJ2dqVSpEqtWreL27dsUKFDAFmFtJleuXPj7+xMeHq6WDkkmPj6ea9eu4erqmtJVEREREZFUziaX7N944w3mzp1L7969MQyDZs2aER8fz7BhwzCZTLz33nu2CGszWbNmBRKeTxUTE5PCtZHUKFOmTBYPhRYRERERuRebJGC9evUiMjKSffv2UbZsWUaMGIGzszOFChWiXr16dOzY0RZhbSpr1qzmRExERERERORJ2CQBc3R0ZNiwYcmmr169GhcXF1uEFBERERERSfVsNmrA33//zaFDhwgPDyc+Ph5IGCkuNDSUffv2sWbNGluFFhERERERSZVskoAtX76cUaNG3bPMMAxMJpMtwoqIiIiIiKRqNhkFcfHixQCUL1+eF154gQIFCvDmm2+SI0cOTCYTn332mS3CioiIiIiIpGo2ScAuX76Mi4sLS5YsoUWLFmTMmJFJkyaxePFiTCYTPj4+tggrIiIiIiKSqtkkAXNwcDA/L6tSpUqcPn2a27dvU6RIETJlysShQ4dsEVZERERERCRVs0kC5u7uTmRkJEOHDqV8+fLY2dnRr18/evfuTUhICHZ2NgkrIiIiIiKSqtkkE+rXrx8ZM2YkICCATJky0bhxY/bu3cvmzZsBeP31120RVkREREREJFWz2iiIic/4atSoEZUrV2b9+vVcuHABgNGjR5MrVy7OnDlD+fLl6dKli7XCioiIiIiIpBlWS8CGDBlC3rx5adSoEQC5c+cmd+7cAGTMmJFBgwZZK5SIiIiIPGf27duHt7c3rVq1onr16ildHZEnZtXngCUOvCEiIiIiYk1eXl6cPn2a8PBwJWCSpmk0DBERERFJ9cLDwy3+yqPbt28fAwYMYN++fSldFcHKLWA3b96kQYMGD53PZDKZB+QQERERERHbUeth6mLVBCwuLg5/f/+HzmcymawS76effmLevHkEBgZSqlQpRo8eTdGiRRk/fjzr1q3D2dmZzp0706lTJ6vEExERERFJa9R6mLpYNQHLmjUrQ4YMseYi7+vSpUuMHj2aJk2aUK9ePaZMmcKoUaNo3Lgxixcv5rPPPuPixYt4enpSunRpqlSp8kzqJSIiIiIicj9WTcBcXFxo1qyZNRd5X3FxcRiGgbu7O5UrVyZHjhw4ODiwZcsWcuTIQdeuXbl+/Tre3t5s3bpVCZiIiIiIiKQ4qyZgz1KRIkXo27cvkyZNYtKkSWTOnJmffvqJPn36kD17dgDz36tXrz7Wso8ePWr1+oqIiIjIk4uKijL/PXjwYArXJm1Jj9suLa+T1RKwKlWqkCNHDmst7qHOnTvHvHnzeOedd3jnnXcYM2YM/fv3JzY2FkdHR4t5H/eeszJlyuDk5GTN6oqIiIjIU0g8N3NycqJSpUopXJu0JT1uu9S8TlFRUQ9s0LFaArZ48WJrLeqRbNu2jfDwcFq3bk3FihVp0KAB8+fPp2rVqpw7dw6AwMBAAPLkyfNM6yYiIiIiInIvabYLYqlSpQD4/vvvadq0KRs3biRHjhzUrVuX/fv3M3/+fC5cuACAh4dHSlZVREREREQESMMJ2KuvvsoXX3zBggULGDhwICVKlGDEiBG8/PLLXLt2jXnz5uHg4MDQoUM1AIeIiIiIiKQKaTYBA2jbti1t27ZNNn348OEMHz48BWokIiIiIiJyf3YpXQEREREREZHnhc1awMLCwlixYgV//fUXISEhuLm5UbFiRZo1a0bGjBltFVZERERERCTVskkCdunSJTp27MjVq1cxDMM8ff369Xh5eeHl5UX+/PltEVpERERERCTVskkXxFGjRnHlyhWcnZ1p2rQpH3/8Mc2aNSNTpkxcvnyZL7/80hZhRUREREREUjWbtID5+vpiZ2fHsmXLcHd3N0/v2rUrTZo0Yf/+/bYIKyIiIiIikqrZpAUsT548uLi4WCRfAEWLFsXFxYXcuXPbIqyIiIiIiEiqZpMErF+/foSHhzNz5kzi4uIAiIyMZMKECURHRzN06FBbhBUREREREUnVbNIFceXKlWTPnp3p06czZ84csmbNSlBQEHFxcTg6OvLVV1/x1VdfAWAymdi8ebMtqiEiIiIiIpKq2CQB27Vrl/l1VFQUN27csHjv7+9vfm8ymWxRBRERERERkVTHJgmYp6enLRYrIiIiIiKSptkkAWvWrJktFisiIiIiIpKm2SQBA4iOjmbx4sVs27aNmzdv8sILL9CgQQPatGmDo6OjrcKKiIiIiEgKiY+Nws7eKaWrYVXWXiebJGChoaF07NiR48ePYxgGAOfPn8fX15cNGzbwww8/kDFjRluEFhERERGRFGJn78Tu8UVtHicyqADgSGTQvzaPV2vwv1Zdnk2GoZ86dSrHjh0ja9asdOnShVGjRtGlSxeyZs3K4cOHmTZtmi3CioiIiIiIpGo2aQH7/fffMZlMLFy4kJIlS5qnv/XWWzRt2pT169czZMgQW4QWERERERFJtWzSAhYcHEymTJkski+AkiVLkilTJm7fvm2LsCIiIiIiIqmaTRKwwoULExYWxtq1ay2mr127lrCwMAoVKmSLsCIiIiIiIqmaTbogtmjRAk9PTwYPHsyPP/5IgQIF8Pf359ChQ5hMJlq0aGGLsCIiIiIiIqmaTRKwjh074ufnx4oVKzh06BCHDh0yl7311lt07NjRFmFFRERERERSNZs9B2zs2LG8//77bNu2jVu3bpEzZ05q1apFxYoVbRVSREREREQkVbNJArZ69WpcXFxo1KgRZcuWNU+Pi4tj8eLFODs707JlS1uEFhERERERSbVskoANGTKEvHnz0qhRI4vpdnZ2TJ06FQcHByVgIiIiIiLy3LFKAmYYBl26dOH8+fPmaTdu3KBBgwYW80VERBAaGkrWrFmtEVZERERERCRNsUoCZjKZ6NSpE127djW/j4uLw9/f/57zN27c2BphRURERERE0hSrdUGsXbs206dPJyQkhGHDhuHq6sqQIUPM5SaTiQwZMpA/f34qVKhgrbAiIiIiIiJphlXvAWvYsCGQkGy5uLjYvKXr1KlTfPXVVxw7dozChQszduxYSpQowfjx41m3bh3Ozs507tyZTp062bQeIiIiIiIij8LO2gu8evUqlStXNidfly5dYsaMGXz55Zf8/PPPREVFWSVOaGgoHTp0ICYmhjFjxhASEsKQIUNYunQpixcvpkuXLtSpUwdPT08OHDhglZgiIiIiIiJPw2otYHFxcYwYMYLVq1fz4YcfMnDgQP755x8+/PBDIiIizPMtWbKExYsXP/VAHDt37iQ4OJgePXpQp04dypUrh52dHUOHDiVHjhx07dqV69ev4+3tzdatW6lSpcrTrqKIiIiIiMhTsVoC5uXlxapVqyymjR49mvDwcFxcXKhWrRq+vr74+fkxa9YsBg8e/FTxLl26BIC3tzd9+/YlR44cfPHFFwQEBJA9e3YA89+rV68+1rKPHj36VHUTEREREetK7EUVFRXFwYMHU7g2acuz3HaVKlWy6fJTijW3m9USsDVr1mAymRgwYACdOnXizJkzHD9+HJPJxPDhw2nRogW+vr60a9eOrVu3PnUCZhiG+e/MmTP55ptv6NevH7ly5cJkMlnMe/f7hylTpgxOTk5PVT8RERERsZ7EczMnJ6d0e5JvK9p2T+9xtltUVNQDG3Ssdg/YhQsXcHFxoWvXrjg4OLBr1y4AMmTIYL4frHLlymTJkoVr1649dbx8+fIB0LRpU1599VUaN25MeHg4uXLlIjAwEMD8N0+ePE8dT0RERERE5GlZrQUscZj5RDt37gQSWpMyZ84MQHx8PFFRUWTMmPGp49WpU4csWbLwww8/YGdnx++//07WrFmpXr06+/fvZ/78+Vy4cAEADw+Pp44nIra1b98+vL29adWqFdWrV0/p6oiIiIjYhNUSsIIFC3LmzBm2bt1Kzpw58fHxwWQyUa9ePfM88+bNIzo6mlKlSj11PDc3NxYsWMCYMWP47LPPKFq0KN999x0VKlQgODiYefPm4eDgwNChQzUAh0ga4OXlxenTpwkPD1cCJiIiIumW1RKwt99+m8mTJ9OzZ08g4d4sFxcX3nvvPYKCgujUqRN+fn6YTCZatGhhlZhly5bF29s72fThw4czfPhwq8QQkWcjPDzc4q+IiIhIemS1e8A6d+7MO++8AyQkX1mzZmXSpEm88MILODs7c+rUKQzDoGnTprz33nvWCisiIiIiIpJmWK0FzMHBgQkTJtC/f39u3LhBiRIlcHZ2BsDFxYW+fftSvXp1KlSoYK2QIiIiIiIiaYrVErBEefPmJW/evMmmd+/e3dqhRERERERE0hSrdUEUERERERGRB1MCJiIiIiIi8owoARMREREREXlGlICJiIiIiKSQyJjYlK6CPGNWH4QjqYMHD+Lj48ONGzcYOXIkBw4coGLFimTIkMGWYUXSvX379uHt7U2rVq300GIREZE0zNnBnjx95ts0xks37uAEnLtxx+axAqZ9ZNPlpwc2ScAiIiLo3bs3f/75p3nayJEj6d+/Py+88ALz588ne/bstggt8lzw8vLi9OnThIeHKwETERERSUNs0gVx8uTJ7N69mxdffNH8LLCIiAhiYmI4efIk33zzjS3Cijw3wsPDLf6KiIiISNpgkwRs48aNODg4sHTpUrJmzQokPIx57dq12Nvbs3PnTluEFRERERERSdVskoAFBweTMWNGc/KVKEeOHNjb2+uqvYiIiIiIPJdskoAVL16cO3fusHDhQuLi4gA4efIkQ4YMISIighIlStgirIiIiIiISKpmkwRswIAB2NnZ8fXXX3Pr1i0AmjVrxq+//orJZKJbt262CCsiIiIiKSA+Niqlq2BV6W19JHWxySiItWrV4vvvv2fKlCkcPXqU+Ph47OzsKFeuHD179qR27dq2CCsiIiIiKcDO3ond44vaNEZkUAHAkcigf20eq9bgf226fHm+2ew5YDVq1KBGjRpERkZy584dsmfPjr29TR87JiIiIiIikqpZLSM6cODAA8svXLhg8b5KlSrWCi0iIiIiIpImWC0Ba9++PSaT6ZHmNZlMHD9+3FqhRURERERE0gSr9gk0DMOq84mIiIiIiKQnVkvATp48aa1FiYiIiIiIpEs2HRUjPj6ef//9lzt37uDm5kaRIkUeuZuiiIiIiIhIemOzBGzRokXMmjWL4OBg87QcOXLQo0cP2rRpY6uwIiIiIgLs27cPb29vWrVqRfXq1VO6OiLyH5skYF5eXowfPz7ZvV43b97kq6++Ii4ujvbt29sitIiIiIiQcD52+vRpwsPDlYCJpCJ2tljoDz/8AECzZs3YvHkzhw8fZsuWLbz//vsYhsH8+fNtEVZERERE/hMeHm7xV0RSB5skYHfu3MHFxYVx48ZRoEABHB0dyZ8/P6NGjSJjxozcvn3barGWLl2Ku7s7K1euJCYmhjFjxlCtWjXq1q2Ll5eX1eKIiIiIiIg8LZskYPXr1ycqKopr165ZTL948SIRERG8/vrrVolz8uRJPD09ze+XLl3K4sWL6dKlC3Xq1MHT0/OhD4gWERERERF5VmxyD9i7777L/v37adOmDS1atCBnzpz4+/