{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Goal\n\nThe goal of this notebook is to better understand how G-Research calculates the Target from the actual asset prices. This understanding is vital to build a model that predicts the G-Research Target as opposed to a model that simply predicts asset prices. However in the process of trying to replicate the Target value. I have found some inconsistancies between the methodology from the tutorial [Tutorial to the G-Research Crypto Competition](https://www.kaggle.com/alexfir/recreating-target/notebook?scriptVersionId=80084997&cellId=1) and the methodoly that is actually used by G-Research in the training data. Becuase of these inconsistancies, the Targets that we were given do not represent the true asset specific return. Please see my findings and notebook below.\n\nI also want to thank everyone contributed to the discussion board regarding this topic [Recreating Target](https://www.kaggle.com/alexfir/recreating-target/comments). I got lots of insights from there.\nAnd also, my notebook is based on another notebook [Recreating Target](https://www.kaggle.com/alexfir/recreating-target/notebook).","metadata":{}},{"cell_type":"markdown","source":"# Inconsistency Findings\n\nNote: In this notebook, I will refer to [Tutorial to the G-Research Crypto Competition](https://www.kaggle.com/cstein06/tutorial-to-the-g-research-crypto-competition) as ***G-Research Tutorial***. All the efforts to recreate the Target in the training data has allowed us to infer how G-Research actualy calculates the target (it's not the same as the G-Research Tutorial). I will refer to the methodoloy G-Research uses to calculate the Target in the traning data as the ***Target-Methodology***.\n\n1. ***Padding for Missing Data(rows)***:\nPadding for missing rows is a best practcie when handling time series, especially for this competition where we are trying to calculate market-returns over the next 15 mins. In G-Research Tutorial missing rows are padded with previous available rows :eth = eth.reindex(range(eth.index[0],eth.index[-1]+60,60),method='**pad**'). However, the target provided in the training data seems to be calculated using NaN for padding. \n\n2. ***Beta = 0***:\nAs a result from padding with NaN (mentioned in above finding), the *Target-Methodology* calculates beta=0 if either the next minute