{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "Facebook_Data_Analysis.ipynb",
"provenance": [],
"authorship_tag": "ABX9TyPnANkP9t1/cPjv8vrtQRTP",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qCza4ucSFEl-"
},
"source": [
"# **FACEBOOK Data Analysis**\n"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "GCIsHw2yDXxf",
"outputId": "67f5ed1e-6830-44ab-909f-ebb347614d36"
},
"source": [
"!pip install opendatasets"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Collecting opendatasets\n",
" Downloading https://files.pythonhosted.org/packages/b6/3f/cdd30cbd950efdb1fa5c766ffb2c38d1da5314292b6cd226e3871171a776/opendatasets-0.1.20-py3-none-any.whl\n",
"Requirement already satisfied: click in /usr/local/lib/python3.7/dist-packages (from opendatasets) (7.1.2)\n",
"Requirement already satisfied: tqdm in /usr/local/lib/python3.7/dist-packages (from opendatasets) (4.41.1)\n",
"Requirement already satisfied: kaggle in /usr/local/lib/python3.7/dist-packages (from opendatasets) (1.5.12)\n",
"Requirement already satisfied: python-slugify in /usr/local/lib/python3.7/dist-packages (from kaggle->opendatasets) (5.0.2)\n",
"Requirement already satisfied: six>=1.10 in /usr/local/lib/python3.7/dist-packages (from kaggle->opendatasets) (1.15.0)\n",
"Requirement already satisfied: python-dateutil in /usr/local/lib/python3.7/dist-packages (from kaggle->opendatasets) (2.8.1)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.7/dist-packages (from kaggle->opendatasets) (2.23.0)\n",
"Requirement already satisfied: urllib3 in /usr/local/lib/python3.7/dist-packages (from kaggle->opendatasets) (1.24.3)\n",
"Requirement already satisfied: certifi in /usr/local/lib/python3.7/dist-packages (from kaggle->opendatasets) (2021.5.30)\n",
"Requirement already satisfied: text-unidecode>=1.3 in /usr/local/lib/python3.7/dist-packages (from python-slugify->kaggle->opendatasets) (1.3)\n",
"Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests->kaggle->opendatasets) (2.10)\n",
"Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests->kaggle->opendatasets) (3.0.4)\n",
"Installing collected packages: opendatasets\n",
"Successfully installed opendatasets-0.1.20\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "OSrPIgm8DYWm"
},
"source": [
"dataset_url = 'https://www.kaggle.com/sheenabatra/facebook-data'"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "EQrghyBcER9n",
"outputId": "e10d0b99-f3dd-4e02-857a-7c1e273fe92a"
},
"source": [
"import opendatasets as od\n",
"od.download(dataset_url)"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Please provide your Kaggle credentials to download this dataset. Learn more: http://bit.ly/kaggle-creds\n",
"Your Kaggle username: manikantasanjayv\n",
"Your Kaggle Key: ··········\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"100%|██████████| 1.82M/1.82M [00:00<00:00, 86.2MB/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"Downloading facebook-data.zip to ./facebook-data\n",
"\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"\n"
],
"name": "stderr"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "TVxVGUwXEUZa"
},
"source": [
"data_dir = './facebook-data'\n"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "c1daImvuE9Kx",
"outputId": "dd4235bd-cd9f-4401-d5f7-4b6c993e364b"
},
"source": [
"import os\n",
"os.listdir(data_dir)\n"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['pseudo_facebook.csv']"
]
},
"metadata": {
"tags": []
},
"execution_count": 7
