{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":61461,"databundleVersionId":6756046,"sourceType":"competition"},{"sourceId":6879236,"sourceType":"datasetVersion","datasetId":3952500}],"dockerImageVersionId":30579,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# IPM/PF3211 Tutorial 3 Group 1","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nmembers = pd.DataFrame({'Name' : ['Chan Wan Lin Kathy','Chin Hong Yi','Gordon Sun Zhen Xiong','Ong Junming Nicholas','Yew Jie Kang, Brian','Zaheer Bin Abdul Malik'], 'Matriculation Number' : ['A0257464W','A0253322R','A0234832H','A0253393B','A0251697R','A0253207M']}, index = ['1','2','3','4','5','6'])\nmembers","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-11-23T21:49:34.316919Z","iopub.execute_input":"2023-11-23T21:49:34.317307Z","iopub.status.idle":"2023-11-23T21:49:34.75592Z","shell.execute_reply.started":"2023-11-23T21:49:34.31727Z","shell.execute_reply":"2023-11-23T21:49:34.754733Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Table of Content**\n* [Section 1: Introduction](#1.0)\n    * [1.1 Background of Project](#1.1)\n    * [1.2 Context of Project](#1.2)\n    * [1.3 Considerations of Project](#1.3)\n    * [1.4 Purpose of Study](#1.4)\n    * [1.5 Literature Review](#1.5)\n* [Section 2: AI Canvas](#2.0)\n    * [2.1 Prediction](#2.1)\n    * [2.2 Judgement](#2.2)\n    * [2.3 Action](#2.3)\n    * [2.4 Outcome](#2.4)\n    * [2.5 Input](#2.5)\n    * [2.6 Training](#2.6)\n    * [2.7 Feedback](#2.7)\n* [Section 3: Notebook Configuration](#3.0)\n    * [3.1 Setting Up Notebook and Importing Dataset](#3.1)\n    * [3.2 Data Cleaning](#3.2)\n* [Section 4: Data Analysis](#4.0)\n    * [4.1 Data Pre-processing](#4.1)\n    * [4.2 Noise Analysis](#4.2)\n    * [4.3 Other Factors for Consideration](#4.3)\n* [Section 5: Prediction ](#5.0)\n    * [5.1 Data Cleaning](#5.1)\n    * [5.2 Prediction Model](#5.2)\n* [Section 6: Conclusion](#6.0)\n    * [6.1 Limitations](#6.1)\n    * [6.2 Future Suggestions](#6.2)\n    * [6.3 Summary](#6.3)\n* [Section 7: References](#7.0)\n* [Create Submission File](#8.0)","metadata":{}},{"cell_type":"markdown","source":"# Section 1: Introduction <a id=\"1.0\"></a>\n## 1.1 Background of Project <a id=\"1.1\"></a>\n![starbucks-logo1.jpg](attachment:221b5eae-e110-49e5-8af1-e3a6b8a6b718.jpg)\n\nTraditionally, Starbucks has been a favored haven for students seeking a quiet space to study. However, the landscape is evolving with more adults choosing Starbucks as their workspace, seeking respite from the distractions of working from home and desiring a conducive environment for efficient work (Baker, 2014). This transition has led to a challenge in seat availability, impacting both those in search of a peaceful workspace and café customers looking to savour their coffee amidst a tranquil ambiance. \n\nIn response to this shift in dynamics and as part of a broader initiative to meet the changing needs of the Singaporean community, Starbucks is undertaking a forward-thinking project. Recognizing the recent bankruptcy of WeWork in the United States and contrasting this with the continued success of its Singapore franchise, which mentions there is still a significant demand for co-working spaces in Singapore (Ganesan, 2023), Starbucks sees an opportune moment to explore and provide more dedicated co-working spaces in Singapore. This strategic pivot aims to capitalize on the prevalent demand for such spaces, seeing if we could potentially leverage and benefit from this evolving trend.\n\nAmidst this transformative journey, Starbucks is acutely aware of the impact of noise on productivity and the rising prevalence of remote work. Positioned strategically to address these challenges, our groundbreaking initiative focuses on establishing a layout tailored to the specific requirements and preferences of individuals seeking optimal work or study conditions. This includes designated areas for focused work, study sessions, and casual conversations, seamlessly integrating with our renowned café experience. This initiative reflects our unwavering commitment to fostering community well-being and adapting to the dynamic shifts in the contemporary working landscape.","metadata":{},"attachments":{"221b5eae-e110-49e5-8af1-e3a6b8a6b718.jpg":{"image/jpeg":"/9j/4QAYRXhpZgAASUkqAAgAAAAAAAAAAAAAAP/sABFEdWNreQABAAQAAABBAAD/4QNtaHR0cDovL25zLmFkb2JlLmNvbS94YXAvMS4wLwA8P3hwYWNrZXQgYmVnaW49Iu+7vyIgaWQ9Ilc1TTBNcENlaGlIenJlU3pOVGN6a2M5ZCI/PiA8eDp4bXBtZXRhIHhtbG5zOng9ImFkb2JlOm5zOm1ldGEvIiB4OnhtcHRrPSJBZG9iZSBYTVAgQ29yZSA1LjMtYzAxMSA2Ni4xNDU2NjEsIDIwMTIvMDIvMDYtMTQ6NTY6MjcgICAgICAgICI+IDxyZGY6UkRGIHhtbG5zOnJkZj0iaHR0cDovL3d3dy53My5vcmcvMTk5OS8wMi8yMi1yZGYtc3ludGF4LW5zIyI+IDxyZGY6RGVzY3JpcHRpb24gcmRmOmFib3V0PSIiIHhtbG5zOnhtcE1NPSJodHRwOi8vbnMuYWRvYmUuY29tL3hhcC8xLjAvbW0vIiB4bWxuczpzdFJlZj0iaHR0cDovL25zLmFkb2JlLmNvbS94YXAvMS4wL3NUeXBlL1Jlc291cmNlUmVmIyIgeG1sbnM6eG1wPSJodHRwOi8vbnMuYWRvYmUuY29tL3hhcC8xLjAvIiB4bXBNTTpPcmlnaW5hbERvY3VtZW50SUQ9IkI5NkU0MTI2RkE0RjQ1NTdGMjk2RUVGRDQ0OTFDRUE1IiB4bXBNTTpEb2N1bWVudElEPSJ4bXAuZGlkOjREQ0ZCOEYyNzJFOTExRUFCODdFOTY1NENCNzNEMTNFIiB4bXBNTTpJbnN0YW5jZUlEPSJ4bXAuaWlkOjREQ0ZCOEYxNzJFOTExRUFCODdFOTY1NENCNzNEMTNFIiB4bXA6Q3JlYXRvclRvb2w9IkFkb2JlIFBob3Rvc2hvcCBDUzYgV2luZG93cyI+IDx4bXBNTTpEZXJpdmVkRnJvbSBzdFJlZjppbnN0YW5jZUlEPSJ4bXAuaWlkOjY4YmVjMmFhLWFlYWUtNmU0OS04NzY3LTExZmYzZjJjZjNkNCIgc3RSZWY6ZG9jdW1lbnRJRD0ieG1wLmRpZDo2OGJlYzJhYS1hZWFlLTZlNDktODc2Ny0xMWZmM2YyY2YzZDQiLz4gPC9yZGY6RGVzY3JpcHRpb24+IDwvcmRmOlJERj4gPC94OnhtcG1ldGE+IDw/eHBhY2tldCBlbmQ9InIiPz7/7gAOQWRvYmUAZMAAAAAB/9sAhAAFBAQEBAQFBAQFBwUEBQcJBwUFBwkKCAgJCAgKDQoLCwsLCg0MDAwNDAwMDw8REQ8PFxYWFhcZGRkZGRkZGRkZAQYGBgoJChQNDRQWEQ4RFhkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRkZGRn/wAARCAGWBLADAREAAhEBAxEB/8QAuQABAAICAwEBAAAAAAAAAAAAAAcIAQYCBAUDCQEBAAIDAQEAAAAAAAAAAAAAAAEDAgUGBAcQAAEDAwEFBQQIAgYGCQQDAAEAAgMRBAUGITFBEgdRYSITCHGBMhSRQlJicoIjFaGxwZKiM0MW8LJTY3Mk0eGDk6OzNEQm8cIlF9J0RREBAAEDAgQDBgUDBAMBAQAAAAERAgMhBPAxQQVREhNhcZGxIjKBocHR4fFCUiMzFBVisjRyQ//aAAwDAQACEQMRAD8AuWgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIFUBAQKoOtJf2UVTJcxMDd5L2gD6SjGb4jq8+XVWmoK+fmbCLl+LnuYW09tXIqnc445zDou6gaFaaO1Thwe++t/8A+amkqv8AnYP87fi5R690RM4Ni1PiJHHc1t7buP8AB6UlMb3DPK+34u9DqXT1wQLfL2UxO4MuInE/Q5QsjcY55S9Fl1ayCrJ43DucD/Si2L4nq+wIIqNoRkVQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBBxdJG1pc5wDRtLiQBs70RN0RrLSNQdWdAabc6O/wA5BLct2G1tCbqUe1sPNy+9Kw8ObuODHzur7kX5n1PY6MuZp/T9xckEhs15I23Z3HlZ5jvdsWM3xDW5e+xX6beOPa0LKeofqLfczbJ9hi43bvItxLIB+Kdz2n+qsPUeG/vWe7lp+H9Wl5LqLr3Lk/P6myLxxZHN8uz+rAGNURkl48u/zZOdzXri9vrzbd3lxcHtmlkkP9pxUeeXmuumZrLreXHxaNm7ZxWKPNLNO4bN5QOVlNw+hQVljlFa0p3jYVNSru2+UydlT5HIXdqeHkzyx/6rgsvNLOzLdbymjZLDqf1ExnKLPVF+Q36s723A+iZr1PqSvx77NZyun4zPzbrjPUbr2yLRfw4/KR7ObnjdbyEfijdy/wBlZRk8Xsx96zxz1hIGF9TWnbijNQYm7xjzvmgLbuL6AGSf2SsvPEtjg73bdpdbT3cQlHT/AFF0Zqflbh83azTu3Wz3+VPt7YpOV/8ABZNjh7hhycp1ltQftoaDsUPZEudRwUpEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQKhBxLttAiKvB1HrDTuk7c3WoMnBYMNfLY936j6DbyRir3/lCPNn3ePD90oK1V6lj47bR2L5t7W5HICgp2tgYeY93O4exYTfDTbjvk8scfFC2oteax1U4/vmZuLiA/+zY7yLanZ5UfK0/mqsJvmWlzbvJl+6ZlrQY1nwgNHYNiweeZmebIGzdREFAEBASoKRtnTvSMmt9WWOCJeyyPPPkZmGjmW8QqSDtoXOLWD2rKy2s6vTtdtOe/yRpV4WaxN1gcxkMJfCl1j7iS3k4c3I6jXAdj20cO4rG62kqclk23TE9HQChgICVBAO3Yg4lrXEcwrTaD3omJo3XTnVLXeli0Y7MyzWjDX5G8/wCahNBuHP42D8Lws/UmHrwb7Lin6ZTbpX1J4i75bfVuPfiphvvbXmuLY9pc2nms9wd7VnGSJbvb96tn/c09sfsm/D53E560ZfYe/t8haP8Ahmt3tkb7DQ7D3FZtzi3GPJ9sxL0qouOYIANUGUBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBBiqioxzJVFWC48ERWXh6k1XgdJWJyOoL+Kyt9oYHu8b3fZYwVc9x7GhFOfcW4YrdKuOtPUTmckZLLRtv+1WW1oyU7Q+7eO1rNrIvfzH2LCb4hzm67zff9Nn0x+fHFUI3l7e5C6kvb+4lvb2X+8urh7pJXbeLnEn3blXddVprrpu5y+FKbFixqICmoJAKZBRIKAO7dXuUi1Ppx0kcbp661XdR8t3m3BlrUbRZwEgEcR5j+Z3sDVfZFIdP2XbzZbOSeukfr+34NQ9SGlBZZew1dbMpDkm/J5AtGwXEQJid7Xxgiv3QoyRWKvH3rbxZki+I+758fJAvFUNIICAgICmASQ/ioHfw+azOn7tuQweQnx142lZIHlvNTg9u1rx3OBWcXzCzHlusmsSn7RPqObWKx11aBuzl/d7RhLfbLCKkd5jr7FZF8S32071TTJGnj1WDxWXxubsosjiLyG+sphWO4heJGnuqOPcs29xZrckVtnzQ7wKhdGrmDsUpqygICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgwSgxUqEMVRDFUS4ukYxrnvIDGipJ3ADeaoiZiIqgnqH6gMdiHSYrRflZTKN8MmSf4rOE8eWn9+4dx5e87ljdfENFve8RZpj1nx5xxxqrRmM1ldQ5GTK5q9lv8AISE1uJjUtHYwABrG9jWiiqm6Zc5kyXXzM3TWZdALFWKQSoICgFIU+lZRIEgbDsKxmlRgkDfT3lE0elp7EXGpc5j9P2Dv+ZyM7IGuaQ4saTV7yOxjAXe5ZW21lbiwzffEeL9AMTjLXDY60xVkzy7Oxgjgt2djI2ho9+xXXO6w4ox2xbHKIeF1B0vHrDSWUwLgPPni57J5p4LmLxxO/rinsUqd7g9bHNqhT/0pHwy/pzxOcyaJ1A5kjDyuaR3OBCom2jiLrLonWGQQdxr7FjLA7qbQgICAkApBQCUDt7EoPe0vrDUWjb4X2nr59qXEGe2d47eYdksRNHdldjhwKytvl6MG5yYprbK0vTvrdgdZGLGZQNw+oXbBbSO/QnP+4kdSp+47xe3erYmJdPs+62ZdL/puS01wO5TRta9X0DqqWTKAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgwSg4kqEMIgqETDydQahxGmMZNmc3eR2ePhHikdtc53BrGja9zuACKcue3Fb5rppCpHUjrJm9bvlxuOMmK0xUgWbTyz3A3Vne0/Cf9m00+1VYTkpycpvu53ZppbpYi0DYKj2DsVLWSzRSgUAgICApBJkfezmitruG4ntY72CJ4MtnM57Y5W8WudGQ5tRxB2KbZpzTFOq1PT3TvRXW+LF7iNO2jLyEAX2NuOeSaGQ/aD3uDmup4XjYfbVXx5ZitHT7HFttxGkUujprxx4pEt+nOgrWnkaXxTS3cflYSa+0tqlacmw/wCv2/WyHs2mEw9g8SWONtbVzfhMMMcZHsLWjepqutw2W6xEaex6JWMrilaVWVUvKudN6evS43mJs7gvJLzLbxvLid5NW8Uqou2uK7na8a46adPrmom0tiz3ttYmH6WhpSZqp/6/BH9kIh6rWHRzRVobSHTVrd6mnbW2sIpZomxA7PNnMcgLWDg3e7h2iPpjnDTdzx7XHbS2P9T3zp+f5K3E1JPKG1PwjcPZtOz3rzzOrn4YRIkApBQCkFILEYcC4U7N380gjROfTPrze4LycLrJ8l9hW0ZDlSC+5twN3mjfNGO34h3qy2/xbzY92ux/Tk+q1aOxvrPJWkN9YTx3NncMD4J4nB7HtdtBDhvVkumsvtvits1h2gUZs8yVKuVVKRAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQcCVCBEOJQijU9ca+wWgsUchlpee5kq2ysIy3zriQcGgnYBs5nHYPoSdIq8m63lm3jXW7wUz1nrfPa7yjsnmZv02EixsGE+RbsOyjAd7iPieRU925UzfM+5yG63V+a6ZulrQWLyigEBAQEBAQEBSPTwOey+mcpDmcHdOtMhbnwvG1j2bzHI3c9juIP8Cpi6YlbhzXYroutXE6Z9VsT1BtPl3BtjqK3YDe41zt4/2kJNC+M/S3ceFb4mrrdj3CzP8ATOl3zSOktlzZQEGKoIX6s9Z7XSQlwOnXMu9TuHLLL8cNmHDe/g+TsZw3u7DE3RDSdy7n6f0Y/u6z4fz8vyVPu7u6yF3PfX077q8unmS5uZnF0j3n6ziVROrmb75ums83xSYYCAoBTAKagogFIKAUwFCdxooG/dOeqGZ6fXgjZzXmnZXVvMWT8PNvkgJ2MeOz4Xcdu1Z2XdJe/Zb7JgurE6eHHH6XI05qPE6qxVvmcLctubGcVa5uxzHcWPadrHN4tKtdfgz25rfNa9miLyqDIKFXKqlIgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIOJKiUSwiGCeHFCYaV1D6g4np/h3X99Se/mDm43GtcBJPIB7+Vja+J/Ad9Ak6c3i3u9jBb/AOXgpdqTUuY1bl5s5nLjz72bY1o2RxRA1bFE36rG/wATtNSqbr6+5xufNdlum66dZeOsZVCgEBAUwCD7WsUM91bwT3DLOGWRscl3I0uZEHGnO4N28ra7aKYiJKTPJKd96fOoNvD59j+35WMt5mfLXBY5wIBqBKxgP0q2cXhLaT2rN5fNFLvdNf2aFmdH6r06XfvmEvbBjDtmkiLoT3+azmj/AIquccvDlwX4/uiY98THzeGDUA7KHcRuWKkUgoG19NsVf5rXmAs8bLJbXDbts0l3ES10cEAMkpBG7mYC33rPHWr17Ky67LbEc68fkvk3YKK2XddHJECDp5K2lvcfd2UMz7WW5gkijuYzR8b3sLQ9pO5za1CMMls3WzbGlYfnpf2V3j7+7sr/AJv3C2nlhu+YkuMzHlrySdpJcCalU383A5K+aYnm66wYCmoVA+Ldw7f4pQbPhOnut9Qhr8Vp69lhdtbcSR/LxEHcfMmLGn3LOLJl6bdnmu5Wz8P15fm2256EatxWKu81qC+xmJx1lGZbl75ZJnta0V2BkdC47gObaVlGPxenJ2zJjsm+6kRHFEVgimzd37P4KqYa0QEkFAKQSQpUb1A27QGvszoDK/P40mfHT0GRxbjSOZrdlR9mQD4Xe47FZZdR7Nrvb8F2nJdXS+p8Rq7D2+awlwJ7KcbeD45B8Ucjd7XtO8H2q3m7Hb7izPbW17mzgi8QZBRMOSlIgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAg4HeoQwSg1nWuscTonBT5zKv5g39O1tmkeZPMR4Y2Dt7TwG1J5PJutzbgs813PopDqnVGX1hm7jO5mTnuZzyxRAkxwRA+GKPsa3t4nbvKquv8zi8+a7LdN106vF9irUiAgKQQEoMqBgjm2V2cQgtV6e9dHMYaTSOSl5slhYwbFzzV0tlXlA27/JJ5fw8q9Ft1YdR2bd+a2cc9OXHsTi5jZGcrw1zXfECAQa91KLKrdzETHSUcas6K6G1SJJhYjE5F1SL6wAhcXdr4wDHJ72qJiJa7P2rDkjSPL7v2Vv110f1XocOvHx/u2CbWuStWOrGAK1ni2ln4hVvsVc2eDnd127Jh9sePHL8fijoEUFKEHiO9Vy19FkPTRpgcuX1fPH4nkY/HuP2W0kmcD3u5W/lKtsjR0XY9vzyTHu/Xj3rHV3Dis3R0eXndR4TTNg/KZ6+isbCMgOlk4uO4NAq5zj2AVSirLntxxW6dHcsb+zyVpDfY64ZdWVw0PgnjcHse08QRvRljvtvtrbNYdg1NNlR/JGaoXqE0wMLrVuZhby2eoIBLUbALqABkv8AWbyO9tVhkt0q5Du+39PNMxyu1446ofPhIr279+07h7VVEVanml7Q/QbU+p2xX2ec7A4d/iAkaHXkrd/hjNBED2v2/dVsY4jm2u07Tly6z9NvHTj8Vh9LdLNE6RYx+LxUct+0AnI3Q8+4qNlQ93wV7GABWV8HQYO3YMccvNPjLd+Vo2ACgG7u7FFXui2I0hV/1E65ffX8WhsdIRZ2LmT5YsOx9wRzRRE9kbTzkfap2LDJdpRzPeN35rvTjlb8+ONEB7Tv3quJ0aIUAgKAQFIe1QMEHeNvcg3Pp11CyPT3NNvrYOuMRclrMrjgf7xg3PYDsErAdnbuKssupo9uy3d2C+vRdvCZrHagxdrmcTcNusfeMEkMzNxB3gg7WuB2EHaDsVsuzw5rctnmt5PRBqiyGRvRLmpSICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAg4kqES41RDo5bK2GFx11lsnO23sbOJ0txM7c1jBUnZtPsCMMuW3HbN13KFH+ouvch1Bz0mSuA6HG2/NHibFx/uoairnDd5slKuPu4Kq66s06OK3m7uz31nk09VvGKaAgKQUApqPa0/pXP6pluIdP2Zv7i1Y181uySJkoY4kcwbI5pc2uw0UxbN3JZiw35JpbFZMlpDVmGDjlsFkLSGP45ZLeQxj2yNa5n8VM47mV+3vsrWJin4PEBbt5SNmw9xWEqqS9zSWprrSWosbqK0qTYzAzxj/Ft3+GWM/iZWneAsrJpK7bZZxZIuhfnHX1rk7G2yNjIJbO7iZNbyN2hzJGhzT9BV8w7nFktvtiY5S7ShbVwexrwWvAcHAgtIqCjCbYuikq79VuhQmbNqLQdqGXVS68wUYDWyk75LetGsfXez4Twod+N1sS0O/7TWfNj/GP24/mZtDaah0jpPEYBlA+zt2i4fSnPO/xyu2/ae4rKjb7PD6eKLeU01eH1E6qYHQNr5czxfZyVnNaYqNw8w13Oldt8qPvO/gkzEc1O97hZgjTW5UHVmsdQa3yf7lnrgSlhItbVlW29u0/ViYSad7j4iqbr6uT3G6vzTW6Xr9P+peoen10PkHfN4eR/NdYeV1Inbdroj/hSd42HiFNl9NFm131+C6tawt9ovXen9dY/5/CXFZGhvzdjIQ24gefqyM/k4VB4K3nq6za7vHnitvPwa51q0fcav0XNHjbc3OZxsjLvHxMpzyOaeR8bfxsJ99FPRR3Tazmx1t5w8bpX0VsNKMhzWo2R5DUpaHRMI5oLMnhHXY6QcXn3d+MW0efYdrjH9d8Vnw8P5TLyqW6hnchya3rfVFro3TOS1FcUcbSIiCI75J3+GJg/E8hHm3m4jDim/wDu5QoXd3V1f3c97eSme8u5Hz3Mp2l0r3Fzj9JVEzWXDXXVmsvjzBxAG87gNpPuURbPKGNGx4zQWt8uObH6byM0Z2tkdA6FhB4h0vK0rOMcvRZtMt3KJ/N5uawmU07kJMTmYG2t/C1rprcSMlLOcVAcY3ODSRQ0rXaoutmFWTHdZdSebzu9YsBIBTILEFIVIII3jaglLo31MfofLDE5SQnS+TkAnBNRazv2Cdv3TukHZ4uCssv6Nr23fzhvpOtk8/3XKjkZKxskbg5j2hzXAgggioIIVjr4pMVhzbvRLmpSICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAUHAqESwd6UFTOvHUZ2oMm7SGImphcZLXISsOy4u208IIrVkP+v+FY5LtKOT7rv/Vu8kfbbxx/RCipaYUApqCgFNQSoIPU07qDJ6XzVlncPL5V/Zv5mB3wSNOx8TxxZI3Yfp3rK26i7BmuxXxdb0Xq0jqjG6zwFnnsY6sF039SF3xQyjY+N4+013/Sr51dttc9ufHWPg8vUfS/RGqmuOVw8AunCvztu35e4B7fMi5SfY6qj2Ks3b8GXWbaT7ONUB629POdwrJL/Sk5zVizabKQBl60fdpSOWnuPtWE4/BoN32i/HHmt+q38/h+3wSD6d9TS3unLzSV+HR5LT03KyGQFsjbaYlzWua6jgY38zd26iztmaatl2jNM2zjn7rdYTeobnqypSINR1z/AJ4kxzbXQkNmMjcuLJ8heSlgto+X4mM5H+Y8nYK7B3qXl3cZZspi+6eqCB6cNY5K4kvM3qGzN5cOL7ictnupHuPFz3+WSsJsrNatFb2XLfrdOvxd9npeuaDm1UwO4gWNR/56enDP/obv8o+H8sS+l+6DaxaqjL+x1iafwmSccH/RXR/dHw/l17HoJ1F0vkYsvpbUWPZkLf8Au5aTQFzd5Y9vLI17HcWu2JFlNYljHac+KYusn81hNMTaimw9vJqu1trTNirLqO0lM0DuU7HsLmgt5xt5dtN1SsrnQ4Jvm2PPze2i0QYKCtXqDzV/ns/h+n2BglvrqFovbq1t2mR75pKshaQNwYzmcSdgqFjfWlHOd4vnJfGK2K0+f9Hy0Z6b57iOK91teut2kBxxVmRz7/hlnoRXtEY/Mpi2IY7Xs111JvmnsTrp7Q2kdLNa3BYi2tHgUM4YHzO9sr6vPvKybrBssOLW238XidU9f2+gdOyXUfJJmrwOixFsdvNLTbI4fYiHiPbsHFRM01Vdw3kbeyn988lJrq6ub+5nvLuZ9xdXMjpbi4kNXPkeaucff/1KiZcdffN01nm+XsNQsWApgEkFFQUgoD3bDvQWZ9P/AFIfewjQmZl5ru0jLsLO8+KSBm10BJ+tENre1vsV9t1YdJ2ffVmMV34fssMztJ71nR0MVjm5okQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEHElQONUQizrV1AdovTZtcfKG5/MNfBY0+KKMUEs5H3AQG/eIUTNIarum79Gykc7lNDUO4kkbztqT2ledx7lJHLCY2yxPj81gkj5mlvMw7nNrvHesqSmjjUblFECiQUgoBAUhvqP4qBKHRbX/APkvUjLDIS8uncw5sV2XHwwTnwxzd1T4HnsoeCtsno2Pbd56N/1fbPNc0OBGzdRWS7OsUZ9u3sCFHijTOIbqBuporZsGZ8h1tNcxeDzoXEO5ZQNj+Vwq0naOG8qaqfQsi/zxFLntKF1REsoMcUqQUruSpNTclEM7EpJpDBpxCalQU/6kPKygwiQivv4oh4uM0zisVkMhlreBpyuVl82+vX+KZ9GhrWcx2hjGtDWtGyinzKrdvZbd5qfVL2qKFsurf3ltjrK5vryZtvaWsTpridx5WsjYOZzie4BSwvutttmZ5Qor1B1pd671LcZqcvZZNrBi7Vx2RWrT4dm7mk+J/t7gqb5q4nd7m7PfMy1X+SweQCAkAkgkAgHw7+KDmIZnxPnbG8wRODZZQ0ljXO2gOd8IJ4AqYiebKImlX0sr28xt7bZLGzutr60lZNbTt3tkjNQdv8e0JE6psvmyaxzXr6eaytdcaZs83CBFclvlZC2BqYrhgHO0923mb2tIV9XbbDdRnxebrGktwCl7RAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQcDvUIde7uYLO2nu7mRsVtBG6SaVxoGMY0uc4k8AAlGF98WR5p5KIa/wBX3OuNUX2dlJFo8+TjYT/h2jK8gp2uPjd3lVX3Vlw+73E5sk3S1WSpidTg07/Yq3mt5ruzaG09rvQeCsczbfqjGWxtL2MBs9u90DPFG+n0t3HivXdFdHYW7LHnwWRMaxbpRUfWejMvobNy4bMMDqAyWV40UjuIa0D29h+03gfcqL7aOW3O3uw3+WWuDbuVcvOLIFAICApGCARtFW/WHakymFxOhWuXap0r+1ZCXnzWCDYJ3OPM6S3IpDL2nwjld3hXRNYdb2jdepj8s87Ut7O1S2xVQOEsscUbpZpGxRR7XyPIa0U31J2KUXTSKzo0LOdY+neAe+O4zcN3cM2G2sq3b+YDcTFzNB9pTSHhy90w2da+5HWU9TuNYaYTT91cjhJdyx24+hnmlYzkta3J33/G34/w0699SOuZy4WVljbBh+A+XLcPHvL2A/1VE5J6Q8d3es8zpSnu/q8C566dULmvLnGW/dBaQN/i5rysfUlTd3XcT/d8v2dB3WHqe7fqa576RW4/lGo9SUf9nnn+5lnWPqcw1bqW4Pc6K3I/jGpi+UR3Pcf5S9G168dT7b4stBcgbxPaxH/UDCp9RZZ3bcRzumfh+zY7D1L6vgp+5YrHXrOJi862d9JMo/gpjJC+zvWWJ+qkt0xPqa07PyNzWGvbAuNHyQmO6YO/6j/7Ky88PZh75bP32/DiEkYHqjoLUbmxY3UFqbh2wW07vlpyewMm5Cfcp5tli7hgv5Xc/FuTXNIBBBadx7UeyvVmoQYqhWkK7eozXLooYNC4+Uh9yG3OYLDug/woTT/aOHO4dgHasb7qQ5/vW8mKY7fx446K17t+1Uy5sSAUAgKQUAg3zpn01yPULKuAc60wNo4DJZADbtFfJirsMjhx3NG08AbbLK6y9uy2V24vpyt8eOP1sB1WwGJ0t0cymIwtpHaWFubUNjaKuJ+Zjq9zj4nPdxcdqsnk33ctvbi2nlt5Vj5wqHTbSu/ivM5RJ/RLXTtIatjsbyUtwecc23uWk+GOfdDN3eLwO7jXgrbJ6Nn2zd+jkis/TPPj2fuuk0ggGqtdmygICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgwdyEuBKhign1F6y/bMFBpGzlpeZnx3oafE2yjO1poajzX0b3gFRdNIaLvW78tsY7Z1nWeOOUqrjsVEOYcJKmN4G8in07Epqyt5w/RDAWxssFi7M7Db2cERr9yNrf6F6Z5u820eXFbHshrPUzQdpr3Tk+PcGR5W3BmxV2dhjnaNjSfsSfC76d4CiYrDzb/AGUZ8c0j6o5fso7cQT2lxNaXcboLq3kdFPC7Y5kkZ5XNPe0ii88xRxc20mj5JCBSCgEkEgOBr7k5jcemerpNF6xx+XL+WwlcLXKN+qbWUgFx/wCE6knuKssmmj17LcThyxdHKvHHuXF1Jr3SWk7Rl1m8rBC2RvPBEx3myyjh5cbKudXu2d6s5Ouz77DjjWfggjVHqVyk5fbaRxbLKGlBf348ybbxbC13K38zj7FhOSI5NJn73fd9kU+f7fNDGd1XqXU8nmZ/LXWRBNfKlkpCDwLYW0jb7mrCb5lp8ua/JNbpq6uIwWVzkz7TD2ct5JBG6acRgBkULBzF8jyQ1g2H4iKncotiZY22XX6xDoAhwG2tRVKK5ijcNIdNdXa3cJMNYFmPOx2TuSYrUU+y6hc/vDAVlbjnq9e32eXNNLY/b4ptwfpmxELWyajzV1ey73QWbW20Q7uZ3mPPuIVvlthusPYo/vu+Dc4OgnTCFnK7DyTn7Ut1cuJ+h4SkPX/0+39vx/Z87roD0ynaWxYy4tXn68F3cAjvo9z2/wAEmIRPZtvMU+qPz+cS0PUHpljDDJpbOSB4Bpa5Fge1x4DzYg0t/qFRNkPDm7HMR9E19/H6IQ1PozU2jroW2ocdJaeYSIbnZJbSkcI5W+En7poe5V3WS02fa5MM0uijxLa2uLy5gsbdvNd3MrIoGcwbzPkIa0VcQBUmm0rGIqotis6Ppk8bfYq9mxmWtZLS+tnctxbTN5XtPbTcQabHDYVM20lnfZdjmkxSXu6d6gaz0s5oweZuIYG0/wCUld8xBQcPLk5gPy0WUXz1W4d1kxfbNOPgmzSfqVgkLLXWeMNuTsdkrDmkjrXe+A1kb+Qu9yy80S3W371WkZI/GOOPBMn+fNKy6du9U2WUt7vE2cL5ZpI3tLhyCvIWbHB53BpFarNtrt9ijHN9YmI6KNZ7NXeoszkM9fkuvMjO6eQb+RpPgjHcxlGj2Ki+ay4vNluyXzdLztixlUKAWQKAUAe5SPV05p/Iapzljp/GNreX8gYHEVbHGNr5HfdY2rv4KbbfNK3Biuy3xbbC92mNNYzSmEs8FiYvLtLRgHMfjkedr5Hn6z3uJLir3c4NvGLHFsdGr9a7Q3XTHUIbs8mBk/ugmY8/wCdHl7rZN+3mns+cKSLzuLYcOYU4U/nsSExouz0Z1odYaNtn3cgfl8Z/yeRr8Tnxgckh/wCIyjvbVeiJrq7HtW69XFSedqShuUtoICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAg4uUSiXxmljiifLKQ2OJpc9xIADQKknuCMZui2JmeihevtUSay1blM8XE280nl2DTubaw1bFQbKcwq8jtKqvuq4Xd5py5Ju8Zaz8W1YPNyexpPFOzup8Jh2MLxe38Mcg/3QeHSH3Ma5ZW/cuwY/PfFvOr9BWgBoA3AbPYrnfRDJqR/QkQTKo/qG0qMNqy2z1tEI7PPxF0xA8IvIKNf3Dnj5Xd5DlhfGlXJ952/p5fNH2zH9UM7agUBPtVTTsFzQ4NcaOd8LRSp9g3lIiZTTSr1rfTOprxofaYPJTspUPjs7hwI9oZRZ+nKyMF/hLnNpXVdu3zLjAZSJn23WVwB7zyJ5Jg/wCPk8JeO+sUhhlaY5W/FG4Frh7WmhCxmJYTbIsWJsoSdvcpHEAA7vERQezsB/oU1qmrZ7HSko0+/Vmdc6w0/wD3ePZQfMZCc7o7cHcz7cp2NG4FZ22RGsrp298WTdy8K8ce3k+OkNJ5XW2egwWIYGvkrJc3LqmO3gB8Uju2laNH1ioizzSbbBOa+LY5pK6oZHDaExUfSvR58tpaybVOSqPPnc5tWwyPFNrh4nAbA2jdxKsuuiIpDY7663Db6OP8Z/T8OOrv9Hei8Wfht9V6vhP7YaPxuJcC0TtG6WYbD5R3sZ9YbTs2LGyymqztvbIyUvv+358fn7udoYIIbeKOCCNkUEYDGRxgNa1o2AAAUAWdXT2WxZFIjR9UTVlEiDFEHRyuJxuaspsblrSK9sJ20mt5mhzHfT2do29iVVZMNmSKXRWFQerPSafQc4ymKL7nSd3IGNc+rpbWR3wxSO3lh3Mf7jwJwut6w5PuHb7sF3mjW35cfn89p0tb4zrXpWTBZmVtv1A0/CP2/LnbJPbbmmXcXtr4JBwNHbysonzQu21tm7sm2f8Ac6e1Cl9i7jBZifE560liuLOby761Y4NkA4mNzgW+IeJjtxVcx5Z1ajJZdbNJ0mOOPjD0tRaTvMHa2WXtpRkdNZRvNjczG3lY8nfFK2pMUzaEFpO8GhKm/H1hnkwTbEXdJ44hrhAP8CRSlabq9qwrKpk/Qoqg21HKPag5QRyXUvk2kTric7PLia6R30MBKmIqyi2ZewzSWrpWh7dO5RzTtDhZXFCP6inySs/4+Twl1bvB57HtL7/D39pGN757WaNo9pc0KPLLG7DfbFZijzmkO+Eg030NaKGExRnZ27kiULJ+mrSrW2+T1ndM/XlcbDHkjYI2UdM8V+0+jPyq6yNHQ9j2+s5J6aRx1/qsWsnSPI1Ni/3vT+Xw5py39lPbivbJGWj+KmHn3OP1MV1sdYfnyWyMJZK0tlYeSRpFCHN2EHvBC88xSXBzzYSqEpdCNWnTeuobCeTkxueAs5g4gNE++B+3jzEs/MrMd3Rs+17icWaPC7SeOOcroDcrHZiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIODt6iUIu656odp3QV7Bbv5L/NOGPtqbw2VpMzhx2RB3vIUXTo1Xdtx6eGY/wAtPwUxGynAUpTuVDj2BsqOwJMiavTnpx2U1dPqCRlbXBW58skb7q6qxtO3ljDz7wrMcdW57Nt/Nl88/wBq2o3f6FWOrkKJlF/XHSd/qzRrIcTaOvMvZXkE9rBHTmcHO8qQVcQKcjy4+xJisUavuu2nLi+mKzDQtH+m6Lkju9bXxkc4A/tdk4taO6Scjmd+QD2rGLIjm8G17JyuyT+HHHtTXgdEaU0zGGYTDWlmQKGVsTTK78UjgXu97lnVucOyw4vtt19urYWtAHKNg+hKvRFsRyD2b0qmnRD3V/WmgMDZuxmYxVnqDPysJgxrmRuMfMNj5ZKF0LfZ4jwS6aQ0ncNxt7I8s2xdd8vx/ZUaaRssskzYmQCRxeIY+by2Bx2NZzFzuVvCpK8901mrlnvY/TZGCm1XmXOtsKHmDHMH99kLqhpHCDujYQTJLwGwVduztsilZ5LLsV02Tdy4/Pj3Nv6SdNW6xvZM7nm+TpDFOLrt7qtbcSMHMYg6uyNg2yOru8PallvV7ths/Uu812lkc544/TxOousZtdajBx8RGFsyLLT+PibQeUCGtc1jRsdM6mym6g4JdMzNIU7vP6t+n2xpCxWncHjui3Ta/wAxeRxvzbbf5rIyVp5104csNu0/YY4hg97uKtikQ6DFjjZYJumnnp+c9OPer50505P1E16xuYcbiF0smTzkrq+NjX85aewSSODPwqq36rqy0OzxTmzRH4z+vHtW5u9e6Fwr2Wl5qDGWkkbQ0W/zEQLWjYBytOxWy6v/AJmCz6axFHOw6haHykrYLDUeNuJnmjI23MXMT2AFwJ9yjmm3fYJmnmtbIHAgOaatIqD2hHpjWKw5ImohOj5TXEFvG6W4kbFCwVfI9waxo7ydgSiLrotiszRq9z1L6f2cz4LnU+LZKz4mfMxOI7thKUo8v/Owf5Q4y5zQeucfd4CPL4/JQX8Lop7aK4ie8scKVArUEbxs3qYY35cG5t9Osaqg2d1k+lPUJzy4unwN6Ybmgp8xaO+LZu/VhcHCvGiq+27Tk5Wy6/bZ/bE8fH9U99bdDWusNMxa2wLBLkrC2FxzRipurBzecgU3ujB52d1RxWd9tW67jtbc2OMtnhX8P4RJ0h1PjorufQmp447vSOpv0vKlPhhvH0EcjTs5fM2Co2h3K7tWOO/pLVbDLb5vTv1tu0909J/Djk8PqDoS46e6kGOvmSXuEnJlx9yDyOntwfFHzgENmjrQ7KbjShUTbSfYo3u0uwX0+E8cfk8fP6alw8NjlbWb9w07lG8+MyrW8ocRtdDK0V8uePc9te8KJspGirJim2K9Hn4m+tsdkba+vMdBlbWB/NLjrkuEcrd1CWEEEcN47QQosmInVhju8t0T4LpdNNWaJ1RiW/5UtbfGvt2j5rEMiihltye1rAA5ruDxsPtV9aux2GbBkt+iItnwb80+ztSrYUYLWvqHta4HeCKhRVE2xPOGo6h6a6J1Ox4y2EtnTv8A/dwtEE4PD9SLld9JKTNXky9uw5K1tiJnwQXrT055PGslv9G3TsrAwFxxl0WMuhTb+lIAGSexwB7ysLscTyaTc9lutitk1448E8dOMC/TmiMBiZYzDcwWcbrqNwo5s8o8yUHv53GqslvO34ZxYYiYpM84baoetjZtNNqJUc6uad/y3r7L2rGFlrfSfP2fCsd14ngfhl52qu/m4fuGH0s0w0TYq3iZbI+F7ZInmKaNwfHK0kFr2GrXAjb4TtU11TbMxNV/tDajj1bpLEagaR5l7bNdcMBB5J2+GVuzseCvQ73aZvVxW3dafm2Pej0CAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAUHzKhE6qk+o3UP7jrC2wUL+aHC2zTI0HZ8xdeI+9sYb9KwyTpRyfec3mzU6Wx/X9EL/AOlFVVpmCQ3b9PanNNKru9H9Hv0douztLlnl5S+JvclvqJZgKMP/AA2BrfaCvRSjsu2bf0sMf5XaykNGxEHFwrRBmn0ICATQd6mBBvVvrXHp3z9N6UlZNqCnLd3wo+KzB4De183dubx27FjdMQ0nce6RZHkx8/FVaaea5mlubqR81zM8vmnlcXve920lznGpKpumZlzF0zMt56X6Bk13nHR3XNBp7GAT5m7ryUZtIia7g6QNNexu3sWWOyur17HaTmv/APGOfu4/V99S5G56o65sMDpuMW2Fhe3G6dtY28scVrH/AHk/Jw5mtLzx5QAs7/qmkcmWW7/kZYttjTSIjj4z/CW+sWQsennTzGaA0/8AouyTTbuc2gf8pFR08jiPrTPcAfxFTfNI0bbuF1u2wRht5zz49qPegGko9Q6yOYuow/H6fYLgAjwm6lJbC3aKeDlc/wBoCxxtf2nberlrd9tus/px7G/epfNugxmE07G4ht/PJd3IB3stgGsBHZzyV9ym+aQ2HfM90WxbHXX9v1V803iM/nsm3Cacjmlv79hZJFFIYmuhBDnea4EARt2E83dsVdtejQYcV2S7y280oRemrW/klzr/ABMUh3Qh0x93MIwB9Cs9P2tn/wBNnmK6V9/8NJ1X0s1po6N0+YxnmY5u/IWx+ZgHGryAHx/naAsbrJh48+zzYtZjR2tC9VdUaHuY2xXEl/hK/wDMYqd5cws3Vhe6picBupsPEJF89U7TfZME/TOngurh8pbZvF2WYsiXWl/BHcQEih5JWhwqOB2qx2WLJGSyLreUvG13q+10Rpq81DcxG4NuWRwWzTQyTSnlY2p2AVO09lVOijebn0MfnpWVLNXa81Pra6fcZ++c63BJix8ZLbSIcAIxscfvPq5UzdMzRyG43WTNNZlsGmuimv8AUttHeQY+LG2MoDop793kFzTxbG1rpKd5aKrL0vGV2Ht2fLFYjT26NgvPThru1hNxb3WMvJ2VLbeOSWOQ02gtc+Plr2VISMdOUr7uz57ba/r/AERNkmZCO+uYMwJv3K3eYbttw4vma+Pwcri4kmlKb1hNa6tXfF0XUnmt50Gzf7306tLOc+ZLiJZMfIHcY20fEDw/u3taromsOs7Rl9XB5Z/tmitHUzSn+TtbZTDwtMdk93zWOI2AW85LmBp/3bg5nuVd8Umrm97hnDlm3pXT3caJ+sLeHrZ0ghjui12pbIGJtwaEx5C1bytedmxs7SC4djlbWLoby23/AJm111vt4196IOl2VsTfX3TTV8BGB1BI6Dkko11nlIzyNcwn4XOc3kqPrBvaVhjuppLV7ObYunFk5TPwnx/Rp+stKZHReobrBZGr3wkPtbkAtZPbOP6co9u53Y6qwus8vuePcYZxZJsnpxx8OjzsTmcrgcjBl8NdSWORtzWK4iPA72ubuex3FrthWMTMTowx5LrJrbNFwOlnVmx17bjH3gjstTwR81xZj4Jmt3ywVNS3tbvar4uieTrO39xtzx5bvv8Amk8Hm2o2nOHJBxIqhTmyBQUQmNGUSweKMUH+onSBy2nYNUWcRdfYIn5ktBJNlLQSbOPlu5X+zmWN1tYabvW289nniNY5qojcO3j71S5WQk/V3hIFl/TNqPnss1pSZwBtJG39owmv6c1I5QB2Ne1p/Mr7JrDpOx7jnZPv/Sf0WLCydEICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIMOKiUS+MsjYmOleQ1kYLnuO4ACpJ9yMbrotiZno/PrU2YfqLUeWzj3F5yN5LPGTwjLiI2/lYGhU3Tq4LcZZyXzdPV5IFTTedqwUylPohoY6t1SzKXsXNgsE9s85cKsluR4oYtu/lPjd3UB3q3Hb1bTtm0nLkrP226zxx+a5Y3KyXYQyiRECFBBxcaIRCButPWA4MS6R0zOBmpW8uSv2GptGOHwM/3zgfyDbvoouvo0XdO4+WJsx8+qrZ2uJJLnEk8ziSSSakknaSTtJKpmXMzdM6y5wwTXE0VtbRGa4uJGxwRN2l8jyGsaPa40UUrJbE3TRY3XcUHSbpHZ6PsXj981AXR5G5YKOk5mh12+vZy8sLewEK+bvLDf7uz/i7aMcfdfz93FI+LqemnTDJbjLaunYCLYDH2BI3OcBJOR+Uxt+lRZFIOx4PNM5J6afHj82j9dM07M9Rb+Br622IihsYRXc5rfMk/tvp7ljknWIa/umbz559mnw/mqbvTvhm2GghknNpLmLua4JptMcTvIZ/qE+9Z2x9MN52TFTDN3+U/LT5ol9Rt6656gw2tSY7HGQMDa7A6R8khPvHKq8ktX3q7/Xp4RHH5tN6b6zGhNU2+eltnXNp5UlvdxMp5hilA2sqQOYOYDtO5TZMRLw7PdTgyeeNW9Zb1Ia2u7hz8TZ2GNtKnkjkjfcy0+84ljfoapnJTk91/esszpSOPb+zhYeozWcZdFmMfjMnaSeGWLkkty5p3ioMg29hanqx4It7xl1i6l1s9KIpzd3jb7L3l7iLF2Nx1xIJbewLg8Q8wBexrgBVnPXl2bAsL5iujV5LoumsRRczopcSXHTDTj5DzObBLGDtPhiuJI27/ALrQr45Ox7XfM7e38fnLSfUzePj0vhbJruWO4yXPIO3yoX0r7ysbuTx99upZbb+PHxVw0vmYNPagx2cubFmTisJvONlIeVr3Bjg3aWuA5XEOGzgqrJpLnMOT074upWnSUn5D1H65uZicfaYywhO0M8uS4cPa57miv5VnOSPBsru855meUR7v6u7pz1I6jtrwDVFhbZDHknzX2jDBcMHAtDnFj/Yae1TGSGeLvWWJ+v6o445Ih1Hm5tS5/J564jEMuSuXTmFu0RtOxjK7K8rQBVV3XVmrVZss5L5unqnn0w3ziNT4xzvA11pcsb2F7XxuP9hqzxz9Le9hvmt0dP6s+pzCt5dP6hY2jy6XH3D+0OHmx19nK/6Vlk5I75i1i/jjm8v00Z0w5rN6de8+Xe2zL2FtaASW7/Lk97myN+hRjlX2XLS6bPH9GvdfNN/5f1y7KWYMVrnYxeROZ4Sy6iIbKW02g15H171jk0mqju2D0s/mjlOvHHVvOqLAdXOkVhqy3jD9U4OJ7p2tHje6HZdRbP8AaNb5rR20Vkx5oerNb/yttGSPus58fmrYDUChqCBQrz0c++9neXeOu4L7H3D7W/tZBLbXMZo9j27iD/Cm47iptuozsvusnzQuJ0m6q22u7A2GSMdvqmyYDd27fC2dlaefEOwn4m/VPcQr7Zi51vb+4W5opd9yUq147UbWjI3IhlAQEHwuraG8t5bW5Y2W3naWSxu+FzHChBHeCkMcllt9s23cpUT6haMuNCaovMI5rjZOJnxk7t0lq8nloe2P4HeyvFVX6S4je7a7DkmJ5dGp7lhLyJC6M5x2C6i4aQv5LbIOfj7nvFwP0/8AxWsWeOaS9/bM3p549unH40XfbuCuduygICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAg4HeoQ0rqrmTgun2or5juSY2b4IDx825pCynvelaPD3G/y4Lvbp8VFaADlG4CleygXncRXq7+Fw2R1Fl7LC4mEzZC9kEcLNvKPtPdTcxg8Tj2KbbaysxY7sl0WxzlevROkrDRWnbTA2HjEDea5uCBzTTv2ySH8Tq7OAoFe7faba3Bj8sc+rZBuR6RAUDKDClKJ+svU5uicUcViHsdqnJRn5f63y0NeUzvHbwYDvdt3AqJmnNqO57+MNvltn6p/JTqR75pHzSvdJPI4vlleeZ7nk1c5xO8k7SqJmZclN0zOrGzZwChCWOgWmGZ7XLcjdM57PAw/NbRVpuJKshB9nieO8K3HHVtO07f1M0V5Rxx7nHr/nHZXqBNZNfW3wdtHaMG9okkAmkcKfja33JlnWIO7ZZvzzHhosP0YxDcP03wMfKGy3UJvJ+0vunGX+DSArejoO12RZt4p114/BTrVd0b7VOfuz8U+TvHg9o89wH8AFRfNbnIZ/8Acn3zPxmq6nS21ZZ9OtLxR7P/AMZBIfxSN8w/S5xV0aQ7Pt8UwW08FYuvZcep2SruFtZ0Hd5A/pKqy83Nd2n/AF546Q8bpr09uuouamx8d0bCwsYhNfXgZ5hHO4tYxrSQOZ9CancAllleanZbO7PfSOXi3jUfpw1TYPD9OXtvmbc745qWs7T7+aN4/MFn6fg9ufs2Sz7Z8zoYn08a/vpQMibLEwVo58kvnvA7WsiBB97wsYxK7ezZppWj0NTenLUmIsfndP5CPPTMFZbIxC1mP/CLnuY72OLfapnHCzP2a+yPpnzce+U/9MsJc6b0HgMPeRmG8t7QOuYnb2SyuMr2nvDnkKzo3vb8Xp4bYpSdfzmqOPUzZvl0rh7xrax2uTDZTvoJoXgfxbRY38ng77bPp2z7UU9N+jeR6gYu7zDsgMVYRSmC0c6HzjO9nxkeJlGNPhrt217FjZZWNWp2fbMm4t80TT46vtkPT71Esrh0NpDZ5KIV5J4bgRAgbqtmDSD3bfak4md/aM0XUe/pn03Z++c6XVWRixdvyO5IbMi4nLyNnM5wEbWjiBWvcojE9G37JfdM+fSETaw0xe6N1Fe6dvntlmtC0suGgtbLFIOZjwDu5hvHArG62ktRnwzivm2eiYPTESc9qMHd8nbGvf5r1lj5S3PYY+u73fskP1E2zZunbpi0F9rkLSSMnte8xn+Dys7uT396sicFfCf3QL0OvH2nU3Bhp2XLbi3kHa18DnD+0wKvHOrRdrumNxb7Z/SUz+pLDtu9HWGXDQZsXfsBft2RXLTG4e9/IrL4rDcd6w1xRd1iafh/WIar6Zs5S7z+l5iHRTRsv7aM7RzNPkzbO8GOqxxzo8vZcus455SifqPpxuk9a5nCxNLLRk4uLEU/9tcDzGAdzSSz3LG+NWq3uD0ss2xyaoRX2rB5XcxOUyGDyVpl8XO62yVlIJLadvAjeCOLXCocNxCmLpjkzx5Jsui6Oi7nTjXuP1/gY8nbtEGStiIcpY81TDNTh2sePEx39IKvtnR2mx3du4tr/fa3YI9rKJowiBAKCOurfT6PXmm3x27Wtz2PrNipjsq+g5oXH7MoFO40PBJisUa7uW09bHWPut4opO+KaGSSCeN0NxC9zJoXjlex7DRzXDgQdlFRMUnVx10Ul9Le7lsLmC/t3cs1pIy4jcN4fC4PB/gluklkzE6c36IYu+iyWOssjAQ6G8gjnjINQWysDxtHtV76BhyRfZF3jEO6pWCAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgwdySiXFQhCPqTyjrXRdhjWEA5LIs8wcTHbsdKf7QasbuTS97yUxRb/lKpzGSSFrGNc6SRwaxjdrnFxoGgDaSSaKqNXLRFZpC4PRfpiNGYo5jLwg6nyUY81pFflYT4hC0/a4vPE7OCvtjyw6ztWw9K3z3R9U8vYl0U4I25VBqupOoejdJ1bnczBBcgVFmx3m3BHdFHzP/gpo8mff4cXO7XwhF2V9TWAgc9uFwt7flpo2Sd8dqw9++R39lY+e1rMnfLY+2PjxLw2+p+85/HpaMxnfS8PN/GKij1LXn/76+n2xx+DYLP1K6XuLSY3uLv7O9ZE90cI8uWKSRoq1gkYQW8x4lgCmL7Xojvtvl1tmv5cfgrVnc7k9SZe8zuXl83IX0nPKdvK0DY2NgO5jG7AqrrvM57Pmuy3ea7m81YqgoLV+mvF/L6TyWUcwB+Rv3Ma/ZtitWNYP7ZcrscUh1PZMflxTd4yrhre9OQ1dqa+c4udNkrwhx+yyVzGj3NaFXkmsue3EzOaa+P6r0aWgZbaXwkEfwRY61a32CBgXol2e1si3BbbH+MfJQbLBzcvkmO3tvLgOHf5r9681/OXEZIpdK8PS+4ZddO9LSxkEDGW7DTgY2BhH0hX9Hadvn/Qt91Fd/UfjDaa7t8hQiPI42JwdTfJbyOjcPc0s+lYXx1c/3nHNuevjEft+jZ/S86Mv1U0bJCLIgceX9YfzU4+T0dhj67/dHzlZLlFOH0LJ0vsKUSUcubNEJ9hsolTo17WGlsdrPAXensm6RltdcjjLCWiVjo3h7XMLgRUEdiQ8+629uazy3O9gcHjtO4mzwmIhFvj7KMRwx/FsG0kn6znEkudxKUZ4cVuO2LbOT0qdoqlVp/Cm9CZ0VB9Rboz1EaGfEMZbCQjt8yU7fcQq8jke8zXPPsbn6YsaRb6lzHCSa3tI9n+ya6R+3/tGrKzS17ew45+q78G2+om5ZF07dE4+K5yFrGzvLXGQ09zFM8pervV9MNPb+ivPR4E9TNLhuyl1IT7BbyEqvHzaLtn/ANFqzXXSJs3S7Okj4PlpG+0XUVFbPV0PeNNvPvj/ANleOhN6+z6nYlrdjb2K6tpAOwwmUf2o1XiaDtV/l3FseP8ALcPU3i2QZrT+aY2hu7aa0lNNlYHteyvukcsskVtevvmOIyRdHWPl/VAY7lS0QoG16A1pfaE1JbZm25pLNxEOUtAaCa2J27Ds52fE3v2biVnZdSXq2m5nDfF3RPWV9S+nLZ5Zh8Re5IjdLIWW0Z/rcz/7Ks89re5e+2f226+3+KvBb6oLrn26WYWV2gXh5vpMKee15/8Avr/8Y+P8Nlw3qT0ndkR5vHX2Kcd8wDLqEDvMVJP/AA1MXw9WLvmO77opPs4hKuB1fpjU8JmwOWtr9oALmRSNMjQftRmj2+8KWyx7zFk0i6K/m9zmB3bexHpDU+zihrVXjrz0uNwybXWAtybiFlc5Zxj+8jYP/UMaPrsA8fa3bwS6zzQ53u+wiI9S3SOv7q0AtIH2XbB3rzdXO6rvdGMkcn0109K4l0lvA60ed5ravdC3+y0L0u17VfN+3j2TP8fkkQGoUtjDKAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAg4kqES48EohWT1PXvNk9M44O/uYLq5c3h+o+NjT/ZcsMnKjmu+z9VseEfP+j0+iHSU2Itta6ogLb4tD8NjZBthaQQJ5Qd0jgfC0/CNu87Jts8qztnbdPUv/CP349vhSwj5I4WOke9rWNFS5xDWtHeTRZOg81tsc0Z6r64aF00JIILw5rJs3WdgWytDtvxzV8pvf4iR2JOnNrdz3bDj5a3fkgDV3XLWupzJb2c/7BjHeEW1kT57mnZ47ggP/qBqrnJ4NDue6Zss86R7OOPBGJLnOdIXF0rqmR5NXOJ3kk7Xe9YVmWtma83APa40aebuG0/wURBSYHOaw0dVv4tn81M2zHMiJly/moQKAQP9ApFzugrGR9L8M5o8Ukt255+981IP5AK+3lDsOz//AD/j+qoOomEZ3ORkEO/cL1pHGvnvVN/Ny2bTLPvXu0Rd/P6O09ebP18ZaPNN1TAyv8V6LubtNjd5sFleflj5KT9QcZ+0a51JjyCPLyM0jNlKsuHec33cr1Rk5uN3mObMsxKy/p3zTL7QLcbz1mw13Nbuad/JIfPYfZSSg9ittmsOj7Nmrhp4T83Q9R+nf3HSlpqCFtZcHcfrHj8tdUjf9EnIfpS7W1h3zD5rIvjnbp8f5Rv6cswzH63u8XK8NZlbB4jqaVltneYAPyF5WGKejXdly+XNTpMcfqtx7d/FWS6xlB5efyV3iMPf5OysJspd2sLpIMdBTzZngbGMJ4lFeW+bbZmIrKuD/Ulq7HZOe3zGm7WBrTQWD3z29zGTu5nSNPN/3YUTdTo53/uctt01t/Dw/N2cL6htZ5jMtt7HSkWTtHEA2Fh58t01pNCTJQs2ffa0d6RfXosxd4zX30i2NVloXmSJj3NMbntDjG6nM0kVoaV3KXQxOj6IlxOyp7VJ4qN9X8wzM9RNQ3sbua3t5m2kTvu2kYjdTu5w5U5JrNHE9wyRk3F0x1n+P0Wj6Padk0z0/wATbXDCy9vGOvrtpFCJLo84aeNWMLW7exW0pFHTdtw+ngjxnVGXqczbeTT+nY3BzueW/uGA7Q1o8mOvtLn/AELHJOjWd9y62446a8fm0ToBjHZDqTaXFD5eLtLm5f2Vc0QN/wDNWOPnLw9pxefPHs14+KeuvN0LbpfmGH4rmS1hA/FcRn/7VZOkS33eJpt5jxmP3Vx6LNLuqGnKcJbgn3Wsv/SqrObnO2//AEW+9MPqda3/AC/p6QgFzchI0O47YHf9AWeTk3Pfo+i3jwVeG5UuYFAKaASANuzvQAQ74amm8gEj6Qp8sz0Jijj5kdeXmHN2HYfoUTFE+WX2t57iznZdWc0ttcx7Y7mF7o5Gnuc0hwU23TCYvmOSYNI+oPVeDMdtqFjM/jm0HmuIhvGt2becDkk/OAT9pWRkieba7bu+THNLvqhPul+rehdWCOKzyjLW/eBXH3lLefmPBoceV/5HFZxq3uDuWDL1pPt/fk3k8j202FhG3cQQfb3I91Yu9sKndZ+kztMXEuqdNw//AB24eXXtnG0n5OVx2uaBuhedv3T93dhks6uW7n270p81sfTP5cdPgkj01XxuNFX9k51XWOTlDW9jJo45f9ZzlNnJseyXzOKY8JTe0rJu4clKRAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEGDuQlxUMWOCJpoqJ6jbl0nUG2jDiPlsXAGEHcXyyuqOw7lhf0cj3vXP+Ecfm0e26k9QbSIRQaoyQjpQB03mEDsBkDiFjOSXgs3WW2KRdd8Z/d4+U1HqLNjlzWZvshHv8u4uJJGD8pdy/wUeeZYXZr7opMzPvmZ+by/gAHfRtO/gAopM8lfNJ+jeiGs9ViO7u4v2HEvofmbtrvPeO2OCocfbIW+9WW4/Fsdt2zLl6eWPGeOOkp6050F6f4NjH3lo7N3Y3zX58xte6EcsQ97Ss4o32LtOGzWdZSLa4XE2MYissda20TAA1kUMbABw2NCmZl7bdtjsikW2/BoHWjUllpLRly+K2gflMnWzxzHxsdyvePHJQj/DZV3toOKTdTVr+6zjxYvLSPr0UxoQADv8ApXmhyQkgkQHZs4qZFxPT5dNn6aWUFQTaXl3C6hqamYyD+D1db9tXXdouicFParT1PxzsT1B1NaFtAchJcM4eG6Anb/rqvLGrnN7j8me6PbP7rQdB8s3K9NsZEX802LfLYzHiPKeSz/w3NVsaxDpu0ZfPgp1tn+fkh/1H6fdYarsNQRMpbZi2EUzgP/cWvh2ntdE5v9VYZIrSWn71h8ubzdJj+J/R0fT3qhuE1m/C3D+S01BD5TanYLqCr4u6rml7foUYp0ow7RuPTzUnldp+3HtWtzWJtc5ib7D37Oa0v4JIJwfsyNLTt7RWoVrqs2H1LJsnqoray5Pp1rWN0zXfuOncjSZoBHmRxuo6leEsJ2e1U/bc4m2bsGavW2eOPBfHHX9rlLG1yVk8S2l5EyaB4IILJAHA7ParZdviyRkti6OUu0TQVRZEPLZqLBy3UtizK2br2BxZNbNniMrHDeHM5uYHbuIWVHnnc4vN5YujzeFYfPI4LT2eaw5bH2WSaz4HTxRTEDuLg5NYY5MODL90Wz8H2srDC4S2Fvj7a0x1q3/ChZHA3+yGpzZY7cWOKW+WGYM7hbm8GPt8jaTX5aXi1jmjfKWt3u5A4uoO2ixoztz2XXeWJir0K7O9FkTo1rXmqINHaUymfmI8y2hItYzvfcSeCJnveR7kebd5/Rxzcpv030xNrXWuNxdxWaAzfO5iV3iDoYSJZOb/AIryGfmVdkVuq5HZ4Jz5oiOI40969Y5WMoKNY0eEcBT+VFa7X7YUX6paoGrtcZbKQv8AMsYX/KY9w2tMFtVoLe57+Z/vVWSXEb3P62Wbulfy41TT6Z8AYMVmNTSso+/mbZ2pP+xttr3D2yPI/KpxxRuux4KW3Xz7n19TOYbDgsJgWPpLfXjrqRm0VitoyKf95I0qb+Se+ZY8ltvXn+n6o69PGON51EbduHNHjbGebm7HSlsLf9YrHFHNruz4/NuImnLX9P1b36n7pox2mbGvjkuricfhZG1lfpkWV/J7++3xS2Pf+itAIO7cqXNikFFR9rW5ns7qC7ti0XNvI2aDnAc3njcHAOadhbUbQUiaTUiY6r3aJzOI1bpjGZ+xtoYorqEebA1jf0pmeGSM0H1HAhemLq8nbbSceXHF0RHwenktM6fzDDHk8XZ3kfAT28clOGzmbsURK7JtMOT7rYn8EYan9POi8s18uEMuAvXA08g+bbE/ehkJoPwFqibYlr8/Zsd+ts+Xj4oA1h0q1lonnnvrL57EsqRlLIOkiA31kbTzI++op3qu7FPRoNzsMuLnGn5NEPLIG7Q9h2jisNYePk93Gav1dhQ1mLz+Qs4Y/ghjuJDGB+Bxc33UWXqSts3F9lPLMxT20j8nYyOvdb5a3da5LUeQuLaRpbJC6UtY9r94c1nLzAjgdiee4ybi+/7pmfxn96Ju9Lt04w6pstwZJZzNHe9kjHf6gVln2t52K7W6Pd85WOCydG5qUiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIMHchLioYsdvYUTHNUHrvis3e9Rb24tcXfXFoLW1jiuIraWSM8rCSA5rSNhO1V5LZmXJ91w33ZpmIR3Z6O1dfyNZZaeycz3GgItJg33uc1rR7ysYxy1sbbLP9s/BImm/T1rbLubJmnW+CtCfEZXCe4p3RRnlH5n+5ZRj11e/B2jLfz+n38fsnrRfSDR2i+S5trT9xy8f/wDp3lJZQe1gpyRfkFe1WcuTe7bteHFrMVnjokOoCVbKIlxe9jBzvIa0byTQfxSGF18RFZeY/UunYnmKTMWLJN3I66hBr2ULqrKimd3h63W/GFRuuGrm6o1tJbWkwlxWEZ8rbOYQ5jpXUdO9pG/xUZ+VU5bujle6bn1cmnKEYLBrRJBIAVr3BRIsv6Y8sx+O1BgXkc8FxFext7WTM8t30OjH0q2yfpo6PseTS633Tx+TWvUngDZanxuoI2n5fK2phldTYJ7Q7Kn70bx/VTLFaPP3vD5csXR/dx+zsemrUXy2Yy+l53gR5GFt5aNJ2edb+CQDvcxzT+VTZNYZdkzTGSbP7Zjjj2Ja62aYOp9BZAQR8+QxZF/ZgA8xMAPmMFPtRF49tFlMVhte64PUwzPW3VTC0u57K4t8hZSeXc20rLi0lH1ZI3B7HfSAqI0mrj7Zm272wv1pHUNvqvTOLz9sAI7+Br5IwfglHhkYfwvDgvQ7raZvXx23cVjRXz1JaSbZ5Ow1laspFkB8nkTw8+JpdC897o2uafwhYX21irQ9628Rd6kf3cfL5PZ9O/UBkts7QeUlDbm1DpsLI87Xwkl8kO360RPM0cWn7qWTWFvZ97p6d34cfn8Vh9+0f6e9ZVdFSmqvnWzo8cmZdYaUs2uybauy2Oib4rkAf30TRvlb9YD4x374m2rnu6bC6frs/GOOP1rOHSNqxr5GvYS17Q57SCNhBFdhHYqvPfGlZc5NtJ1j8n1t7a8yNzDZWkc15eTuEdvax88kkj3bg1u8p5758U2WTM0thb7pB0nttC2Iy2Tjjl1XesIuJG0c21ica+RG7t+27ie6iuiNHX9u2Hox5rq+f5JY2DZxJ2hGyjSPeqT1616zUWdZpfGyc+IwchN1Ix1WzXtOUgUO6EEt/EXdiwyXaUhyfd936l/ljlbx/HxSJ6cdJjGacuNUXMdLzOP5bVxrVtnC4tbSvCR/M7v2KbY8sNl2bbeWyck854lt/WLVx0jom9lt5DHlcl/yOPIPia+YHmkH/Dj