uzYsUKMmbMSNmyZVm9erV5/qZNmz52jNDQUPr27UuRIkU4deoUAFu2bCFHjhx07dqV69ev4+3tzdatW6lSpYqV1kxEREREROTJ2SQB++STTzCZTBiGwfTp083TDcPAZDIxZswY8zSTyfRECdjIkSNxdHTk008/5eOPPwYgICCA7NmzA5j/Xr169bGXffTo0cf+jMizFBUVZf578ODBFK6NdaTHdRIRSUnP8rhaqVIlmy4/JTyr36L0uO3SI2vuDzZJwPLly2eLxZotX76cP/74g6VLlxIUFARAbGysOcFL6kmeO1amTBmcnJysUlcRW0jcP52cnNLNgTs9rpOISErScfXpaJtJUo+zP0RFRT2wQccmCdjWrVttsVizX3/9laioKJo3b26e9vnnnwOQM2dOAAIDAwHIkyePTesiIiIitqNnWYlIemOzBzHb0siRIwkNDQXg2LFjjB49mu7du5M5c2a++eYb5s+fz4ULFwDw8PBIyaqKiIjIU9CzrEQkvbFJAnbt2jW++OILDh48SFhYWLJyk8nE8ePHn3j5L730kvl1Yv/mQoUK8fbbb3Pt2jXmzZuHg4MDQ4cO1QAcIiIiaZieZSUi6Y1NErChQ4eyZ88eWyw6mWrVqplHQQQYPnw4w4cPfyaxRUREREREHodNErC//voLk8lEr169KFeuHI6OjrYIIyIiIiIikqbYJAHLnTs3gYGB9OzZ0xaLFxERERERSZPsbLHQ/v37ExYWxvTp07l16xaGYdgijIiIiIiISJpikxawChUqULBgQWbOnMnMmTOTlT/tIBwiIiIiIiJpkU0SsIEDB3Lx4kW1fImIiIiIiCRhkwTs0KFDAPTu3Zvy5cvj4OBgizAiIiKShB5aLCLPC8cMhsXftMQmCVihQoUICAjQIBwiIiLPkB5aLCLPC4+XAvnzvBs1iwSndFUem00G4Rg2bBiRkZHMnj2boKAgdUUUERF5BvTQYhF5XpR4IYLOVa5S4oWIlK7KY7NJC9i4ceNwcXFh6tSpTJ06NVm5BuEQEREREZHnkU0SsNOnT9tisSIiIiIiImmaTRKwRYsW2WKxIiIiIiIiaZpNErCqVavaYrEiIiIiIiJpmtUSsKFDh+Lm5sbgwYMZOnToA+c1mUyMGzfOWqFFRERERETSBKslYKtWrSJPnjwMHjyYVatWYTKZko1+mDhNCZiIiIiIiDyPrJaANW3aFDc3N/Nrk8lkrUWLiMh96MG7IiIiaYvVErCvv/76nq/vJT4+3lphRUSea3rwroiISNpikwcxN2jQgNatWyebHhcXR+3atWnWrJktwoqIPHf04F0REZG0xSotYIZhsG7dOnPLlr+/P6GhoaxevdpivtDQUIKCgrhz5441woqIiIiIiKQpVknATCYThw4d4qeffjK/v3Pnzj1HQzQMgyJFilgjrIiIiIiISJpitXvA+vXrx/79+wkLC+PKlSvY29uTK1cuc7nJZMLe3p78+fPTq1cva4UVERERERFJM6yWgGXJkoV169YB4OHhQa5cuVi2bJm1Fi8iIiIiIpLmWS0BS2rr1q0W72NiYggJCSF79uy2CCciIiIiIpImWHUUxLNnzzJ8+HBzy1d0dDRffvkllSpVombNmtSpU8fcSiYiIiIiIvK8sVoL2MmTJ2ndujWRkZG4uroC8O2337J06VLzPNevX2fQoEG4urpSp04da4UWEREREZH7iLezt/grKctqLWAzZ84kIiKCAgUKUK1aNcLDw1m6dCkmk4k6deqwYsUK3n33XQzDYOHChU8d74cffqB+/fqUL1+e1q1bc/LkSWJiYhgzZgzVqlWjbt26eHl5Pf2KiTzn4mOjUroKVpce10lEROR+rucqS1jGXFzPVTalqyJYsQXs4MGDZMiQgSVLlpA7d262bNlCREQEJpOJ/v37U6pUKUaOHMlvv/3GsWPHnirW7t27+frrr2nZsiW1a9dm7Nix9O7dm/bt27N48WI+++wzLl68iKenJ6VLl6ZKlSpWWkuRh4uMicXZIf1cYbKzd2L3+KI2jxMZVABwJDLoX5vHqzX4X5suX0REJDUJzZKf0Cz5U7oa8h+rnSXevn0bV1dXcufODSQkSQA5cuSgVKlSAGTMmJHMmTMTERHxVLGyZs1K7969adu2LdmyZWPt2rVs376dLVu2kCNHDrp27cr169fx9vZm69atSsDkmXJ2sCdPn/k2jfHSjTs4Aedu3LF5rIBpH9l0+SIiIiLPE6slYFmzZuXOnTuEhobi4uLCli1bMJlMvPrqq+Z5Lly4QHBwMIULF36qWGXLlqVs2YQmVF9fX3bs2EHNmjW5cOGCeaTFxL9Xr159qlgiIiIiIiLWYrUErEKFCmzdupVevXrh4uLC9evXMZlMNGnShLi4OLZt28akSZMwmUyUL1/eKjG3b99Ov379cHNz44svvuCjjz7CZDJZzHP3+0dx9OhRq9RPnk+VKlVK6SrIIzh48GBKV8EqoqKizH/TyzrJk0uP+0N6XKdn5Vluu/T42/es9rf0uO3SI2vuD1ZLwHr16sWePXvYt2+fedqrr75K3bp1uXXrFr169QLAxcWFHj16PHW89evXM3DgQAoUKMD3339PgQIFyJUrF+fOnQMgMDAQgDx58jz2ssuUKYOTk9NT11EebN++fXh7e9OqVSuqV6+e0tWR50x6+cFLPFY5OTmlm3WSJ5ce94f0uE7Pirbd09E2k6QeZ3+Iiop6YIOO1RKwUqVK4e3tjZeXF9evX6dKlSp06tQJSOgO6OzsTKVKlRg2bNhTd0E8efIkgwYNwt7enj59+nDp0iUuXbpEvXr12L9/P/Pnz+fChQsAeHh4PO2qiY14eXlx+vRpwsPDlYCJiIiIyHPBqkO1FS9enLFjxyabbjKZ2L9/P46OjlaJs3DhQmJiYoiJiWHAgAHm6Xv37iUgIIB58+bh4ODA0KFDNQBHKhYeHm7xV0REREQkvXtmY2VbK/kC8PT0xNPT855lw4cPZ/jw4VaLJSIiIiIiYi1WexCziIiIiIiIPJgSMBERERERkWdECZiIiIjIMxQZE5vSVRCRFPRM7gEbP348t2/fZty4cc8inIiIiEiq5exgT54+820e56Ubd3ACzt24Y/N4AdM+sunyRdKTZ9ICtn79elatWvUsQomIiIiIiKRa6oIoIiIiIiLyjCgBExEREREReUaeSQJWrlw5Kleu/CxCpVv79u1jwIAB7Nu3L6WrIiIiQnxsVEpXwerS4zqJSOrzTAbhmDZt2rMIk655eXlx+vRpwsPDqV69ekpXR0TEZvbt24e3tzetWrXS8S4Vs7N3Yvf4ojaPExlUAHAkMuhfm8erNfhfmy5fRASeUQImTy88PNzir4hIeqULTiIikp7pHjAREUlVdMFJRO7FMYNh8VckrVICJiIiIiKpnsdLgRTJFoHHS4EpXRWRp6IuiCIiIs9AZEwszg762RV5UiVeiKDECxEpXQ2Rp2a1X4IZM2aQOXNmOnXqZK1FioiIpBvODvbk6TPfpjFeunEHJ+DcjTs2jxUw7SObLl9EJL2yWhfEGTNm4OXlZa3FiYiIiIiIpDu6B0xEREREROQZUQImIiIiIiLyjFj1buBr165RqlSph85nMpk4fvy4NUOLiIiIiIikelYfjskw9GwGERERERGRe7FqApYtWza+/fZbay5SREREREQk3bBqAubo6EjVqlWtuUgRkTQrPT73KT2uk4iIyLOkX1ERERtJb899Aj37SURE5GlZLQFr2rQpbm5u1lqciIiIiIhIumO1BOzrr79+pPlu3LjBN998w4QJE6wVWkREREREJE2w6nPA5s6di4eHBxUrVqRdu3YcPnzYXBYfH8+CBQto3Lgx69ats2ZYERERERGRNMFqCdi8efOYPHkyV65cITw8HF9fX7p27cr169e5dOkSLVq04JtvviEsLAx7e9veerZ161YaNWpEpUqV6N27N0FBQTaNJyIiIiIi8iisloCtW7cOk8mEh4cHw4cPp0yZMty5cwcvLy/atWvHiRMnMAyDcuXKsXLlSmuFTebmzZv069ePAgUKMGLECHbs2KHujiIiIiIikipYrSnK398fZ2dnpk2bhr29PR4eHjRo0IAffvgBwzDImDEj/fv3p127dphMJmuFTWb37t1ERUXRoUMH6taty6+//srWrVsfaxnVq1fn+vXrDBgwgE8//dSi7Msvv2Tu3LkAfP7553Tr1s2ifNCgQfz4448AjB8/nnbt2lmU9+zZk9WrVwMwY8YMmjVrZlHesWNHNm/eDMAPP/zA66+/blF+8OBB8ufPD8DPP//Mq6++alHeuHFjjhw5AsCGDRsoW7asRXmtWrX4999/Adi5cyfFihWzKK9YsSLXrl0zx8qTJ49FeYkSJQgLCwPg1KlTZM6c2aI8sW6QsE8kFRoairu7OwCZMmWievXqFuUBAQFUqlQJgNy5c/PXX39ZlJ89e5Y6deoAULRoUXbv3m1RfvjwYd544w0AXnnlFTZu3GhRvmfPHlq2bAlAjRo1+OWXXyzKN23aROfOnQF47bXXWLhwoUX5qlWr6NWrF5Aw6Mx3331nUb5kyRIGDx4MgKlIJYxK71qUm/z+xO7I7wDEF38Vo2xjy/LjW7E7sT2hvFQ9jJc9LMsPb8Tu9B4AbuctSC7XTJblB9dgd/5gwucrvIPxYmXL8v0/Y3cpYd+Ir9ICo5DlvmH35xJMAX4AxNVoA/lKWpR/uSKG4/4JD1r/ork9pQtYXr8ZsjSGf28klHt+YM+LuSzL+y2K5mpwwusp7R3Il83yOLD/yAViYuIAaFfegeyZLcs7zoomMibhtVc3B1wcLcvfnxZtfr28j6NFWUS0QafZCR92doCzgy2Kbb7vceNfMuz8AQAjZxHi635oWX7lJBn2/pRQnqcE8TUtjxumi4exO5Cwv8YXfAWjakuL8uDgYAICTpLh8AHibbzvzX45xubHvbu1aNGCvXv3Amn/uEfju3a+iDtkWD8RAMM5C/FNBlqWh9wkw6ZpCeWZcxDfqK9ledAVMmydnVDulhcKFbAst/G+t/loHPO2Jvy/bVDajo8bWJ5WrPsrjiW7E8qbVLCjQ23L8p/3xfLL/ngAWlS1o2V1y/JFu2L58+9zABTJn527zd0Sy5ZjCZ/v6pGB18pksCiftjGWP/0Syns3ykAtd8vy8Wtj+Ot8wnFr0Fv21Lpr+bbe9+x++wZTZAgAcW9+Bi5ZLcvXjMEUm3Bsi3tnODg4WZRnWPGF+XXce6MtKx8Txb+HDwBgsrOD4m9bllt738NyhNRjl+MZvTIWgJfzmxj5noNF+cFz8Uz4NaG8YhETg9+xLN99Ko7pvyfsOzVL2NGnseW+Yet971mf793NbscCTDfPAxBXpzO8UNSyfMssTMFXE8o9ukG2fJblv0/FFHorofz1PpAlp2W5Dfe90NBQ82+yswMs7G75mxwYatB9QcJvcrZMMPsjy/IrQQb9FyeU53WDbztYlp+7Hs/QZQn7TtEXTHzd2nLfsfW+l/R8r23btskaembPns2cOXP4/vvvuR+rJWDh4eHkypXL3L0w6Q/YK6+8wtSpU8mXL9/