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "gG7SRuhqE_M_"
},
"source": [
"project_name = \"facebook_data_analysis\" "
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "5YSTfD-kFVB0"
},
"source": [
"## **Data Preparation and Cleaning**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "Qr_8TgDEFA7C"
},
"source": [
"import numpy as np \n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"%matplotlib inline\n",
"import seaborn as sns"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "AeESvwobFZl_"
},
"source": [
"df = pd.read_csv('./facebook-data/pseudo_facebook.csv')"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 225
},
"id": "UxhyuZBrFcNe",
"outputId": "c77c8f66-0f12-4a4e-ff41-8d03ce8c573e"
},
"source": [
"df.head()"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" userid | \n",
" age | \n",
" dob_day | \n",
" dob_year | \n",
" dob_month | \n",
" gender | \n",
" tenure | \n",
" friend_count | \n",
" friendships_initiated | \n",
" likes | \n",
" likes_received | \n",
" mobile_likes | \n",
" mobile_likes_received | \n",
" www_likes | \n",
" www_likes_received | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 2094382 | \n",
" 14 | \n",
" 19 | \n",
" 1999 | \n",
" 11 | \n",
" male | \n",
" 266.0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" 1 | \n",
" 1192601 | \n",
" 14 | \n",
" 2 | \n",
" 1999 | \n",
" 11 | \n",
" female | \n",
" 6.0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" 2 | \n",
" 2083884 | \n",
" 14 | \n",
" 16 | \n",
" 1999 | \n",
" 11 | \n",
" male | \n",
" 13.0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" 3 | \n",
" 1203168 | \n",
" 14 | \n",
" 25 | \n",
" 1999 | \n",
" 12 | \n",
" female | \n",
" 93.0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" 4 | \n",
" 1733186 | \n",
" 14 | \n",
" 4 | \n",
" 1999 | \n",
" 12 | \n",
" male | \n",
" 82.0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" userid age dob_day ... mobile_likes_received www_likes www_likes_received\n",
"0 2094382 14 19 ... 0 0 0\n",
"1 1192601 14 2 ... 0 0 0\n",
"2 2083884 14 16 ... 0 0 0\n",
"3 1203168 14 25 ... 0 0 0\n",
"4 1733186 14 4 ... 0 0 0\n",
"\n",
"[5 rows x 15 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 11
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "PIy5jiYAFecy",
"outputId": "7bf928f2-2a9a-4231-a8cd-0781ce3a6612"
},
"source": [
"df.shape"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(99003, 15)"
]
},
"metadata": {
"tags": []
},
"execution_count": 12
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 319
},
"id": "XueTdqh4FgHd",
"outputId": "44533bc8-f9fb-4c1a-a540-1e466a308fb2"
},
"source": [
"df.describe()"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" userid | \n",
" age | \n",
" dob_day | \n",
" dob_year | \n",
" dob_month | \n",
" tenure | \n",
" friend_count | \n",
" friendships_initiated | \n",
" likes | \n",
" likes_received | \n",
" mobile_likes | \n",
" mobile_likes_received | \n",
" www_likes | \n",
" www_likes_received | \n",
"
\n",
" \n",
" \n",
" \n",
" count | \n",
" 9.900300e+04 | \n",
" 99003.000000 | \n",
" 99003.000000 | \n",
" 99003.000000 | \n",
" 99003.000000 | \n",
" 99001.000000 | \n",
" 99003.000000 | \n",
" 99003.000000 | \n",
" 99003.000000 | \n",
" 99003.000000 | \n",
" 99003.000000 | \n",
" 99003.000000 | \n",
" 99003.000000 | \n",
" 99003.000000 | \n",
"
\n",
" \n",
" mean | \n",
" 1.597045e+06 | \n",
" 37.280224 | \n",
" 14.530408 | \n",
" 1975.719776 | \n",
" 6.283365 | \n",
" 537.887375 | \n",