5ne2iyiaavV3TcejhpHOdFKILeaWSG1tmeZcTPZFbx7y57yGNb7SSF541lx0fVK/mjtPw6U0xi9Pw0IsbZjJnjZzzOHNK/wDM8kr0u62eGMOO2z4+/qqd101IM/r++ghfzWWFjbYQUNW+Y0l8xHfznl/Kqsk9HK90z+rmnwjT4fzVKXpnwRgw2Y1FMyj8hcNtbZx3GK1B5iPbI8j3LKyKQ2nY8NLbrvHRpPqOzHzutbLFROBbirBvM37Mt08vIPfyNYmTR4e9ZfNm8vS2Ijj4whbZw3KhpxAWUBt4b+Cmgnr0661tsTeZPS2Uuo7axum/O2MszwxjZmUZKyriAOZvK4ewqzF9tG77PvIx3TbfNIn58fJZKDP4O5f5dvlbOaQ7mR3ET3fQHFZ+V0MbnFWnmj4w9DmB3ba7lEw9FWHtY9vI5oc13xNI4d6QTbF0UnkijWXQfSGqDLd49hwOUkqTPaNHkvdxMkHwGva2hUTFebVbrtGPJrZ9MoM1B0G6g4SRzrO0jzlm0mk9k8CSnCsMha4HuaXe1V3YvBo8/as1k6RWOPx/Jo1xpXVVq8x3Gn8nC8b2us7gfyZRYzbMPHG2yz/bPwTl6a8XlsfltRPyGPurOGa1tvKknglha97JJKhpe1ocQCNytxxSG97Liusm7zRMLKLJ0D6DcpZQICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgwdyEuKhiwh82KV28R71Eyc+ZSvsU1REQxsbw29qFYefl89iMDZSZLM30NhZRDxTTuDB7BXee4Iwy57McVumiv+svUgQZLPRFoCBs/db0GhPbFBUH3vI/CsZviGg3PeprTFH4oNzurtTalldJncvd3/Mdsb5C2EcdkTOWMD8qwm+ZaXJuMmTW6avCMMYr4GnvoFgq88+LkAAABuG5ESypQKQUAoEmdC8/+x9RMfE93LbZeOSwmqaDmkAfF/4jA0fiWeOaT72y7VnjFnivKdPj/NE99e8CMx09vLxjOa6wssd9GRtIjYeSX/w3ud7lbMN73fD58FetsqpaTz0mmNTYjPR15cfcxyTAb3QuPJM33xucqcc0ly23yenki7wnj9l/Wviu4A9tJbeZlQd4cx42fSCr3dxMX2+yf1UG1pgnaX1bmsBT9Kwu3tt9u+CSksJ/7twVOSNXC7nD6eSbfBOfpo1JWHMaRneSIiMhYg7fBJSOZoHAB3K78yzsmsU8G77HuJrNk++OPgmHqNptmrtHZfCcoN1Nbuks3Hc24h/UjNfxNos/Y22/wRlxTb1poopY3t5jru2yFlK61v7SRsttM3Y+OVhqPoOwg79y8/m8suKi6bLqxzXO6WdUbDX2NENwWWmpLJg/cbEGgfw86Ku10bvpadh4E+isTydd27uNuePLOl8fn7v18PgkfYd3vHeobOdYrDUM70y0Jqa5N7mMFbT3jzWS4YHQyv73Phcwu96mrw5u3YMs1mKT7JmPlLuac0LpHSjnO0/hrexmcOV9w1pdMR2GR5dJTuqkrMGyw4Z+i3X26/OrY9g2VGxRD1TCFOs/VuPTNvNpfTtwH6juWFt1cM2iyjeNpqP8ZwPhHD4jwrF00aTufcvTjyWT9XVVzDYq5zmXx+DtBW4yVzHbMO+hmcAXmv2RVxr2Kq2PNLmsdk33REc5foHjcda4rH2eMsmCK1sYWQQMG4RxtDW/yV7vcWKLLYsjpCqXqH1K7L6ziwML62eCgDX/AP8AauAJHk8PCzkH0qvJNHLd5z+fL5Y/teL0O08M/wBQ7B8ree1xEbshPUVq6PwRDb/vHh3uUYudVHa8Hq5o8I1+H80W51Xm4dNabyufnoWY61lnAP1ntb4G1+86gVrrN1l9PHN3Wmj8/ri4uJ5ZLy5cZLmd75rh53vlkPM4+9xXnmay4SZ80yvnoLAs0tovDYU0ElpaMNydw86QebKf67nK+jt9njjDhiPZWfmpVrXOf5k1bms4NrLy7k8kk/4Mf6UVPyMBVV86uN3Ob1ck3eLXxuVc81AgICmowQCCCAR37UqRLj5UQ2ljBwqAB/JTWWXmnxlteneoes9LPY7DZq5jgaQPlJ3G4tyBuHlylwA/DRTF8xzejDvMuL7ZonrRnqNxOQdHY6xthirk0b+5Q8z7RxPF4+OGvfUd6ti+Jbza96i6YjJH4x+ydLS8tb+CO7sbiO6tZhzRTROa9jmniHNqCpbuzJbfFbZrEvuBWu8dqM6ABA2EVrw7EqUnoU27Nn+nFKmjkg5AqUwyiRAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQYO5CXFQhgojq0/O9S9FaYyT8Rm8zFZZBjGSugkbJUMkB5SC1haa0PFKw82be48d1Lp1a9fdeumlmxzo8pJfSAbI7W3mfXuBc1rPpKTMeLyX93wW15zKNdTepe9nY+30niG2vMKC8yDhI8V4thjPL/Wf7ljN8Q12bvl06WRSOOOqEM7qLOalvf3DP5CfI3QPhdM7wR1+rGwUYwfhAVc3zLS5M1+Sa3TXjj2PPgt7m7uY7S0hkuruY0jt4WOlkce5rQSVFsTLC22buSRMP0Q6k5Zgk/aWY+Fwq199M2EkfgYHvHvCz9J7sXbM2TpR5Gt+nWc6fmwZm57OSTIiUwx20j5HBsPLzOdzsZsq8LG6ykVUbraZMExF3Vp1R2rGHmEBSCgFA7FhfTYy/tcnbmk9lPHcR0+1A8SD+Syt5s7LvLdEw/QC+trfUGnrm3cA+3ytk9padoLbiLZ/Nejq7nJbGXDPhdb8357+W5jjFKCHR1ZIDsoWktP8AELz3RSXCXViV4+kOWfm+nOnbuVxfPHbfLTOO8utXmHb7eRejpV2nbL5v29s+GnwQB6jscy015b38bA1uSx8b5HDc6SB74z7w3lVV8cpaDvFlM80jSYjj8mu9Fso/GdS8E4GjL10tnIK72zROoD/2jWlRZzU9rv8ALnt10XbpUbRWm8q3q7TooT1ExTcJrnUeMjAbDHfyyRNGwBlxSdoHcBIqcmkuF3mPyZro9rwsbkb7D38GTxdzJZ5C1fzW91E6j2Hj7WncWnYQls0eey+62YmOaymh/UVjbuKOw1vD8heijf3SFrnWsm4Ve0VfD372+xWxdEuk2verbqRkjXxTVjdSafzEIucZlbO7hefC+KeN47OBU0bizc48kViYdTM600rp+F0uXzVlZtFTyvmZzmm8NYCXuPsCUYZN7hx/ddFfDqgXX3qIlvIZsVoWN9tG9pbJm528stD/ALCI/Cfvv3cAsZviOTSbzvM3R5cfLx6/wr66SSV75pXufLK4vkke4ue57jUuc41LnE8SqZloLprOqVPT/imZLqNbXD280eKtLi627udwELP/ADCQrMcay2faMfnzxXprx8VxiQxtTupt9n/0Vrr5mmr8+dSZN+a1DmMs9xeb++uJmuO3wOkIYPcyipvmsy4HPf5skz7fnqn70w4wNttS5pw2vmgs43d0TTK7b2fqNWeONG/7Dj+672cfo2L1G5R1noa3xzSQ7K5CKKQV/wAKAOnI9nMxqm6aQv71f5cMR4yrTojHDM6x09jCOaO5yMAkbvrGx4kf/ZaVVZH1Ob2+ObskR7Y+a6PUjLuwOg9R5OJ3LNDYSthduIkmHlMP9ZwV9aQ7HfXengupPPT46KHNaGtDRuaAPoXlcPM1ZU0BTEAokEAIN/0d0l1PrjEOzOEuMf8ALslfBJBPLIyVr2AHaBG4CrSCNqstsrD3bbYZM8TNnRwzPSDqJgWPlusHLdW7N9xZObdN/qM/Up+RLscsc2wz4+ds8e6v5tELXse+J4LZmEtfG4crmuHAg7QfasZiYeSYo9/S2tdT6NufP0/kX2rCeaa0cPMtpDvPPE7w1P2m0d3pF8wvwbm/FNbZ44/hOenPUxbOY2DVOGkhkAAdeWDhIwniTFIWuHuc5WRfDdYO+U0yW/Dj9W/2fXTpneN5v3wWz9lWXEE8bhX2x0/isqx4thZ3XBd1/Js+mtdaW1dPc2+ncnHkJLRrX3Ija8BgeSG7Xtbv5SlYevDubMulstlReyES5qUiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgwdyEuKhiwdymDoqH6jIHQ9QYJR8Nxi7d39SWVpVWRyXe4j1/wjj8kOAcXb+NFVVqHONj5ZmQRMdLPK4NiijaXve47AGtbVxNeACmkymLZnkmbQ/p+1BnhFf6qc/B4t1HNtRR188HhQ1bDX71Xdyttx05tvte0ZMlJu+m3jp+/wWT0zonTOj7X5XT2Ois6j9a4pzTyHtkldV7z7SrKujwbXFhj6YbEPCPFtWNXpjRT71D5Y5DqE6xjfWLE2UEBZwEktZ3/wexYXz0cj3i+Ls8+yIjj4okO+lNyqalhZQCiQUQCkcZKch202H6KbUTbzX+0UJRovTonBbN+12fmA7wfIZUFeqebt9nExtrIn/G35KJZvyxmssIv7sX11yU3cvnvp/Bea/m43P/uT71tvT2JG9NrLzTsdd3ZjH3POd/TVX2cnU9nmmH2VRv6nCz95022tJBZ3RcOxpkjp/IrDJya7vtPPb7kUdPWyP17pZsIJk/dbXaOLQ8F39mqxx/d8Wp2sTOW2n+Uf+0L8Gu0N48VY7yVJOt3L/wDtHUBbwNrX2/KxVWGTm4ruf/0Xfh8oaBFBPcytgtoXzzSV8uGJrpHuoKmjWgk+5Y0rpDw22zdNI5uM0cltK6C4jfDO34oZWmN49rX0IUTbMJusmJ1fPkjBqWivbTd9CjXojzSNjjaS5jRU7zSiV8Sbp6vvbW9zeyGGwt5buYAkxwMdM4AbyQwGinyptx3XS+XiqQ5pDmkhzSCCCN4ISYox5Jz9MroxqzNgkCU4xvIONBOA7+hWYerd9jp60+6f0WluuYWs3Ltd5b6Diag0Wbp8mlsvzmBcB4/iBId7RvVF0avn006LWemYt/yhmB9YZd/MO75eGiux/a6fsX+3d7/0eb6nw/8AbNMkf3XzdyHHhzeSKfyKjJyYd8+23jwRF0b8s9TtMl9OXz5aV+18vJRYWc2o7d/9FvvWQ69eZ/8ArHMeWCR5lp5tODPmo6qy7lLo+7/7E++PmpmOzsVEuOBuQFMAokFAbEFiPTFlXNuNQ4F7wWubBfQRk7a7YZTT+or7J0dB2LL9d1tenHzWVpU0J3nYFk6SrS9Y9MdI62iJytkI8gBSPJ29IrlnZ4wPEPuuBCmeWrw7nt+LNE6Uu8VZdc9E9V6RdLd2UTs7g21PzVqw+fGP97CKu/Myo9iqux+Dm912zJh1jW3xRe2j6uBqFXMU5tbOjNSAQCmgsh6XrbwaqvHAeJ9nA13aWtlef9YK6z7XRdhsmt09KR+qxwWTomUHIblLKGUBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBBg7kJcVDFgolG/UPpHh+ol9ZZC/v7qwubKF0DDbiMhzHO5/EJGncUpEw1u97fbuLoumaNSs/TRpSJ7XXuXyd2ytTGDDC004Esj5voWMWw8lvZMVazdKStM9PNHaQ8WDxEFvcEUddkGW4Nf8AeyFz6ewrOrY4e34cWsRWfa2qgFSP4JL1xSOSNtadZtHaNfJZyTuymYZsdj7Lle5hpUCR5PJH9Ne5RWIa3dd0xYdI+pDOU9Sur7t7v2jF4/Hw02CbzbqTu2gxN/srGb4q1GTveWeURHHHREObzN/qLL3mcyrmvyF/IJblzG8jOYNDQGipoAAOKqumstRly3ZLpuumsy89QrEgFMgsQOxSNq6faQuNb6qssJGx3ydRPk5hujtYyC7b2yfAPas8cavVs9vObJFsLj661Ja6K0bksvsYbW3MVhCNzp3jy4WN/OR7lc6/eZowYZ91IUTgt7q9uIbW1Y+5v7qVsUMbdrpJ5SGgD8TyvNrMuItjzTRffRWnYtJ6WxOn49rrK3a2eRu50zvHK780jiV6OTudng9HFFn4/qqf1y1HHqHqDeMtniSzw8bMfGWmrTIyr5j7pHcvuWGS7Wjle6ZvUzzPGn81dzoBp6TNa8hyjmH5LAwuupX8PPkBiib/ABe78qxxxrVZ2jDN2avS3VcRzg2pcfCNpJpQAK3q7CZpqoFrbNN1Bq/O5prg+C8vZTbuHGGM+XGf6jWlU36y4Hc5PUyTd7U6+mbBRfKZ7Us0LTM+dllbTObUtbGwSS8pPBxe2tOxWY4pDd9kwRS7JPhSP1/ROeY03gdQw+Rm8Xa5GIDwi4ibIR+EkVHuWUN3k22LJP12xLRrroN0zuZfMbiH29aksguZ42bfu89FFIno8U9owV5T8X2suhvTOxkbKMGLp42gXM007fe17y0/QpiIjozt7Tt7ZrSW+4/FY3FW4tcXY29lbs+GK3jZE36GgBTWr2WYLLIpbbHwVU9ReChxmtLPJW8Ihiy9kHSuYKB9xbvLHHs5uR0aryRpDl+8YPJlrEaTH59f0eL0LzceG6j49kzg2LKxS49xcaDnkAkj95fGGj2qMU9FPa83p54nx0+P80XQJrSo9ysdnd0UN6i6dk0xrbNYjlLIW3L7iyJFA63uCZYyO5vMWe0FVXRSXC73D6WW6328fkk/016kZZZrK6YuXhrMnGy6sqkCs1uC2Rorxcwh35Vnj5UbLsu5izJ5J/u449yW+tWk5tU6Guo7OLzsni5G39nGN7jECJGDvfE5wHeppWG27rt5yYJpzt1U6wWYmwOZxudtfFJj7mK5aytC4RuBcz8zatVVs0lyWK6bL4nrEr2ZGzxWu9IzWglEmKztl+lM3gyZnMx7e9pofaFfR2t3l3GH2Xx+aieaw2Q09l73CZSPy8hYSGKcDc6m1r2n7L20c3uXnuto4nLjnHdNs84dDbvKQrFFQQFAVHFSPf0lq7M6Iyrszg3xNvXwOt3CdhljMb3NdtaC01q0cVlbfRft9xdhu81vNLWH9TGoIJmtz+GtLy3PxyWb3wSjtIbIXsd7OYKz1IbbF3zL/dET+H9U36M6n6R1u0R4m9DMjSr8Zc0iumgDaQwn9Qd7CQsqxLdbXuGLPy0nwbpRtNu0Hgpe2Yjq0bU/SfQurHvuMlio4r5+031qTbTk7qudHQP/ADAppPN4M/bcGXWnlloE3pk0w+Qm2zuSijO5jvIkI/MYwsZsivJ4P+js/wAkjdPenmM6d467sMbc3F587OLiaa45OfmDGxgAMa0AUap5Nls9nG3tmImtW6+1HsEHIblLKGUBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBBg7kJcVDEQYPZxQYLmtBLyA0bSTsSiJujryaPqnqpofSTJBkMtHcXrR4cdZkXNwTSoBYwnkr2vICTpzeHN3HDiifq80+EK46665ao1b5mPxRfgcI+rXRQP8A+amB/wBpMKcoP2We8lVzk8HPbvuuTLpH0x7ETAMaKEUHDZTasKtZWZZ3AHdVQhyIpvUDCkEkFIdyiYH2tLS5vrqCxsoHXV7dSNit7Zgq+R7jRrQEpVlZZN00hdbpb0+t+n+AbBNyS5y9LZstdAbC8DwxMJ+pEDQdpqeK9ERSHZdu2UbezX7+qvnXDqINYZwYXFyh2nsO9zWyNPhuLv4ZJQfrMZ8DD7TxVd93RoO6b7176R9tvH9P5bd6fem75JW69zEHLEwFuBgePiJBa+5I7KEtj957FNltHs7Rsaz6l8cuSUerevo9C6akktpGnP5EGDFQfZcR4piN/JEDX20HFZzNIq2Pc93GGyYifquUsiiuL24jgiZLd3t1KGxRjxSzTSGgFN5c9x+lUUm6XH6zK73SzQkegtLw2E3K7L3R+ZyszfhM7gPAOPLG0Bo+nir4imjs+3bP0McV+6XgdcddR6V0tJi7KWmbzjHW9sGnxxQHZNNsNRRp5Wn7RSZ8uqju26nFZ5I5yp9DBNPLFaWsJkuZXNit4Gglz3uIa1oA3kuNFRGsuSjVe/p5pVujdI4zAkh9xDGZLx43OuJXF8p4bA40HcFe7nY7f0cMWzrLbUeuRECDBUJ6op666Nl1Vo513ZRmTK4NxvLZjRVz4gKTxgcSWeId4CmYrFGp7rtvUw+aOdqnVvPPbTQXtrIYriCRk1vKN7ZIyHscPYRVeeJpLkrbptnTovX071nba50xZZmMht5Tycnb7OaK6jFHin2T8Te1pC9Ptdtsd162KLusc2lddenkmqMK3UGJh587hmOJiYPFPaHbJGKbS5nxs944rGYrDxd32XqW+e2NY+X8KpYfK32FyVlmsZJyX1lK24tnndzMNeV33XbWu7lVbd5XL2XzZdExzhe7RmrMZrbT1pnbA0ZM3luLcmroJ2/HE4drT9I27lfR3G13FufH5lX+tvTp2kM2c7jIv/jmWlc5tN1tdOHM+I8OV+17PeOAVV9tdXMdz2PoX1j7LuXHH5Nt9PfUUQOGg8xMAx7jJgZnHYHHxSW9T27Xx+8diytuq9nZ97SfTu/Djj5Nu64dMzqnG/5kwkPNqHGxHzoGjbdWzdpZu/vGbXM7d3FTdbV6+7bH1LfPb90c1SW05RRUS5SWUgEBA28BVQG7ZvJ7EAgjaRRByjkkikbNBI+KeJwfFNG4texw2hzXChB9imJpqmJmE26H9Quawojx+r4X5rGigbkI+Vt5GPvN2Nm/su/EroyRPNudp3e/HpfHmjjj9Vh9O9QNH6piY/DZm2nmcAflXvEVw3udFJyyD6Flzb/FvsOSlLoifBs49te9HqrVmqMubKIEHIblLKGUBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBBg7kJcVDEQaX1Tx1zk9Aaggs5JYbuK0dc28kL3MkD7YiYULdu3koph4u4WzOG6Y6RX4KQTZbLXcfLc5O8uIXipjluZntIO0Va5xCo81zjLst06TLotY1o5RQfaAH81jMsJmZdvH2F/l7yHHYu1lvr+Y0itYGF8jj20G4DiTsCmLZllZjuvmkQnTSfpvyV4xl1rDJHHNfQjH2fLJMARufM6rGnua13tVsWRDdbbsl98VyfTH58fFIN30L6bYvD3twzGS3M9tbTSNknuZ3nnZGXAkB4bvFdyzpR7snacEWzMVmacclP4yTG0naSASV5pcrdzclCBSCTIwSG7Tu413U7U5lKrSdB+l7cRZx6zz0NMveR1xVrIKOtrd4p5hB3Syj6G+0q+yKOl7XsKR6t/4fv8AsdeOpzsPav0Vgbjly95H/wDlbmM+K2t3iojBG6WUH8rdvEJddSGXd9/5f9OydeqIuknTiTX2d8y8Y5mmcaQcjIPCJX7227SNtXDa4jc3vIWFlvVqO37Kc9+v285njx46LdZ7O4fRWn58rfltri7CINjhjABNByxwxN2AucaNaArZl1mbNZt8czMcuUfoo7rLV2T1pnrrP5Uhpf4ba2Dqst7dpPLG2v0uPE1Kovuq4vcZ7s1/mnnKfug/S8Y2KLW2obflyNyyuHs5BtgheP75wO6SQHwj6re8q22KQ3vathT/AFL416cceKZdU6mxekMHd5zLvLbO1ZXlbQvkkcaMjY073POwf9Clt91uLMNnmu5KNat1Rk9Y526z+VcRPcENhgqSyCFleSJlfsjaTxNSqb5q4rcZ7s183SnLoF0xP6Ovs7EQSD+w2rxua4UNy4Hi4Gkfd4uIWdlrd9p2H/8AS6PcsgNgCzdEygICAg4uYHVrxFDsrsQp08VQOtvTN+kco7UWHh/+OZOWsjGg0tbp5JLT2RynazsNR2LC+3q5Luex9G7zR9stZ6ZdQbnp9qBt84Olwt5yxZa2bUkx12SsHGSKpp2ioWNl9NJ5PLsd1ODJWOXX3ccaruWV7aZKygv7CZlxY3cbZLeeMgsfG8Va4HvBVztLL7braxylVnrj0vOn7yTWOEhpg72SuSgYNlrcSH+8AG6KV2/7LvbsryW11cv3Tt84vrt+2fy46fBp3S3qJc6AzzZZeeTTt8Wx5e1bU0A2CZg+3Fx+03Z2LGy7y83l2G7nBfr9s81xshjsJrLT0lpc+XkMJlbcEOaQWuY8BzZGOG5w2OaRuKudbksx7jF423cv4Uk1rpDKdPNSS4u5e8GF4ucTkY/CZIg6scrCKUkYRR1Nzu6iqmKTo4/c7e/BkotN0g6lRa8wptMi5rdS41rW5CMUpMz4WzsH2X/WHA91FZbdV0nbd9Gezy3fdHH9UTdeembcJdSa2wsIbibuX/8AL27RQQXEhoJh/u5XfF2O28VjfbVq+67CbJ9S37Z4/NBNaqlo2VAKQ2IPT05awXmosNZXcQmtLnIWsNxGSW88cszWuaSCCKg8CsrPuW4Yi6+InxWzyHp96b3sbhb2d1jpDXlltrmUmv4ZTI0/Qr5iHUX9mwXRpW3j21RFrH09akwjJL3TU4ztk3xOtSPKvWt48o+CX3UPcq5s8Gq3XaL8etv1QhiSKSCR8E7HxTxOLZYZGlj2OGwtc11CD3FVTDU3WzbNJcOUcwcd43Hj7kiWNXpW2Rz8z4cfY5O+Y+d7IYIo7qdvikdytAAfTeVnbdMzzXY8t9uls/g/QPG2nyOPs7LmL/loI4eZxJJ8tgbUk7TuVrvMUTFkRPOjtoyEHIblLKGUBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBBg7kJcVDEQfKaKOaKSGVodFK0se07QWuFD/AAUouiJikqHZbQOqsfmb/FWuBydxFbXUsNtNHazOZLE15Eb2vDeWjm0NaqmbJ8zhsm0yW3+Wkt00l0A1lnJ2zZxjdP4365mIkunDjyRtJDfa93uKz9Pxevb9pzZOf0x7VltHaB03oax+VwdoGTuaBc30lH3ExHF7+z7raAcAsqdHSbXZY8Mafd4thvL+zxts+8yFxFaWkYrLNM9sbGDfUudQBS9F99tkVumiL9TdbOm7MdkMdDl/m7i4tpoozbQyzMLnsc0eNreXaTvqorDW7jumHyzbWuinTAWsa0ihAAI9i88uRmayykQgSQQSZ0Z0G3WmqW3GQi58DhuW4vQR4ZZSf0YT3Egud3CnFWY7erZdt2f/ACMlJ+2OfHHVZvqTra10BpefK0a/Iyf8ribY7n3DgS2v3GAczvYrbpo6Te7q3b46xz5R+6ltjaZnV+oIrKJzrzO5q52zPqS6WU1fI+lfC0VcexoVER5pcdbbdlv8ZmeOPxXn0lpfHaN09aYLGtHkWjCZJnbHSynxSSvP2nu2925Xu3223twY/L7FU+s/UOTWuoDjrCX/AOOYd7o7UNPgnnbVsk54GhBazuqeKqvu6OU7jvfXv0+2OX78fu5dE+nzdaahff5KPm0/hiyS6Y4VbPcO2xw97RTnf3UHFMdvVl23ZRnvrd9sc1yfDHFQkNYwbTuAA/krObsaxbClvWDqFNrnUL7ezkP+W8S90dhGD4ZpR4X3BH3vhZ2N9qrvu6ON7lvZz36fbxxxLj0e6ejXWoufIRF2nsWWy5HgJn747av397vu+1LLa6nbdpObLFftjj8+Oi6kUbI2NjjYGRsAaxjRRoAFAAOAVjsbYiIpGj6IkQEBAQEHn5nE2Odxt1iMnC24sLyN0VxC8VDmuH8CN4PAqYV5cVuS2bZjSVFte6Pu9Dalu8Dcl0kEYEthcH/GtpK8jj94EFju8Ki+yjiN1t7sGTyylDoB1FdjMizRGVlrjL95diJHHZDdElzoRX6k29o4O9qsx3V0bLtG+9O7yXcp449vvWdvrG0ydnPZX0TLmzu43RXELxzNdG8UIoe0FZVdNfii+2bbtYlRnqHou40Hqe6wjy6SxcBPi7g732z6gAni6Mgsd9PFVZIpLiN7tZwZPLKUPT51DdZXzdCZWUmxui5+Ekef7qba58G36rx4mdhqOIWVl/Rs+0bzy3eS7lPzS/1V0HFr3TUttAxgzdkHT4qdwpSUDxRE7+SVvhPfQ8FZPKjb9x2MZ7NPvjl+ynmm9QZXRuftM5j+aK/sZS2aB/hEjA7llgkHAOoQew7VRWbZclgzXYckTHRePF5HDa80tBfRxtucNmbUiW3ko7Y8Fskbx9ppq0969Euyx327nF5uk9FK9e6PudD6nvcBIXPto6TY64f/AItrJtYSftNpyO7wvPfFJcfvNv6OSbZausXmEmQSo9HA3MFjnsVkLtxbaWl9bTzENLiGRSte6gG07AptmkrMV8W3RPhK5OK61dNcxMLeHOx21wfhbeMktQfY6UNb/FXxNXYWd0293Wnvb/DLFPG2aGRssT21Y9hDgQdxBGwhS99t3mjSWia86UaZ12x093F8lmWtpDlrYBs1BuEg+GVvc73EKJiOrwbrtuPPFeV3irVqTojr7TskhgsRmrBleS6sPG/lG6sDj5od3DmWE2eDm8/bc2OeVY9mvHwffpToTPXnUDCHK4e+s7CwmN7cS3NvLCwG3aXxjme0Cpl5dii22Yll2/a3X54i6NIXOHbSncrHZQygIOQ3KWUMoCAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICDB3IS4qGIgwabzU9yHJig3DYOzghTU2UruAU0J5VRT1E61ae0aJLDGuZmNRAUFpE/9GEnjPI2oFPsDxezeomYhqt73S3FFLdblVNT6v1FrK9N7qG+ddODiYbUeG2hB3Nji+EU7TV3aVTdfMuXzbi/JdW6XhnbvO7fsWKgUApqCkPb8PFRMi6HQzARYXp1jJw1ou8xz39y/fXzj+mD+GINCviNHY9qwRZhiY+65BXqA1NJm9cPw7HH5LARNgjZXYbmYCSV/0FjfcsMkzyaTu+49TNSOVvE8exsHpq07HeZnMamnbVuNibZ2daEebOOeR3tDA0fmKnFyX9k28XXzfPTjj3pe6zakn0zoHKXFq8x39/y2FnIDQtfc+F7h2FsYcR3rOtG17pn9LBOut2n7qSeGNtPqtGz2ALzuO1mV4Oj2nYtOaAw0PIRdXsIvrx1KOMtz4zX8LS1o7gvRGkUdl2vDGPBExGt2vH4Or1r1FNpzp9kpLWQx3uTczHwPBoW/MGkhFOIiD6d6coR3XP6eCYjncpVsYCNzWjZ2ABeaZq47mu10Z07Hpzp9iGFg+cyUYv7x1Npfc0e0H8MfK33L0xFIo7LteKMeCJ63a/t+SRkbEQEBAQEBBiiJQb6kdOx3ulbTUkYpdYe5bHI/tt7siNze+knln6VF/Jo+97eJxxf1hVWOWWCRlxbvMU8D2vhkaaObIx3M1wp2OFVRGmrmLZpNV/tHZsal0vh88ByuyFpFNK3slc0eYPc+q9Eu72uX1cdt3s/NF/qN09FkNIW2fa0C6wt0zmk4m3uSInt9nOWO9yi+Kw1fe8UXY4v6xoqlBcTWk8d1auMV1bPbNbyCoc2SMhzHVHEEKiOcOYtmYmJhf/SWcGpdMYjPBoa7I2kU728Gve0Fw/K6oXpl3e0y+pitunn1VK66aeh0/wBQbuW3ZyWmYibfxNAoBI4ujmAp2vZze9VZY1q5TumD08005Trx+NW+emnUsnn5fSE76wln7jYg/VdzCOdo7jVjqe1ZWzV7uybiazjnrr8Hs+pfAwXGAxWpGNAubC6+WleNhMN0NgP4ZGtp7SpvtrC/veKJsi+I+pV1UTzcwJQEBJGCdoBoAd+yqmJG46J6k6o0JcN/abkz4sms+Inc51s8bzybzE7vZ7wVlGSXs229yYZ0nTwWy0J1T0vruFsdlP8AK5YN/XxVwQ2dtN5btpI3jVnvorY1h1O17jizacrm9Dld9UCm7YKo2GslC4gk7uKIiZq5AUCDKAg5DcpZQygICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIMHchLioYiDCDUOo+V1BgtHZTM6aETsljmNuCyaMysMDHAzeEFpqI6kbeCmHk3uS7Hhuus5wqTn+rfUHUkLoLzNSW9pIKPhsmttWvFKEF0f6hHcXKmckuTzdwzZNLpaK0U2Cg9m/fXasHjl7um9I6k1dcutNPY6W+fGQJphRkEZO7nldRjfZv7lMWVXYdtkyz9MJXsfTRqmaLnyObsLSTYfLjjluNvGpPlBWRj9rZ2dkyUrMxH4oazOLmwmYyOGuHB8+NuZbZ7wC0OMTy3mANSA6lVXdbSWovtm2ZiXRqoYGwbahQO/h8LlNQ5CHE4S1kvr+4NGQxitBuL3Hc1g4k7FlbbWVmPFdfdS2KyvnpDFXOD0thMNeOYbzH2UFvO6MksL4ow13KSASKjevRLuNpinHittnnCk/UhkjOoGqBKCH/ALnMfFvoSC3+yRRUZJ1o4zd19W6vjPzlPnplez/K2caKc7cn4u2ht46fyVuPk33Y6Rju977ephkjtH4mRpPlMyrPMA+9BKG1/Mk8pT32P9O33/oqhL4o5Ozld/JUOZt5w/Q3TskUmBxUsNPJfZW7mU3cpibRem53m2mJxWzHKkIf9TLXu0biXivlsyzOem7bBLSvvUXfa1Pff9u33/oqnKaxv/C7+S83RzFvOH6DaUkhl0xg5YCDC/HWroyDUcphbSlF6pd3s6ejZT/GHtKHoZQEBAQEBAQRp11fG3pdnQ8irjbNYD9o3UVEnk1neP8A5p99vzhStwNKVptXnnk46JXa6JMkZ0v06JAQTFK5oP2HXEpb7uUii9HSPc7LtNY29tfG7/2ljrc+IdL9R+ZShjhDa/bdPGG095UxPM7tT/jzX/KPnCk/fSv/ANV5XGrsdEY5I+l2nRLWropXsr9h88jme7lIovVPKHZdoiYwRXxn5yh71NviOo9PRtp5zLCd0g48rpgG194csMkaNV3yY9SI9n7tf9PjZD1IhLCQ0WF26UD7B5Bt/MQsMfNT2WJnP+Cw3V/TeW1Xoe+xWEjZNfiWCeOB55fMELw9zGuOwOIGyuxW89G+7nhuy4Ji1SWeC4tJ5LW7hktruE8s9vM0skjcN4c07QqJikuMutm2aS+YodyirEQbJojSV3rfUdvp6znbayTxyyuuXsMjI2QtqSWtIJqaN3qbLayv223uzZIsjqkfK+m3WNnF5mMyGPyjxUmAh9q93c0v8xp95CsnH7Wzy9lyW/bNUSZjC5fT967G5yxmsL1u3ypm0LgPrNIq17e9pKrmJhqcmK6yaXRSXRY98MrJoXujniIdHKxxY9jgdha5tC094KiLqMImYSHhutXUrExMtIMoMizYyGO9ibcScxNABIOSQkkje4qyL5mWww9zz2RTzVhcnCnJnE2Dsy6N+Wdbxm+dE3kj84tBeGtJNGh2wbVY6/DN02RN3Oj0UWCAg5DcpZQygICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIMHchLioYiDCEvnPFHNFLDM0SQytLHxkVDmuFCCOwoi62Jik8pUF1zpqTRuq8np6QcsNrNz2bjXx20x54SDx8J5T3gqq+3Vw26wzjyTbPTj5N96bdE8zquaHJ6iimxWmwQ/lcDHd3TexjT4o2H7bhu+EcVNtni9mx7ZflurdFLFr8PhMXp+whxmHs4rOwgFI4Im0HtJ3l3aTtKso6nDhtxW0tijzM9rvR+mn+RnM5Z2Vwd8D5QZadvltq/+CmirLvsOO6kzCmnVDJYXJ66zOVwl7FeYu/fFPFMwFo53RNbI2jwDXnBO5V30q5HeXRkzXTbyq1/HYfMZmQQYfHXOQkrTltoXy0J3Vc0co95VflnweezHdfNIiqWtJ+nfVeXfHPqWVmBsDQviHLPeOHEANJjjr2ucfYs7cfi2u37Pkvmt/wBNvHH6LHaR0JpvRVkLTA2TYXP/APU3T/HcTkcZJDtPcNw4BWOh2+yxYY0jXx6tnpv9iRzeuOanXX/AuxHUCTIBtLbN28Vyx3AzRNEMo/stPvVeSNauO7vh8maZ6S9r02aibY6lyenp3jy8tbtmtgTQGe0rVoHa6N1fyrKydF3Zc3ly+WeV0cfqnPqtpuTVehMxjLdnmX8cYurJvEz2xEjWj8fKW+9ZUb3uOD1cMx1hRltHAHcHCpB71RMUcROi6fQ7UTM/09xkbnh11iAcfdN+sDAaRk/ii5SrrdYdn2rNF2GI/wAXp9WNMSaq0Hl8bbML8hFELuyYN5ntj5rWj8YBb71PRn3Hb+phmOsaqMhwIqNxA5QV550cTMLjdAtSMzWg7fHveXXuCkNjMHUJ8qpfA78PlkN9xXojWIdb2fP58VJ52/LjT8EshG3ZQEBAQEBBgolXj1L6lZFYYrScL/17qT568aDuhhq2MO/FIaj8KxvnRzvfM+sWRPtVvs7K5yN5bY6zYZLy+mjgtWDjLM4MaB7yqo1mjnrI80xEP0D07iYsDg8dhYKeVj7aK3aRx8tgbX30qvQ73b4fSxRb4Qhn1KahZa6fxmmY3Az5S5+YnZx+Xtdu32yln0FYXzSGn73npZFkdVYrKyuspeW2Osml95ezMt7ZnbJK4MbX3mqqtisuastrdEeL9BMBiocHhMbhrf8AusdbRWzKbiImBtffSqvmXebfH6eOLf8AGFOetefj1B1Dybrd4fa4xseOgcN3NBV0tP8AtXOHuVWSejke55fPnmeOOaQPTJgXvvM7qh4HlxsbjrV3a5xE01PZSNZ2RSGw7Jh1m/winxWYpQ9ld9FLpOrRtcdLdL68i8zI25tcqxvLBlbejLhoG5rzukb3OHsopmk83h3Xb8eeNY8t3jCuGqug+ucA982Nhbn8e0ktltPDcBoH1oHnmr+AuVc4/Bzu47TmxVmPqj2ft/VGF9Z3uNlMGRtJrKYfFHcxvhI9zw1YTZMNbNkxNJ5pN6Fag0xpnU9/mdR5OLHxtsTb2hkDiHPlka51C0GlGsWeOYhsu15bMeat800n9FsMJqvTmpI3uwOWtMjyNDntgka97ebdzNrzCveFbMdXUYt3jyfbdE3cdHw1Xo3Aa0xb8XnrRs8TtsU7fDPC/g+J42tI+g8aqKwbjaWZ4pdH4qh9QelOotBTyTvY/IafLv0MtC2oaDubO1tTG4bub4T2jcq77PBye77fkwzyra7fRDSjdU64tbqVgfi8GG3107e10oP6Efvf4vY3vTFDLtm29TL9X2268ceK6QA4blY7JyQEBByG5SyhlAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQYO5CXFQxEBBhB5txgcLdZCLLXWOtZ8nC0MhvJIWPmY0VIDXkFwFSdynzSpu22K67z3RE3Ry0d6R7Io3Pkc1kTQXOe4gNDW7SSTsChbNIjWaQrT1U66TTPn09oW58q3aSy8zraFzzuLbU12Dtk/q9qxuvpyc33Dus3VssnTxV8e50sj5ZHufNIS6SVx5nuJ21c41cdvaVVWWhmZ6p89N1xi7m9zmFyFpbXFyWRXlnJNEx7w0fpSgFwLqfAaK3HMzFG57LbjuyTExE3TGn4f1WdihigbyRRtjYNzWNDR9AWUzLqbbYjlFH0GzftRPJlBhEwijrro9+p9GyXtlF5mWwbjeWwAq58TRSeMcdrPEB2tCiYrDUd22vq4/NEa21+Co2FzF5gstYZvFuDbvHzMuID9U8u9p7ntJafaqrdJrLlceS7Hd5o0uX301n7HU+Bx+exjuazv4RIwVBLSR4mO+8x1WnvVzutvmjLji+PxVH61aHfo/Vkt3ZxFuDzbnXNk4DwRzHbND9J52jsPcq8kdXJ9y2k4ckzEfTPHHso+vQ/W7dJasbYX0nJhc4WW05Pwx3IP6Eh7ASeQ9x7lOOeie17v0cmv23aLlbKUA40B/krHY1hTDrToV2jtUy3dnFy4LNudcWbmghsU/xTQ91CeZv3fYqr7erje5bP0clY+2eTz+lGuTofVkN1dP5cLkALTLt4CNx8E1P907afukpZdRX2/dTgyRP9s8/dxxqu7G9sjWPjcHxvaHNeNoIIqCCOBVku1tmJpMfbL6IllAQEBBhB0MxlbHB4y8zGSlEVjYwvnnk7GsHNsHEmlAivLktx2zdPSKqGau1Ne6v1FkNRXtfMvJf0YK1EVu3wxRj8Ld/3iVTfdVw24zTlvm6Uv+nbQjr7JSa3yEZ+SsS+HE81aSXBHLJK37TY2nlaftE9istjq23Z9pN1/qXRpby9/HGiztzc29nby3dzI2G2hY6SWV5o1rGCrnE8AAFnTR0t18WxN08lEeoWr5tbarvs74vk3H5fHQuFOS1jJ8vZ2vqXnvKpunX2OH3m4nNkm6UoenfQpv8AJy63yEJFljy6DEh3+JckUklHaI2nkHeT2LOy3q2XZ9p5rvUu5Ry96bOp+s4tD6Tvcm17RkZm/LYqL7VzIDyn2M+M9wWftbvuO6jDj/8AOeSjsbLq6nbFEH3V5cyBrRvfLNK6g9rnvP0rz85cXETfdTrK93T3SsejdJY3BAN+ahj5754+vcynnlNeIDjyjuCvdtscHo4otn7urbUeuRBxIqeP/Wg+Fxa21wzluYI527iHta4fQ6qlhdjtunWIlTrrveWD9fTY7G28Nta4q2igkbBGyIGaWszyeQCtA5rdveq8s9HH908vrzFsRFNOPj+SNLG8vcZew3+OupbS+gdzQXUDjHIxw7CP4g7Cq4umNXhsyTbMTHOFpOlHXCDUHk6f1fIy0z2xlpfGjILwnYAdzY5j9mtHcOxXWXRc6XYd0i6luSdfFOLmMkaWvAdG6vM00II9hUxo3kxF3udHHYTDYh9w/F462snXTxJcut4mReY4bi7kA5ipqqxYMeOvltiKvRG5QtZQEBByG5SyhlAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQYO5CXFQxEBAQcHGmxDrRTvrFqnqA3UWS0pn8gWYqJ/PbW1qz5eG4tpNsb3kEuk2HlcC7l5huWN8zHJyHcc+aMk2XTx+vHgiYUI2DYOHYqdWqbfovpzqjXczv2S1aywjPLPk7kmO1YRvaHCpkd91g2caLKLJl7NtssueaWwsb066IR6GzNvqCXOTXt/FDJFJBHEyK3c2UDmBB5nkA7RV29W22xDodl2z0L/NM1TGDVKtuypBBgoVdS/urKztJ7rISxwWUMbnXE0zgyNsYFSXE0FFMMMt1sWz5tLVAtTOwjtQZV+my84GS5kdj/MbyERONaBuw8la8ldvLSqpvpVwebyzfPl+3jj+Uten7X4wuWdo3JShuLy0nPjnuNGx3hG2PbwnA2feH3lnZdXRte07307vJd9t35cfssFr3R9lrrTd1hLjljme3zbG6I2w3LB+m/wBldjhxFQs6eLf73axns8s/gorkcbeYq+vMTkoXQ31pI6G6gO9r2H6pG8EbWnsIPFUTpLir7JsupOkwt10Q6h/5vwAw2Tm59RYdjY5y74ri3HhjmHaR8L+/bxCttnzOq7VvYy2eSfvj5fw3PXWj7HXOnbvB3hEb5G+ZZ3RFXQ3Df7uQewmhHEEhS9e82tufHSefRRbK4u/wmSu8Pk4jDf2MrobqN32m8QfrNc01aeIKouiYnVxWTHNl0xOkwsr6f+o37nYDROYmJyGOjDsTI7fNaN2GOp3vh/1fYrrZrDou0b6Lo9K+f/z+3H6J9FKbNylvmUBAQES4k/SpqieWiqvX7qKMxff5MxUodi8dIH5adhJE123a2Go3th3n7/4VXkupyct3be+pd6dvKEXaJ0jkNbajtMBYVYJv1Ly5pshtmEeZIfpo3tcVhbbWWs223uzX+W1erD4ewwGJs8RjIRBYWETYbeMbaNaNhJ4knaTxKvdxix24rPLbyhA3qF6h+XF/kLEzfqztbJm5WO+GI7Y7f2ybHP8Au0H1ljfMxDRd43tP9Oyff+yCtIaVyOtNRWWnsd4JLk1uZ9vLDbs/vJD7AaN7XUCqstq0m2wTmvi2F7cPicfpzEWmJx8bbbHY+IRxN3UawbS49p2uJ7Ve7bFhsw2REcoU36wa8OudUSG2eXYHF89vi2DdIa0kn/7Ugcv3QO1VZJ6OR7hu/XyVjlHJ8ekV3pmx15jbzVE3y9rDzOsZX08lt4dkZlcfhA28p3B1Ex81ewnHGWJyfbH6cl3mua4AtoWkVaRuoVY7esT0q5ggoRqyiRCjifZxCmETyQDrH07PzuRyObxmoZP3C+nkunwXsTXRF8hLgwPi5XMaPhGx2xY3W1aLcdlm+6brbudfz9v8K96n0nqDR9/+3aisnWs7qmCUeOGZo3uikGxwHHiOKqvtmHP5tvfiml0UeGQC01FWdn9Kxr4KViOguquoOezJxE2RN5pfGQ892+6jEszCQWwxMmqHVc7b4ubwtV9szPNv+z7jLff5JmtvPjjosuFLpmUQICAg5DcpZQygICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIMHchLioYiAgIMEVQRJ1x6fu1bp4ZbGRc+oMI18sDWjxT252yw7OOzmZ3inFJtrFGo7vs4yY/PH3W/JCnSzo7kdaTQ5fOQy2GlWEOFasmvfuRA7Wx8HP4/V7RhZZTm1Gx7Zflurdpbxxxpba1tMXgsa22tIocfirGPlbG3liiijYNvYAKbSSs3VRZZispERbEId1T6jdO4m5fZ6dsX558ZLX3YeILSoqPA4hzpPaG07Com6Iafcd6tsmlkV46JF6e6yh11pi0z8cbbed5fHd2rX+Z5M0ZIczm2E7KOFRuIUtjst3G4sr7W2hHsnmwTQ04oirT9ZdR9LaIh58vfNN6W1hxsFJLqQmtPAD4WmnxPoFM6Q8O67jjwxrOvhHNU/qD1S1D1AndDcO+QwMbqwYmJ1WEjc+Z2zzHd3wjgOKpuv8HMbzf5M86/b4NDAJ7z2BYPANL2StfG50csZBa9p5XNc01BBG0EEJWiYmmq7vSTXA1zpO3vLh7f3mxItcqz/fMAIeB2Sto7Z3jgvRWurs+27r1scV+6EZeorQjXwxa7xsNJIuW3zYaKc0Z8MUzu9jvAe4jsWN0Vhre87PX1LY9/H5fBBOlNS5HSGfs89jCfPtJKSQg8omhdQSRO7nge40KrtmjR7fPdivi6F8MFm8fqLEWWbxsolsr6ISwO40dvaRwc0+EjgQrnc4M9uWyL45ShP1C6AbfWLdb42I/O49ojy7WCpktK+GQ04wk7T9mvYoutrDS952cU9S2NevHH5K1YzJX2IyNrl8bMYL+xlbPbTCux7e0D6rhsd2hU2TSXO2XzZNY0lezQmsLLW+mrLPWVGPmHJd29auhuGCkkZ9h3dooeKvdvst1GfHWOcc20fwR62UQIMIURr1i18NEaZf8lKBncpzW+MaKVYafqTkdkQNfxcoUTNIq1ndN36OOls/VKlb3E1c9zpHOcS9zqlznE1JO3aST9Kp5uP5yud0X0A3Remm3N/GRqDLtbcZAuHiiZSscA/4YO37xPcvRpEUdf2zaRhx+afulsfULWVtobTF5nJg2S5A8rH2x2ebcybGN7aD4nfdBSHq326jBj83Xoope3l1f3dxkcjO6e8upHT3Vw/aXvftc7/TcFRN1ZcRdfN81nnK3XQvQjdL6aGYv4SzOZ1jJpecUdFbb4otu7Yed3ee5WxFNHV9o2fpY/PP3XOh6gdeHA4JulsdLy5bNscLhzT4orIbHk03GX4B+bsU3TSFPeN3FkenbOs81ThtpQcNw7tq89HLhAOwirTvCFUsdOOtea0YyLE5hj8tppvhYwurc2zeyJzjR7B9hx2cDwVlt9ebabLul+H6Z1t45cfBafTOsNPaushf4C/ivYzTzGNPLLG48JI3eJh9oVlHUYN1ZlitsvfqN+6qPRUqOCJmKI66pdS4+nFhYzx2bMjkL+csitHS+UBFGKyPLg1x8PhA2cUnRrt/v/8AjRGlZl4+iuvWltU3EWNyUbsDlJnBsMdw9r7eRx2BrJ2gNDq7g+ndVIuiVG17vjyT5bo8s/kkHUumcJq3FS4jN2rLq0kB5TufG8CgfG4bWPbXYQpq9+522PNbS6Pcp7rrpRqTRuYhs4LabKY3ITNixWQhYT5j3nlZFKB/dybfYd44qmceujk9327JhvpSsccUWq6a6Jt9CaXtcQzlfkJf18ncDb5ly8AuodnhZsY3uCul0/b9rGHHEf3Tzbqoe4RAgICDkNyllDKAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgwdyEuKhiICAgIOJG3+aJh17q6tMbaTXd5NHa2du0yTTSODGMY3aSTsAAU82E3W2W1nSIVD6s9XLrW1xJhcHI+20pA/xHa1965p2PeN4iB+FnHeewYX39Icjv+4zmnyxpZxx/PKJaUbXcBv7FU1dUldK+p2S0DPkI2Y6XK4K5a2e+t4iQ+3fGOXzgaFrRy7HB1K7Nqsx3acmx2O+v2+nOJ6JOvPU9jmRn9v0zdSTHcLi4ijbt7eQSO/gsvVhsru+Wx9tv5/wjvUnXjXufjfb2k8WCtH1HJYtJmIIpQzScxHtYGlYTl8Hg3Hdc2TSJpHs0RdLJLcSvnuJHyzynmllkcXvc7tc5xLj71j5qtbN0y4U3U2AcFixYeDR9DQ8uw94RMN26iaediLvDZeGNsVnqXE2uSYGANY2d0TPmGtH46P/ADK7NbFXoz7f04tmPtutinw4/Cj3+g+ppMDru2x730x+eYbSZlfD5zGmSFw76hzPzKMc9Hr7TnnHmjwlbvL421zWLvMTfMElnfwvgnaeLZGkHv2KyObrM2KMtk2zyl+f2XxdxhMrkMLc/wDqcbcy20hOypicWhw/EKFUX6TRweWybLpiVgPTXqx5OS0XdSVZGPn8Y012BzuWdgrspzFr6d5Vls1b3sm4ms2TPu446ysTdWsF7azWd3G2a1nY6KaJ4q17HDlc0jsIKz5OhvsjJbNt2sTFFCdaacl0jqnK6dcD5djOflnu+tbSfqQmvb5bgD3qm62kuE3WGcWSbZSL6e9XPwurHaduJSMdnwREw/C28haXMdt2DnYC09pDVOOejY9m3E48vl6XLcN3AVr3qx1kcnJEiIcXGgJ2ADbU9yFaQoz1V1c/WWs8hfxyl+Ns3myxYB8PkwuIc8f8STmfX2KvJPRxG+3PrZZnp0445vQ6LaUZqrXdoLqPzMbiG/uF0CCWudG4CFh9snip2NTHFZqz7Zt/VzRHTjj4rq7hSlf+tW83aT4Kh+oLVkmc1h/l+F5/b9PM8vlB8LryZofI7ZsPlt5WDv5lVlno5Lu+5m/L5elvHHuab01023VuuMNiJo/MsTL8zfNpUeRb+NwNOD3crPeoxRq8Ozw+pki32/l/Re3wRtOwBrR7AAAruru5+mPZChevtSSat1jls2Xl1vLO6GxBNQ22gJjjp+IDn9pVOSdaOE3mb1ck3O5g9Ol2gdV6wlaCLd1tjLEkbn3E8ZuHjvEZDPzFZ2xSKlm382Kcn+Mx8ePm0zu7FU8zHHbuQdqxv7/F3bL/ABl1NY3sX93dWz3Ryj8wp9B2KYmWePJdZNbZSzp/1Ea2xTGQZaG1zkDKAvlBtrgjvkjBYf8Au1nGSOraYe857NJmsN5j9T2HMPNcabvWS02hk0L2V/EeU/wU+pEvbHfLafbr7/4Qt1H1nltbajdkMpZvxpt4mwWmMk5uaGH4qu5w2rnk1LuUDcsb5nwabe7m/Nf5rtGmUBbygAtI2gquryrCdHOtAtHQaV1jdE27uWPF5eY1LNtBDcPNfD9h59ju1W23Vb7tncvJPlyTp4+HHHssu0ska12xzTRzdx2cKKx0lImK83MCihLkgICAgIOQ3KWUMoCAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICDB3IS4qGIgICAgIPNzmGsNQYq8w2UhE+Pvo3RXEZ4tcN47CDtB7Uhhksi+2bZ5So3r3ROS0JqCbD3wdLavrLjL0ijbiCtAa7udtaPb29xCpvto4jdba7BfMTybB0u6VX3UC7N5d+ZZaXtX8t1eN2Pme3fDBXj9p9DTdvWVlnWXo2Pb7881/tWwttMaW09p6fCQWNtZ6fMD47prg1rHRuaQ8yvdtcSN7nFXVo6e3a4seObZiPJ1mVF89j8fjM1fY/GX0eSxlvO9tnfRHnbJDWrDWgqQ2gdTiF574pLiclIumni87+SwYCApgfezsZ8neWuNtW893fTMtrdo4vmcGDd3mqmIrLKyJm6IhYj1FY61x2nNH2sTWtdYySWsQpT9Jlu0H3VY1W5K0b7vOK23HZEdIp8kEaSdIzVmn3QA+aMpZ+WBvr8wxV2zq023/3LffD9Bv6eCv6u9jkpH1rhZB1R1CyOnLI+3kNNnjfbRk/yVOTm4ruX/wBF/v8A0j93y6N3stl1M04+I08+aW3kb2slheDX3gJjnU7ZdTcWz7f4/VeHhsVrtaUhVD1LY6K21fisizY+/wAcWS04utpaA/1ZKKvJyhy3e8dMsXeMIaxt/LislYZWD+8sLiG5j4eKF7X099FjbOsNPju8t0T1h+iMTxJGyVvwvaHD2EVV0voETWInxfREiDWtfZSTDaL1Dk4TSa1x9w+J3ZIWFrT7iQlaPPvLptw3THPyyoI1vKGjg0Lz1cJM1We9MeOiZhtQ5YgGae9itmn7kMQeP4ylXY+To+x2R5bruukJ/LqA14bSs4b+ZpV+eOZvZMnm8pkpa+ZeXtxcOB3gySuNP6FRk5vn+S/zz5vHX46ph9NFtDJq7L3ThWW3xlIx3Szt5j9DQs8XVt+yWxOaZnpE/os5nnStwWUdB/fCyuDHTfzeU4t/irIdLuJ/07v/AMy/PGKnlxkb+UbO8heZwV3OVmNGadbn/Txksbas57y4+duImj4nXFvcGSMe0+W0L0W/a6Db4Yv2N3jz+CtDCHjzBudtVDnpimjlRRVAoBBufS/FYLLa1xsWor63ssZbvFw5ty8MbcSxuHlwgu8PicQ49wpxVuKldXq2dlt2SIumkLf6t0NprXGP+Tzdqx7w2lrfxhrbiBx2h0cgBI27aGoPYrZdduNniz26xEe2FOdfaDy/T/MnG5H9e0mBfjck1pbHcR12jsbI36za942FVXW0cjutpfgv8t3HH5Pd6R9NJde5k3GQjLdL494OQk3CeQbW27Tx5v8AEpubs3lTZb1ejt2znPfrpbbxx/RdGGJkMbIomBkUbQ2NjdjQ1ooAO4BZuypEcuT6oCAgICAg5DcpZQygICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIMHchLioYiAgICAgwUGr620RhdeYg4fMxuDWPbLbXURDZoZG7OZjj2tJaRxCaPPuNrZmtpc9C3gwukcE2CJsOOwuJgqK+COKGMEku/ma7z3pDKPLgx+yIU+6n9Usnr+/ktbaWS10tC+lpY1oZuU7JpwDtJ3tZub7VXfd4OS32/uzXf8Aj4I62DZUV+hVtcUpUkUA3qCopDZxQTp6etCvyWYk1rkIz+34suixnMNkl08cr3jtbE00/Ee5W44bvs+0m+/z3R9MfPj9Hz9SOoI7/U+NwELw6PD2rpbgA7RPdkUafwxsB/MpyzSKI73mi7LFsf28fs1bolp12f6hYtxbzWeI5shcmlQDF4YhUdshafcsMUa1eXtmD1c8ezX4arrE0oeHH6Fd1dpyUL6h5puodc6gzEZDoJrx8du4bjFbgQMd+ZrKqnJzcJvMvqZbrva2HoZiX5XqTi5AP0cZHNfSmnBjPLb9L5B9CyxxrV6O145vzxTpr8OIXUqKdyzdpWsqoepa/Zc6vxWPjoTY40vl7nXEpIH0RrC9yne8kTmiPCP3QvY2cmSvbXHQtJlvLiK3jptJMrwwUHvVdvOGostmboiH6JwR+TBHDwjaGj2AUXol32O2bbYiX1UMxBq3UTHSZbQ2o8fCKzT464EQHFzYy5o95CUq828iuG6PYoOHBzeYbnCo9689HCzFJWg9MWQjdhNQYon9W3vYrmn3J4gwH+tEVdj5Ok7FfHlut90p+cARSta7+z+Cy6t/Ouni/P8A1liZMDq3OYmRvJ8rfztjadn6T3mSM/8Advaqb+bg9zj8mSbfBvPQDMsxfUS3tpdkeVtZrMEmg8wUmZv7fLICzxzR6+05Is3Ee3T4/wBIXGkY17HRSDmY8FrweLSKFZ1djdbExMT1fn/q7Ay6X1Pl9PyAj5C6eyEmo5oH/qQu29sbmqm+KS4Lc4vTyTb4LB+mnPsuMLl9Myn9WxuRd27TxhuRyup+GRh+lWY5rDfdkz1tnHPv446on6x6IfovVs0kDKYTMPfd494+FjiazQf9m41H3SFF8U1aruO0nBkp0nWOPZy+COVS14ge6v8AQsoGCA4FrtoOw1FQsStE3dHer9zp65t9MaluTNgJ3Nisb2VxL7N52Na5x/wXbN/w+zdfbfXSW57b3H0p8l32/JY7V2kcLrjCT4XLxl9vN44LiMgSQyj4ZYnGtHD+I7lk6Tc7bHnt8t3xd3T+nsXprEWmExEAgsbNgbG0fE529z3E/E9zvESjLFhtxWeW2NHrItZQEBAQEBByG5SyhlAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQYO5CXFQxEBAQEBAQYQo1LqHo4a60vd6fN5JZSSlskMrCeTzYzzMbK0U54yfiHvR5d5tvXxTbXVSDO4LK6ays+Gzds61yFt8bDta5laNex31mOpsd/SqLomHFZcV2OZiW2dMummR6h5J3M51pp60eBkciAOYnYfJhrUGQjeTsaNvYFnjs6y9Gy2V24vpH2xznw/n+s+3butHSSz0lDBqLTMZZguVlvkLNzi4wy/CyZpfVxbJuf2OoeJWV9kc4ezuWwjBEXW8kJjcqZaZsWitI5HW+obbA48Fgk/Uu7qlWwW7TR8h79vK0cSs7Lar9vt7st8Wwufe3GA6ZaLkljjbb4bB2pEEI+KR1PC3tdJK87e0mqudjfNm1w0jpHxn+VHMvlL3OZa9zOSk5ry+mfcXBB2AvNaDfRrBRo7gvPfd5pcVkyTfMzOsytb6ftHu0/pI5y+j5MrqEtuKOG1lq0HyGe8EyH8XcroikUdR2fbRZjm/rPy/n5Ni6vawGjtF3l1DIGZW/BssYK+LzpgQXj/hs5n+6imZpD0dz3XpYtOdykIFAA0bhs7V54mrjKrV+nLSbsbp271TdR8t1nHhtpzDaLOAkNI/4j+Z3sor7aRDqOybebbZvnnOkccck4SSNiaXSODWtaXPcaAUG01Ut3M0ivgoRrvUR1Zq7MZ5rj8vd3Dm2vZ8vCBHFv3czG83tKqvmsuF3eX1Ms3e1uPQbSztQ66t7+VnNjsBH87M47QZ3VZA3+tzP/KssfOr19q23q5azyt1446LlLOXYsogQcJGte0tcAWuFHNO0EHtQmImKTyUK6gaal0jrDLYMtLbeKczWR4Otp/HGR+EHk9oVN/Nwm8wellm1tHQrUrdO69trad/JZZxhx8hJoBKTzwH3vHJ+ZTjl6u1bj080eE6cfkueKHhVWuyVd9SOk3WmVsNY2rB5N+0WWQoKUuIgXRPPbzsBb+VY5IrDlu87aLboyR/dz9/9PkgqxvrjHX1pkrN/Jd2UzLiB/ZJE4OafZUbVXbNJaWyZtmsL+aV1Daar07js/Zf3F9A15ZxY8eF7D3seC0q6Yd1tc/rY4vQV6kNHEfJa4s2V5OWxytBua4kwSnuDiWH2hY3RWGk73taUyR+KGdAatl0RquxzzKutWOMORibvfaykCQAdrKc47wq8c0lqdluJw5IuXE1lpbEdSNJvx5lYYrqNl1isi0c/lylvNFK0g7WkHaOLSr6dJdZucNm7xaU9kqQZbE5DA5O7w2VhNvkbGUxXEZ+0NzgeLXjxNPEGq8820lxmXHNl02z0dEkD4tgG8p0VrEdM+hmOzelJsvqzzWXmXia/FMhfyvtId7Jdh5XSSby11QG7N9VdZZEc292HarMuPz3deSHdb6KzGg80/D5ZvPG4GSxvIxSO4hBpzN30cNz2nce6hVV1lJ9jV7ra34L/AC3GitEZnXmXZiMRHywCjshfPFYreI7y7tc76rd59im22s1Ttdtfnvpbxx+a8+BxMeCw1hh4p5rmKwgZAy4uHc8rwwUq93Eq2522HF6dsW86PTRYICAgICAgIOQ3KWUMoCAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICDB3IS4qGIgICAgICAgwQkjS9f9OcH1Ax7bbID5bIW9TY5OJrTNC528CvxMd9Zp2e9JpMPHu9jjzxSdHo4rGYHQel47KAtssLiLculmfs2NHPJK88XONXHvKmNFlsY9vi8ItU86k9Rcl1BzLp5C+3wNs4jFY6tA1u7zZANjpHj+ruHaab768nI73fXbi6vKPBpMbHyPZHE10sz3BkUTQXOe5xAa1o4kkgLGlZo8URMzSF1+k/T+LQWnI4p2tdn8hyzZaZu2j6eGFp+xEDTvNTxV9KRR2XbtnGCys/fKDuvuvTn84NKY+WuHw0h+aLDVs16BtGze2AHl/FXsVd86UaTu299XJ5bftt4/hpXTLRz9b6us8TIwnGQEXWVfTYLeMjwV4GV1GDur2KMdtZq8mx205skR0XnYyO3jbHG0MjYA1jW7GtAGygCtiXbREWxSOSmHWnWw1hq6SC0k58NhOa1saGrZJAf15e/mcA1vcO9YZLujje57r1stY+2NOOPBqmjNL3Gs9TY/TsHO1t3LW7lb/hWsfimeTwPJsb3kKu22svNtcF2XJFsL62NnbY6zt7GzjbDaWsbYoImijWsjHKAPYAr5d1jx247Ytt5QizrzrP8Ay1pB+MtZSzLZ7mtYQ0+JkAFZ3/1DyDvckzTVqu77jyYvJ1u+Sng5GCv1QN1OAXnjnRyc1ldToxow6R0Xam6j8vMZYi9yFR42l4Hlxn/hsoKdtV6Iijse2baMOGs/dckxGzEQIMEImEDeozRpyGFtdYWcVbvDnyr8tHidZyuFHGm/yZNvsLljdFYaHvO181sZIjWNJ445quMe+KRssMjo54yHxSNNHMew1a5p4EOFVTE0lzMTML29N9YR610jj80CBeFnk5CMU8F1D4ZBTgHHxN7iF6Zdt2/c+tir1jTj5u9rLTFpq/TWS07e+Fl5CRDNxjmb4o5B+B4BUQs3m3jNjmzr096hV/YXeMv7vGZCLyb6zmfBcxGuySM8ppXgaVHcqLoo4e+ybJpKb/Ttrf8AbcpNou/k/wCUyhdPii41bHctb+pGN4AkaOYd4ParbLomKNz2feeS/wAl3KVlc5iLLUGHvcNkI/Msr+F8EzDwa8UqO9p2jvWTo8uKMls2z1UG1Dg7vTOcyGByIPzeOmdE5/22bCyRteEjSHKi62YlwufFdjvm2eiwXp5198xbv0JlJf1rVrpsK9x+OEGr4Nv+yrzN+77FdZNYb3tG9if9K6fd73s9eunQz2IOrsTEXZrFR/8AORsHiuLNpJNe18PxN7qjsS62sL+8bPz2+pbzjmqhzVHMKH6zT2jtVEOWol3ox1Tm0jkYNPZm4J0vfycjHSO2Wc0h8L213RPcfGNwJ5u2ttt3Rte27+7Dd5bv9uefs9v7/H32S17oTFdQcH+1X7zBMx4lschG1r5IX7iW12EPbUOB2ELN0m62lu4spPxelpTSeF0biIsPg7cQ27Nskjtsssh3ySu3uef+obFNWW22tmCzy2x+L3t6h6mUQICAgICAgIOQ3KWUMoCAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICDB3IS4qGIgICAgICAgIMURLyNR6fx2qMNd4HLMMmPvGcszGucx2w1BDm7QWkAhFGbDGWzySp51E6S57QM0l6A7JadLqQZSNu2ME0Dblo+A8A74T3HYq7rKcnJb3t9+DXnZ4vZ9P2lI9QaydmLyPnstPRicMcKtddy1bDWv2AHPHeApx261Wdp28ZM0TP226/t+fyWF6q6w/yXo29yVu4DKXFLXGNNP/UTAgOp2RtBee4LOtHQdx3Ho4ZnrOijriXVke4ucaue9xqXOcSS4k7ySaleeZrLi5mZlb/oHo8ae0fHmrmPlymoOW5kJ+Jls0HyGe9pLz3uXotikUdX2fbRZji//J6HWvWztIaRkis5DHmcy51nYOaaOYCKyy/9mzd94hJmIhb3XdelipHOeP4UvDQKU+ECg7V53H1Ws9O2jP2rATatvY+W+zg5LTmFHMsmO8JGz/Gd4vZyr0WxSHTdl2vltnJMazpH68ctE4OIZGXHYGgnspsSG85Rr0Ub6p6xdrbWF7kYn1xVp/yeMAPhMERPNIP+K+rvZRVXy4nf7qc+WvR2OkGj/wDOOtbOC5j8zE42l9kQRVpbE79KM8P1JANnYCpxx1Zdv205ssR06+7jRd8CgAG4bAPYrHa06MokRAgIl1MhYWuTsrnH3sQmtLuJ8M8R2tcx45XA+0FIV5ccZLZtnlKg2rdOz6S1Jk9O3RLnY+Ythk4vgf44X/mYRXvqqb7aOF3GKceSbfBI/p+1kMBql2nryUNxeoKMj5jRrL2MVjO00/UbVntDVlZNdGw7RuvSy+W77buI461W6BB3Dftqe/uVjroVg9RuixY39trWyjpb31LXKUHwztH6Mpps8bQWHvAWN8aOY7ztPLd6kf3IItrqeyuYL6yk8m8tZWT20w3sljcHNd9IVMTSaw0Vt02zVfHQmq7bWWl8dnoQGS3EfLdwg18u4Z4ZWH2OGzuovS7jZbmM2OLo59UNepLSDXQ2Ot7Nnjic2xygHGN5JgkP4XnkP4h2LC+Kw1Pe9ryyR7p446K84vJ3uEydlmca/wAq/wAfMye3cK05mGvKafVcKtd3FVWzSXP475suiYlfbTWcstV6dx+csgH2mRgbJ5ZIdylwo9h/A4Fp9i9E6O62+WM+KJ8ef6qXdUNLs0drXK4mFvJj3Pbd2PYLe58Qb+R/MwexVXx9Tjt7t/Ryza3Hpr0OymqzFl9Tskxum3Ucy1NWXV23sFdsUbvtfERu7Vlbj6y9ew7bdlmLrtLeOPktta20Vpbw2kDeWC3jbHE2pNGsAaBUkk7BxWTrLbYttiIfZEsoCAgICAgICAg5DcpZQygICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIMHchLioYiAgICAgICAgIljeiHymgiuInwTxtlhlaWSRvAc1zTsIIOyhU1Y3WRdHlmPpl4Gl9Fae0aci3T1r8nFlJxcTwtJMbXtaGUjB+BvHl3DglVO32tmKsW9VffUvmn3GocJp8OIhsbN149p2B0lw8xtNO5sZ+lYZJpDQd8yTN8W+EfP8Aoh/SmEOptS4jAMGzIXbIpd+yFvjlPbsia5V2RWWp2+Kb8kQ/QGGKKCGOGFojiiaGxsGwNa0UACu5u8tsi2IiOimHW7VDtS68vbeOQusMI35C127PMaazuHe6Tw/lVeSdXHd03E5Ms+ENP0np6XVepcVp6Elv7hcNjmeN7YBV8rx+GMOp30WFtszLybbFOTJFvjK/lpa29jaw2VpG2G1to2xQRNFGtjYA1rQO4BXzWXdWWW2W+W2KRCN+uOrH6Y0Rcw2khjyeaPyNqWmjmtkBMzx+GMGh7SEnSGu7tufTxUjndpx8lMBQUaNgG4d25edyErd+nvTH7Nov96nj5b3PyG4BIo4W0fghbU8COZ/5lfbFIdX2fB5MU3TGt36JkG5S3MsogQEBA7UFbfUtpcEYnV8EZq0nH5Bw4tdWSFx9h5m+8LG6NHO98wUmMke5XWKWWCWO4tpHQ3ELmywSt2FkjDzNcD2ghUxNHP23TbNV9dCanj1fpTFagZQS3cA+ajBryXDPBKz3PBXpl3Gzz+rjtu+L76y05bas01k9P3QHLfQOZG8jYyYDmjf+V4BUc2W7wRlxzbP4e9QS4gntJ5rS6YYrq2kfDcRne2SNxa8H2OBXnmKS4W62Ymkp19N2qTZZzIaTuH/8rkozeWTSdguIABIAPvx+L8qvxzo3PZdx5cnknld8/wCnyWK1ZgbfVGnMpgLkAx39tJE132XkEscO9rqELJ0W8wxlxzbPvfn6+KWCSS3naWXMTnMmYQfDIw8rga9hBXnmKS4S6KStL6ZsvJc6ay+HkcXDGXvPCDtDY7pnPyj87XH3qyzWHT9jvmbJhKGU0LprN6kstU5SybeZTHweTaeb4omAPLw/k2hzwTsJ3cFnVsb9njyZPNdFZo2gCmwCg7EeqNGUBAQEBAQEBAQEBByG5SyhlAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQYO5CXFQxEBAQEBAQEBAQEBBhRKWt6r0RprWloLTUNiy45AfIuWjkuISeMcrfE3+R4rKujybjZ4833R+KL9GdD7nRfUC1z0F6zIYCCC48nzhyXUUsjQxoIaOR45S7xDl9ixi2I1a7bdp9LNF0zW2E0ZS+bjsZfZB/w2ltLOa9kTC7+hZNxmv8AJZN3hEvzvluH3Usl3O4uuJ3ummcd5fKS5x95K88zWXAXVmZqnL004Vt3qfL5p4B/bLNkMJI3SXbySR3hkVPes8fJuex4ouyzd/jHH6rU7gBuVjqVSPUXnjktbW+FY6tvhLRocAdgnuqSPPujEYWGSejku85/Pm8sf26fr+3wQ9a2st9c29hbitxdzR28Q4l8zwxuz2uVcRWjVWWzddERzfoZirCDE42yxdq3ltrG3it4R9yJgYP4BX3O+wWRjxxZH9sQ7oRZDKAgICAg0rqnhG5/QGoMfyc8rbR9zb9vnW36zKe9lPelKvD3HH58F3s1+CigPOKjZUVHsK87iqUWV9Mudc+1zum5HbIJIr61aT9Wb9OUDu5mg+9W45rDouxZvus/H9/0WJB7dlNyzh0Kk/WzCx4bqPlWQsDYciI79jQKUM7aSfTIxx96qyc6uL7li9PNdTjiWu6Eyr8LrbT2Sa7l8jIwMe6n+HM4RSbPwPKiydYefa5Jx5Lbo6SvydwPZ2K6XeT4q/xenpuW1dmc1qG+8rB3OQmubTHWmyWSOV5kHmSH+7FSRRor3hR5YaC3svmyzddP01rx8k24PT2G05YsxuEsYbCxjFGwwt5aniXHe4ntdtUt1iw244pbFIesi2RAQEBAQEBAQEBAQEHIblLKGUBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBBg7kJcVDEQEBAQEBAQEBAQEBAQEHSyePt8tj7vGXYcbS9hkt5wwlrvLlYWOo4bRsO9IYZcduS2bbuU6K26n9NeStQ+fSGTZexNHhsb+kcwHY2ZgLHH8TB7VhOOJc5uOyXRNbJr8+Pg270+6YzumLbUtrqHGzY67fdQeWJgOWRrYjtje0ua8AneCsrbfLD19n292LzTdFJ5cfFOB3e7+Knq3cc1E+qs8lx1G1RK/aRfGMV4NjjawfwCpv+5w+/mua73uv03tW3nUDS9u7a05KB5PdE7zP/ALVOOdWGyt82a2P/ACj5wvoBT2q2Xd2xRlAQEBAQEHwu4mT200D9rJY3McO5wof5qWGSK2THjEvzoLPLc5m4Nc5o9jSR/QqLopMw+fVrql705zuj6iviafDcYy5a8cKNfE8fyWWNt+y/7/4Tx+S3/BWOtVu64aE1Vq/XePdp3Fy3UQxcUc924titmOFxKaOkeQKgOrQAlRfbMxDnO6bXJl3EeWJn6Y+c/wAOxpL03Ntri2yOq8qZZYZGSssLEFkYfG4OHPM8c7to+q1qRZEM9r2WbZib5WJAoAFlLoI00FAygICAgICAgICAgICAgIOQ3KWUMoCAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICDB3IS4qGIgICAgICAgICAgICAgICDFESUA4D2oiIhg1JQrrVAGvPT9d6iz2T1Dh81FDPkZfOfZXMLuQPLQDSSN1aEj7KibInVoN32i7JfN9sxrxxo0/S/R3qDpTW+nspdY+C7sLO/ifc3VpO17WxbWucWvEb9gO4NWNuOk1eTB27NizW6aVjXote2tNqzdXDkgIgQEBAQfG4LmxSOY3meGuLWDiabApY31op3iugXUnJuMl3aWuKa9xc43dw17vEa/DAJO3iQq5srNXI4+z57tKUp48SmXph0Wk0FmnZ++y7b+8Nu+2ZbxQ+VEwSOaXO5nOc5x8PYFlFsWtxsO2Tgv810pkUtwcra1I2pUpANwQZRNRECAgICAgICAgICAgICAg5DcpZQygICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIMHchLioYiAgICAgICAgICAgICAgICAgwgUQKKAUjKAgICAgIOLhVCGaImREasoCAgICAgICAgICAgICAgICAgIOQ3KWUMoCAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICDBQcaFQgoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUChQKFAoUHMblKRAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBB//9k="}}},{"cell_type":"markdown","source":"## 