9Pm41AQEBAGTPnnCgzpYtG8HBwURGRuLs7PxYy7py5QoHDx60mJb4Iw1w+fJlDh48SIlSpcmS8fGWLc9WVEQofn5+5vchISHJvtuzZ8+aX9++fTtZeeKPKEBgYGCy8gsXLphft69ZkgkTLH+MZs+O4av/ToK71S/DyJGW5ZMmBTP5v5Pgz96oyKefWpZ/+eVl5v53Epw9U8KB8MUXsrL7v2HBBw06xY//JWDffFDzHj8Gf7H6vwRsZsd69/gx2Mnm/xKwRR83NCf/sTGR1Br8L64HWoB/wonIK62XJjsRybytMdxIWH75juuSnYg4r6sFwQnbsFLXLclOREyziwIJB7yqPfclOwnOML8ExCScBNfofzTZSTDT/n8SXGvwvxZFoaGhMDvhJDiDYyaiIkI5evyUufzWrVvm1zExMcm+26Qn1VFRUcnKz5w5Y34dHh5uLi9RqjQB0z5KSP7/Owl+tXhefrlrKPdNmzbR+b+T4IZlCrHwrvJVq1bR67+T4OaVivFdkvIOHXZw7Pr/57X1vhcfH0t6EhURSkxMjPn94cOHkyVR8fHx5td///03GTNmvO/y7t43wsPDza8Nkg/jHxAQQKX/ToLzuGbkr7vKz549S53/ToKT/n9PWt83/jsJLlswJ7leyIq/f4h5Xlvue7ExkbzUaBxsTTgRyVO+NbUGW56IHJ09G3Z/BUD+Kl2oNXikRbnPpEmwfzIAhWr1o9ZdFz23RH4JfyecBNu7ZKfW4CMW5WtvDYJjCSfBLzUaR627jntLL/YEv9UAuL89lVp3HffmHe8I5xNOgku9Ny/ZsSEkJMT82s/PDycny5PQpN/viRMnLPYlSDheJDp27BjBwcHA/48NFXd/x7X/ToL/+ap18uR/43jC/jsJPvNNh+TJf5KT4Lv3rdDQUNzXjgXAzmSy+b6X+FuRyG7PHliZkLC7FqpOrcGWFz3DN22CXxMuemZ/qQG1Blte9LyxahX8nnDR84WX36HWYMuLnueXLLHpvrfp8xHm14nnexb1u3HD/PrChQvJygMDA82v//3332Tlt2/fNr+OiIpJ9v20aLGBvf8lYCt7v3mP5P9njvyXgG0a+O49kv8f+Pe/BOzPES2SX3iy4b4XHHTT/DqDYyZqDfazKA8ICIAFCRc9HTPnptbg5Bc9WZxw0dM5W1FqDba86Jn18GFYlnDRM3OeMtQabHnR0xb7XtJjQ9LzvRs3biT7bi9fvszDWC0BMwzDomUrQ4YM5r+zZs0iZ86c9/uoTSTWxTAMi/ePI1++fOar4ol+/fVX8+sCBQqYyxOfv2M6eNLcr3Pgsj/5bH+UxedNB8+ay3ss3E73bYEW5XZHL5JY0w5z/4BfLwH/f9ZP5H8tBADNp6+HZScsP3/ppvnzr3+zBrIdsCy/ccdcXnPML8mviNwON5fv/656slaIuOj/tzLsnVImWStEUrvHW16tiYg2kiwnjMigfwFHIoP+Zff4ogSG/r88OvRass9fCfp/eeJnkjp3/f8nSaEBRy3Kaw3+lxIlSpjfZ8mSJdl3m/Qk3NXVNVn5xYsXza+zZ8+erPzECcvvIr2wd0h/FxecXDJbfH+JF24AHBwckn23SR+x4eTklKzcweH/V88yZsyYrDw9sbOzT/Z/L+Cf/ydlZ34fxm7/zy3Kbxz/f/mpdX3Z7TfAojzwzP9PWk+s6EpkUCGSHhtuX/x/+ZGlrYnfZdm6Ghrw//J/Fr7NnbtaXyOD/n/cOjivAVeTtL7WGvyvxfdXtmzZZCcidnb/X16FChWSJ/9J3P3dh4aGml/bru9Hyngejg1ZsmQxvy5RokSy7zdpMl6qVKlkJ8FJE7bSpUsnOwlOT9Lb/pDB/v/HhaTne4leeOEF8+vChQsnK09sCICEnhN3l7u6uppfuzhZtsCkdeltXwDLY0PS870XXngh2Xd74IDlufe9mIzEDOUplSxZkjx58rB9+3aLably5WLnzp3WCPFIVq1axZAhQ5g3bx516tTho48+4ujRo/j4+Dz0s1FRURw9epQyZcoku8r1MDZ/2OrpdThFhxDlmIUzd3cjsIGAaR8lO8mytmm7C3Ar3JEcGaPpU+vhVwuext0tImldhw4d8Pf3J3/+/CxatCilq2MV6XGdnoWU2G46NqRe6fH/UXpcp2dF204kZTwsp7DqcIQ3b96kQYMGFtMCAwOTTTOZTOZ+r9b26quv4uDgwKJFiwgMDMTX15cmTZrYJJaIiIiIiMjjsGoCFhsbm6zv/L2m2XIQjty5czN9+nTGjx/P6NGjqV27NgMHDnz4B0VERERERGzMagmYp6entRb11OrXr0/9+vVTuhppWnxslM275sw91gHC/f+7wXKXTWPFx0ZhZ/943UpFRERERKzNagnY3SOqSdqW3pKV9LY+IiIiIpI2WbULIoCvry/Ozs6UKVMGgH/++Yfly5dz69YtSpUqRYcOHciRI4e1w4qIiIiIiKR6VkvAIiIi6NatG/v376dz586UKVOGbdu20bt3b+Li4jAMg127drFmzRqWL19O7ty5rRVaREREREQkTbB7+CyPZvbs2fj4+GAYBpkyZQISngweGxtLtmzZaNeuHXny5OHatWt89913D1maiIiIiIhI+mO1FrDff/8dk8nExIkTadKkCUePHuX8+fOYTCZGjhxJo0aNeP/993n77bfZvXv3wxcoIiIiIiKSzlgtAbty5QpZsmQxP3Nr166EUe0cHByoV68eAMWLF8fV1ZWbN29aK6yIiDxDGiFVRETk6VitC6K9vT0xMTHm9zt27MBkMlGhQgXzE6Cjo6MJCwsja9as1gorIiLPUHpLVtLb+oiISOpntRawokWLcvz4cZYsWUL27Nn5559/MJlMeHh4ABAfH8/XX39NbGwsRYsWtVZYERERERGRNMNqCVjLli0ZNWoUY8eONU9zc3OjefPm3Lp1iyZNmnD79m1MJhPt2rWzVlgREREREZE0w2pdED/44AO6d++Ok5MThmFQpEgR5syZQ5YsWcicOTPBwcGYTCZ69uxJo0aNrBVWREREREQkzbDqg5j79u1Ljx49uHPnjsXDlp2cnBg/fjzVqlUjT5481gwpIiIiIveQMWNGi78ikjpYrQUskYODg0XyBRATE0Pt2rWVfImIiIg8I506daJcuXJ06tQppasiIklYtQXs7NmzLFiwgFdeeYUPPviA6OhoPD09WbFiBTExMeTKlYvPPvuMt99+25phRSQd0JVaERHrql69OtWrV0/paojIXayWgJ08eZLWrVsTGRmJq6srAN9++y1Lly41z3Pt2jUGDRqEq6srderUsVZokedOekxWOnXqhLe3N61atUrpqohIKpIej3ci8nyzWgI2c+ZMIiIiKFiwINWqVSM8PJylS5diMpmoXbs2ffv2ZdGiRaxZs4aFCxemqwQsMiaWgGkf2TRGhw478PcP4cUXsrLbxrEgYZ2cHazaQCpWlB6TFV2pFZF7SY/HOxF5vlntDPvgwYNkyJCBJUuWkDt3brZs2UJERAQmk4n+/ftTqlQpRo4cyW+//caxY8esFTZVSI+JSnpcp/REyYqIPC90vBOR9MZqg3Dcvn0bV1dXcufODcDu3bsByJEjB6VKlQISug9kzpyZiIgIa4UVERERERFJM6yWgGXNmpU7d+4QGhpKXFwcW7ZswWQy8eqrr5rnuXDhAsHBwRoNUUREREREnktW62dWoUIFtm7dSq9evXBxceH69euYTCaaNGlCXFwc27ZtY9KkSZhMJsqXL2+tsCIiIiIiImmG1RKwXr16sWfPHvbt22ee9uqrr1K3bl1u3bpFr169AHBxcaFHjx7WCisiIiIiIpJmWC0BK1WqFN7e3nh5eXH9+nWqVKlifvBf9uzZcXZ2plKlSgwbNozChQtbK6yIiIj8R0O2i4ikflYd6q548eKMHTs22XSTycT+/ftxdHS0ZjgRERFJQkO2i4ikfs9srHElXyIiIralIdtFRFI/q42CKCIiz566nImIiKQtaTYB++GHH6hfvz7ly5endevWnDx5EoCYmBjGjBlDtWrVqFu3Ll5eXilbURERG+rUqRPlypUz33MrIiIiqVuaTMB2797N119/Tc2aNRk/fjz+/v707t0bgKVLl7J48WK6dOlCnTp18PT05MCBAylcYxER26hevTqTJ09WtzMREZE0wiYJ2K1btx5YvmHDhqdaftasWenduzeffvopjRo14pVXXuHKlSvExsayZcsWcuTIQdeuXc1J2datW58qnoiIiIiIiDXYZBCOVq1aMXfuXIoVK2Yxfc+ePUyaNIkTJ07wxhtvPHQ506dPZ8aMGcmm9+rVy5xc+fr6smPHDmrWrIm9vT0BAQFkz54dwPz36tWrj1X/o0ePPtb8z0JUVJT578GDB1O4NtaRHtdJRJ6ejg0iIpKe2SQB8/f3p02bNkyfPp2qVaty5MgRJk2ahI+PD4ZhkClTpkdaToUKFfjwww/vOR1g+/bt9OvXDzc3N7744gtzuclkspj/7vcPU6ZMGZycnB7rM7aWWB8nJycqVaqUwrWxjvS4TiLy9HRsEBGRtCwqKuqBDTo2ScDq1avH9u3b+eijj6hatSp79uzBMAxcXFxo27YtXbp0eaTl1KpVi1q1at2zbP369QwcOJACBQrw/fffU6BAAQBy5crFuXPnAAgMDAQgT548VlgrERERERGRp2OTe8Bmz57NJ598QkxMDHv27AGgffv2bN68mc8++ww3N7enWv7JkycZNGgQ9vb29OnTh0uXLrFnzx5iY2OpV68eN2/eZP78+ebuix4eHk+7SiIiIiIiIk/Nai1gV65csXj//vvvkzVrViZPnkx8fDw3btwgMjLSPF++fPmeONbChQuJiYkhJiaGAQMGmKcfOHCADh06EBAQwLx583BwcGDo0KFUqVLliWOJiIiIiIhYi9USsAYNGjyw/Pfff+f3338HEu7JOn78+BPH8vT0xNPT877lw4cPZ/jw4U+8fBEREREREVuwWgJmGIZN5hUREREREUkvrJaAbdmyxVqLEhERERERSZesloDlz5/fWosSEZHnWMaMGS3+ioiIpCc2GQUR4J9//mH79u1AwqiFH3zwAY0aNWLWrFm2CikiIulAp06dKFeuHJ06dUrpqoiIiFidTZ4DtnnzZvr164eHhwf16tVjwIAB5mdzTZs2jaxZs9K2bVtbhBYRkTSuevXqVK9ePaWrISIiYhM2aQGbM2cOsbGx5MiRg6NHj3Lu3DnKli3LsGHDMAyD5cuX2yKsiIiIiIhIqmaTBOzff/8lc+bMfP755+zbtw+TyUTTpk3p0KEDrq6uXL582RZhJY3RfR4iIiIi8ryxSQJmMpkwmUzY2dmxd+9eAKpUqUJUVBSRkZE4OzvbIqykMbrPQ0RERESeNza5B6xo0aIcOXKEXr16sW/fPvLly0ehQoXo1asX0dHRVKlSxRZhJY3RfR4iIiIi8ryxSQtY9+7dsbOzY/PmzcTHx9OzZ08cHR3Zv38/jo6O9OzZ0xZhRUREREREUjWbtIDVr18fb29vDhw4QJkyZahcuTIAbdq04Y033qBs2bK2CCsiIiIiIpKq