" 196.350787 | \n",
" 107.452471 | \n",
" 156.078785 | \n",
" 142.689363 | \n",
" 106.116300 | \n",
" 84.120491 | \n",
" 49.962425 | \n",
" 58.568831 | \n",
"
\n",
" \n",
" std | \n",
" 3.440592e+05 | \n",
" 22.589748 | \n",
" 9.015606 | \n",
" 22.589748 | \n",
" 3.529672 | \n",
" 457.649874 | \n",
" 387.304229 | \n",
" 188.786951 | \n",
" 572.280681 | \n",
" 1387.919613 | \n",
" 445.252985 | \n",
" 839.889444 | \n",
" 285.560152 | \n",
" 601.416348 | \n",
"
\n",
" \n",
" min | \n",
" 1.000008e+06 | \n",
" 13.000000 | \n",
" 1.000000 | \n",
" 1900.000000 | \n",
" 1.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
"
\n",
" \n",
" 25% | \n",
" 1.298806e+06 | \n",
" 20.000000 | \n",
" 7.000000 | \n",
" 1963.000000 | \n",
" 3.000000 | \n",
" 226.000000 | \n",
" 31.000000 | \n",
" 17.000000 | \n",
" 1.000000 | \n",
" 1.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
" 0.000000 | \n",
"
\n",
" \n",
" 50% | \n",
" 1.596148e+06 | \n",
" 28.000000 | \n",
" 14.000000 | \n",
" 1985.000000 | \n",
" 6.000000 | \n",
" 412.000000 | \n",
" 82.000000 | \n",
" 46.000000 | \n",
" 11.000000 | \n",
" 8.000000 | \n",
" 4.000000 | \n",
" 4.000000 | \n",
" 0.000000 | \n",
" 2.000000 | \n",
"
\n",
" \n",
" 75% | \n",
" 1.895744e+06 | \n",
" 50.000000 | \n",
" 22.000000 | \n",
" 1993.000000 | \n",
" 9.000000 | \n",
" 675.000000 | \n",
" 206.000000 | \n",
" 117.000000 | \n",
" 81.000000 | \n",
" 59.000000 | \n",
" 46.000000 | \n",
" 33.000000 | \n",
" 7.000000 | \n",
" 20.000000 | \n",
"
\n",
" \n",
" max | \n",
" 2.193542e+06 | \n",
" 113.000000 | \n",
" 31.000000 | \n",
" 2000.000000 | \n",
" 12.000000 | \n",
" 3139.000000 | \n",
" 4923.000000 | \n",
" 4144.000000 | \n",
" 25111.000000 | \n",
" 261197.000000 | \n",
" 25111.000000 | \n",
" 138561.000000 | \n",
" 14865.000000 | \n",
" 129953.000000 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" userid age ... www_likes www_likes_received\n",
"count 9.900300e+04 99003.000000 ... 99003.000000 99003.000000\n",
"mean 1.597045e+06 37.280224 ... 49.962425 58.568831\n",
"std 3.440592e+05 22.589748 ... 285.560152 601.416348\n",
"min 1.000008e+06 13.000000 ... 0.000000 0.000000\n",
"25% 1.298806e+06 20.000000 ... 0.000000 0.000000\n",
"50% 1.596148e+06 28.000000 ... 0.000000 2.000000\n",
"75% 1.895744e+06 50.000000 ... 7.000000 20.000000\n",
"max 2.193542e+06 113.000000 ... 14865.000000 129953.000000\n",
"\n",
"[8 rows x 14 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 13
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "mIdLkQv6FhV5",
"outputId": "e65cb086-e11a-4823-f19e-30aa4c19f565"
},
"source": [
"df['age'].value_counts()"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"18 5196\n",
"23 4404\n",
"19 4391\n",
"20 3769\n",
"21 3671\n",
" ... \n",
"87 42\n",
"112 18\n",
"111 18\n",
"110 15\n",
"109 9\n",
"Name: age, Length: 101, dtype: int64"
]
},
"metadata": {
"tags": []
},
"execution_count": 14
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "3o1FkmKvFiwb"
},
"source": [
"df = pd.get_dummies(df,columns=['gender'])"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "BFvmELFlFlZG"
},
"source": [
"## **Exploratory Analysis and Visualization**\n",
"**Analysing facebook data visually**\n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "5aLCR3IqFkpT"
},
"source": [
"import seaborn as sns\n",
"import matplotlib\n",
"import matplotlib.pyplot as plt\n",
"%matplotlib inline\n",
"\n",
"sns.set_style('darkgrid')\n",
"matplotlib.rcParams['font.size'] = 8\n",