1.2 Context of Project <a id=\"1.2\"></a>\nIn the context of this project, it's crucial to recognize the impact of environmental factors, particularly excessive noise and discomfort, which can drive individuals to seek alternative spaces for work or study. With an understanding of the adverse effects of unfavorable conditions in outdoor spaces or at home, our proposal aims to proactively address this by offering suitable facilities in our stores and enhancing the layout of our stores. This proactive approach ensures that individuals in those locations can access a comfortable environment, alleviating discomfort and facilitating productive work, ultimately drawing them to Starbucks.","metadata":{}},{"cell_type":"markdown","source":"## 1.3 Considerations of Project <a id=\"1.3\"></a>\nTo identify which Starbucks outlets would benefit the most from this concept of dividing the space into two separate spaces, a dining area and a work-study area. These are some factors to consider:\n1.\tOutlets that are experiencing high noise levels in their proximity. This would suggest that the outlets’ proximity has a high level of human activity which would require a dedicated space with a suitable noise level to allow for productive work or study. \n2.\tOutlets that have a long table turnover rate. This would suggest that it takes a relatively long time for tables to become available for new customers. Implementing a work/study space that is separate from the dining area might alleviate the issue of the long table turnover rate and create more room for customers who just want to dine in.\n3.\tThe proximity to educational institutes can be an additional consideration. Locations close to universities, colleges, or other educational institutions make the outlet easily accessible for students who are one of the main target audiences.\n","metadata":{}},{"cell_type":"markdown","source":"## 1.4 Purpose of Study <a id=\"1.4\"></a>\nThis study's central objective is to harness existing data for the purpose of tailoring an environment and layout that precisely meets the needs of individuals seeking conducive work or study settings. Through the utilization of pertinent data and predictive insights, our goal is to elevate overall productivity and instill a culture of efficient space utilization. This data-driven approach guarantees that our facilities and layouts seamlessly align with the evolving needs of our community, cultivating an environment conducive to optimal productivity and well-being.","metadata":{}},{"cell_type":"markdown","source":"## 1.5 Literature Review <a id=\"1.5\"></a>\nA 2017 study conducted by NUS researchers in Singapore measured outdoor sound levels at 69.4 decibels, surpassing the recommended sound limits of 67 decibels set by NEA (Chia & Loo, 2021). The sources of these sounds include construction, renovations, road traffic, and building density. These factors pose negative impacts on work productivity. Thus, people would seek public spaces such as cafes (such as Starbucks) which would provide a conducive environment away from noise distractions. However, this effect of people working in cafes has led to complications which will be elaborated below.\n\nAccording to an article from The Strait Times by Baker (2014), a response from a customer who frequently visits Starbucks to work emphasises the idea that cafes can be quiet and enjoyable, a place that is not tied to the pain of work and study. However, the customer would leave once there is a crowd as the cafe no longer constitutes the idea mentioned earlier. As many Starbucks outlets are located near train stations or in commercial buildings such as shopping malls, high levels of human activity are expected within the proximity. The high level of human activity will lead to a high level of noise disruption, affecting the productivity of customers who are working or studying within the cafe. \n\nFurthermore, Starbucks is also one of many cafes that experience the issue of seat hogging due to mainly students and adults working for long periods of time within the cafe. Seat hogging is an issue as it will create a long table turnover rate which will affect the rate of customers, especially during peak periods (Oh & Vinod, 2016). Seat hogging would also cause the cafe to have limited spaces available, denying many customers who want to have a dine-in experience.\n\nBased on this review, our client, Starbucks is looking to implement this concept of dividing their cafe into two separate spaces, dining space and work-study space to selected outlets to test this concept. This would help alleviate the issue of noise disruption and seat hogging. We will be using an AI machine-learning framework to help predict Starbucks outlets that have the highest noise levels within their proximity as a way to identify outlets that are crowded. This way, we can advise Starbucks on which outlets are in demand for this two-space concept and can benefit the most from it. ","metadata":{}},{"cell_type":"markdown","source":"# Section 2: AI Canvas <a id=\"2.0\"></a>","metadata":{}},{"cell_type":"markdown","source":"![AI Canvas.jpg](attachment:526757fb-5598-420a-9bda-7cc37e3d83de.jpg)","metadata":{},"attachments":{"526757fb-5598-420a-9bda-7cc37e3d83de.jpg":{"image/jpeg":"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"}}},{"cell_type":"markdown","source":"## 2.1 Prediction <a id=\"2.1\"></a>\nWe want to predict the perceived noise distraction across Singapore. In general, the noise level of an area is dependent on the surrounding environmental factors. Noise level can be affected by many factors such as the location and points of interest. \n\nFor the prediction phase of our project, which aims to establish optimal work and study environments in Singapore, Starbucks can focus on understanding the perceived noise distraction levels within the proximity. This phase will involve collecting and analyzing relevant data to make informed decisions about which Starbucks outlet will be chosen to adopt a new layout.\n","metadata":{}},{"cell_type":"markdown","source":"## 2.2 Judgement <a id=\"2.2\"></a>\nWhile considering whether to implement the changes to the layout of some Starbucks outlets, we would also need to consider factors that were not taken into account during the prediction phase. They would need to determine the relative returns in implementing the new layout at the most suitable outlet against the main objectives of the project, as well as the intended outcome. \n\nThey would need to determine the relative returns in implementing the new layout at the most suitable outlet against the main objectives of the project, as well as the intended outcome. \n\nWe would have to determine the relative returns of changing the layout of the outlet to have separated spaces for dining and work-study versus the cost of a false positive (there is no demand for the dedicated work-study area), versus the cost of a false negative (there is demand for the dedicated work-study area) versus not changing the layout of any stores at all and identify which is the best option. Therefore, the human weighting of the objectives is crucial in the decision-making process.\n","metadata":{}},{"cell_type":"markdown","source":"## 2.3 Action <a id=\"2.3\"></a>\nTo separate Starbucks in noisier areas into two main areas where one is a quiet space for people to study or dining area. After identifying the change in internal layout of the Starbucks outlet based on the perceived external noise level, Starbucks will have to decide if they want to adopt this new layout. \n\nThe ultimate decision will be based on judgement factors such as the expected returns from changing the existing layout. To ensure the success of the new layout, the selected Starbucks outlet should ideally be in a location with a high amount of external noise. The goal of adopting the new layout is to ensure that the outlet can be separated into a work-study area and dining area, to increase the turnover rate in the dining area, eventually increasing revenue earned by Starbucks. ","metadata":{}},{"cell_type":"markdown","source":"## 2.4 Outcome <a id=\"2.4\"></a>\nOur outcome is to make Starbucks the most popular work-study area in Singapore where people will choose our areas as their go-to instead of other cafés. The outcome of the action will be a 10% increase in revenue for Starbucks as there will be higher turnover rate for the tables that are dedicated for consumption of food and beverages. This will result in improved crowd management as there are dedicated spaces for people to study and to have their food and beverage. This will also reduce the number of complaints regarding people not being able to find tables to consume their food. ","metadata":{}},{"cell_type":"markdown","source":"## 2.5 Input <a id=\"2.5\"></a>\nThe data needed to run the predictive algorithm includes noise level, location, population indices, building morphology and point of interest. Firstly, noise level and location are required as inputs to allows us to focus on which Starbucks outlet is most suitable to be chosen. Next, population indices will allow to identify the demographic of a location as a younger demographic would infer that there are more students or young adult who will be more likely to visit Starbucks. At the same time, more children present in a location would result in higher noise level as they tend to be louder. Building morphology and points of interest will indicate how noisy the surrounding area is likely to be as more footprints in a location or more food and recreational establishments would tend to result in higher noise levels and more discomfort. ","metadata":{}},{"cell_type":"markdown","source":"## 2.6 Training <a id=\"2.6\"></a>\nOur project consists of predicting the most uncomfortable outdoor location of Starbucks outlet which will allow us to identify which outlet we will choose to change the layout. Hence, in order to do so, we have identified that noise level of the location, building morphology and population indices will affect the overall noise level of the surrounding. This means that theoretically higher noise level will result in lesser comfort for people. As a result, we have decided to train noise level to predict how comfortable someone feels within the proximity of a Starbucks outlet. Once we are able to predict the locations whereby people feel most uncomfortable, we will be able to rearrange the layout of existing Starbucks outlet in the area to increase comfort level and attract more people to visit. ","metadata":{}},{"cell_type":"markdown","source":"## 2.7 Feedback <a id=\"2.7\"></a>\nBased on our findings, in theory, the implementation of our changed layout would provide people with a conducive environment to do their work. As more comfort data is inputted into the predictive algorithm, we would observe higher levels of accuracy in determining the suitability of a location. This would result in more effective planning for Starbucks. \n\nHowever, we also identified that the data collected can be very subjective. Different people may have different levels of comfort and it is difficult to analyse the data collected accurately. A common problem is that two individuals can have different noise tolerance given the same noise exposure. Our AI predictive algorithm seeks to overcome this problem by predicting the comfort level based on how majority of the people feel at a given noise level. We can also collect new data by using sensors to identify which spaces in Starbucks people tend to stay at longer, as this signifies higher comfort, to overcome the problem mentioned previously. \n\nSensors can also be used to identify whether the study area or dining area is in higher demand for a particular outlet, and make the necessary adjustments for its layout to better optimise the spaces, if the demand for one area is higher than the other, for instance. At the same time, we will also conduct two separate surveys to both groups of customers to determine if the separation of space was useful for them. \n","metadata":{}},{"cell_type":"markdown","source":"# Section 3: Notebook Configuration <a id=\"3.0\"></a>\n## 3.1 Setting Up Notebook and Importing Dataset <a id=\"3.1\"></a>","metadata":{}},{"cell_type":"code","source":"# Import libraries\nimport pandas as pd \nimport numpy as np\nfrom xgboost import XGBClassifier\nfrom sklearn.metrics import accuracy_score, f1_score\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nimport plotly.graph_objects as go\nimport math\nimport plotly.express as px\n\nfrom math import cos, asin, sqrt, pi\npd.set_option('display.max_columns', None)","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:49:34.785229Z","iopub.execute_input":"2023-11-23T21:49:34.785974Z","iopub.status.idle":"2023-11-23T21:49:36.832326Z","shell.execute_reply.started":"2023-11-23T21:49:34.785932Z","shell.execute_reply":"2023-11-23T21:49:36.830992Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Read Data\nRead all csv file into dataframes.","metadata":{}},{"cell_type":"code","source":"#Read data\ndf_train = pd.read_csv('/kaggle/input/ipm3211-city-scale-noise-and-heat-analysis/5_xesh_split_ipm_train.csv', index_col=[0], keep_default_na=False, na_values=[''], parse_dates=['time', 'ws_timestamp_location', 'ws_timestamp_start'], date_format='%Y-%m-%d %H:%M:%S.%f%z')\ndf_solution = pd.read_csv('/kaggle/input/ipm3211-city-scale-noise-and-heat-analysis/5_xesh_split_ipm_test_public.csv', index_col=[0], keep_default_na=False, na_values=[''], parse_dates=['time', 'ws_timestamp_location', 'ws_timestamp_start'], date_format='%Y-%m-%d %H:%M:%S.%f%z')\ndf_rain = pd.read_csv('/kaggle/input/ipm3211-city-scale-noise-and-heat-analysis/3_weather_rainfall_processed.csv', parse_dates=True, index_col=[0])\ndf_temperature = pd.read_csv('/kaggle/input/ipm3211-city-scale-noise-and-heat-analysis/3_weather_air-temperature_processed.csv', parse_dates=True, index_col=[0])\ndf_humidity = pd.read_csv('/kaggle/input/ipm3211-city-scale-noise-and-heat-analysis/3_weather_relative-humidity_processed.csv', parse_dates=True, index_col=[0])\ndf_wind_speed = pd.read_csv('/kaggle/input/ipm3211-city-scale-noise-and-heat-analysis/3_weather_wind-speed_processed.csv', parse_dates=True, index_col=[0])\ndf_wind_direction = pd.read_csv('/kaggle/input/ipm3211-city-scale-noise-and-heat-analysis/3_weather_wind-direction_processed.csv', parse_dates=True, index_col=[0])\ndf_stations = pd.read_csv('/kaggle/input/ipm3211-city-scale-noise-and-heat-analysis/3_weather_stations.csv')","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:49:36.835724Z","iopub.execute_input":"2023-11-23T21:49:36.836508Z","iopub.status.idle":"2023-11-23T21:51:09.178123Z","shell.execute_reply.started":"2023-11-23T21:49:36.83646Z","shell.execute_reply":"2023-11-23T21:51:09.176962Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 3.2 Data Cleaning <a id=\"3.2\"></a>\nCombine training data (`df_train`) and data needed to predict the solution (`df_solution`) for more convenient data processing.","metadata":{}},{"cell_type":"code","source":"#Combine training data (df_train) and data needed to predict the solution (df_solution) for more convenient data processing.