or the next 16th minute is missing (NaN). This is a pretty unrealistic way to calculate beta in my opinion. Beta is supposed to represent a type of correlation between a given asset and the market. Missing data or simply no trade during a period, doesn't mean the correlation with market is 0 for that period. If we set beta=0 for these periods, the beta time sereis will not be smooth. Please see plot below for Asset_ID = 5.\n![Beta.JPG](attachment:12ca4ddb-ea5f-4dbe-a614-8c658a320c0a.JPG)\n\nI think a better way to handle this is to follow the G-Research Tutorial, where we pad missing rows with previous avaible rows. In that case, stock price will be smooth and beta will be less noisy without the random discontious jumps to 0. The *Target-Methodology* approach to calculate beta will not result in an accurate measure of asset specific return.\n\n3. ***Market-Return Calculation Not Ideal***:\nBased on G-Research Tutorial, market-return is calculated as follows: $$M(t) = \\frac{\\sum_a w^a R^a(t)}{\\sum_a w^a}$$ \nR^a refers to log-return for an asset, which is calculated as follows: $$R^a(t) = log (P^a(t+16)\\ /\\ P^a(t+1))$$ \nLet's look at this following case. Assume real world log-returns are constant from time-2 to time-4 for Asset1, Asset2 and Asset3. Simply assume beta = 1 and all three assests are equally weighted. However, in training data, log-return for Asset2 at time-3 is missing. If we follow G-Research Tutorial's approach to pad missing rows, there will not be any missing prices (no NaN log-returns), target should look like below:\n![image.png](attachment:9b499be1-2e45-47a0-971b-216509966c3f.png)\n\nLets take a look at the same case but with the *Target-Methodology*. We will have a NaN log-return for Asset2 at time=3.\n![image.png](attachment:c84fa743-6281-4420-b8b8-af146a38f0aa.png)\n\nAs you can see, becuase of the NaN for Asset2, market-return has changed significantly. This is because in the *Target-Methodology*, the market-return treats NaN as 0 and averages over all assets (instead of averaging over only the non NaN assets). This approach is strange because a NaN log-return in Asset2 results in Asset1's and Asset3's target value to swing