"matplotlib.rcParams['figure.figsize'] = (20,5)\n",
"matplotlib.rcParams['figure.facecolor'] = '#00000000'"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "CJM5TrOCGV74"
},
"source": [
"**AGE ANALYSIS** - Exploring which age group uses more facebook comparatively and we clearly see teenagers are more using facebook comparatively to others"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 349
},
"id": "T0WdeHulGSZj",
"outputId": "e264419c-ff5a-4092-a6c2-21e45a589fdd"
},
"source": [
"sns.countplot(x='age',data=df)"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
""
]
},
"metadata": {
"tags": []
},
"execution_count": 17
},
{
"output_type": "display_data",
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABJQAAAE7CAYAAACL2NvZAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nO3de5glZ1kv7F/SvdY0gWSG6AAKbpFPLRRELgQEIXIUwhmSAMpBEJWjgIioIJ9u3chWRFERQXTLQQ4KIQmQQDipHASBDRthg74istnIx9EwwwjM9Exnvj/WatJTXW/1qmFWT3fPfV9XrnTX+k31u6rW865aT1dVn3b06NEAAAAAwKxOP9kDAAAAAGB70VACAAAAYBANJQAAAAAG0VACAAAAYBANJQAAAAAG0VACAAAAYJDFkz2Ab8aVV155dGXl6MkeBgAAAMCOMRotfCnJ3r7Mtm4orawczb59XzvZwwAAAADYMfbuPfNTG2Vc8gYAAADAIBpKAAAAAAyioQQAAADAIBpKAAAAAAyioQQAAADAIBpKAAAAAAyioQQAAADAIBpKAAAAAAyioQQAAADAIBpKAAAAAAyioQQAAADAIIsnewD0O3v3riyMx72ZleXlXLH/0CaNCAAAADjVaShtcQvjcT73/Gf0Zq7zmKcn0VACAAAANodL3gAAAAAYREMJAAAAgEE0lAAAAAAYREMJAAAAgEHmclPupmmun+S9Sf4pyXIp5S5N0zwlyX2SfCrJw0sph2ddNo8xAgAAAHB85nmG0ltKKbefNpOuleQOpZTbJvlwkvvOumyO4wMAAADgOMzlDKWpOzRN884kFyUpSf5uuvytSR6c5KszLnv1HMcIAAAAwEDzaih9Nsn3JjmU5LVJzkzyhelj+5Psmf73lRmWAQAAALCFzKWhVEo5lEkzKU3TXJpJk+i604fPSrIvk4bR9WZYVrWwcFr27DnjhI59u7IdAAAAgM0yr5tyn1lKOTD99jZJnpvkQUmeleTOSf4hyfuTPHaGZVUrK0ezb9/X5vEUtoy9e8+cKbfTtwMAAACwOWbpRczrptznNE3zgaZp3p3kM6WU9yZ5R9M070py0ySXlFK+MMuyOY0PAAAAgON02tGjR0/2GI7b4cMrR3f6mTl7956Zzz3/Gb2Z6zzm6fniFw/0ZgAAAABmsXfvmR9IcvO+zLzOUAIAAABgh9JQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABlk82QPg1HXN3eMsjnf1Zo4sH8qX9y9v0ogAAACAWWgo7SBn796VhfG4N7OyvJwr9h/apBH1WxzvSnnefXozzeNem0RDCQAAALYSDaUdZGE8zmf/5Gm9mW977DOTbI2GEgAAALA9uYcSAAAAAINoKAEAAAAwiIYSAAAAAINoKAEAAAAwiIYSAAAAAINoKAEAAAAwiIYSAAAAAINoKAEAAAAwiIYSAAAAAINoKAEAAAAwiIYSAAAAAINoKAEAAAAwiIYSAAAAAINoKAEAAAAwyOI8V940zZOSnF9KuW3TNM9JcvMkHyylPHH6+EzLAAAAANg65naGUtM0u5LcdPr1zZJco5RyTpJx0zS3mHXZvMYHAAAAwPGZ5yVvP53kJdOvb5XkLdOv35rk1gOWAQAAALCFzKWh1DTNKMntSyl/M120J8lXpl/vn34/6zIAAAAAtpB53UPpoUleseb7/UnOmn59VpJ9SVZmXFa1sHBa9uw54wQNeXsbsh222zbbbuMFAACAnW5eDaUmyU2bpnl0khsl+dYkN0nyqiR3TvLiJEeSPGqGZVUrK0ezb9/X5jH+LWPv3jNnyu3b97VB2a1gu40XAAAATgWzfF6fyyVvpZRfLqXctZRybpKPllJ+I8nBpmnemWSllPK+UsoHZ1k2j/EBAAAAcPzmdYbSN5RSbjv9/xM7HptpGQAAAABbxzz/yhsAAAAAO5CGEgAAAACDaCgBAAAAMIiGEgAAAACDaCgBAAAAMIiGEgAAAACDaCgBAAAAMMjiyR4AJ8fZu3dlYTzuzawsL+eK/Yc2aUQAAADAdqGhdIpaGI/zmec9oTdz3cf9URINJQAAAOBYLnkDAAAAYBANJQAAAAAG0VACAAAAYBD3UGJDZ+8eZ2G8qzezsnwoV+xf3qQRAQAAACeThhIbWhjvyqef+9DezHc8/i+TbI2G0jV3j7O4QQPsyPKhfFkDDAAAAI6LhhI7zuJ4Vz74gnv1Zm726NdnqzTAAAAAYLtxDyUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGCQxZM9gFPR2buXsjAeVR9fWT6cK/Yf3MQRAQAAAMxOQ+kkWBiP8vkX/F718Ws/+slJNJQAAACArcklbwAAAAAMoqEEAAAAwCAaSgAAAAAMoqEEAAAAwCAaSgAAAAAMoqEEAAAAwCAaSgAAAAAMoqEEAAAAwCCLJ3sAO8XZu5eyMB5VH19ZPpwr9h/cxBEBAAAAzMdcGkpN09w4yQuTrCT51ySPSPL7SW6e5IOllCdOc8+ZZdl2sDAe5Qsv+OPq49d69M8l0VACAAAAtr95XfJWSik/Uko5Z/r9LZNcY/r9uGmaWzRNc7NZls1pfAAAAAAcp7mcoVRKObzm20NJ7pTkLdPv35rk1kmOzLjs/fMYI/Nxzd3jLI539WaOLB/Kl/cvb9KIAAAAgBNtbvdQaprm3kmemeTjST6b5CvTh/YnuVEmzaN/m2FZ1cLCadmz54wTO/A5GjLWoc9rXuseml0cLeTfnnvf3twNHn9J9uyZ/aU3r328nV47AAAAsJXMraFUSnldktc1TfPcTBpFZ00fOivJvkzurzTLsqqVlaPZt+9rJ3jkx2fv3jM3zKyO9URnV/M7OTvEvNYLAAAAp4JZPlfP5R5KTdOsvebpK0mOZnLZW5LcOck/JHnPjMsAAAAA2ELmdVPuc5umeXvTNG9Pcu0kv53kYNM070yyUkp5Xynlg7Msm9P4AAAAADhOM13y1jTNg0spL1/z/f1KKRfX8qWU1yZ5bWvxEztyMy0DAAAAYOvYsKHUNM1Ckp9pmuYVSU6b/pufSVJtKAEAAACwc/U2lJqmeViShye5aZK3ZdJQWk7yhrmPDAAAAIAtqbehVEp5SZKXNE1zi1LK+zdpTAAAAABsYTPdQynJjZumeXaSldUFpZQ7zmdIAAAAAGxlszaUHp3knFLK8jwHAzXX3D3O4nhXb+bI8qF8eb+XKAAAAMzbrA2ldya5YdM0H01yNElKKVfObVTQsjjelY/8yb17Mz/w2Ndlcouv2WlUAQAAwHCzNpR+aPrfqqNJXPLGtrc43pX3/em9ejO3fNTrM7RRBQAAADvZTA2lUsod5j0QAAAAALaHmRpKTdP8baaXuq1yU24AAACAU9PgM5SaprlJkvPmNiIAAAAAtrTTj+Pf/HOSu53ogQAAAACwPcx6yds7M7nk7bTpoj+b24gAAAAA2NJmveTtnHkPBAAAAIDtYdYzlO6Y5L8lOZJkIcl/LaW8dZ4DAwAAAGBrmqmhlOQZSe5aSjnQNM1ZSd6UZMc3lM7evZSF8aj6+Mry4Vyx/+AmjggAAADg5Ju1oXRakiunX1+Zq+6ltKMtjEf54gteWH1876MfmURDCQAAADi1zNpQenqSy5umWb0x99PnNyQAAAAAtrLTZ8z9QpIfLaX8aJLbJfn5+Q0JAAAAgK1s1obS1UspR5OklHJlkjPnNyQAAAAAtrJZL3n7eNM0z0jy7iS3TvLx+Q0JAAAAgK1s1jOUHpnkfya58fT/Pzu3EQEAAACwpc10htL0crdL5jwWAAAAALaBWc9QAgAAAIAkGkoAAAAADKShBAAAAMAgGkoAAAAADKKhBAAAAMAgM/2VN2CYa+4eZ3G8qzdzZPlQvrx/eZNGBAAAACeOhhLMweJ4V97+Z/fozdzuZy9LoqEEAADA9uOSNwAAAAAG0VACAAAAYBANJQAAAAAG0VACAAAAYBA35YYZ+cttAAAAMKGhBDNaHO/K37/wnr2Z2zzy0vjLbQAAAOx0LnkDAAAAYBANJQAAAAAG0VACAAAAYBANJQAAAAAG0VACAAAAYBANJQAAAAAG0VACAAAAYJDFeay0aZofTvKcJFcmeX8p5UlN0zwlyX2SfCrJw0sph2ddNo8xAgAAAHB85nWG0qeS3LGUctsk12qa5nZJ7jD9/sNJ7ts0zbVmWTan8QEAAABwnOZyhlIp5XNrvj2c5EZJ/m76/VuTPDjJV2dc9up5jBEAAACA4zOXhtKqpmlukmRvkn2ZXP6WJPuT7Jn+95UZllUtLJyWPXvOOMGjHmbIz59XdquMQ3a+2a3itNOOZHFxV2/myJFDOXp0rtMLAAAAJ9HcPvE1TXN2kj9O8oAkP5TketOHzsqkwbR/xmVVKytHs2/f107swNfYu/fMDTOrP/9kZlfzstszu93s3XtmXvOic3sz5//U5fniFw9s0ogAAAA4kWb5TDuXeyg1TbOY5GVJfnF6+dv7k9xu+vCdk/zDgGUAAAAAbCHzOkPp/klukeRZTdMkyVOTvKNpmncl+b9J/qCUstw0zYbL5jQ+2DL27B5nNO6/hOzw8qHs27+8SSMCAACAfvO6Kfcrk7yytfg9SX6nlfudWZadKGfvXsrCeNSbWVk+nCv2H5zHj4dOo/GuvO3P79GbudPPXJZEQwkAAICt4ZS6a+7CeJQvPv/FvZm9j3l4Eg0lAAAAgJq53EMJAAAAgJ1LQwkAAACAQTSUAAAAABhEQwkAAACAQTSUAAAAABhEQwkAAACAQTSUAAAAABhEQwkAAACAQRZP9gCA2e3ZPc5ovKs3c3j5UPbtX96kEQEAAHAq0lCCbWQ03pU3/Y+792bu+tNvSLKs+QQAAMDcaCjBDjUa78plf3G33sw9HvHGJBpKAAAADKOhBAAAADB19u6rZWHc3y5ZWT6SK/Z/fZNGtDVpKAEAAABMLYwX84Xnvq03c63H32mTRrN1+StvAAAAAAyioQQAAADAIBpKAAAAAAyioQQAAADAIBpKAAAAAAyioQQAAADAIBpKAAAAAAyioQQAAADAIBpKAAAAAAyyeLIHAJx8e3aPMxrv6s0cXj6UffuXN2lEAAAAbGUaSkBG41157V/crTdzn0e8MYmGEgAAAC55AwAAAGAgDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGAQDSUAAAAABtFQAgAAAGCQxZM9AGDn2rN7nNF4V2/m8PKh7Nu/vEkjAgAA4ETQUALmZjTelb9+0bm9mQf+1OVJNJQAAAC2E5e8AQAAADCIM5QAYAs7c8+uLI3GvZmDh5dzYN+hTRoRAABoKAFbyJ49o4xGS9XHDx8+mH37Dm/iiODkWxqNc/eLf6M384b7/XoOREMJAIDNo6EEbBmj0VJe/uK7Vh9/8MPflERDCQAA4GRzDyUAAAAABnGGErAtuTwOAADg5NFQAral0WgpL3nxXaqPP+zhb87xXB63e88o455GVZIsHz6Y/ZpVAADAKUxDCWCN8WgpL/zL+n2ckuSRD3UvJwAA4NQ2l4ZS0zTfnuTSJN+f5BqllCNN0zwnyc2TfLCU8sRpbqZlAHzznH0FAACcKPM6Q+mKJHdKcnGSNE1zs0waS+c0TfP8pmlukWRllmWllPfPaYwAp5TxaCm/+df9Z1/92gOdfQUAwMbO3n1GFsYLvZmV5ZVcsf9rmzQiNttcGkqllINJDjZNs7roVkneMv36rUluneTIjMs0lAAAAGALWRgv5PPP+cfezLWf9IObNBpOhs26h9KeJP82/Xp/khtl0jyaZVnVwsJp2bPnjBM/2AHr3ArZrTIOWdntnB1qnus+2Xbyc9sqrjz9yuxaGPVmDq0czulXnj7zOu03AGAr2snHKDv5uc1isxpK+5OcNf36rCT7Mrm8bZZlVSsrR7Nv3+ynz+3de+ZMudV1zpLfCtnVvKzsds4m86ujIYaOeTvZyc9tKzhzz64sjca9mYOHl3Ng36Hs3Xtm7n7Jr/Zm33Df38oXrzhgvwEAW9JOPkbZyc9tVrNsg81qKL0nyaOSvCrJnZO8OJOzkWZZBvBN2ehm1G5EfWo5c884S6NdvZmDhw/lwL7lQU2ipdE4d7/kF3uzb7jvs3MghwaPeVZDxgsAAN+Mef2Vt1GSNyb5wSRvSvK0TO6p9M4kHyqlvG+am2kZwDdjPFrK/3jJXaqP//TD3hw3oj51LI125W6v/cnezBvv89IcyHKWRuPc7bWP2yD7