\ndf_train['source']='train'\ndf_solution['source']='solution'\ndf_all = pd.concat([df_train, df_solution])","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:51:09.179566Z","iopub.execute_input":"2023-11-23T21:51:09.180015Z","iopub.status.idle":"2023-11-23T21:51:09.516309Z","shell.execute_reply.started":"2023-11-23T21:51:09.179982Z","shell.execute_reply":"2023-11-23T21:51:09.515262Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Interpolate Health Data\nHealth data, e.g., `ts_heart_rate`, and the watch survey responses, e.g., `q_thermal_preference`, do not have the timestamps. Hence, the health data needs to be interpolated at the timestamps of the watch survey responses.\n\nThe interpolated values are stored in columns with the prefix `ws_` which stands for 'watch survey', e.g., the interpolated values of `ts_heart_rate` are stored in `ws_heart_rate`.","metadata":{}},{"cell_type":"code","source":"# Function to resample health data at the timestamps of watch survey responses.\ndef resample_health(df, col_name, col_name_new):\n    df[col_name_new] = df[col_name].interpolate(method='nearest').bfill().ffill().mask(df['ws_survey_count'].isna())\n    return df","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:51:09.517645Z","iopub.execute_input":"2023-11-23T21:51:09.518448Z","iopub.status.idle":"2023-11-23T21:51:09.525059Z","shell.execute_reply.started":"2023-11-23T21:51:09.518411Z","shell.execute_reply":"2023-11-23T21:51:09.52356Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Resample health data\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_heart_rate', col_name_new='ws_heart_rate').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_audio_exposure_environment', col_name_new='ws_audio_exposure_environment').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_oxygen_saturation', col_name_new='ws_oxygen_saturation').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_resting_heart_rate', col_name_new='ws_resting_heart_rate').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_stand_time', col_name_new='ws_stand_time').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_step_count', col_name_new='ws_step_count').reset_index(level=[0], drop=True)\ndf_all = df_all.groupby('id_participant').apply(resample_health, col_name='ts_walking_distance', col_name_new='ws_walking_distance').reset_index(level=[0], drop=True)","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:51:09.526473Z","iopub.execute_input":"2023-11-23T21:51:09.527441Z","iopub.status.idle":"2023-11-23T21:51:21.304954Z","shell.execute_reply.started":"2023-11-23T21:51:09.527397Z","shell.execute_reply":"2023-11-23T21:51:21.303826Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Interpolate Weather Data\nThe weather data is distributed over several dataframes. Each measurement, e.g., rain or air temperature, is in a separate dataframe. The column names are the IDs of the weather stations.\nThere is one dataframe (`df_stations`), which contains meta information to the weather stations, e.g., coordinates and names. \n\nTo make the weather data usable, we need to find the nearest weather stations for each watch survey response in `df_all`. Then we can transfer the measurement values with the same timestamp to from the weather data dataframe, e.g., `df_rain`, to the dataframe with the Cozie data (`df_all`).","metadata":{}},{"cell_type":"code","source":"# Function to get weather data for a given timestamp and location from the nearest weather station\ndef get_weather_data(df_weather_data, lat, lon, timestamp):    \n    # Get timestamp with no seconds or microseconds\n    timestamp = timestamp.replace(second=0, microsecond=0)\n    \n    # Get weather data for timestamp above\n    weather_data_row = df_weather_data[df_weather_data.index == timestamp]\n\n    # If no weather data is available for timestamp above, get weather data for next minute\n    if (weather_data_row.empty):\n        timestamp = timestamp + pd.Timedelta(minutes=1)\n        weather_data_row = df_weather_data[df_weather_data.index == timestamp]\n        # If there is still no weather data available, return NaN\n        if (weather_data_row.empty):\n            return np.NaN\n\n    # Get weather station ids from weather stations with with data\n    station_ids_with_data = weather_data_row.columns[weather_data_row.count() > 0].tolist()\n\n    # Get weather stations with data\n    df_stations2 = df_stations[df_stations.id.isin(station_ids_with_data)]\n\n    # Compute distance to each weather station\n    df_stations2['distance'] = df_stations2.apply(lambda x: distance(x['latitude'], x['longitude'], lat, lon), axis=1)\n\n    # Get nearest weather station\n    station_id_nearest = df_stations2[df_stations2.distance==df_stations2.distance.min()].id.values[0]\n\n    # Retrun NaN for cases where the nearest weather station is more than 10km away\n    if df_stations2.distance.min()>10:\n        return np.NaN\n\n    # Return weather data from nearest weather station\n    return weather_data_row[station_id_nearest].values[0]\n\n# Function to compute distnace on spherical earth\ndef distance(lat1, lon1, lat2, lon2):\n    r = 6371 # km\n    p = pi / 180\n\n    a = 0.5 - cos((lat2-lat1)*p)/2 + cos(lat1*p) * cos(lat2*p) * (1-cos((lon2-lon1)*p))/2\n    return 2 * r * asin(sqrt(a))","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:51:21.309713Z","iopub.execute_input":"2023-11-23T21:51:21.310689Z","iopub.status.idle":"2023-11-23T21:51:21.324093Z","shell.execute_reply.started":"2023-11-23T21:51:21.310645Z","shell.execute_reply":"2023-11-23T21:51:21.322758Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Apply above function to the dataset for all weather data\ndf_all['ws_rainfall'] = df_all[df_all.ws_survey_count.notna()].apply(lambda row: get_weather_data(df_rain, row['ws_latitude'], row['ws_longitude'], row.name), axis=1)\ndf_all['ws_air_temperature'] = df_all[df_all.ws_survey_count.notna()].apply(lambda row: get_weather_data(df_temperature, row['ws_latitude'], row['ws_longitude'], row.name), axis=1)\ndf_all['ws_relative_humidity'] = df_all[df_all.ws_survey_count.notna()].apply(lambda row: get_weather_data(df_humidity, row['ws_latitude'], row['ws_longitude'], row.name), axis=1)\ndf_all['ws_wind_speed'] = df_all[df_all.ws_survey_count.notna()].apply(lambda row: get_weather_data(df_wind_speed, row['ws_latitude'], row['ws_longitude'], row.name), axis=1)\ndf_all['ws_wind_direction'] = df_all[df_all.ws_survey_count.notna()].apply(lambda row: get_weather_data(df_wind_direction, row['ws_latitude'], row['ws_longitude'], row.name), axis=1)","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:51:21.325536Z","iopub.execute_input":"2023-11-23T21:51:21.326697Z","iopub.status.idle":"2023-11-23T21:52:13.284178Z","shell.execute_reply.started":"2023-11-23T21:51:21.326639Z","shell.execute_reply":"2023-11-23T21:52:13.283133Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Section 4: Data Analysis <a id=\"4.0\"></a>\n## 4.1 Data Pre-processing <a id=\"4.1\"></a>\n### Check Dates\nWhen checking the last date of different kinds of dataframes it becomes clear that the watch survey responses only last until Jan 21, 2023, while the weather data lasts until July 3, 2023.","metadata":{}},{"cell_type":"code","source":"# Check dates\nprint(df_train.index.max())\nprint(df_solution.index.max())\nprint(df_rain.index.max())","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:52:13.288529Z","iopub.execute_input":"2023-11-23T21:52:13.289447Z","iopub.status.idle":"2023-11-23T21:52:13.298538Z","shell.execute_reply.started":"2023-11-23T21:52:13.289404Z","shell.execute_reply":"2023-11-23T21:52:13.297233Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We don't really need the weather data after Jan 21, 2023, so we might just as well get rid of it.","metadata":{}},{"cell_type":"code","source":"# Clear weather data after Jan 21, 2023\ndf_rain = df_rain[df_rain.index<'2023-01-22']\ndf_temperature = df_temperature[df_temperature.index<'2023-01-22']\ndf_humidity = df_humidity[df_humidity.index<'2023-01-22']\ndf_wind_speed = df_wind_speed[df_wind_speed.index<'2023-01-22']\ndf_wind_direction = df_wind_direction[df_wind_direction.index<'2023-01-22']","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:52:13.300387Z","iopub.execute_input":"2023-11-23T21:52:13.300773Z","iopub.status.idle":"2023-11-23T21:52:13.344761Z","shell.execute_reply.started":"2023-11-23T21:52:13.300742Z","shell.execute_reply":"2023-11-23T21:52:13.343707Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Check Weather Data","metadata":{}},{"cell_type":"code","source":"# Check weather data\n# Show new shortened air temperature dataframe\ndf_temperature.describe()","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:52:13.346268Z","iopub.execute_input":"2023-11-23T21:52:13.346603Z","iopub.status.idle":"2023-11-23T21:52:13.502236Z","shell.execute_reply.started":"2023-11-23T21:52:13.346569Z","shell.execute_reply":"2023-11-23T21:52:13.500967Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"It looks like there is no temperature data available in before Jan 21, 2023 for weather station S117. So, we might just as well remove that column","metadata":{}},{"cell_type":"code","source":"df_temperature = df_temperature.drop(columns=['S117'])\n# Get dimensions of the air temperature data\ndf_temperature.shape","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:52:13.503694Z","iopub.execute_input":"2023-11-23T21:52:13.504081Z","iopub.status.idle":"2023-11-23T21:52:13.516693Z","shell.execute_reply.started":"2023-11-23T21:52:13.504038Z","shell.execute_reply":"2023-11-23T21:52:13.515312Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The weather dataframes are rather large. This can make the plotting of the data slow and the output images large. To make it a bit lighter, we are going to resample the data hourly.","metadata":{}},{"cell_type":"code","source":"# Resample weather data\ndf_temperature_average = df_temperature.resample('60min').mean()\ndf_rain_sum = df_rain.resample('60min').sum() # note: for rain the data is aggregated with a sum instead of the mean\ndf_humidity_average = df_humidity.resample('60min').mean()\ndf_wind_speed_average = df_wind_speed.resample('60min').mean()\ndf_wind_direction_average = df_wind_direction.resample('60min').mean()\n\n# Check size of resulting dataframe\ndf_temperature_average.shape","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:52:13.518652Z","iopub.execute_input":"2023-11-23T21:52:13.519252Z","iopub.status.idle":"2023-11-23T21:52:13.623165Z","shell.execute_reply.started":"2023-11-23T21:52:13.519207Z","shell.execute_reply":"2023-11-23T21:52:13.622046Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Map Watch Survey Questions to Question ID","metadata":{}},{"cell_type":"code","source":"ws_questions = {\"q_noise_nearby\": \"Noise distractions nearby? (without earphones)\",\n                \"q_noise_kind\": \"What kind of noise?\",\n                \"q_earphones\": \"Wearing earphones?\",\n                \"q_thermal_preference\": \"Thermally, what do you prefer now?\",\n                \"q_location\": \"Where are you?\",\n                \"q_location_office\": \"What kind of office?\",\n                \"q_location_transport\": \"What kind of transport?\",\n                \"q_alone_group\": \"Alone or in a group?\",\n                \"q_activity_category_alone\": \"Category of activity? (alone)\",\n                \"q_activity_category_group\": \"Category of activity? (group)\"}","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:52:13.625008Z","iopub.execute_input":"2023-11-23T21:52:13.625347Z","iopub.status.idle":"2023-11-23T21:52:13.632229Z","shell.execute_reply.started":"2023-11-23T21:52:13.625318Z","shell.execute_reply":"2023-11-23T21:52:13.630873Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 4.2 Noise Analysis <a id=\"4.2\"></a>\n\nFor the analysis of noise, we analysed the noise exposure in the proximity of the respondents, with regards to the activities carried out.\n\nWe sorted the noise exposure based on the data from (`ws_audio_exposure_environment`) into three categories. We classified any sounds above 70 decibels to be in the undesired range, and noise between 60-70 decibel to be in the acceptable range, as this noise mainly comes from conversations happening in the surrounding whereby, although they may be slightly distracting, they are generally acceptable. The last category would be noise level below 60 decibels, they are considered desired range as these sounds would most likely barely be heard and negligible. This is backed up from our research, where The Center for Disease Control and Prevention has provided a guideline that sound levels above 70 decibels would start to cause annoyance to the people if they are listening to it over a prolonged period of time (CDC, 2022).\n\n\n","metadata":{}},{"cell_type":"code","source":"# Sorting audio exposure into ranges\n\n# Create new DataFrame with the columns 'ws_audio_exposure_environment'\nnoise_levels = df_all.loc[:,['ws_audio_exposure_environment']]\n\n# Define temperature ranges\nnoise_bins = [0, 60, 70, float('inf')]  \nnoise_labels = ['<60', '60-70', '>70']\n\n# Create a new column 'noise_range'\ndf_all['noise_range'] = pd.cut(df_all['ws_audio_exposure_environment'], bins=noise_bins, labels=noise_labels, right=False)","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:52:13.633946Z","iopub.execute_input":"2023-11-23T21:52:13.634435Z","iopub.status.idle":"2023-11-23T21:52:13.654952Z","shell.execute_reply.started":"2023-11-23T21:52:13.634395Z","shell.execute_reply":"2023-11-23T21:52:13.653896Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 4.2.1 Noise Level by Activities \n#### Noise Level by Activites When Alone\n\nGenerally, when doing activities that require focusing, it is assumed that a low noise level is the most optimal. However, from the graph, it is observed that for more than 50% of the time, noise level would fall outside of the desired range. The same trend follows for leisure and other activities as well. Therefore, this could be a reason why more people are going to Starbucks outlets around the country in an attempt to escape from the noise and carry out their activities productively.","metadata":{}},{"cell_type":"code","source":"# Plotting stacked bar chart for noise level by activity - alone\n\n# Create new DataFrame with the columns 'q_activity_category_alone', 'noise_range'\nnoise_by_activity_alone = df_all.loc[:,['q_activity_category_alone', 'noise_range']]\n\n# Create pivot table\nactivity_noise_table = noise_by_activity_alone.pivot_table(index='q_activity_category_alone', columns='noise_range', aggfunc='size')\n\n# Clear row with 'Not applicable' data\nactivity_noise_table = activity_noise_table.drop('Not applicable')\n\n# Add a column for 'Total'\nactivity_noise_table.loc[:,'Total']=activity_noise_table.sum(axis=1)\n\n# Change into percentages\nactivity_noise_table = activity_noise_table.drop('Total',axis=1).divide(activity_noise_table.Total,axis=0)*100\n\n# Plotting stacked bar chart\nactivity_noise_table.plot.bar(stacked=True, cmap='viridis')\nplt.title('Noise Level by Activities - Alone')\nplt.xticks(rotation='horizontal')\nplt.xlabel('Category of Activity')\nplt.ylabel('Proportion')\nplt.legend(title='Noise Exposure (dB)', bbox_to_anchor=(1.05, 1), loc='upper left', labels=['Desired Range (<60)','Acceptable Range (60-70)','Undesired Range (>70)'])\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:52:13.65628Z","iopub.execute_input":"2023-11-23T21:52:13.656628Z","iopub.status.idle":"2023-11-23T21:52:14.122747Z","shell.execute_reply.started":"2023-11-23T21:52:13.656597Z","shell.execute_reply":"2023-11-23T21:52:14.121649Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Noise Level of Activities When In Groups\n\nIn common practice, when studying, a quiet and peaceful environment is preferred where the noise is within the desired range. However, as seen from our graph, the noise present around them that falls under the undesired range and acceptable range are still significantly larger than 50%. This could lower their productivity levels greatly, by having a work-study space, they could benefit much more as they are away from this noise.