2SQBAyhdujSlS5e2mDZ48GAAjh8/zssvv2yr0CIiIiIiIqmSTRKwO3fuMHHiRA4dOkR4eDjx8fEAGIZBaGgooaGhHD9+3BahRUREREREUi2bJGDjx49nxYoV9y13dXW1RVgREREREZFUzSaDcOzYsQOTycTIkSOpVq0aFStWZP78+TRp0gSTycSQIUNsEVZERERERCRVs0kCFhwcjJubG61bt6ZRo0ZcvHiRmjVr4unpibOzMz/88IMtwoqIiIiIiKRqNknAsmfPzu3bt/H396dixYrcvHmTw4cPExQURGxsLJcuXbJFWBERERERkVTNJglYnTp1iI+Pp1u3bri7u5MzZ07at29P48aNiY2NJXfu3LYIKyIiIiIikqrZJAEbMmQIDRo04MUXX8RkMtG3b1+io6OJiIggQ4YM9O/f3xZhRUREREREUjWrjYLYoUMHcuTIwZQpU8icOTPfffcdMTExALRs2ZLy5ctz5swZypQpQ8GCBa0VVkREREREJM2wWgK2f/9+8uTJYzHNwcHB/Lp48eIUL17cWuFERERERETSHJt0QRQREREREZHkrPog5ujoaHx9fTEM46HzVqlSxZqhRUREREREUj2rJmBBQUG0b9/+ofOZTCaOHz9uzdAiIiIiIiKpnlUTMOCRWr8eZR4REREREZH0xqoJWO7cudm+fbs1F/lQS5cuZdSoUXh6etK8eXNiYmIYP34869atw9nZmc6dO9OpU6dnWicREREREZF7SdODcJw8eRJPT0+LaUuXLmXx4sV06dKFOnXq4OnpyYEDB1KohiIiIiIiIv+XZhOw0NBQ+vbtS5EiRSymb9myhRw5ctC1a1d69+4NwNatW1OghiIiIiIiIpas1gXR09MTFxcXay0OgOnTpzNjxoxk03v16sX58+dxdHTk008/5eOPPzaXBQQEkD17dgDz36tXrz5W3KNHjz5FrW0jKirK/PfgwYMpXBsREREREXkSVkvAmjVrZq1FmVWoUIEPP/ww2fRcuXIxb948li5dSlBQEACxsbHExcUBCaMsJnX3+4cpU6YMTk5OT1hr28iWLRs3b94kW7ZsVKpUKaWrIyIiIiIi9xAVFfXABh2rj4JoTbVq1aJWrVrJprdv356oqCiaN29unvb5559jb29Prly5OHfuHACBgYEA5MmT59lU2IY6deqEt7c3rVq1SumqiIiIiIjIE0rVCdj9jBw5ktDQUACOHTvG6NGj6d69O/Xq1SMoKIj9+/czf/58Lly4AICHh0dKVtcqqlevTvXq1VO6GiIiIiIi8hTSZAL20ksvmV8n3htVqFAhsmfPTocOHQgICGDevHk4ODgwdOhQqlSpklJVFRERERERMTMZeiqyWWJ/zdR4D5iIiIiIiKR+D8sprNYCNnTo0Eee12QyMW7cOGuFFhERERERSROsloCtWrUKk8nEgxrUEsuVgImIiIiIyPPIaglY06ZNH3u4dxERERERkeeJ1RKwr7/+2lqLEhERERERSZdsNgpidHQ0Z8+eJSwszNwtMT4+ntDQUPbu3cuIESNsFVpERERERCRVskkC5uvrS/fu3c3P6roXJWAiIiIiIvK8sbPFQidPnkxISAjOzs44ODjg4uJCzpw5zS1h7733ni3CioiIiIiIpGo2aQE7deoUDg4ObNmyhRkzZnD69GkWL17M5s2b6dWrF3Z2Nsn7nlpighgdHZ3CNRERERERkbQoMZe43+jwNknA4uLicHZ2Jnv27FStWpUVK1YQExPDa6+9hqurKzt27LBF2KcWExMDgJ+fXwrXRERERERE0rKYmBicnZ2TTbdJAlagQAHOnj3LwoULadKkCVFRUUybNo0cOXJw+/Ztc6KT2mTKlIkSJUrg4OCgIfVFREREROSxGYZBTEwMmTJlume5TRKwTp06MWLECNatW0fHjh2pUKEC33//vbm8UqVKtgj71Ozs7MiSJUtKV0NERERERNKwe7V8JTIZ9+uc+JS2bNlCQEAAbdu25d9//2XgwIGcOXOG8uXLM27cOPLly2eLsCIiIiIiIqmWzRIwERERERERsWSTLogHDhx46DxVqlSxRWgREREREZFUyyYtYCVLlnzgIBYmk4njx49bO6yIiIiIiEiqZpMWMLj/uPdZs2YlR44ctgorIiIiIiKSaj2Te8Di4uIICQlh1apVTJ8+HS8vL8qWLWvrsCIiIiIiIqnKMx+E44033iB79uz8+OOPzzKsiIiIiIhIirNZF8R7uXTpEgEBAVy9evVZhpV7iIuLI0OGDBiGoYdOC/Hx8djZ2aV0NURERCQN0Pnj07FJAtagQYNk06KjowkKCiIuLo5ixYrZIqw8gsTEK0OGDACEh4ff9yndkv4lNoAnTb6UjD3f9P1LIu0LklR8fDwmk0kn3ZLs2KBjxeOzydby9/dP9u/GjRvExsbi7OzMoEGDbBFWHiI+Pt6ceB0/fpyPPvqISZMmpXCtJKXExcWZf0zv3LnDgAEDCA0Nxc7O7r6D6Ej6lvRHdPPmzVy+fDmFayQpIT4+HsMwzPvCqlWrWL16dcpWSlJMVFQUkHChzmQyERkZmcI1kpQSHx8P/P+i7dy5cwkICNB5wxOwSQuYp6dnsmkmkwlXV1fKly9PtmzZbBFWHsLOzo5r167x5ZdfEhERwYEDB7h48SKHDx/WoCjPocRkfP78+Vy4cIH169eTNWtWRo0apa4Fz6nEY8Ty5cvx9vZm8ODBFChQIKWrJc9Y4smVj48PPj4+zJkzhypVqlClShXy58+fwrWTZ+nPP/9kwIABfPfdd1SuXJmpU6dy+PBhZs6ciZOTU0pXT56xxGPDnj178PX1ZebMmfzzzz/MnDlT5wyPySYtYM2aNUv2r2nTptSvX1/J1zMUFxeXbNqMGTM4efIkbdu25aOPPuL69essXLgwBWonz5phGOYrVIZhEBYWxqeffsr8+fPJli0befPmZdmyZfz111/Y2dmZr3RJ+nX3MSIwMJDPP/+cmTNn8uabb1KnTp0Uqpk8a3dfvV6yZAkdO3bk+vXrlCxZEh8fH3799dcUqp2klMjISBwcHJg1axYA69evp0KFCjg5Oek34jmR9LwhPj6e2bNn061bN65fv07OnDnZunUr27dvB9A+8Ris3gJ2584d1q9fz6FDhwgMDCQuLo7s2bNTrlw53nrrLVxdXa0dUu6S+J8lsYXj1q1bZMqUCWdnZ86fP4+bmxuvvfYar732GmfPnmXr1q2sXbuWd955JyWrLTaUeO9f0tcxMTH89ddfvPnmm/Tv3586deowdOhQxowZw8qVK9WfO50zDMO8Txw+fJisWbNSuHBh3n77bY4cOUJ4eDiurq5qDU3nEn8v7v6ODx48SKlSpRg8eDBZsmShSZMmrFq1isqVK1OpUqWUqKo8I7GxsdjbJ5weNmjQgKNHjzJ37lwmTZpEhgwZCAoKAtBvRDqX2CU98diQ+Hfnzp1Ur16dL7/8kkOHDjFmzBi++uor6tWrp33iMVh1S61evZp69erx5Zdfsnr1anbs2MHu3btZt24dY8aMoV69eqxatcqaISWJpD+kJpOJwMBA2rdvT5s2bZgwYQIARYoUITg4mJ07dwKQN29eYmJi+Pnnn7l582aK1V1sJ+m9fz/88AMTJ07k+PHjODk5kTlzZvz8/AAoV64cOXPm5Pjx4+bHROhqVvqT9DgRHBzMxx9/TM+ePenTpw/9+/enePHiNGjQgBUrVnD27FlMJpP2g3QqNjbW/Huxa9cupkyZwoEDBwAICQkhNjaWGzduANCwYUPOnz/P6tWriYiISMlqi40lJl++vr7cvHmT5s2bU7FiRRYvXsy5c+dYsWIFAwYMYO/evSlcU7GVmJgYczK1d+9evv/+e44dO4bJZMLBwQF/f38yZMhAxYoVefHFF/H392f27NmAzhseldUSsN27dzN06FDCw8NxdnamatWqNGnShCZNmlCjRg2yZMlCREQEw4YNY8+ePdYKK/+ZPXs248ePN7+fO3cuv/zyC5kyZSJ37tz89NNP/PTTT3z88cfExMQwePBgvv76awICAqhZsyZ+fn4cO3YsBddArMnX19d8ImVnZ8f58+cZNWoUM2fOxMvLi549exIeHk79+vXZv38/48ePZ/v27eTKlYvy5cszc+ZMIiIidDUrnbm7NWv79u0EBwczdOhQgoOD2bx5M3FxcTRp0oT8+fMzatQoQFe605OwsDDzibO9vT3BwcFs2bKFzz77jPnz59OrVy98fX358MMPOX36NLNnz8bX15fbt29TrFgxdu7cyaFDh1J4LcSW9u/fj4eHBx9//DG1atUCoEmTJmTJkoV8+fIxcOBATp48SefOnZkwYYIS8nQiNDTU/H/bwcGB0NBQFi5cyMcff8zEiRPp0qUL169fp1atWpw9e5aJEydy+PBhMmbMSNmyZZk9ezY3b97U78UjstpWmjdvHoZh8Prrr7Nr1y4WLlzIpEmTmDRpEgsWLGD37t20atUKwzCYP3++tcIKCf9pAMqUKUNQUBBHjx5l1qxZTJs2jRYtWjBhwgTq1KnDd999R6ZMmZgwYQL169dn8+bNFC5cmNdeew2TyUS+fPlSeE3EGoKDg+nXrx9Xr14lOjqajRs30rhxY44cOcKsWbMYO3YswcHBLF68mA8++ID33nuPdevWMXToUJydnXnppZfIkiULwcHBKb0qYgVnz57lk08+4cCBA5hMJv744w8+/fRTIiMjOXHiBKdPn2bw4MG89NJLzJgxg8OHD/PKK6/QpEkTDhw4wOnTp1N6FcRKQkJC6N+/P0uXLiU+Pp4zZ87w1ltv4enpSc+ePZk5cyYZM2Zk6tSp1KhRg7Zt27J9+3Z69uzJmTNnaNOmDbdu3TK3kEjaFxsba/E+Li6OOXPmULp0aSZPnsy8efMoWLAgjRo1onr16gQFBeHh4cH69ev5/PPPadu2LS4uLilUe7GW6OhomjZtytatW4mKiuLYsWNUr16dDRs24OnpyVdffUVMTAxz5szh7bffpnnz5ixatIgePXpw7tw5KlSogLOzM1euXEnpVUkzrJaAnThxAjs7O7766isyZ86crNzR0ZHBgwdjb2/P0aNHrRX2uRYTEwNA5syZad++Pfv27aNXr17kzZuXXr16YRgG9vb25MmTh6ZNm2JnZ8eIESOoUaMGn3zyCRUqVODWrVuMGzeOhg0bUrhw4RReI3kaiQMquLm58csvv3Du3DnWrFlD1apVKV26NBcuXCBXrly8++67NG/eHC8vL27dusXYsWMZO3Ysr732GpUqVWLPnj28/PLLZM+ePYXXSKzBz88PHx8ffvrpJwC+++47HB0dcXZ2plixYkRERNCwYUM8PT05e/YsX375JSEhIbRr147du3dTvHjxFF4DeVqJ3U6zZMnCF198QaNGjViwYAH58+encuXKBAQEULp0aerUqUPTpk3x8/Nj4cKFfP7556xYsYJ69erRrFkzfHx8yJ8/v44N6UDiPpGYTPv7+xMVFUVQUBB+fn5kz56devXqUbt2bbZu3cqBAwdo3rw5sbGx5t42bdu21aiYaZy/vz87duzA0dGROXPmULRoUX777TcKFChA2bJl+eeff8ifPz8tW7akbdu2LFu2jAsXLjBu3Djmzp1L9erVadOmDefOnSNPnjwaNfcxWC0BCw0NxdXV9YGDbGTKlAk3NzdCQkKsFfa5dPjwYcLCwnBwcAASRi7LlCkTL730EgcPHuTPP/+kYcOGvPLKK0yaNInw8HAaNWpExYoVuXTpEiEhIYSFhVG0aFECAwOZOXMmX331FY6Ojim8ZvIkEv8/Jd7nBZAnTx7Wr1/P999/T1BQEL179yY0NJQ//vgDgJYtW+Lg4MC4ceMwDIOoqCguX77M9OnTeeedd5g8ebKGGE7D4uLizCdYb7zxBu+88w5//vknc+fOJS4uzvzw9VatWlG2bFk2b97MmDFjWLRoEQ0bNiR79uy88MIL5MyZMyVXQ55SfHy8+T6vRC+88AK7du1i4sSJXLlyhU6dOpE5c2YWLFgAQKdOncidOzezZ8/m4sWL3Lx5k5CQECZPnkxoaCiLFi3ixRdfTKlVEitJ3Cc2bdqEh4cHXbp0YebMmeTMmZMXXniBs2fPcvLkScLCwpg9ezbe3t7UqFGDuXPn8u2336Zs5eWpJf4+7NmzhwkTJnD69GmcnZ3ZuHEj48ePx9/fnwEDBgAJtxhFR0fz7rvvki9fPoYOHWr+jQkKCmLcuHHExcUxb948XZx5HIaVuLu7G3Xq1HnofHXq1DFKlixprbDPncmTJxvu7u6Gj4+PsWfPHuPdd981WrRoYWzfvt0ICQkxunTpYnh4eBj+/v7G+vXrjTJlyhgTJ040DMMwAgICLJYVFxeXEqsgVhAfH2/Ex8cbnp6exieffGIYhmHcuXPHGDNmjLF48WIjMjLS8PX1NV5++WVjwoQJRkhIiNG3b1+jfv36xsGDBw3DMIwtW7YY58+fNy/zzJkzRnBwcIqsj1hH4n6R6MqVK4ZhJHy3b7/9tvHaa68Z7u7uhoeHh+Hp6WmEhIQYt27dMmbNmmV88sknxuTJk1Oq6mJl27ZtMzp16mRcu3bNMAzDWL58ubFkyRLj1q1bxrlz5wwPDw+jffv2hmEYxpQpUwx3d3fjjz/+MAzDMDZt2mR+bRiGcfHiRePEiRPPfiXEakJCQgxvb2/jr7/+MqKiogzDMIw9e/YYVatWNb799lvj/fffNypUqGDs2bPHOHDggFGmTBnj9ddfN4YMGWK88sorxsqVK1N4DcRaDh06ZOzZs8cwDMPw9vY23N3dDXd3d2PmzJnGiRMnjLJlyxojR440QkJCjBEjRhg1atQwz79+/Xpj48aNhmEYRkxMjHHixAnjyJEjKbYuaZlVO3JHRkayevXqh84jjy9xONDmzZuzbNkyli9fTkREBIULF+bvv/9m0KBBrFmzhk6dOtGnTx+WLl1Kx44dqVevHpcvXyY2NpbcuXMD/x9iVjdKpl2JVy8DAwM5ePAg06ZN46+//uLUqVMEBQVx5coVevfuzfvvv4+3tze1a9emd+/eNGnShE2bNlGuXDk8PDyA/w9LX6xYsZRcJbGCxP0iJCSEfv36cerUKTw8PBg8eDCtW7fG09OTzJkz07BhQ5YvX87y5cvp2bMn3bp1IyYmxtyqLmlfeHg4e/fuZeXKlfj7+7Nu3ToiIyNZtWoVv/zyCx06dMDT05P169fTpk0b1q5dy1dffcVrr71Gw4YNLZZVsGDBFFoLsYZ58+Yxffp0MmXKRGRkJCNHjqRp06YcOXKEAgUKkDdvXtzc3MibNy8zZszAy8uLiRMn8scff+Dv78/XX3/Nm2++mdKrIVayYcMGjh8/TlxcHA4ODri4uBAfH8/LL79MyZIladWqFT///DN169ale/fu/PzzzyxZsoQKFSrwxhtvmJdjb29PyZIlU3BN0jaTYdz19MUnVLJkyUd6Vozx3yhcJ06csEbYdC/p85sSff/990ycOJHixYuzYMECzpw5Q79+/XjjjTcYPHgwkyZNYsmSJaxevZp8+fKRNWvWFKq9WJvx34MQE/eJoKAgPvjgA6Kjo6lZsybt27fnxx9/5Ndff2Xq1KmUKFGC9957jyJFijBt2jTOnDlD1apVU3gtxJoSL84k8vLy4saNG1y4cAHDMNiyZQvdunWjd+/efPzxxxw7dsz8nLc5c+ZQp04d6tevn4JrINaS9PlNERERjBo1ik2bNlG+fHl69erFn3/+ycyZMxk5ciTvvfcen3zyCX///Te7d+/m8OHD5MmTR90L05ETJ04wePBgAgIC6NGjByVLlmTEiBG8+uqrjB49mjt37hAREcGKFSsoWbIkvr6+LFiwgGbNmuHp6ZnS1RcrSvo7sWTJEsaMGQPAnDlziIqK4uuvv6ZIkSIsWLCA0NBQmjdvjpubG1OnTuXEiRO8+OKLFClSJAXXIP2xWhNIvnz5yJs370P/Jc4nD2ckeVDq9u3b+fbbb9m6dSvvvvsuVapUITo6mujoaCpXrsz777/P8uXLOXToEK1bt2b48OGULFnSnHwlDtAgaVfixYvEB2H6+fmRLVs2Bg4cyNWrVwkKCsLd3Z1PP/0UNzc3lixZgr29PZ988glOTk44Ojqaky/tD2mfYRjExcVZJF/Hjx/Hy8sLLy8vGjduzJQpU6hduzarVq3i9OnTdO/eneDgYDw9PcmTJw8jR45U8pWOJCZfp0+fxsnJiY4dO5I7d24uX75MqVKlaNeuHXXr1mXixIlER0fTrl07smbNyuXLl3n11Vd58cUX9QyfdMTLyws/Pz+6dOlCp06dcHZ2Jj4+nmPHjjFlyhSuXbvGuXPnzBfnQkNDKVasGCEhIYSHh2tfSAfi4+MxDMPidyJxqPjMmTOTM2dOXn/9dZo0acLff//NrFmzuHPnDp999hmXL18mKioKDw8PihQpov3B2lKs86PcU+K9O4aR0L82OjraGDNmjFG2bFmjZs2aRosWLYygoCBj+/bthru7uzFt2jQjOjra8PPzM2rXrm2MHz8+hddAbCXxnr25c+ca5cuXN8qVK2e0a9fOMAzD6Ny5s+Hh4WHs2LHDMIz/9+tesWKFERsbm2J1Ftvz9/c3pk2bZqxZs8YwDMP44YcfjJIlSxre3t6GYRjGjh07jLp16xoffvihYRiGsXTpUuPy5cspVl+xnpCQEMMwDPP/8YMHDxqNGjUyypcvbzRv3tw4evSoMX/+fOPll182Nm3aZBhGwr2f7u7uxqeffmoYhmFxz6CkD4m/FX5+fkbTpk2NZs2aGYMHDzZKlSpldO7c2ejfv79RsmRJo2vXrsbZs2eN2rVrG6VLlzYaNmxo7N+/P4VrL7awdetWY9CgQcaCBQuMa9euGbt27TJq1qxpDB061DCMhH2ldevWhru7u1GjRo1kYwaI9SkBS2V+++03o0OHDsbNmzeNoKAgIzAw0GjQoIExb94848qVK0ZMTIxhGIYRFRVljBo1yihfvryxe/duwzD+f8N9Iv2wpn3ffPON8csvv5jfnzhxwqhVq5YxZ84cw9vb2zh37pxhGIbxzz//GNWqVTP69u1r3L592zAMw3wCnkiJWNq3YsUK8/caFxdn/Pjjj0bZsmWN119/3XB3dzd+/vlnIyIiwmjXrp1RrVo1IzQ01DAMw+jfv7/x1ltv6Uc1HTl06JAxduxY8/vbt28bH3zwgdGtWzdj5cqVxvr16w3DMIzr168brVu3Nt577z3j2rVrRkREhLFkyRLjzJkz5s/q2JD+JH6n8+fPNypVqmRUqlTJ2LVrlxEZGWkYhmF07drVqFevnnH16lXj2LFj5gs4kvYlnicm7gNLliwxatasaYwbN85wd3c33n//fePvv/825s6da5QqVcr44YcfjMOHDxu+vr6Gl5eXxbEhcVlifRqFIRU4ePAgffr0ISwsjNjYWHx8fHjzzTeZPXs2ISEhXL58GVdXV/LmzUtkZCRfffUVM2bMoHPnzsD/hyFP7NqZ2L3sUe7Jk9QnPDyc9evXAwnf5ahRo/jggw84ffo0J0+eJDAwkIoVK9KyZUuKFi3K0qVLKVCgAM2aNWPjxo34+voCCUPNA+ZuA3ffSyhph4+PD+3bt2fOnDlMnDiR0NBQ7P7X3p0H1Jj2jx9/ty+SJUtaiLLNUEj2KTOYaCxliyFblmwhJgzCZMvOxNg19l1k7GMYWyKakW1oUKFkK5W2c+7fH37njMY888z3GaR8Xn9N59znct1zzrnO9bmWz6WrS0REBB06dKBv374YGxszffp0VCoVgwYN4sWLF0yaNAmAyZMnExERoU3EIwq/Gzdu8MMPPzB27FhWr15NWloaly9f1p7Z1aZNGy5cuMDly5cZNGgQsbGx7N+/H2NjY3r06IG9vb20DUXEnw9Thj/eU3d3dxwdHTE3N8fc3BwjIyMSEhJITU2lRIkSWFhY8NFHH9G+fft3XW3xhmn6fpqlyJmZmQDExsZSq1YtkpKSAHBzc8PS0pLPP/8cFxcXZs2axeLFi7G3t6d3797Y29u/VpZ48yQAew9oNjimpqaSlZWFiYkJOTk51KtXD0tLS5ydnVm1ahW//fYb8fHx7Nu3DwsLCypWrMjPP/9M69at85UnP6aFV3p6Ol999RUHDhwAXjaoubm5XLlyBQsLC6pVq4aiKNy4cYOMjAwiIyOZNm0a58+fZ8iQIaxcuVKb3VBDsl0WXunp6fj7+9O7d28sLS3p1q0bAPPnzwfA2dmZunXrcu/ePUaOHImenh5z586lQYMGuLu7k5aWRk5OjiTiKQKU/7/nT6NChQo8fvyYPXv2YGZmhr6+PtbW1hw9ehSAx48fExgYyJkzZ2jSpAmzZ8/Gx8cnX3nSNhRuf+4k79+/n9OnTwMvM04PGjSItWvX8vnnn6MoCitWrGDv3r3069ePxMRERo0aJZlPiwjllZwBd+/eZeDAgfj6+gKQmprK8ePHSUhIYN26dRQrVowxY8ZQoUIF5s2bx/Tp01mxYgUlS5Z8rSzx9khoW4A0WWl69uzJ5s2bGTZsGJ6enkyfPp2pU6dy6NAhPv/8c/z8/AgMDMTHxwd9fX1KlixJs2bNAChevDhqtRodHR2Z8Srk8vLyMDMzIygoiMuXLxMUFMQXX3zB9evXiYqKIi4uDhcXF9q0aUNwcDBRUVFkZGRQrlw5ateuTfHixfnkk0+APxJ2iMIrPDyccePGUa1aNZYtW0bz5s159uwZ165dY/fu3XTs2JExY8YQGhrK3bt3+fTTTylVqhSbN2+mcePGfP3119ofVFG4abLh6unpkZ6ejkqlIjU1FXd3dw4dOsSTJ0+wtLSkXbt2hIaG4ufnR4UKFUhLS6NevXoYGBhoZzg0vzvSPhR+mk5ycnIyI0eO5NKlSwB4eXmRlZXFb7/9Rq9evWjatClXr15l27ZtHD16lO7duzN58uSCrLp4QzRtg46ODs+fPycoKIi7d+/y8OFDHj16RExMDB06dODUqVNUrlwZU1NTjhw5gomJCYqiUKZMGTp16vRaWeLte2Np6MU/o/wpjfilS5cIDw+nUaNGjB07ljZt2hASEsK0adOIiIhg5MiRfP7552RnZ3Py5Eny8vLo0aNHAd+FeJNeTQ/79OlTzpw5w88//8yePXtYuXIlVapUoV+/fhgaGhIREYFarWbmzJncunULPT09xo8fL2d4FTG5ublMmzaNrVu3EhYWRqNGjdixYwenTp2iZs2a7N69mzJlyrBhwwbc3d159uwZDg4OGBgY0KZNG7y9vQv6FsQbkJSUhKWlpfbvJUuWsG7dOipUqICvry9t27alW7duPHv2jPnz51OhQgX27dvHgQMHyMjIoHfv3trOlSh6VCoVwcHBREdHU7NmTTw8PFi/fj1nzpxhxowZeHl5kZOTg6GhIdevX2fz5s3069ePSpUqFXTVxb/05+NHANavX8/ChQsJDg4mIyODVatWoSgKhw8fJigoiIiICEqVKkVWVhbz5s2jcePG2tfKoG0BKJCdZ0KbKOGHH35QqlevrqSmpiqzZs1S6tWrpxw6dEhJTk5WWrVqpdSpU0dp06aNkpCQkO/1sjGyaOrXr5/i7e2tnD9/XmnXrp3Svn17RVEUZePGjUr16tWV7t27K+vXr1cURVEyMzO1r9NkvRJFR3x8vPLZZ58pPXv2VLy9vZWaNWsqy5YtUzIyMpQFCxYoH3/8sXL8+HElOjpa8fHxUfr166fcvn27oKst3oC4uDilbdu2ysCBA7Ub4pctW6Y0bdpUWb9+vdKkSROlU6dOSkJCgvLLL78o1atXV/r06aPMnz9fefz4sZKRkZGvTZD2oWhSq9XK2rVrlerVqysBAQGKoijK2bNnlaZNmyoDBw7UXifvf9EVExOjdOrUSTl48KDy7bffKnXq1NEmYAsLC1OqV6+ufP/994qiKMqNGzeUw4cPy+fhPSELwN8BzTkMGj/++CMNGjRgz549lC5dmmrVqnHo0CEGDhxIiRIlWL9+PYaGhoSEhNC2bVtGjRqFjY2N9vWKosjGyEJM+f+zoBoXL15k0qRJPHnyhM6dO3Pjxg1q1KhB9+7duXXrFmFhYXTt2hUfHx+uXbvGvXv3ADAxMQF47SwoUTTY2NgwaNAgzp8/T1ZWFjt27GDQoEGYmprSoUMHPv74Y4YOHUrNmjVZvnw5q1evloMyi4j9+/dz8+ZNoqKiiIyMBOD27dvUrVuXvLw8PvroI27cuMHGjRtxdHRkyJAhXLlyhStXrgBgamqKrq6udo+QtA9Fk46ODh07dqRp06bcuHGD+/fvU69ePTp37syJEye0+wHl/S8aNP0GtVpNdnY28+bN46uvvqJq1ao4ODhQrlw5srKy2L59O/CyHdDX1yckJIR79+5RrVo1WrVqha6u7l8mbhHvlnwr36InT55oO8c6Ojpcv36djIwM7fLD77//nitXrpCdnc3t27cpVaoUvXr14vz584SFhVG3bl2Cg4Np1apVvnJlmrhw09HRQVdXl+zsbAD27t3L9u3bmTVrFs+fP6dy5cocOnSIL774AldXV0JCQrh//z4TJkzgxx9/ZOzYsfnKk82yRZOOjg6tW7emWbNm5OTkYGpqqn2ucuXKdOrUicGDB2NiYqINxkXhdeLECa5evQpAjRo1cHBwQKVSsXXrVmJjYxk9ejQBAQGkpKQwceJEGjZsSHh4OGFhYfj7+7N161ZWrVpF6dKltWVK21D0mZubM3DgQBITE9myZQuGhoZ4eHjQs2dPatSoUdDVE2/Anw9T1tXVRVdXl5iYGOLj46latSr29va4uLjg6upKUFAQI0aMICIigvbt22NkZER4eHi+MmUQv+BJAPYWpKenM378eLy9vfH09GTv3r3Exsbi6enJtGnTaNKkCZUqVeLJkyckJiZy9+5d7Shnnz596Nu3b749HHL6eOEXHh5OSEgIK1asIDc3l4MHD+Lt7c21a9do1qwZBgYGxMfHs3z5clQqFQ8ePMDc3Bx3d3ccHBx49OgRAKVLl0atVstn4gNhbm7OgAEDuH//PuHh4dq0wvDymIGhQ4cWYO3Em5CZmYmfnx+DBg1i1qxZREZG4uTkhI6ODu3ateP27dvs2rULY2Nj9u7dy+rVq4mJiSE3N/e1oBzIlylRfBicnZ3x9PRkxYoV/Prrr1SrVo2JEyfmWzkjCi/NIP7Zs2cJCgpi9erVxMfHM3XqVMqUKcOxY8dQqVRUrlyZMWPG4O/vz+PHj7G2tqZ58+YYGRlJMP4ekgDsDYuLi8Pb25vbt2/j4eFBrVq1yM7OplatWowbN47IyEjGjh2Li4sLdnZ2uLi4YGZmxtWrV7UZjMaOHUuFChW0yxZl+UDh9eDBA7p168aMGTM4efIka9as4ZdffkFfXx9jY2OGDh1KsWLF0NPTo02bNjg5OXHjxg1+/vlnANq2bUtERAT16tXTlqkZ/RIfBk3natmyZdy8eVP7uMyEFw1qtRorKysA7t+/r81OV7FiRZ4/f87AgQPZtm0bUVFRWFpaUrJkScaOHYuZmRlhYWH06dMnX3ky6/Xh0dfXp1+/fowZMwZHR8eCro74l7Kysvjmm2+IiYnRbllYtmwZgwYNIiEhge+++47u3btTrFgx7RmhGzZsAKBq1ar07NkTOzs7Xrx4wcSJE3FycqJhw4YFfFfizyQL4ht2+PBhpkyZwuLFi6lfvz5RUVE8ffqUKlWqULVqVc6cOcPQoUPR19enatWqzJs3j+joaH777TcCAgK05SiSkaZIWL58OT/88AMzZ87ko48+4sqVKxQrVoyKFSuSlZWFr68vOjo6XLlyBU9PT8aNG0eXLl0oU6YMy5cvx8DAAD09PW16WPFhio+P5/Dhw/Tv37+gqyLeglu3bjF8+HB0dHQwMzMjMzOTJk2asHXrVrZt28b48eMpVaoUo0ePRqVSkZKSoj3vT44hEaLo2LhxI/Pnz8fExIRly5ZRq1Yt0tPT6dmzJ87OzgQGBnLx4kUmTpxI3bp1mTJlCj4+Pjx48IBdu3ZhZWXF48ePOXnyJCdOnKBdu3avnQ0q3g+yCPQNe/DgAampqSxcuBBFUYiOjtY+N2LECAYPHsycOXOYO3cuFy9eJCUlhbZt22qv0QRe8mNauGnex6SkJH7//Xdu3rzJ4cOH+fHHH1EUhcqVKzNq1CiWLl3K7Nmz+eWXXzh69CgBAQGsX78+3z4OkFHtD13FihUl+Coi/mpwzc7Ojp49ezJ9+nSmTZvGxo0b+eGHH8jOzubixYv4+voyevRo/Pz8cHFx0b5OBmaEKBoSEhLw8/Pj3r17+Pn50bNnT8zMzMjNzSUzM5OHDx+iKApGRkbUr1+fjz/+mKtXr2JmZkbnzp21ZwECWFhY4OnpiaenZ8HelPhbEoD9C6/++Gl+VD08PHjy5Am7d++mUqVK9OrVixo1anD69GlWrVpF3759admyJaVLlyYzMzPfcoG/OtdBFE6aDlajRo04efIk48aNw9jYmEqVKlGpUiXtQYizZ8/mq6++wsLCArVane/g3Ly8PNkoK0QR8XeHnOrr69O6dWsiIiIIDw9n+PDh7Nq1i8OHDxMdHU1QUBA//fQTFSpUyPc6Cb6EKBri4+OJi4uje/fu2kBszJgxNG3alE6dOmFvb8+xY8f47LPPsLOz4+nTp9qtCXI2bOEkSxD/By9evMiXdUwTOL06sqlWq3n27Jl2JmPSpElcunSJ1atXU758+XzlyXLDwu/vgqWHDx+SlJSEkZER1tbWmJmZ4ePjg46ODuvWrXvHNRVCFKSNGzeSlpaGi4sLjo6OGBoaap87deoUw4YNY/DgwTRs2JAtW7bg5uZGmzZtAFluKERR9tVXX3H27FkaNmzIDz/8QNOmTRk7dqz2qKLQ0FASEhIoWbIkarWa+fPnU79+fW0fUgbxCxcJwP4hRVFQFIWFCxdy/fp1VqxYwYsXL/D398fDwwMvL69812/cuJEjR47g6OiISqViw4YN9OnTB39/fxm1LELCw8OpXLkyTk5OAGzfvp1GjRpha2sLoE2kcvLkSW7evEmrVq24ePEic+fOxdvbm2HDhuXrTEkDKkTRlJqaSmBgIPfu3cPGxobjx48TEBDAgAEDtG1AVlaW9riJiIgIbTsihCg6bt26xYkTJ/Dy8qJ06dLaACohIQFvb2+ePHlCUFAQ3bp1A/5IxHb37l2io6N58eIF3t7eskKmkJOe3j+kObvpzp072v06cXFxnDx5kqZNm752vb29PVlZWURERHD8+HG++eYbRo0aJcFXERIXF8ecOXMIDAwEYM2aNUydOjXfNTo6OuTk5BAdHc2CBQvo0aMHQUFBtGrViqFDh742ki3BlxCF31+lgn/w4AF37tyhc+fOJCYmUrZsWezt7fMdLWBsbExAQAA7d+58bRBHCFH4KYpCREQEc+bMITo6Wht8KYqCra0tAwcOREdHR3uY+qsHqleqVImOHTvSo0cP9PX15TDlQk5mwP4LTQpQTeB08+ZNAgICMDU1pU6dOuzfv58FCxZQv359IP8Mhkql4v79+/lGMWWGo/DT7OVQFIVNmzYRHBzMtGnTSExM1I5caxpVzbWPHz/m999/5/bt27i4uGjP7JHPgxBFx5+XCO7fvx9DQ0NcXFy4desWQ4YMITU1lS5duuDl5cXGjRtxdXWlQ4cOr7UF0jYIUbRo+gXPnz/H29ubChUqMHHiRG1/ACA7O5uuXbtiYmLC1KlTqV69+t+WJQovad3/hubHVE9Pj7S0NFJSUqhatSqdOnUiJSWFrVu3kp6eTmBgIOHh4aSnp2t/MBVFQU9PTxt8aUYw5Ae18NKcRq8JxnV0dGjZsiVubm4EBwdz4sQJ4uPjWb9+Pbdv3wb+eL8tLCxwcXGha9euVK5cWXuYsnwehCg6NAempqSkMHz4cO2hqP7+/qSnp1O1alUsLS1p3bo1aWlp/PjjjxgYGGhf++eyhBBFh46ODlFRUUyZMoXy5csTGRnJ8ePHycrKAl72MYyMjAgMDCQmJob9+/eTk5PzH8sShZu08H9D8wO4cOFC3N3dGT58OMeOHdN2orOysnB1daVhw4YEBQXh7u7O5cuXgde/HLL0sPDTdK5Onz7NqFGjCA0NxdzcnC+//BIrKyuuXbtGlSpVCA0NpX///mzatIknT568Vo6iKHKYshBFxJ+XG65cuZJ27drx4sUL1q9fz4wZM/j111+Jjo7Gw8MDQ0NDAgMDGTt2LE5OTjRq1KiAai6EeJs0bYNmoVliYiJjxoxBrVbTuHFj7O3tWbduHdevXwf+6HM2bdoUf39/OnTokC9JjyhaZAffK/683DAvL49ly5axb98+hg0bxu3bt6latSqmpqYMGTKEq1evoqury8yZM/Hy8uL8+fPUrl27gO9CvEmvzlKp1WoWLVrEunXraNCgAb/88guZmZnUq1eP5s2bc/fuXUaPHo2NjQ3Tp0/nyJEjtG7d+rUyZeRKiMJP06nS/F7cvXuXSpUq0ahRI0JDQ0lMTKRSpUo4OzsTGxvLjh072L9/P5988gkXLlzA3NycFi1aFOQtCCHegj+3DZrf/Li4OB4+fMinn35K+/btadOmDe3atWPfvn3Y2NhQpkwZ7dLCIUOGaMuSPkPRJAHYKzTLDdPT09HX18fY2JhLly6hVqs5d+4cJiYmBAYG8uTJE/bv30+LFi3YsWMHnTt3pmnTpjRo0KCgb0G8ISqVSpt4BV42gunp6Zw/f54vvviC6tWrk5GRwapVq3