vLk2iYZYGo1z94v/e2/mDfd76tzHe+aepSyN6pf0HTx8OAf2HZzrGAAAmK953ZT7cCZnGK313o7cE2dZBgCcePNq/CyNRrnHRc+tPn7ZeY/PgWgoAQBsZ5t1yRvAjrPRpXSJy+m+GcMuTZs9y1WWRqPc4+LfrT5+2f2eMvfGz04+m2mj55Zs7+cHAJzaNJQAjtN4tJQ/edldezOPfcibsh0vpztrzzi7NmjQHDp8KF+ZY4NmabQrD7nk3N7My+57+fTStF0593X36M1efu/LciAaSsdrvmcz/Un18cvOe+y2PZtpaTTKPS98WW/m0gsesm2fHwBwatNQAmCdXaNd+dVX9zdzfuv+lycDGzRboVHF8Zk0fp5Tffyy856kMQIAcArRUALYBPO6PG67XXa3a7Qrj7mov1H1/POGN6o4NczrEjKXpg135p6rZWnUfxh58PCRHNj39U0aEQCw2TSUADbBeLSUP3p5/+VxT3jw8MvjxqOl/PZf9a/3V358vpfdOeuIzbI0GuUer/nT3sxl5z9q8JlSS6NR7vmaF/VmLj3/p5yBtcbSaDH3vvC1vZnXXXCfHNik8QAAm09DCWCL2Y5nHT35wv6zjn7vAmcdAQDATqKhBLDFjEdL+b1X9p919OSf2J43+wYAAHaG00/2AAAAAADYXpyhBADsOG7gDQAwXxpKAMCOM7mB95/3Zi47/2eO8wbeL+nNXHr+wwavV6MKANhuNJQAAE6ypdEo97zwFb2ZSy94UA7kYM7cc7UsjfoP4Q4ePpID+74+KAsAMISGEgDANrI0Wsw9L/zr3sylFzwwB1azr351f/b+98+BEzg+AODU4KbcAAAAAAyioQQAAADAIBpKAAAAAAziHkoAALiBNwAwiIYSAABZGi3mXhde1Jt5/QXnuYE3AJDEJW8AAAAADKShBAAAAMAgGkoAAAAADKKhBAAAAMAg2/6m3GfvXsrCeNSbWVk+nCv2H9ykEQEAAADsbNu+obQwHuWLz39Zb2bvYx6SREMJAGCznbnnalka9R9yHjx8JAf2fX2TRgQAnAjbvqEEAMDWtTRazL0vvLQ387oL7pkDmzQeAODEcA8lAAAAAAbRUAIAAABgEA0lAAAAAAZxDyUAALaEITfwdrNvADi5NJQAANgSlkaLuc+Fb+zNvPaCu+XANHvfC9/cm73kgrsMvtm3RhUAzEZDCQAAppZGi7nfa97em7n4/Nv5q3TASXX27jOyMF7ozawsr+SK/V/bpBFxKtJQAgBgR3PWEbDTLIwX8rnf/WRv5jpP+a5NGg2nKg0lAAB2tMnlcX/Tm7nkgju6PA4ABtBQAgCA47A0Wsx5r/n73sxF59/G5XEA7EgaSgAAMGdn7jkjS6P++50cPLySA/vc7wSA7UFDCQAA5mxptJDzX/Pe3sxrzv9hZzMBsG1oKAEAAHBSXHP31bM4Pr03c2T5ynx5/1c3aUSnNn89buc7e/fVsjDubwWtLB+ZaV0aSgAAsMVsdInc2svjhmRhq1kcn573/8UXejO3eMS1kmg+bYaF8UI+9/sf681c5xe+f5NGwzwsjBfzhT/5697MtR77wJnWpaEEAABbzNJoIRe85oPVxy88/2bfuDxuabSQ+7/mI9Xsq8//gW9kd3Lzafeeq2c86m82LB++Mvv3aTZsV4vj0/OhP+9vPt30Z661SaPZPpx1xLxoKAEAwCliabSQB7zmn6uPv+r8Gx7XfZzO2nNGdm1w0/FDh1fylTk2q8aj0/Ociz/Xm3nS/a4zt58PW9XCeCGf+71/6c1c58nfu0mjYSfRUAIAANYZ8pfpdo0W8uiLP92bfcH9viPJ1mg+ATvDrPcDumL/1zdpRKcWDSUAAGCdpdFCfvyiT/Zm/uq87xp8RtOu0UJ+5eLP9GZ++37XHbhW2JrO3n31LPTc92ll+cpc4Z5Px21hvJjP/+Hf92au/cTbJNF8mgcNJQAAYEvaveeMjDc4m2n58Er2Dzybacj9lvbsuXpGG2QPH74y+wZmt4Ih473mnqtncYPskcNX5stb5LkNvYH3Rvnjvdn3wvj0/Puz65diXu8Xr7oMcyff62jIc5vXdlgYL+bzf/T23sy1n3C7Qes81W3JhlLTNM9JcvMkHyylPPFkjwcAANh849FCnnHxZ3szT7/ftx3Hek/PCy76fG/m0eddO0kyGp2eF1/0xd7sw8/b+43sK1/zpd7sT5z/rQNGOjGvptZodHre9or+53anB02e2+Lo9LzjZf3ZH33IJLsVmk+L49Pz0Rf07+MbPfrax+T/5Xn1/Pc+7qrs/JpPC/nss/rP3vu2X9qeZ+8tjBfy+T/4QG/m2j//Q1dl//C9/dkn/vAJGxvHb8s1lJqmuVmSa5RSzmma5vlN09yilPL+kz0uAACAE2Vo4+f1r+pvVN3rAZNG1Wh0ei7/q/7suT8+vKk1xOLo9LznJf3Np1s/bO9cxzBPi+PT88k/rJ919F1PdPN3Tg1brqGU5FZJ3jL9+q1Jbp1EQwkAANgxRqPTc9GF/Y2f8y6Yb+MH+OYNuTfTVsieSKcdPXr0hK7wm9U0zdMyudTt8qZp7pzkR0opv1mJfzHJpzZvdAAAAAA73ncm6T2VcCueobQ/yVnTr89Ksq8nu33PkwQAAADYpvov2j053pPkTtOv75zkH07iWAAAAABo2XINpVLKB5McbJrmnUlWSinvO9ljAgAAAOAqW+4eSgAAAABsbVvuDCUAAAAAtjYNJQAAAAAG2Yp/5W2wpmm+PcmlSb4/yTWS3DDJC5OsJPnXJI8opRztypZSjkyXPynJ+aWU2/as93pJ3pvkn5Isl1LuUsuWUo40TfOTSR6WZCHJg0spn6ms985JfmV1VUkeU0q5pJIdJ3l1kqtn8hfxHlBKOVTJJsnLklw7yftLKb+0Zrw/nOQ5Sa6cPvakpmmekuQ+ST6V5OGllMNd2SS/lOQdSX4gyU1LKf9aW2+SP0ry0iRHk/x7koeWUlYq2d9K8rokh6fP7YGllK/Xxjtdfl6SPyylfMcGz21/kv81jZxXSrmiJ/tjSZ6aScP1yaWUD1TG+5IkfzBd53dOx/EHleyTp9vhvyRZTvLjpZQv9YzhudPt+29JfnbNNrtxWq/tJL+f5OZJPlhKeeKa7dDOPj3J69N67VeyL+ja3pXs7yf503TX27rxllKOVuqtnf3NTG7Kv67eerbFQ9Ndc+3sq5L88uqqcmzNtbM/N8131Vw7+8gkf5mOmlsz7m8896ZpntO179rZJA9Ix7xVyT45lX3XkX10exuu7ruu8XZ9X1nvQ1KZKyvboXOu7FjvM1KZKzuyd0llruzI3j71ufL67efSM1cek01yj9Tnynb2UanPle3sg1KfK9eNd7q8a67sem6dc2VPvjZftsf8S6nPl+3suanPl11j6Jwvp/ljXltJfjGVmuvIds6XHdlfT/LfU6m5Sraz5rpqoVZzreyvJrko9fmy/dzu1P45leyfJfnZ1YfSqrmO9b4wlZprZR+W5HfSXXPnplXnSb4n3TXXzj4hyS+ku+ba2WclOS/dNdfOPn663q6aWzfeUsollZrrem4vSb3muvJfTXfNtbO/k+S+0+/bNdfOPm66LbpqrmsMd0r3McoZac27SX473cco7ewTklyc7mOUdvaZqR+jtLO/luT56T5GWTfeUsqhyjFKO7t6LNz1maBrOzww3ccn7exfJFl9Pu3jk3b2J5O8oj3+njG8JN01t5jWe2DP+9wx2Uzmntr7XDv7/NTf59rZZ6X+PrduvNPlXTXX9dxqnwm6srX3uPZ4X5H6e1w7+yupv8d1jWHde1zlc+e6Y8rpsh9J8l2Z/PX0zmxrfR/rW++azy2L0+e6uye7epy8kOS7M3k9Vsc7HfOvJ3nKdP219V4/k2OBTyS5cSafj/u2w09m8l520ySjnvWuznfjJLfI5LV6RiW7WmPXnG6vpZ71ru7X70jy/yTZk8ln9Wu192Ntv3Vla/utku3cb5Vs5+e3VOyUM5SuyOTNbfUvwpVSyo+UUs6Zfn/znmyaptmVyQtso/UmyVtKKbfv+IB0TLZpmusmuV0p5U7T/Gdq2VLK5dPM7ZP83yRv7RnDuUneO82+b/p9LXu/JP9YSrlDkqs1TfODa7KfSnLH6ZvltZqmuV2SO0y//3CuOghZl82kYXffJBd2bLN29npJ7llK+dEkn0xy957sdZPctpRyuyQfSHLPnvH+wHT5BUk+3TeGafYjq9t47cFaJfuoJD82zX6gZ7wra/bbhzMpxlr2nEwOOH40yYsyOfCujeGcJOPpej/a2g7t1/YtMyn+c5KMm6a5RU/2Bln/eq5lxx3bpZZd6qm3dbXYU2/t7LemXm9d+R9Nveba2S/11Fw7+3Op11w7+/Op19wxc03TNDdLfd+156WuuaiWrdVKV7Zvrlw3N/bsu67HqvuutR365spjshvMle0x9M2V7WzfXHnMc2ma5lqpz5Xt530k9bmynd2X+lzZzn459bmynV3VNVd2ZWtzZde2uFrq8+Ux2VLKh3rmy1iV9KgAABEOSURBVPY4bpr6fNkewy1SmS/br61MDtA7a64j+x+p1FxHtqRScx3Zd9dqrqsWajXXsd7PpFJzHdm0f07PGF5eq7mO9f5wKjXXkb1lKjXXUecfTKXmOrKXp1JzHdkLU6m5juxbUqm5nnlpXc1VstWa68i/LZWa68j+ea3mOrJfSqXmOrL/kfoxSnve/ZXU3+fa2Zum/j7Xzt4w9fe5dvb6Pe9z694net7nut5Tau9z7eyPp/4+186mVnMd2ft2jKlvDLX3ufZ7YN9ngmOymXwIrb3PtbP/JfX3uXa27zNB7T27632uK1urua5s7T2uPd6jPe9x7WzfZ4KufdFVb+3PneuOKVeXJbldJr8g+Wgtu2Z978vkF3LV9WZ6nJnJcfc7knykJ1tKKT8yHcPlG4xh9djsu6fr7BtDMpmX75hJc6RvO1x3+vN/LJPXYDW7Ot9N1/uPmTStamM4d/r4HZM8N8nHe7L3m67vTpk0Sj/StR/X/vv2fuvK1vZbJdu53yrZ0jNvrrMjGkqllIOllC+v+f7wmocPZc3k0s5O/XQmXfve9U7doWmad05/e9GXvWuShaZp3tY0zXObplnYYL1pmuYGST5fSvnPnuwnMunuJpPu5n/0ZG+QyaSWJB/KpNO5mv1cKeXg9NvDSW6U5O+m3781ya17siullM+3x1/J/kcpZf/af9uTPVxKuXL6/UKmhVkbQ9M0d5+OdfXfVLNJvm+63367aZrTerLnTNf3xqZp/rJpmqtvsN5MM9cpa34r05FdfU7J+v3Wzt4x9f3Wfm3fKZMJNVm/39rZj3e97nqy655rJfvp2veVbK3e2tmFVOqtkr9N6jXXOeZKzbWz/5B6zbWzZ6Sy76bWPvdbpbLv2tnanFHJdr5OK9m+fdkeb9f3fdnqvmtlq3Nl7Wd27beObHWu7MhW58qO53LzVObKdraUcrQ2V3Zkv1ybKzuyK7W5smO8qc2VXdlU5spK/tapzJeVdXfOlx3Zz6QyX3Zk+/bdMa+t6XhrNdfOHu6puXb2iz01186u3QftmuuqhVrNtdfbN1+2s+d2/Jy+MdRqrr3evpprZzequW/8zEx++/x308VdNbd2fAc2qLm12U9vUHNrs/s3qLljttEGNdfenhvV3NptcYv019y6fdVTc2vXW9Jfc2uz3576vmu/Bo6mXnPrXi89NdfOfqKn5vpeh+2a68rWaq6d/UDqNdfOfmfqNdc53krNtbP/p+e5trPXT32/teuxr+bW1W5PzbWz399Tc13rrdXcumxPzXXNNbWaa2dvm3q9dc5hlXprZ2+fer11Zdf9nI7jwq5jyltl0vQ8mOQNmZzp0plds74rM/kFV3W9q8eZ0/V+NZM6r2UPr443yYFMarA23mRSfy/Ksa+NWvYO0+UP3yB710y292WZXP2w0XqTyTz3/60ZR1f2E0muPn1uS5n8ErGWvUGSD0+z783k7KDa8X3nfuvK1vZbJdu53yrZjT4fHGNHNJS6NE1z76Zp/ncmv5Fc98a4JjdKcvtSyt/MsNrPJvneTF7Ad26a5iY92Wtn0lG+U5KvZXLa6EbOy+R03z4fT3Lrpmk+mskHm3f3ZEsm3c1Mx7ynHZg+h72ZvAi/Ml28vy9bSvnYBmNcl20mp+T9WJI392Wbprll0zT/M5Omyic3WO/DMjl9cJYxfE8mHdlrJrlXLZvJb/6/LcndMtm2j9rouU2zl/eNIcm7MvlNwz9lcrr4RT3Z1+aq/XbHtPZF67U9Ss9+m7UOatnaPm9n+35Ox2PVemtl/1c2qLdWfiE9NVcZY2fNtbIfSk/NtbIfS6XmOuaaPansuyHzUi3bte+6srV91872janjsepc2ZGtzpU9P3PdfuvIVufKjmzfXHnMc5muq1ZzQ94jOrOVuXJdtmeu7Fpvba7syvbNle1tcU7q82VtW3TNl+31Xif1+bKd/Wzq82X7tbU79X035D27M1uZL9dle+bLdvaC1OeBdvbmqb/22tnr9DzX2nbomivb2RulPle2sx/PBscna35mda7syM7imGzf8cna7EbHJ6319h6ftLK9xyet/LWzwTFK1m+L6jHKmuyXssExyprs2vmyXXPtefdI6vtuyPFsZ7ZSc+uyPTXXzr4/9ZrrytZqrp1dSb3matuh6zXdNYbaNmxnP5J6zXW9B9b224afLTbKVmpuXban5rrWW6u5rmyt5trZs1Kvt9p26Kq3dvZI6vXWzi6n5zPBGl37rL1ssSdb03esuvq55Wt92Vb9Ha5le475utbbPha4ek+2/f7zrTNsh3b9dWXbNba/J9ver323HarttxOiY7/VcjN/htyxDaVSyutKKTfO5Brd9uUAaz00k+teZ1nnoVLKV8vk+sZLM+ng1+xP8vbp13+T5Ptm+BH3yuQ0