unpredictably. ","metadata":{},"attachments":{"9b499be1-2e45-47a0-971b-216509966c3f.png":{"image/png":"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"},"c84fa743-6281-4420-b8b8-af146a38f0aa.png":{"image/png":"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"},"12ca4ddb-ea5f-4dbe-a614-8c658a320c0a.JPG":{"image/jpeg":"/9j/4AAQSkZJRgABAQEAkACQAAD/4RDoRXhpZgAATU0AKgAAAAgABAE7AAIAAAAKAAAISodpAAQAAAABAAAIVJydAAEAAAAUAAAQzOocAAcAAAgMAAAAPgAAAAAc6gAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAE5pbmEgV2FuZwAABZADAAIAAAAUAAAQopAEAAIAAAAUAAAQtpKRAAIAAAADMTIAAJKSAAIAAAADMTIAAOocAAcAAAgMAAAIlgAAAAAc6gAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADIwMjE6MTI6MjIgMTY6MzY6MDUAMjAyMToxMjoyMiAxNjozNjowNQAAAE4AaQBuAGEAIABXAGEAbgBnAAAA/+ELHGh0dHA6Ly9ucy5hZG9iZS5jb20veGFwLzEuMC8APD94cGFja2V0IGJlZ2luPSfvu78nIGlkPSdXNU0wTXBDZWhpSHpyZVN6TlRjemtjOWQnPz4NCjx4OnhtcG1ldGEgeG1sbnM6eD0iYWRvYmU6bnM6bWV0YS8iPjxyZGY6UkRGIHhtbG5zOnJkZj0iaHR0cDovL3d3dy53My5vcmcvMTk5OS8wMi8yMi1yZGYtc3ludGF4LW5zIyI+PHJkZjpEZXNjcmlwdGlvbiByZGY6YWJvdXQ9InV1aWQ6ZmFmNWJkZDUtYmEzZC0xMWRhLWFkMzEtZDMzZDc1MTgyZjFiIiB4bWxuczpkYz0iaHR0cDovL3B1cmwub3JnL2RjL2VsZW1lbnRzLzEuMS8iLz48cmRmOkRlc2NyaXB0aW9uIHJkZjphYm91dD0idXVpZDpmYWY1YmRkNS1iYTNkLTExZGEtYWQzMS1kMzNkNzUxODJmMWIiIHhtbG5zOnhtcD0iaHR0cDovL25zLmFkb2JlLmNvbS94YXAvMS4wLyI+PHhtcDpDcmVhdGVEYXRlPjIwMjEtMTItMjJUMTY6MzY6MDUuMTE4PC94bXA6Q3JlYXRlRGF0ZT48L3JkZjpEZXNjcmlwdGlvbj48cmRmOkRlc2NyaXB0aW9uIHJkZjphYm91dD0idXVpZDpmYWY1YmRkNS1iYTNkLTExZGEtYWQzMS1kMzNkNzUxODJmMWIiIHhtbG5zOmRjPSJodHRwOi8vcHVybC5vcmcvZGMvZWxlbWVudHMvMS4xLyI+PGRjOmNyZWF0b3I+PHJkZjpTZXEgeG1sbnM6cmRmPSJodHRwOi8vd3d3LnczLm9yZy8xOTk5LzAyLzIyLXJkZi1zeW50YXgtbnMjIj48cmRmOmxpPk5pbmEgV2FuZzwvcmRmOmxpPjwvcmRmOlNlcT4NCgkJCTwvZGM6Y3JlYXRvcj48L3JkZjpEZXNjcmlwdGlvbj48L3JkZjpSREY+PC94OnhtcG1ldGE+DQogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIAogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgCiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAKICAgICAgICAgICAgICAgICAgICAgICAgICAgIDw/eHBhY2tldCBlbmQ9J3cnPz7/2wBDAAcFBQYFBAcGBQYIBwcIChELCgkJChUPEAwRGBUaGRgVGBcbHichGx0lHRcYIi4iJSgpKywrGiAvMy8qMicqKyr/2wBDAQcICAoJChQLCxQqHBgcKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKir/wAARCAHhAx0DASIAAhEBAxEB/8QAHwAAAQUBAQEBAQEAAAAAAAAAAAECAwQFBgcICQoL/8QAtRAAAgEDAwIEAwUFBAQAAAF9AQIDAAQRBRIhMUEGE1FhByJxFDKBkaEII0KxwRVS0fAkM2JyggkKFhcYGRolJicoKSo0NTY3ODk6Q0RFRkdISUpTVFVWV1hZWmNkZWZnaGlqc3R1dnd4eXqDhIWGh4iJipKTlJWWl5iZmqKjpKWmp6ipqrKztLW2t7i5usLDxMXGx8jJytLT1NXW19jZ2uHi4+Tl5ufo6erx8vP09fb3+Pn6/8QAHwEAAwEBAQEBAQEBAQAAAAAAAAECAwQFBgcICQoL/8QAtREAAgECBAQDBAcFBAQAAQJ3AAECAxEEBSExBhJBUQdhcRMiMoEIFEKRobHBCSMzUvAVYnLRChYkNOEl8RcYGRomJygpKjU2Nzg5OkNERUZHSElKU1RVVldYWVpjZGVmZ2hpanN0dXZ3eHl6goOEhYaHiImKkpOUlZaXmJmaoqOkpaanqKmqsrO0tba3uLm6wsPExcbHyMnK0tPU1dbX2Nna4uPk5ebn6Onq8vP09fb3+Pn6/9oADAMBAAIRAxEAPwD6RooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigArL16fWoLND4dtLW6uC+GW6lKKF9cgGtSsnxDc6SumyWmu3i2tvdLsLNN5RP0bPBoAzfCnii81fUNQ0zWLSG2v7B1WRbdy6HIzwTVfX/ABXq8OvHSfC+nW99cwx+ZcfaJGRU4yACM8kVh+AZNO0fxDq9tpdwJdJMi7LqWTfltvQOfvd+9Whqtn4b+JWr3WsTpb29/FG8EshwpCJggE9+aAOp8LeII/EuiC+RPLdZGhlQdFkQ4YfnWvJIkMTySsERFLMx6ADqa4v4V20sHhe6lmQoLjUbmaMHujSEqfxBrS8X6bq95pl1JputGwiW3ffF9nWTeNp4yelACr8Q/CLKCviLTyD0PnCj/hYPhL/oYbD/AL/Cs/4daNpsnw30J5tPtJJGs0LO0Ckk4+ldL/Yek/8AQLsv/AdP8KAMr/hYPhL/AKGGw/7/AAo/4WD4S/6GGw/7/CtX+w9J/wCgXZf+A6f4Uf2HpP8A0C7L/wAB0/woAyv+Fg+Ev+hhsP8Av8KP+Fg+Ev8AoYbD/v8ACtX+w9J/6Bdl/wCA6f4Uf2HpP/QLsv8AwHT/AAoAyv8AhYPhL/oYbD/v8KP+Fg+Ev+hhsP8Av8K1f7D0n/oF2X/gOn+FH9h6T/0C7L/wHT/CgDK/4WD4S/6GGw/7/Cj/AIWD4S/6GGw/7/CtX+w9J/6Bdl/4Dp/hR/Yek/8AQLsv/AdP8KAMr/hYPhL/AKGGw/7/AAo/4WD4S/6GGw/7/CtX+w9J/wCgXZf+A6f4Uf2HpP8A0C7L/wAB0/woAyv+Fg+Ev+hhsP8Av8KP+Fg+Ev8AoYbD/v8ACtX+w9J/6Bdl/wCA6f4Uf2HpP/QLsv8AwHT/AAoAyv8AhYPhL/oYbD/v8KP+Fg+Ev+hhsP8Av8K1f7D0n/oF2X/gOn+FH9h6T/0C7L/wHT/CgDK/4WD4S/6GGw/7/Cj/AIWD4S/6GGw/7/CtX+w9J/6Bdl/4Dp/hR/Yek/8AQLsv/AdP8KAMr/hYPhL/AKGGw/7/AAo/4WD4S/6GGw/7/CtX+w9J/wCgXZf+A6f4Uf2HpP8A0C7L/wAB0/woAyv+Fg+Ev+hhsP8Av8KP+Fg+Ev8AoYbD/v8ACtX+w9J/6Bdl/wCA6f4Uf2HpP/QLsv8AwHT/AAoAyv8AhYPhL/oYbD/v8KP+Fg+Ev+hhsP8Av8K1f7D0n/oF2X/gOn+FH9h6T/0C7L/wHT/CgDK/4WD4S/6GGw/7/Cj/AIWD4S/6GGw/7/CtX+w9J/6Bdl/4Dp/hR/Yek/8AQLsv/AdP8KAMr/hYPhL/AKGGw/7/AAo/4WD4S/6GGw/7/CtX+w9J/wCgXZf+A6f4Uf2HpP8A0C7L/wAB0/woAyv+Fg+Ev+hhsP8Av8KP+Fg+Ev8AoYbD/v8ACtX+w9J/6Bdl/wCA6f4Uf2HpP/QLsv8AwHT/AAoAyv8AhYPhL/oYbD/v8KP+Fg+Ev+hhsP8Av8K1f7D0n/oF2X/gOn+FH9h6T/0C7L/wHT/CgDK/4WD4S/6GGw/7/Cj/AIWD4S/6GGw/7/CtX+w9J/6Bdl/4Dp/hR/Yek/8AQLsv/AdP8KAMr/hYPhL/AKGGw/7/AAo/4WD4S/6GGw/7/CtX+w9J/wCgXZf+A6f4Uf2HpP8A0C7L/wAB0/woAyv+Fg+Ev+hhsP8Av8KP+Fg+Ev8AoYbD/v8ACtX+w9J/6Bdl/wCA6f4Uf2HpP/QLsv8AwHT/AAoAyv8AhYPhL/oYbD/v8KP+Fg+Ev+hhsP8Av8K1f7D0n/oF2X/gOn+FH9h6T/0C7L/wHT/CgDK/4WD4S/6GGw/7/Cj/AIWD4S/6GGw/7/CtX+w9J/6Bdl/4Dp/hR/Yek/8AQLsv/AdP8KAMr/hYPhL/AKGGw/7/AAo/4WD4S/6GGw/7/CtX+w9J/wCgXZf+A6f4Uf2HpP8A0C7L/wAB0/woAyv+Fg+Ev+hhsP8Av8KP+Fg+Ev8AoYbD/v8ACtX+w9J/6Bdl/wCA6f4Uf2HpP/QLsv8AwHT/AAoAyv8AhYPhL/oYbD/v8KP+Fg+Ev+