\nFor the other three activities, the acceptable and desired noise is present in more than 70% of the cases. However, it is important to recognize that participants actively contribute to the observed noise levels. This active participation introduces a broader range of noise, yet within parameters deemed acceptable by the participant. They serve a critical role as a form of cross-checking, ensuring the integrity and accuracy of the sought-after results.","metadata":{}},{"cell_type":"code","source":"# Plotting stacked bar chart for noise level by activity - group\n\n# Create new DataFrame with the columns 'q_activity_category_group', 'noise_range'\nnoise_by_activity_group = df_all.loc[:,['q_activity_category_group', 'noise_range']]\n\n# Create pivot table\ngroup_activity_noise_table = noise_by_activity_group.pivot_table(index='q_activity_category_group', columns='noise_range', aggfunc='size')\n\n# Clear row with 'Not applicable' data\ngroup_activity_noise_table = group_activity_noise_table.drop('Not applicable')\n\n# Add a column for 'Total'\ngroup_activity_noise_table.loc[:,'Total']=group_activity_noise_table.sum(axis=1)\n\n# Change into percentages\ngroup_activity_noise_table = group_activity_noise_table.drop('Total',axis=1).divide(group_activity_noise_table.Total,axis=0)*100\n\n# Plotting stacked bar chart\ngroup_activity_noise_table.plot.bar(stacked=True, cmap='viridis')\nplt.title('Noise Level by Activities - Group')\nplt.xticks(rotation='horizontal')\nplt.xlabel('Category of Activity')\nplt.ylabel('Proportion')\nplt.legend(title='Noise Exposure (dB)', bbox_to_anchor=(1.05, 1), loc='upper left', labels=['Desired Range (<60)','Acceptable Range (60-70)','Undesired Range (>70)'])\nplt.show()\n\n# Remove column for noise range after visual is plotted\ndf_all = df_all.drop(columns=['noise_range'])","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:52:14.124091Z","iopub.execute_input":"2023-11-23T21:52:14.125213Z","iopub.status.idle":"2023-11-23T21:52:14.763496Z","shell.execute_reply.started":"2023-11-23T21:52:14.125177Z","shell.execute_reply":"2023-11-23T21:52:14.762315Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 4.2.2 Noise Map\n\nThe noise map has undergone classification into three distinct groups, aligning with the recommended guidelines established by the Center for Disease Control and Prevention (CDC, 2022). In the first group, areas registering sound levels below 70 decibels are denoted in green on the map, signifying adherence to the desired range that poses no risk of hearing damage. The second group encompasses sound levels ranging from 70 to 85 decibels, depicted in pink (a lighter shade of red) on the map, indicative of noise that may cause annoyance when heard. The third and final group pertains to noise levels exceeding 85 decibels, marked in red on the map, serving as a cautionary indication of potential hearing damage, warranting avoidance.\n\nFrom our map, notable areas are marked in red, designating them as higher-priority locations for further investigation and potential modification of outlet design. These identified spots with elevated noise levels serve as focal points for our exploration and consideration of strategic changes to enhance the overall experience. However, we have identified a limitation in our study—specifically, not every location in Singapore is comprehensively covered in our dataset. While certain spots, including those with our outlets, are absent from our data set, this omission may impede our capacity to pinpoint the most suitable outlets for implementing changes, particularly in areas where the surrounding noise levels are most pronounced.\n","metadata":{}},{"cell_type":"code","source":"#Plotting noise map\nimport folium\nimport pandas as pd\n\n# Assuming df_all is your DataFrame with 'ws_longitude', 'ws_latitude', and 'ws_audio_exposure_environment' columns\n# Make sure to replace this with your actual DataFrame\n# df_all = ...\n\n# Filter out rows with missing longitude, latitude, or decibel values\ndf_filtered = df_all.dropna(subset=['ws_longitude', 'ws_latitude', 'ws_audio_exposure_environment'])\n\n# Create a map centered on Singapore\nsingapore_map = folium.Map(location=[1.3521, 103.8198], zoom_start=12)\n\n# Add markers for each data point in df_filtered with colored markers\nfor index, row in df_filtered.iterrows():\n    decibel = row['ws_audio_exposure_environment']\n    popup_text = f\"Decibel: {decibel}\"\n\n    # Assign marker color based on decibel range\n    if decibel > 85:\n        marker_color = 'red'\n    elif 70 <= decibel <= 85:\n        marker_color = 'pink'\n    else:\n        marker_color = 'green'\n\n    folium.Marker(\n        location=[row['ws_latitude'], row['ws_longitude']],\n        popup=popup_text,\n        icon=folium.Icon(color=marker_color)\n    ).add_to(singapore_map)\n\n# Display the map\nsingapore_map","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:52:57.167244Z","iopub.execute_input":"2023-11-23T21:52:57.167697Z","iopub.status.idle":"2023-11-23T21:53:03.313712Z","shell.execute_reply.started":"2023-11-23T21:52:57.167662Z","shell.execute_reply":"2023-11-23T21:53:03.312027Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 4.3 Other Factors for Consideration <a id=\"4.3\"></a>\nIn addition to noise considerations, our evaluation extends to encompass various external factors that could potentially influence individuals' utilization of our work-study spaces. Through the gathered data, we have successfully extracted information pertaining to respondent demographics, points of interest, and their thermal comfort in diverse temperature settings. This comprehensive analysis allows us to broaden our perspective and consider a multitude of factors as we formulate strategic decisions for the execution of our project.\n\n### 4.3.1 Demographics\nWe assume that in the dataset the adults were further classified into men and woman, therefore adding the two categories up would give us the percentage of adult population in that area. \nNotably, Starbucks traditionally targets individuals aged 22 to 60 years old as its primary audience (Srikanth, 2023).\n\nIn alignment with our new project, which caters to individuals engaged in work and study, we have expanded our target audience to encompass youths and adults. This inclusive approach recognises their spending capability and acknowledges the benefits derived from dedicated spaces for their café-related activities.\n\nThe pie chart illustrates the widespread presence of our target audience within the population, affirming the validity of our predictions derived from the dataset. This observation underscores the effectiveness of our dataset in accurately capturing the demographic groups constituting our target audience for the project.\n","metadata":{}},{"cell_type":"code","source":"# Plot population pie chart\ncolor_scheme_pop = {\n    'Men': '#fd7f6f', #red\n    'Women': '#7eb0d5', #blue\n    'Elderly': '#b2e061', #green\n    'Youth': '#ffee65', #yellow\n    'Children': '#ffb55a', #orange\n    #'Other' : '#bd7ebe', #purple\n}\n\n# Create new DataFrame with the columns 'men', 'women', 'elderly', 'youth', 'children'\npopulation = df_all.loc[:,['Men', 'Women', 'Elderly', 'Youth', 'Children']]\npopulation_sum = df_all[['Men', 'Women', 'Elderly', 'Youth', 'Children']].sum()\n\n# Plotting a pie chart\nplt.figure(figsize=(4, 4))\nplt.pie(population_sum, labels=population_sum.index, autopct='%1.1f%%', startangle=90, colors=[color_scheme_pop[x] for x in population_sum.index])\nplt.title('Distribution of Population')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:53:31.067111Z","iopub.execute_input":"2023-11-23T21:53:31.067538Z","iopub.status.idle":"2023-11-23T21:53:31.272522Z","shell.execute_reply.started":"2023-11-23T21:53:31.067502Z","shell.execute_reply":"2023-11-23T21:53:31.270912Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 4.3.2 Points of Interests\n\nThis graph illustrates the distribution of people's points of interest, which significantly contribute to noise in the vicinity. The top three contributors are food, commercial, and recreational activities. Food, as a necessity, leads with restaurants, cafes, and street vendors generating noise from kitchens, customer conversations, and outdoor seating. Commercial areas, including retail and shopping centres, follow with high human traffic and events causing increased noise levels. Recreational spots like parks and sports facilities also contribute to noise from various activities. Other interests, such as entertainment, healthcare, institutional, civic, and social, similarly impact noise levels in their surroundings. \n\nThe extent of noise pollution depends on factors like establishment density, local regulations, and urban design. By considering these factors, since the noise levels in the surroundings are relatively high as compared to indoors in our work-study space, people needing a place to work, or study will be more inclined to visit our space. ","metadata":{}},{"cell_type":"code","source":"# Plot points of interest bar chart\ncolor_scheme_interest = {\n    'Civic': '#fd7f6f', #red\n    'Commercial': '#7eb0d5', #blue\n    'Entertainment': '#b2e061', #green\n    'Food': '#ffee65', #yellow\n    'Healthcare': '#ffb55a', #orange\n    'Institutional' : '#bd7ebe', #purple\n    'Recreational' : '#FFB6C1', #lightpink\n    'Social' : '#C0C0C0' #silver\n}\n\n# Create new DataFrame with the columns for points of interest\npoints_of_interest = df_all.loc[:,['Civic','Commercial','Entertainment','Food','Healthcare','Institutional','Recreational','Social']]\npoints_of_interest_sum = df_all[['Civic','Commercial','Entertainment','Food','Healthcare','Institutional','Recreational','Social']].sum()\n\n# Plotting the bar chart\nplt.figure(figsize=(10, 6))\nplt.bar(np.arange(8), points_of_interest_sum, width=0.5, color=[color_scheme_interest[x] for x in points_of_interest_sum.index])\nplt.xlabel('Categories')\nplt.ylabel('Count')\nplt.title('Distribution of Points of Interest')\nplt.xticks(np.arange(8), ['Civic','Commercial','Entertainment','Food','Healthcare','Institutional','Recreational','Social'])\n\n# Show the plot\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:53:36.504317Z","iopub.execute_input":"2023-11-23T21:53:36.504704Z","iopub.status.idle":"2023-11-23T21:53:36.882495Z","shell.execute_reply.started":"2023-11-23T21:53:36.504674Z","shell.execute_reply":"2023-11-23T21:53:36.881612Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Section 5: Prediction <a id=\"5.0\"></a>\n## 5.1 Data Cleaning <a id=\"5.1\"></a>\n### Remove Irrelevant Rows and Columns\nWe are now at a point where we have completed the (basic) feature engineering and start preparing the data for the machine learning. For that, we are going to remove some of the rows and columns that we no longer need as it reduces the amount of data that we need to handle. More importantly it makes the dataframes easier to read for humans.","metadata":{}},{"cell_type":"code","source":"# Remove all rows that are not a watch survey response\ndf_all = df_all[df_all.ws_survey_count.notna()]\n\n# Remove some timestamp columns\ndf_all = df_all.drop(columns=['ws_timestamp_location', 'ws_timestamp_start'])\n\n# Remove columns of the original health data those are no longer needed since we are going to use the interpolated values\ndf_all = df_all.drop(columns=['ts_heart_rate',\n                              'ts_audio_exposure_environment',\n                              'ts_oxygen_saturation',\n                              'ts_resting_heart_rate',\n                              'ts_stand_time', \n                              'ts_step_count',\n                              'ts_walking_distance',])","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:53:42.422882Z","iopub.execute_input":"2023-11-23T21:53:42.423384Z","iopub.status.idle":"2023-11-23T21:53:42.472106Z","shell.execute_reply.started":"2023-11-23T21:53:42.423343Z","shell.execute_reply":"2023-11-23T21:53:42.470967Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Remove columns not needed for our project\ndf_all = df_all.drop(columns=['dT','Footprint Proportion','Footprint Stdev','Perimeter Total','Perimeter Stdev','Complexity Mean','Complexity Stdev','Green View Stdev','Sky View Stdev','Building View Stdev','Road View Stdev','Visual Complexity Mean','Visual Complexity Stdev','q_location_transport','Perimeter Mean','Green View Mean','Sky View Mean','Building View Mean','ws_oxygen_saturation','ws_resting_heart_rate','ws_stand_time','ws_step_count','ws_walking_distance','ws_relative_humidity','ws_wind_speed','ws_wind_direction'])\n\ndf_all.info()","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:53:48.352139Z","iopub.execute_input":"2023-11-23T21:53:48.352568Z","iopub.status.idle":"2023-11-23T21:53:48.376415Z","shell.execute_reply.started":"2023-11-23T21:53:48.352533Z","shell.execute_reply":"2023-11-23T21:53:48.375244Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Split Data\nWe split the data into the training set and solution set according to the original data (before we combined `df_train` and `df_solution` to `df_all` in the section [Read data](#Read_data)).\nFurther, we are going to take some data from the training set `df_train` and create a test set (`df_test`) in order to score the quality of our model. The split into training and testing data is need because the submission to the public leader board is limited to two per day and we want to avoid overfitting of the model.\n\nThe current split is 28 watch survey responses for the training set and the rest of responses for the test set.","metadata":{}},{"cell_type":"code","source":"# Separate training and solution data again\ndf_train = df_all[df_all.source == 'train'].copy()\ndf_solution = df_all[df_all.source == 'solution'].copy()\n\n# ws_survey_count might contain missing values and might reset. \n# To avoid any issue we are creating a similar column ws_survey_count_2 without missing and duplicate values\ndf_train.loc[(df_train.ws_survey_count.notna()), 'ws_survey_count_2'] = df_train.loc[(df_train.ws_survey_count.notna()),].groupby('id_participant').cumcount()\n\n# Add 1 to start at 1 instead of 0\ndf_train['ws_survey_count_2'] = df_train['ws_survey_count_2']+1 \n\n# Split data into training and testing sets\ndf_test = df_train[(df_train.ws_survey_count_2>28)]\ndf_train = df_train[df_train.ws_survey_count_2<=28]\n\n# Drop the helper columns ws_surve_count_2 and source again\ndf_train = df_train.drop(columns=['ws_survey_count_2', 'source'])\ndf_test = df_test.drop(columns=['ws_survey_count_2', 'source'])\ndf_solution = df_solution.drop(columns=['source'])\n\ndf_train.info()","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:53:51.86299Z","iopub.execute_input":"2023-11-23T21:53:51.863408Z","iopub.status.idle":"2023-11-23T21:53:51.923872Z","shell.execute_reply.started":"2023-11-23T21:53:51.863375Z","shell.execute_reply":"2023-11-23T21:53:51.922702Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Data Preparation\nFor the machine learning model below, all input and output values need to be numeric. At this point, the watch survey the response columns, e.g., `q_noise_nearby`, are of type string. Hence, we need convert the values in these columns into numbers.","metadata":{}},{"cell_type":"code","source":"# Find columns with values that are not numeric\ncat_vars = list(df_train.select_dtypes(include=['object']).columns)\ncat_vars","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:53:56.849122Z","iopub.execute_input":"2023-11-23T21:53:56.849505Z","iopub.status.idle":"2023-11-23T21:53:56.858019Z","shell.execute_reply.started":"2023-11-23T21:53:56.849475Z","shell.execute_reply":"2023-11-23T21:53:56.857113Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# encoding categorical variables\ndict_cat = {}\n\nfor var in cat_vars:\n    print(var)\n    if var == 'id_participant': # no need to encode the participant ID\n        continue\n    # convert categorical variables into 'category' type\n    df_train[var] = df_train[var].astype('category')\n    df_test[var] = df_test[var].astype('category')\n    df_solution[var] = df_solution[var].astype('category')\n    \n    # dictionary to keep track of the variable mapping: {variable-name: {number1: string1, number2: string2, ...