uD4PS/L6UsqNMum0PqQn+/pMJqy3ZdJdPOY3CE3TnJ3kjzPpBu/PVZ3rs3Jsd7qd7dXONpPTF1+SyXW/7ftQHJMtpbyvlHLzTIr4EbVs0zR3TPKeUsryLGMopVxRJtd+XpLWfuvYDu8qk2u61+23yna4X7obRGuzd8nkt9jfl+S/ZnIfj85sKeVDSf530zR/m8m+OGa/tV7bR9Kz3wbUwbps3z5vZ/t+TuuxJ6Sn3lrZu29Ub638lempucoYO2uulX1semquYwy1mmvPNX01N/O81JXt2Xfrsj37rp3tG9Mxj20wV3Zth9p+q/3Mrv3WzvbNle1sda7seC6fSGW/DXmP6MrW5squbG2urIyhc66srLc6V3bkP57KfNmzLdbNl5Vs53zZkb1e6vNl+7V1Wuo1N+Q9e122p+bWZXtqrp397tRrbl2257XXzqY9pr7xTr/uqrl29rtSr7mu9VaPT1o/s/f4pGd8Nd/I9h2ftLN9xydrsxsdn3Sst1pzHfneY5T2uqc6j1Fa2d5jlLXZDY5R2vPuKPV9N+R4dl22p+bWZXtqrp395dRrrp19YE/NtbMLqddcbTt0vabb2adU/m1X9szUa679Hrgv9f3W+9miZV22p+bWZXtqrmsMtZrrWm+t5trZvnqrbYeueuvavrV661pv9TPBGl3zZHvZkZ5sTWe2Un+d2Vb9fUtPtnbMty7bcSxw9Vo2699/zphhO7TrryvbrrFr92Tb+7Xv/aG2375pQz7PD/kMuSMbStPJatVXkny9L57kMU3TXJ7kRk3TPL5nvWeu+fY2mXywqHl3ktXfVtw03b/NWrvu62RyPW1vBzCTA+LV632/lOkpc13K5LKIx5dJR3YlyZvW/LzVm4P9Yinlc5n8lmO1c3rnHHstZzvb9zy6si9M8ryy/iyXY7JN04zXPHzMfutY742T3HvNfntGz3qv3lx1evEx+62yHVbfMI7Zb13PbdpN/75Syj9usB2q+61rvaWU3yyT66f/I5NJajXbfm0fzeSyt2T9fpu5Djqyh9tj6sle2fr+6z3ZB6RSbx3ZtRPounrryK+kUnNd26JWcx3Z/anvu3b2q7WaS2uuyeQ3JJ37rp3tm5cq2Vq9trNrb0rcfo20x/u7PWPqG29737XX+y2pz5Xr1tszV7bXO059rmxnH9szV7bn/X9Nfa6c+T2ikq3NlX3rbddcO/s9qc+V7exnanNlzzhq8+W6bM982c5+d+o1t269tfky69+Hq/NlR7bvPbud/XTqNdfO/vuax9o1184+PPW66ltve991bYfac123HXpqrmu9tZpbt96eubJ9TFQ9PunI9urIdtZcO9t3fNKx3urxScd6q8cnPduis+a6nl+t5jqyvceW7fX21Fx7PUm95mY+nq1kazXXzl5zzWPtfdfOPjH1musbb3vftbN9NbduvT2v6XZ2X8+Y2tmzajXX8Xnh0lRqru+zRVsl21lzHdm3rXn4mP3Wkf2OVGquawy1muvIXpZKvVXW21lvHdnqfutab0+9rfWerK+19rKv9GRr1mV7Phd2ZWufGbrG0D42u27PetvHAl+vZbP+/edgT7b2ntKVbdfYYi3bsV+PuV9eS22/fVMGfp4f0kvJaUePVm/YvW1MC/iNSX4ok5s3viOT0wKTyW9QH1mm1+F2ZJ9WSlm94da7yrF/0aFrvffOpLP4zlLKL/dkn5bk/pmcAvelJA9a7ZxXsjdNMiql/PEGz+1pmVz/uSuTD/0PLFf9dYJ29jeT/EYmxfvSUsqL16z3JzL5C2yrN/p6aianf94rk5sAPnzNeLuyT8rk2uJPJnlWKeW1Pdk3Z3KteTL5qwcXV7K/Ph3zlZkU2kNLKV+rrbeU8p7pY+391jWG5yX5z+l4H1Gu+qsSXdlbZfIbhq9lst+u6MmelcnN+tpnHLWz/28mByrfmkkj96dKKZ+oZH81k794t5LkbaWUZ65Z730y+UszyfS1nckd+2+W5EOllMf3ZB+XyRtR12u/nf3bTP5aRdf2bmdf3x7TmnpbN941j7X3Wzt7UZL/lo5669kWz0p3zXVlfzbdNdfO/lKSV6a75trZX0/y8nTUXOtnvKtM/rrZH6Zj37WzmZwe2zlvdWSfl0qtdGR/t71dylX3LFg33tr3Het9Znr2XXs9TdM8Ox37rZJ9VDr2W8cY7pnkr9Ox3zqyD0xlvzWT+zIc81yapvnldM+VXdlXpXuuPCabyW9Ka3NlO/uaTPZd11y5bgztbVh7bpm8zv8iHXNlz/N7Urrny67sXdM9X7bH8atJ/ird82U7+9RMfuO4br6c5o95bU23W2fNtbIPTmW+7Mi+PsmzU6m5VvYv01NztVroqrlW9qWZzD+1+bK9HZ7Z9XMq2Z9KpeZa2cdOn19nzbWyT87kLIXOubJd57Waq2Q7a66dbZrm1qnUXEf2lqnUXNcY1izv2m9r13vT9NRc5fl11lwl21lzHeNYTKXmOrKnp1JzTdPsSWvezeR12XWM0s4+JJN5uOsYpZ19cerHKO3sy3LV2S3t45B1410zh7Xny3b2RZm8jrvm2q7t8LR013ZX9v7pfj11ZWvHJ+3sw1N/n7tu+7Ge97mubO197phsJpf91N7n2tmPpf4+t24Ma55Le7+11/uhVGqu8txq73Fd2dp7XHsML0v9Pa6dfWk66q3y+fBBadXa9DjzhzK5j9c1atnW+o5m0hx5fyW7+rnlY5k0ahZ6sqvHyadl8tfNzugb75rn9sXpOGrjXT0WWM7kssTdG2yHZ2dyD7obZvILx77sozKpm3v3bd81NbaUyS8SFjJ5bXdlV/fr0Uz+WNO3r1nvb6U17/Xst99qjemDPfutnb1Bz35rZ6+TGT4frNoRDSUAAAAANs+OvOQNAAAAgPnRUAIAAABgEA0lAAAAAAbRUAIAAABgEA0lAAAAAAbRUAIAAABgEA0lAAAAAAZZPNkDAADYKZqm+fYkL08ySvLhJE9K8uok4yT7klxeSnlx0zS/luSOSa5M8ohSyv85OSMGADg+zlACADhxvpTkx0opt01yVpKfT/LuUsq5Sb6cJE3T3CTJdUspt0/yuCRPPUljBQA4bs5QAgA4cb4lyfObptmT5PpJPp7k/dPHPjT9/w2T3L5pmr+bfv/ZzRwgAMCJ4AwlAIAT50FJLpmeffT3Sf45yQ9MH7vJ9P//kuTNpZTbT3M/udmDBAD4ZjlDCQDgxPmbJC9tmua+0+/3JblN0zRvSvKfSQ6XUj7UNM3npmcoHU3yyiQvPCmjBQA4TqcdPXr0ZI8BAGDHappmsZRypGma5yd5aSnlPSd7TAAA3yxnKAEAzNdlTdNcI8m/aiYBADuFM5QAAAAAGMRNuQEAAAAYREMJAAAAgEE0lAAAAAAYREMJAAAAgEE0lAAAAAAYREMJAAAAgEH+fwhhbc7RhFrBAAAAAElFTkSuQmCC\n",
"text/plain": [
"