B2dsbT05Njx44RFBTEsWPHWLlyZQHfgRDibdJ0is6fP8+0adN49uwZXbp0oU+fPgwYMIBVq1Zx7tw5PvnkE4yNjdHT0+P58+fY2trm2xcshykLUbRo2oazZ8+ybt067OzscHV1pUaNGhgaGpKUlEROTg55eXmYmZmxYcMG6tWrh4eHR75gS4Kvou2DD8DWrl3Lb7/9xsyZMwFYtGgRO3fupHbt2vj5+eHn58eECRMwNzfH0tKSFy9ecPnyZa5fv86AAQNo3bp1viyI8oUp3K5evYqhoSEODg7Aywb06NGjODk50b59e/T19dmxYwdOTk6UL1+en3/+mV27dnHgwAF69uxJQkJCvplU6VwJUXTk5uZq92zBy+Br1KhRtGrVigcPHhAWFkbVqlX58ssv2bdvH6NHj+aLL77g1KlTNG/enHLlyr1WprQPQhR+4eHh2NnZUadOHRRF4dSpU4wfP5527dpx8OBBNm7cyKJFi/jyyy9ZtGgR8fHxWFhY0Lx5czIzM3F0dHytTOlLFm0fbAB2/fp1vv76a+Lj4xk8eDBpaWksWbKEgwcP4u3tzdKlSwEICQnh8OHDbNy4UduprlKlCmXKlKF8+fJUqlQJ+CPwki9M4ZSbm0twcDDbtm0jICAAOzs7Zs2axY4dO7CxsWHLli0YGhqyZs0aUlJSuH79OkZGRpibm3P37l2MjY3p0aOHdsZM06mSzpUQhV9cXBx2dnba4Ov58+cUL16clJQUDA0NcXR05PHjx5iYmBAWFkadOnUIDAxkyJAhGBgYMGnSJNq2bVvAdyGEeBuysrI4c+YMu3fvxsPDg3bt2hETE4OlpSVJSUk8ePCA/v37Y21tzbBhw3j06BFRUVGkpqYye/Zs3NzcCvoWRAH44AKwFy9eMG7cOA4dOgTA1KlT8fb25sWLF0RFRdGyZUsMDAyoWrUqV65cYceOHbi6urJw4UKMjIywsbFhwYIFlC9fPl+5EngVXjt27GDu3Lk8e/aMxYsX4+bmRlJSEufOnWPQoEGo1WrWrl3LvHnzqF+/PleuXGHYsGGUKVOG7OxsZs6ciampqbY8yW4oRNERFBTEgQMHWLNmDSYmJkybNg0jIyNGjBhBo0aN+P777zl48CAdO3akUaNGTJ8+nZUrVzJgwABatGjBpUuX8PHxAWS5oRBFxasrXYyNjcnOzubcuXNcvHiR+vXrU6xYMWJjY1GpVCxfvpy0tDRt8q4ZM2aQmppKqVKltIcpS7/hw/NBvdupqal8/fXX3LhxgylTpqCvr8+FCxe0I5fffPMNXl5e5OTkMHXqVPT09NixYwcPHjwgKiqKjRs3smXLFuzt7VGr1QV9O+JfSk9Px8PDg2nTplG2bFksLCxITU3FyMgIPT09Wrduja2tLXl5eQwaNIi0tDQ2btyo3WQ/dOhQTp8+TcuWLfOVK42oEIVfdnY2AF5eXjx//pzt27czc+ZMcnNzOX/+POPHjyc3N5dnz54xb9484uLiuHPnDmZmZjx69IhixYrh5+fH3bt3iYmJyZfgSQhReL16RFF2djbPnz/HxsaG4sWLU7p0aczNzalXrx5WVlYYGRmhq6tLZGQkubm5WFlZYWhoSNmyZfMdpiz9hg/PBzUDZm5uzvDhwylWrBjly5fn/v37rFq1igYNGtClSxdq165N7969efLkCVWqVKFEiRJkZGRw584dmjZtql1uKKOYRYOZmRndu3encePGqNVqvvrqKzZv3oyrqysVKlTA19eXCRMmULx4cerXr4++vj7fffcdDRo0yBd05eXlaUexhBCF2549e9i7dy96enp06dKFVq1a0aVLF7Zt24aLiwvz58/n8uXLjB49mt27d1OnTh3s7e2ZM2cO5cuXZ/78+dp9wbVr12bfvn3aPaVCiMJPEyytXr2aAwcOYGZmxpgxY6hatSozZ85k9erVjBs3jhEjRjB9+nQmTpxIVlYWU6ZMwcjIKF9Z0nf4cOkomnyZH6hmzZphbW3NN998Q/Xq1Zk1axYbNmzQHrI7duxYLC0tC7qa4g1JSkrC0tJSGzRpPv46OjqEhYWxbNkyvLy8GDt2LDk5Obi4uFCqVClMTU2pWLEiX375Ja6urtryJOmKEEVDZmYmU6dO5ejRozRu3JiUlBQaNmzIiBEjyM3Nxc3NDQsLC8LCwihXrhwTJ07k+PHjLFy4kFKlSnH58mXc3d0xMTEBZKBOiKLkz7/1S5cuZf369bi5ufH06VNmzpyJkZERQUFB/PTTTwwdOpTGjRtTpUoVYmNjcXR0lDO9RD5FNgBTqVTag3P/iiab1eHDh/H392fYsGEMHjyYvLw89uzZQ6lSpWjVqhXwx3SzdLQLr+zsbIKDgzl58iRHjhzB0NBQu+Za07BmZmYyYsQIbt26RUhICA0aNCAiIkKb3Wjs2LHaBlQCLyGKlsuXLzNq1CgGDBiAt7c3T58+5ddff6VKlSrY2toSHh7OuHHjGDNmDL6+vvz222907NgRX19fAgICtOXIjLgQRcdfDaRkZ2czcOBATExMWLBggXbQJSkpieTkZCZPnsz169dp3bo1Cxcu1L5O2gbxqiIZgL36hbl16xYlSpSgRIkSGBoa/uWXydfXl8jISJYuXfpaNhoZxSz8NO/h0qVL+f777+nRowf+/v6vHbKsq6vLiRMnCA4OxtbWlrVr1wIvE7fIqLYQRVtsbCydO3emZcuWlClThqNHj5KRkYGhoSHe3t4EBATg4+NDYmIic+bMoX79+ty6dSvf8kIZmBGiaNq0aRMPHz6kUaNGNGrUiO7du6Ojo8PixYspU6YMISEhREREcPToURITE0lJSaFx48YFXW3xHisyu/5ycnI4f/48gPbAy8GDB9O/f39Gjx5NUFCQ9jkNlUoFwKRJk6hfvz41a9Z8rVzpbBd+mvfQxsYGBwcHNm/ezO3bt9HV1dV+BjSBmJubG05OTty/f587d+4AYGJiki/jkRCi6LG3t6dfv36cOHGCo0ePUq1aNXr16oWjoyPr1q3j5s2bBAYG8uDBA5KSkgC0wZemHZHgS4jCT/N9hpcDsH5+fqxbt46rV6/Sp08fVq5cydChQ7l48SJz587lxIkTnDlzBldXV4yNjXFwcNAGX6+WJcSriswMWNeuXUlMTGTZsmU4Ojqya9cudu7cSY8ePZg6dSqpqals2rSJevXq5RullBmNoi8pKYmRI0eSm5uLsbEx0dHRuLu7s2jRonzXaT4Ljx8/xtzcPN+Bq0KID8PTp0/Jy8ujbNmywMsDVoODg9m4cSM1atTg3r17WFtbF3AthRBv2qurYp4/f861a9coXbo0gYGBtG7dmt27d/PixQuGDx9Op06dmD17NhEREeTk5GBtbc28efOoXLlyAd+FKCwK9WJURVFQqVTo6+szcuRI+vXrx4EDB6hZsyZRUVH8+uuvXL9+HQcHB/z8/EhMTMTe3p4SJUpoy/jzjJgEY4XbX62xvnTpEjdu3GDBggVUq1aNxYsXc+jQIY4cOUKrVq2077vmvbewsADk8yDEh+ju3busWrVKm+l0+fLlODk5adsFa2tr2RcsRBGyfft2ateuTY0aNQA4fPgw69evp1y5cvj7+3P16lWuXr3KF198wZdffsnOnTtJS0sjMDAQX19f7t27h6OjIyDLkMU/VyiXIGrO4NLR0dFmsmvSpAnu7u5s2bKFyMhI3NzcyM3NpW3btixatIgrV64wc+ZMMjIy/mO50tku/DTB17lz5/j999+Bl+d95ebmoquri5WVFR06dODFixd8++23ZGdn/8f3XT4PQnx4ihcvzqNHj5g5cybTp0+nVq1aLFmyRDsjBvxtgichROFx/fp1Nm/eTHJyMnl5eWzduhV/f3+ysrLo1q0bJUqUoGXLlpQtW5Z27dqRk5PD3r17sbGxAV4O2GqCL5VKJe2C+McK3QzYiRMnWLlyJaGhoZQsWZLt27ejVqtp3bo106dPp0mTJmzZsoWuXbvStGlTdu3aRV5eHhcuXMDJyYly5coV9C2ItyguLo6RI0eiUqnIysqibdu2ODk5YWNjw6pVq6hSpQrZ2dnY2dmRnJzMqVOnaNGiRUFXWwjxnrC3t2f58uXcuXOHkiVLyvmPQhQxiqKQmJiIra0tNWrUIDQ0lIULF5KRkYGTkxMNGjQgKSmJGjVqULx4cfr06cPQoUO1h687OjpSt27d18qV9kH8XxS6PWArVqwgNDQUT09PDAwM2LdvHxkZGVSuXJnQ0FDOnz/PxIkTmTRpEi1atODbb7/lwYMHVKpUiQkTJkgK0CJuwYIF3Lhxg1atWjFhwgSqVq3Kd999R0REBKtWraJYsWKo1WratWtHnz59KF++fEFXWQjxHlMUBUVRtHtDhBCF186dO1m+fDm5ublUqlQJPz8/7OzsGDJkCJmZmXz//fecPXuWr7/+msDAQPr06QO8XJp8+/Zt8vLytMuThfg3CkUA9uq+npycHEaOHElsbCx2dnYEBARw584dFixYoF0q4uXlxZMnT1i6dCkff/wxWVlZGBsbAzKKWRS8ulEWXjaoT548YcCAAfj5+REVFUVWVhYdOnSgTZs2JCUl4enpyeXLlzlx4gRVqlTB09MTIN9BzEIIIYQoeu7cucO4ceO4ceMGXbp0QVEUzp49S0pKCvPmzSMrK4uvvvoKX19funXrxsyZMzl37hwbNmzAzs7utfKkLyn+rfd6SE8z8qgJvn7//XcMDQ3x9fUlJyeHe/fuUadOHTw9PXF1dSUmJoaUlBTGjBlDenq6thxjY2NJI16EvBp8PXv2jFWrVrF+/XoePXpE3bp1yczMpHfv3gQGBnLo0CEWL15MRkYGzs7OBAQEaIMv2UgvhBBCFG1ZWVmEhIQQExNDSEgIY8eOZcKECYSEhGBubs7atWuxsrLCy8uLNWvW8OjRIzp37syjR484ePDgX5YpfUnxb72XAVhOTg6AtnN89uxZ3N3d8fX1ZerUqdStWxdvb28eP35MWFgYarUaW1tb1Go1arWapk2bEhUVxccff6wtU0dHR5aQFFKKohAXF8eTJ0+Al5+PiRMnsmvXLkqWLMngwYNRqVSEhobSr18/rKys2LZtG9988w379++nU6dO+TJfama95PMghBBCFG3Gxsb06tULU1NTrly5Qm5uLvDyHL++ffty+vRpUlNT6d69O8WKFWPGjBnUrFmTXbt24efnV8C1F0XVe9cDPXHiBGvWrNH+ffXqVQIDA3Fzc6NGjRrs2LGDnTt30q9fP+zs7Jg1axb+/v5s2bKFhg0bUrx4ce1MV15eXgHeiXgT9uzZQ6tWrejduzeffvopZ86c4dGjR8TGxvLdd9+RmppK+/btady4Mfv27eP69eusXr2aXr16kZWVxbhx4xg1alS+YEtmvIQQQogPh4uLC56enmzatInLly+jKApGRkbUr1+fYsWKce7cOapWrUqfPn2wt7fH3Nycjz76CJDDlMXb8d5lpMjNzWXx4sXcvn2bFi1akJeXh7m5OVWqVCE5ORl7e3vWr1/PZ599xoABAxgzZgylS5dm+vTp2pPHNSThRuG2d+9eQkJC6NKlCxYWFjx79gwTExPt2RyjR49m1apVjB49Gnd3d/bt28eECRPYtGkTI0aMyLdXTNZrCyGEEB8mfX19+vbty/Hjx/n++++xt7endOnSPHz4EH19fapVqwaAj48PhoaG+V4rfQfxNhR4hPLnvVnZ2dmo1Wr27NmDq6srLVu2pH79+uzfv5/PP/+c5ORkZs+ezcSJE1myZAmZmZl07NhR+3rpaBd+moMMjxw5grW1Nf3799fObGoCqrp16+Lp6cnatWupWLEi6enpuLi4YGVlRWZmJqampujq6mpfI58JIYQQ4sNlY2ND//79CQ4Oxs3NjdKlS/Ptt99Svnx5atWqBaANvv6c7EuIN61AA7BXO8fp6elkZGRQqVIl6tevz4ULF3j69ClGRkbcvXuXWbNm4evri1qtxt7enuzsbDIyMujSpctrZYnCTbNE8Nq1azg7O1O8ePF8j+/fvx8HBwd69uzJ5cuXmTp1KpaWlnzzzTc0adIkX1nSgAohhBBCR0eH9u3bc+zYMSZNmoSuri7u7u5Mnz4dU1PTfNdK30G8bQWShv7OnTv50nqGhYWxYsUKcnJy+PLLL/H09GTu3Ln8+uuv7N69G0VR6N27NwkJCZQsWZLg4GA+/fTTd11t8Q4pisKYMWOIiopix44d2vO6EhMT6dWrF25ubkyePJnU1FSioqL45JNP5KgBIYQQQvytU6dOsWbNGoYPH649UFn6DeJde6czYHl5eYwePZr79++zdetWdHV1tUk3unXrhp6eHq1bt6ZKlSp069aN6OhoAgICaN68OfPnz+fmzZu0bt1aO0UsX5iiS0dHhzZt2nDs2DGWLFlCYGAgZmZm3L9/n7S0NGrWrAlAiRIlaNWqFfDH50E+E0IIIYT4K02aNKFZs2bAy9VTIPu8xLv3TgIwtVrNypUr6dGjB4MHD+bp06dERETQoUMH4uLieP78Oe3bt8fOzg6VSsWPP/6IjY0NgwYNYv78+WRnZ+Pt7a3tdGsOZpYvTNHm6uqKj48PK1as4Pbt29SuXZvIyEgqVKhAgwYNXrtePg9CCCGE+DuSnEu8D97JIte9e/eyYMEC5syZo00lP3bsWOLj4ylXrhyGhoacO3cOeDk1PHToUFJTU+nXrx979uxh27ZtmJmZAeQ7mFkUbYaGhowcOZJx48ZhZGREZGQkNWrUYOvWrX95Mr0QQgghxD8hwZcoSG91D1hubi4GBgYAjB49mtOnTxMWFsaLFy/w9/enTp06LFy4kC5dunD//n28vb25cuUKycnJLF++HCsrK21Zmlkv8eFKTU3VHqgsI1dCCCGEEKIweqszYAYGBqSmpjJv3jxSU1N59uwZ8+fPp27dunh5eXHkyBEiIyOZN28ejRs35ujRo2RmZjJnzpx8wRfImV4fMs0YQYkSJV47tkAIIYQQQojC5I3OgP353ITMzExGjhzJ3bt3tcsJY2JimDFjBq6urgwaNIjHjx9z4MABjIyMSEpKwtLS8i/LEkIIIYQQQojC7o1FOCqVShswabLKqNVqbt26hbOzM97e3to9YN999x3GxsbapYcnTpwA0AZfr5YlhBBCCCGEEEXFG1vXp6enx/PnzwkJCaF48eLUrFmTZs2aUaFCBX777TcArK2tKVeuHMePHyc4OJiZM2fStGlTrK2tXytLCCGEEEIIIYqa/3maSVEUXl29+PDhQ7p3705KSgpJSUkEBgYSGRmJi4sLCQkJ+Pr6smHDBnJzc+nSpQuffPIJ8DIoU6vVFMB50EIIIYQQQgjxTv1PM2CvZiSMiYkhISGBihUroquri5WVFfv27cPR0REHBwcaNmyIkZERu3btYuHChXh7ezNy5EhtdkRAlhsKIYQQQgghPgj/OAmHoigkJiZia2sLQHp6Onv37mXJkiUMHDgQExMTgoKCKF68OP3796dRo0ZMmjQJPz8/PDw8SE5OJi8vT7vcUJJsCCGEEEIIIT40/2gGbNeuXSxduhSVSoWbmxvDhg1j3bp1rFixAmdnZ7p3746hoSErV65EV1eX8uXLExsby4MHD6hQoQIA5cuXB/5I0CHBlxBCCCGEEOJD87cB2J07dxg3bhw3btzAw8ODx48fs2XLFszNzfH392fXrl08e/aMe/fuUblyZSZOnMiMGTOYOXMmKpWKdu3a4ejomK9MCbyEEEIIIYQQH6r/uAQxKyuLUaNG8dNPP/Htt9/SvHlzDAwMcHd3x9zcnO3bt7NlyxamTJlCQEAA/fv3R1dXl0ePHhEXF4eFhQUODg7v+n6EEEIIIYQQ4r31H6ejjI2N6dWrF6ampsTGxmJgYEBWVha5ubmYmpoC0K1bN5ycnNi2bRvnzp0DoEyZMjRs2BAHBwfUarV2yaEQQgghhBBCfOj+dgli/fr16dChA1u2bMHAwIBNmzZRunRpJk2apL3m66+/xtvbmydPnrz2elluKIQQQgghhBB/+K9ZEOPj4xk6dCg3b97Ex8eHIUOGUKpUKe3ZXXp6ety/fx8rK6t3VWchhBBCCCGEKJT+6xSVjY0NvXr1AqBWrVqYm5u/fKGuLnp6egBYWVnJYcpCCCGEEEII8V/81wBMV1eXNm3a0KRJE+bOncvdu3f/43U6OjpvvIJCCCGEEEIIUVT8o01aZmZm9O3bF1tbW4oVK/a26ySEEEIIIYQQRdJ/3QOmoSiKzHAJIYQQQgghxL/wj9MUaoIvlUr11iojhBBCCCGEEEXZP54BE0IIIYQQQgjx78hBXUIIIYQQQgjxjkgAJoQQQgghhBDviARgQgghhBBCCPGO6Bd0BYQQQohX+fj4EBUVle8xAwMDSpYsiZOTE/369cPZ2fmd1cPJyYlt27b95TXjxo1j9+7d/7UsLy8vZs2a9cbqlpiYSIsWLQCYMmUK3bt3f2NlCyGEeLtkBkwIIcR7Lzc3l5SUFI4ePYqPjw/h4eEFXSUhhBDifyIzYEIIId5LH330Ed999x1qtZr09HQuXLjAwoULSU1NZfLkyTg7O2Nra1ugdRw/fjwjR47U/j148GCuXr1KnTp1WLRokfZxExOTAqidEEKI95EEYEIIId5LBgYGWFpaav+uVq0a1tbWDBw4kKysLNavX8/XX39dgDWEEiVKUKJECe3fBgYGABgaGuaruxBCCKEhSxCFEEIUGm5ublSoUAGAn3/+Wfu4j48P1atXp2vXrvmu/6vHFUUhLCyMdu3aUbduXerUqUObNm1YunQpubm5b63uSUlJjB8/nubNm1OrVi0aNGhA7969OXv2bL7rTp8+jY+PD87OztSuXZvPPvuMqVOn8vjx478t/9atW9SrV4/q1avj4eFBamrqW7sXIYQQ/zuZARNCCFGoVKtWjQcPHnDnzh1ycnIwNDT8P71+yZIlfPvtt/ke+/3331m0aBHZ2dmMGjXqTVYXgJycHPr27cvvv/+ufSw1NZXIyEiio6MJDw/HwcGBy5cvM2jQoHyB4L1799i0aROXLl1ix44d6Ou//tP97Nkz/Pz8yMjIoEyZMqxYsSLfzJwQQoj3h8yACSGEKFSKFy8OvJzJev78+f/ptXl5eezatQsADw8PDh48yO7du6lVqxYAJ0+efLOV/f/Onj1LfHw8urq6hISEcPToUUJDQ9HT0yM3N5fIyEgA9u/fT25uLpUrV2b79u0cPXqUiRMnApCcnMzly5dfK1ulUjFixAgSEhIwMTFh2bJl2NjYvJX7EEII8e/JDJgQQohCS6VS/Z+u19fX59ixYyQkJFCqVCnMzMxISkrC2tqa2NhY0tLS3ko93dzcuHTpEomJiVSpUgWVSsXTp08pVqwYaWlp2uWCRkZGADx8+JDo6GhcXV3x8fGhbdu2lCpV6i/LXrFiBcnJyQBMnjyZ2rVrv5V7EEII8WZIACaEEKJQycjI0P63ubn5316rKMprj+Xm5nLhwgV++uknLl26xMOHD7XPqdXqN1fRP3n06BE//PADZ8+e5dq1a2RmZr727/r4+HDgwAHu3LnDrFmzmDVrFmXKlOGTTz6hR48efxlcaYIvgOjoaLy8vN7aPQghhPj3ZAmiEEKIQiUuLg6AihUrYmxsnO+5PwdQOTk5+f5WqVT07duXcePGERUVRYsWLZgzZw7dunV7q3W+evUqX3zxBaGhoWRnZ+Pr68vatWspX758vussLCyIiIhg9uzZuLu7U7JkSR49esTu3bvp2rUrJ06c+MvyHRwcANi1a5f2/48QQoj3k8yACSGEKDRiY2OJj48HoHnz5trHNenfX50dg/yzQwDnzp3j/PnzACxatIiGDRsCEBMT85Zq/NKaNWvIzMzE1taW7du3o6uri0qleq2+t2/f5tatW1hYWLB48WIUReHGjRsMGjSIpKQkdu7ciZubW77XtGzZkrlz5+Lu7k5ycjILFiwgNDT0rd6PEEKI/50EYEIIId5Lubm5JCUlAZCdnc3169eZM2cOAMbGxvTq1Ut7bdmyZQG4c+cOZ86cwcXFhVWrVmlfr/Hqsr8DBw5Qvnx5Ll68yO7du4GXSTreBs2/m5yczPHjx7GxsWHt2rWkp6fn+3eDg4M5ffo05ubmzJgxgxo1apCcnExWVhbAX2ZAbNasGSYmJgwZMoTJkydz5MgRYmJiqFOnzlu5FyGEEP+OBGBCCCHeS1evXn1ttgdAT0+PyZMnY2trq32sVatWhIeHo1ar6du3Lzo6Oujq6lKzZk2uXbumva5evXqULFmSZ8+esXnzZjZv3pyv7NTUVNRqNbq6b3aF/meffcaPP/5ITk4OgwcPfu35p0+fAjBmzBhiYmJIS0tj2LBh+a4xNDSkd+/e//Hf6Ny5M6tXryY+Pp65c+eyYcOGN3oPQggh3gzZAyaEEOK9p6+vT9myZXF3d2fz5s107Ngx3/MtW7Zk0qRJWFtbY2RkRJ06dVi9ejUuLi75ritdujQrVqzA2dkZU1NTypQpw6effsqKFSsAyMrKIioq6o3Xv3PnzgQGBmJra4uxsTF2dnb4+fnRv39/AE6dOgXARx99xLZt22jbti1WVlYYGBhQsmRJmjdvzoYNG3BycvqP/4a+vj7Dhw8H4Pz58xw/fvyN34cQQoh/T0f5qxRRQgghhBBCCCHeOJkBE0IIIYQQQoh3RAIwIYQQQgghhHhHJAATQgghhBBCiHdEAjAhhBBCCCGEeEckABNCCCGEEEKId0QCMCGEEEIIIYR4RyQAE0IIIYQQQoh3RAIwIYQQQgghhHhHJAATQgghhBBCiHdEAjAhhBBCCCGEeEf+H3smjmzI/FpIAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "thresh_subs_tests = pipeline(SSRTs_ThreshSubs, strip_str='_wThresh_subs')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "thresh_subs_tests.to_csv(f'result_csvs/dataset-{dataset}_metric-SSRT_wThresh_subs_tests-validationContrasts.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}