}\n    dict_cat[var] = dict(enumerate(df_train[var].cat.categories))\n\n    # encode variables, missing values are encoded as -1\n    df_train[var] = df_train[var].cat.codes\n    df_test[var] = df_test[var].cat.codes\n    df_solution[var] = df_solution[var].cat.codes\n    \n#dict_cat","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:53:58.91886Z","iopub.execute_input":"2023-11-23T21:53:58.91946Z","iopub.status.idle":"2023-11-23T21:53:58.967835Z","shell.execute_reply.started":"2023-11-23T21:53:58.9194Z","shell.execute_reply":"2023-11-23T21:53:58.966621Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 5.2 Prediction Model <a id=\"5.2\"></a>\nFor our prediction model, we are predicting for (`q_noise_nearby`), however we also predicted for the other factors such as (`q_noise_kind`), (`q_earphones`), and (`q_thermal_preference`), which could be effective to be explored in the future to help us make more informed decisions regarding our project. \n\n","metadata":{}},{"cell_type":"code","source":"def predict_any_column(column_name, df_train, df_test, df_solution):\n    # Remove rows where the predicting variable is missing\n    df_train = df_train[df_train[column_name] != -1]\n    df_test = df_test[df_test[column_name] != -1]\n    \n    # Remove rows where the predicting variable is missing\n    df_train = df_train.drop(columns=['id_participant'])\n    df_test = df_test.drop(columns=['id_participant'])\n    df_solution = df_solution.drop(columns=['id_participant'])\n\n    # Count classes in predicting variable\n    num_class = df_train[column_name].unique()\n    \n    # Break dataframe into variables and ground truth\n    y_train = df_train[column_name]\n    X_train = df_train.drop(['q_noise_nearby', 'q_noise_kind', 'q_earphones', 'q_thermal_preference'], axis=1)\n\n    y_test = df_test[column_name]\n    X_test = df_test.drop(['q_noise_nearby', 'q_noise_kind', 'q_earphones', 'q_thermal_preference'], axis=1)\n    \n    X_solution = df_solution.drop(['q_noise_nearby', 'q_noise_kind', 'q_earphones', 'q_thermal_preference'], axis=1)\n    \n    # Initialize model\n    clf = XGBClassifier(num_class=num_class, objective='multi:softmax', enable_categorical=False)\n    \n    # Train model\n    clf.fit(X_train, y_train)\n\n    # Predict and evaluate\n    y_pred = clf.predict(X_test)\n    score = accuracy_score(y_test, y_pred)\n    print('XGBoost model accuracy score: {0:0.4f}'. format(score))\n\n    # Predict solution\n    X_solution.shape\n    y_solution = clf.predict(X_solution)\n    \n    return y_solution, score","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:54:02.5729Z","iopub.execute_input":"2023-11-23T21:54:02.573351Z","iopub.status.idle":"2023-11-23T21:54:02.584992Z","shell.execute_reply.started":"2023-11-23T21:54:02.573316Z","shell.execute_reply":"2023-11-23T21:54:02.583874Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Create an empty list to collect the scores\nscore = []\n\n# Create a copy of the solution dataframe for submission\ndf_submission = df_solution.copy()","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:54:08.769701Z","iopub.execute_input":"2023-11-23T21:54:08.770123Z","iopub.status.idle":"2023-11-23T21:54:08.776288Z","shell.execute_reply.started":"2023-11-23T21:54:08.770091Z","shell.execute_reply":"2023-11-23T21:54:08.775029Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 5.2.1 Prediction `q_noise_nearby`","metadata":{}},{"cell_type":"code","source":"df_solution['q_noise_nearby'], this_score = predict_any_column('q_noise_nearby', df_train, df_test, df_solution)\nscore.append(this_score)","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:54:11.367356Z","iopub.execute_input":"2023-11-23T21:54:11.367808Z","iopub.status.idle":"2023-11-23T21:54:12.145157Z","shell.execute_reply.started":"2023-11-23T21:54:11.367758Z","shell.execute_reply":"2023-11-23T21:54:12.144229Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 5.2.2 Prediction `q_noise_kind`","metadata":{}},{"cell_type":"code","source":"df_submission['q_noise_kind'], this_score  = predict_any_column('q_noise_kind', df_train, df_test, df_solution)\nscore.append(this_score)","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:54:35.825497Z","iopub.execute_input":"2023-11-23T21:54:35.826015Z","iopub.status.idle":"2023-11-23T21:54:38.542333Z","shell.execute_reply.started":"2023-11-23T21:54:35.825971Z","shell.execute_reply":"2023-11-23T21:54:38.541348Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 5.2.3 Prediction `q_earphones`","metadata":{}},{"cell_type":"code","source":"df_submission['q_earphones'],this_score = predict_any_column('q_earphones', df_train, df_test, df_solution)\nscore.append(this_score)","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:54:39.961887Z","iopub.execute_input":"2023-11-23T21:54:39.962301Z","iopub.status.idle":"2023-11-23T21:54:40.91202Z","shell.execute_reply.started":"2023-11-23T21:54:39.962268Z","shell.execute_reply":"2023-11-23T21:54:40.910942Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 5.2.4 Prediction `q_thermal_preference`","metadata":{}},{"cell_type":"code","source":"df_submission['q_thermal_preference'],this_score = predict_any_column('q_thermal_preference', df_train, df_test, df_solution)\nscore.append(this_score)","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:54:42.239216Z","iopub.execute_input":"2023-11-23T21:54:42.239647Z","iopub.status.idle":"2023-11-23T21:54:43.765356Z","shell.execute_reply.started":"2023-11-23T21:54:42.239612Z","shell.execute_reply":"2023-11-23T21:54:43.764485Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 5.2.5 Compute Overall Score\nThe model for this score used only part of the training dataset. This is because we need some reference data to compute a score. This also means that the score computed in this notebook will not necessarily be the same score as in the leaderboard.","metadata":{}},{"cell_type":"code","source":"# The overall score is just the average of the scores for each column\nscore_total = np.mean(score)\nprint('Overall accuracy score: {0:0.4f}'. format(score_total))","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:54:46.367774Z","iopub.execute_input":"2023-11-23T21:54:46.368849Z","iopub.status.idle":"2023-11-23T21:54:46.374815Z","shell.execute_reply.started":"2023-11-23T21:54:46.368807Z","shell.execute_reply":"2023-11-23T21:54:46.373539Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Section 6: Conclusion <a id=\"6.0\"></a>\n## 6.1 Limitations <a id=\"6.1\"></a>\nOur team identified several significant limitations that would detriment the outcome of the project. The initial phase of the study was confronted with a scarcity of data, specifically pertaining to audio exposure in distinct locations across Singapore. Given that audio exposure serves as the primary metric for our evaluation, the study was inherently constrained by the limited availability of data, leading to a restricted scope of audio exposure analysis.\n\nFurthermore, a notable deficiency in information related to building occupancy rates emerged as a critical limitation. Occupancy rates play a pivotal role in influencing noise levels, with higher occupancy typically resulting in elevated noise levels. Regrettably, due to inadequate data on these crucial factors, our capacity to accurately predict building noise levels was impeded.\n\nAdditionally, the lack of data during the presence and utilization of specific facilities, such as kitchens or television screens in the Starbucks outlets, will affect the finalized layout planning of the Starbucks outlet itself.\n\nMoreover, a series of specific data gaps were identified, each presenting its own set of challenges. The absence of data to track the demand split between work-study spaces and dining areas hinders a comprehensive understanding of customer activity among different outlets. Insight into the income demographics of the population around the outlet is lacking, a critical consideration as the economic status of the surrounding population can significantly impact customer patronage. An assessment of the potential service disruptions associated with the separation of spaces is currently unavailable, thereby limiting our ability to evaluate the cost implications of such changes. Data on the availability of free existing work/study spaces for public use is also absent, which prevents us from having a thorough examination of the context in which our project is situated. Additionally, the study does not account for space constraints within outlets when deciding on the separation of spaces, highlighting the need to recognize and address these constraints for the accurate implementation of any spatial changes.\n\nTo enhance our study, we need to take into consideration the aforementioned limitations, ensuring a more comprehensive analysis to improve the accuracy of our predictions.\n\n","metadata":{}},{"cell_type":"markdown","source":"## 6.2 Future Suggestions <a id=\"6.2\"></a>\nLooking towards future works of the project, we would like to recommend further inputs that serve as comprehensive and forward-looking suggestions for the ongoing development and optimization of the work-study environment within Starbucks outlets.\n\nFirstly, data focusing on obtaining more data related to the audio exposure, such as how long does the noise present in the surrounding. By doing so, the project aims to attain a deeper and more comprehensive understanding of the environmental context in which the participants are exposed to.\n\nReal-time data integration can be another recommendation. The project should explore the incorporation of real-time data feeds such as building occupancy data.  This may involve integrating data related to building occupancy, providing timely insights for decision-making processes.\n\nFurthermore, the introduction of a user feedback mechanism within work-study facilities can be proposed. Directly gathering insights from users can provide qualitative data for further improvement.\n\nSmart technology integration constitutes another significant avenue for advancement. Leveraging cutting-edge technologies such as sensors and IoT devices is recommended to monitor and optimize various aspects of the work-study environment. This may include the deployment of automated sound damping systems, occupancy sensors, and smart lighting to create a more responsive and user-friendly space.\n\nAn essential consideration involves the incorporation of sustainable practices into the design and operation of work-study facilities. This encompasses the adoption of energy-efficient technologies, eco-friendly materials, and waste reduction strategies. \n\nContinuous performance monitoring is essential. The implementation of a robust system for ongoing assessment allows for regular evaluations of the impact of changes on noise levels and overall user satisfaction. This allows for adjustments based on real-world feedback, ensuring continuous refinement.\n\nThe modification of the layout introduces challenges in effectively allocating space for work and study areas, alongside leisure spaces for patrons. As the project progresses, it becomes imperative to continually assess areas with varying levels of demand and adjust spatial arrangements accordingly to meet the dynamic needs of patrons.\n\nBy embracing these future recommendations, the project can meet the immediate needs of the work-study environment but also anticipates and responds to future challenges and opportunities.","metadata":{}},{"cell_type":"markdown","source":"## 6.3 Summary <a id=\"6.3\"></a>\nIn conclusion, our feasibility analysis for implementing a two-space concept in Starbucks outlets within Singapore unveiled significant limitations. Challenges encompassed data gaps regarding building noise levels, occupancy rates, and other influential factors. The absence of post-2022 data and insights into customer activity, demographic income, service disruption costs, and available free work/study spaces further added complexity.\n\nConsidering the importance of recognizing that not all AI predictions are directly applicable in real-world scenarios, the client must exercise their own judgment after concluding on the suggested Starbucks outlets for implementing the two-space concept. This judgment considers various aspects, including potential revenue/profit, suitability for the building aesthetic, and budget constraints. Additionally, given the dynamic nature of consumer demand, the decision to implement the space segregation concept may be influenced by rapidly changing factors.\n\nMoreover, monetary concerns add another layer of complexity, as different outlets would require distinct systems, each demanding varying amounts of funds. It's crucial to be mindful that AI predictions may not always be accurate, and some decisions inherently require human judgment to arrive at the optimal outcome.\n\nLooking ahead, strategic recommendations aim to overcome these limitations and enhance the project's effectiveness. Proposed measures include data enrichment with socio-economic factors, real-time data integration, user feedback mechanisms, smart technology adoption, incorporation of sustainable practices, and continuous performance monitoring. Integrating these forward-looking initiatives envisions a dynamic and adaptive project that not only addresses immediate needs but also anticipates and responds to evolving challenges and opportunities in the work-study environment. The implementation of these factors ensures a more comprehensive and robust approach to the development and optimization of the two-space concept in Starbucks outlets in Singapore.","metadata":{}},{"cell_type":"markdown","source":"# Section 7: References <a id=\"7.0\"></a>\n\nBaker, J. A. (2014, October 29). Seat hogging at Starbucks: Students are not the only ones, say cafe owners. The Straits Times. https://www.straitstimes.com/singapore/seat-hogging-at-starbucks-students-are-not-the-only-ones-say-cafe-owners\n\nCDC. (2022, November 8). What Noises Cause Hearing Loss?. Centers for Disease Control and Prevention. https://www.cdc.gov/nceh/hearing_loss/what_noises_cause_hearing_loss.html#:~:text=Sound%20is%20measured%20in%20decibels,immediate%20harm%20to%20your%20ears\n\nChia, L., & Loo, H. (2021, December 3). Too much noise can harm your health. That’s potentially a problem in Singapore. CNA. https://www.channelnewsasia.com/cna-insider/too-much-noise-can-harm-your-health-thats-potentially-problem-singapore-2350251\n\nGanesan, N. (2023, November 12). WeWork bankruptcy: Singapore co-working spaces report strong demand. Channel NewsAsia. https://www.channelnewsasia.com/singapore/wework-bankruptcy-co-working-office-strong-demand-3908881 \n\nOh, R., & Vinod, V. (2016, June 02). How to solve the perennial problem of seat-hogging?. AsiaOne. https://www.asiaone.com/how-solve-perennial-problem-seat-hogging\n\nSrikanth, R. B. (2023, March 14). Starbucks: Segmentation, Targetting, and Positioning. Medium. https://medium.com/@r.b.srikanth/starbucks-market-segmentation-target-and-positioning-stp-65c714be9176#:~:text=Starbucks’%20target%20audience%20is%20primarily,out%20to%20be%20highly%20successful\n","metadata":{}},{"cell_type":"markdown","source":"# Create Submission File <a id=\"8.0\"></a>","metadata":{}},{"cell_type":"code","source":"# Convert classes back form integers to strings\nfor key in dict_cat:\n    if key in df_solution.columns:\n        df_submission[key] = df_submission[key].replace(dict_cat[key])\n\n# Select only necessary columns for submission\ndf_submission = df_submission[['id_unique', 'q_noise_nearby', 'q_noise_kind', 'q_earphones', 'q_thermal_preference']].set_index('id_unique')\n\n# Write dataframe to csv file\ndf_submission.to_csv('submission.csv')\n\nprint('Congrats! The Notebook executed successfully!')","metadata":{"execution":{"iopub.status.busy":"2023-11-23T21:54:59.361083Z","iopub.execute_input":"2023-11-23T21:54:59.361507Z","iopub.status.idle":"2023-11-23T21:54:59.39212Z","shell.execute_reply.started":"2023-11-23T21:54:59.361471Z","shell.execute_reply":"2023-11-23T21:54:59.391061Z"},"trusted":true},"execution_count":null,"outputs":[]}]}