hhsP8Av8K1f7D0n/oF2X/gOn+FH9h6T/0C7L/wHT/CgDK/4WD4S/6GGw/7/Cj/AIWD4S/6GGw/7/CtX+w9J/6Bdl/4Dp/hR/Yek/8AQLsv/AdP8KAMr/hYPhL/AKGGw/7/AAo/4WD4S/6GGw/7/CtX+w9J/wCgXZf+A6f4Uf2HpP8A0C7L/wAB0/woAyv+Fg+Ev+hhsP8Av8KP+Fg+Ev8AoYbD/v8ACtX+w9J/6Bdl/wCA6f4Uf2HpP/QLsv8AwHT/AAoAyv8AhYPhL/oYbD/v8KP+Fg+Ev+hhsP8Av8K1f7D0n/oF2X/gOn+FH9h6T/0C7L/wHT/CgDK/4WD4S/6GGw/7/Cj/AIWD4S/6GGw/7/CtX+w9J/6Bdl/4Dp/hR/Yek/8AQLsv/AdP8KAMr/hYPhL/AKGGw/7/AAo/4WD4S/6GGw/7/CtX+w9J/wCgXZf+A6f4Uf2HpP8A0C7L/wAB0/woAyv+Fg+Ev+hhsP8Av8KP+Fg+Ev8AoYbD/v8ACtX+w9J/6Bdl/wCA6f4Uf2HpP/QLsv8AwHT/AAoAyv8AhYPhL/oYbD/v8KP+Fg+Ev+hhsP8Av8K1f7D0n/oF2X/gOn+FH9h6T/0C7L/wHT/CgDK/4WD4S/6GGw/7/Cj/AIWD4S/6GGw/7/CtX+w9J/6Bdl/4Dp/hR/Yek/8AQLsv/AdP8KAMr/hYPhL/AKGGw/7/AAo/4WD4S/6GGw/7/CtX+w9J/wCgXZf+A6f4Uf2HpP8A0C7L/wAB0/woAyv+Fg+Ev+hhsP8Av8K2dN1Oy1ixS80u6iurZyQssTZU44PNR/2HpP8A0C7L/wAB0/wrnPhaqp4JVUUKovLgAAYA/etQB2NFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFV7zT7LUECX9pBcqpyFmjDgfnViigCpFpWnwQeTBY20cWd2xIlC59cYou9K0/UAovrG3uQn3fOiV9v0yKt0UANjijhjWOFFRFGFVRgAfSqms/8gK//AOvaT/0E1dqlrP8AyAr/AP69pP8A0E0AY3w3/wCSa6D/ANeafyrpq5n4b/8AJNdB/wCvNP5V01ABRRRQAUUUUAFFFQyXcENxHDJKiyyHCITyfwo3C9iaiiigAooooAKKKKACiiigAooooAKQkKpLHAAyTS1X1D/kGXX/AFxf/wBBNNasT0QWl9bXyO9pMkqo20lCCM1Yrz34OEt4UuWPJN038hXoVaVqfs6jguhlQqOrTU31CiiisjYKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACuP+F/8AyJY/6/Ln/wBGtXYVx/wv/wCRLH/X5c/+jWoA7CiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKpaz/wAgK/8A+vaT/wBBNXapaz/yAr//AK9pP/QTQBjfDf8A5JroP/Xmn8q6auZ+G/8AyTXQf+vNP5V01ABRRRQAUUUUAFeaeKHY/GTQUz8uwHHvhq9LrzPxN/yWnQf9wf8As1deE+N+j/I48X8EfVfmemUUUVyHYFFFFABRRRQAUUUUAFFFFABVfUf+QXdf9cX/APQTViq+o/8AILuv+uL/APoJpx3QpbM4X4N/8ilcf9fTfyFehV578G/+RSuP+vpv5CvQq6cX/Hl6nNg/93h6BRRRXKdQUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFcf8L/+RLH/AF+XP/o1q7CuP+F//Ilj/r8uf/RrUAdhRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRWVruvw6DAkk1peXRkbaqWkXmN+VAGrRWN4f8UWPiITi0SeCa3YLLBcpskQkZGRVPXfHFhoWsw6XLZahd3UyNIqWlv5nAxnPPvQB0tUtZ/5AV//ANe0n/oJp+m341KxS5WCe3Df8s7hNjj6imaz/wAgK/8A+vaT/wBBNAGN8N/+Sa6D/wBeafyrpq5n4b/8k10H/rzT+VdNQAUUUUAFFFFABXmfif8A5LToP+4P/Zq9MrzPxP8A8lo0H/cH/s1deE+N+j/I48Z8EfVfmemUUUVyHYFFFFABRRRQAUUUUAFFFFABVfUf+QXdf9cX/wDQTViq+o/8gu6/64v/AOgmnHdClszgPg1cIfDlzbg/vBOXI9sCvR68w+DDp/Z14gZfM35K98cV6fXVjFavI5ME74eIUUUVyHYFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUVm+ItSfR/Dl9qESB3t4i6qTgGnFOTSQpSUU2+hpUjMq43HGax/CmsSa/4atdRnjWN5gSVU5AwcVyXxGup4fFnhuKKVkR5ssqnGfmFbQouVT2b8/wMaldRpe0Wq0/E9GooByBRWBuFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAVx/wv/wCRLH/X5c/+jWrsK4/4X/8AIlj/AK/Ln/0a1AHYUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAVna3q9loWmSX+osFjiGQMZZj6AdzWjWB4q8G6X4xt4INYNz5cD+YggnMfPvjr1oAy/A2mXcl3qXiHUo/Il1SQPHCP4FAxz9cA07xD4T1K+8TQ67o+srp89tC8e1oFkDBsdc9OlXdO8D6dpdu8Nveam6MQf3t67kYHbPQUus+CNO1y4Wa6u9SiKqFxb3jxgjHcDrQAzwH4iuPEnh57m9VRPBcy2zlejmNtu78cU7xfp+sXemXT6XrIsYlt3Lxm3WTeNp4yela+k6RZ6JpyWWnR+XCpJx1JJ6knuT60az/AMgK/wD+vaT/ANBNAGL8Nsj4aaBk5P2JOfwrp65n4b/8k10H/rzT+VdNQAUUUUAFFFFABXmfif8A5LRoP/XMf+zV6ZXmfif/AJLRoP8AuD/2auvCfG/R/kceM+CPqvzPTKKKK5DsCiiigAooooAKKKKACiiigAqvqP8AyC7r/ri//oJqxVfUf+QXdf8AXF//AEE047oUtmeS/BQf8TjUTu/5dxx/wIV7FXjXwUP/ABPdS/69h/6FXstd2Yf7w/kcGXf7uvmFFFFcB6AUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABWB47/5EPV/+vZq36wPHf8AyIer/wDXs1a0f4kfVGVb+FL0ZU+Gv/Igad/ut/6Ea534mf8AI4eGf+uv/sy10Xw1/wCRA07/AHW/9CNc78Tf+Rv8M/8AXX/2Za7Kf+9y+f6nFV/3OP8A27+h6Wv3B9KWkT7i/Slrzj0gooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACuP+F//Ilj/r8uf/RrV2Fcf8L/APkSx/1+XP8A6NagDsKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAqlrP/ICv/8Ar2k/9BNXapaz/wAgK/8A+vaT/wBBNAGN8N/+Sa6D/wBeafyrpq5n4b/8k10H/rzT+VdNQAUUUUAFFFFABXmfif8A5LRoP+4P/Zq9MryD4lahLpfxI0u9twpkiiUru6dSP6124NOVRpdmcONko0030aPX6KZC5kgjc9WUE0+uI7gooooAKKKKACiiigAooooAKr6j/wAgu6/64v8A+gmrFV78btNuQOpicfoacdxS2PFPhFqsNh4qkt5QS97GIo8eoOf6V7nXzt4CiaH4jaZG/DLMQf8Avk19E16OZRSrJrqjzMsk3RafRhRRRXmnqBRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFYHjv/kQ9X/69mrfrnvHhI8Catj/AJ92rWj/ABI+qMq38KXoyt8Nf+RA07/db/0I1znxNIPi/wANAHkS8/8AfS10Pwz/AORBsPo3/oRrj/iGxPxE0gZ6Sp/MV3UlfFy+ZwVnbBx/7dPWo/8AVr9KdTY/9Uv0FOrzD1AooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACuP+F//ACJY/wCvy5/9GtXYVx/wv/5Esf8AX5c/+jWoA7CiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKpaz/yAr/8A69pP/QTV2qWs/wDICv8A/r2k/wDQTQBjfDf/AJJroP8A15p/Kumrmfhv/wAk10H/AK80/lXTUAFIzBRliAPelrhfivdvbeF4jFI0bfaEIKnHrWlKn7Sah3MqtT2cHPsd1RVXS2L6PZuxyWgQk+vyirVQ1Z2NE7q4V4r8Xf8AkdrH/rin/oRr2qvE/jC2zxjaP/dt1P8A48a78v8A4/yZ5+Y/wPmj2azObKH/AHB/Kpqy/DWoDVfDVjehdgmiB2+nb+lalcMk1JpnfFpxTQUUUVJQUUUUAFFFFABRRRQAVDd/8eU//XNv5VNUF823T7hvSJj+hprcT2PBPCH/ACVOx/6+W/8AQTX0FXzx4HmE/wAStOlAwHnJx/wE19D16WZaVI+h5eWa05eoUUUV5h6oUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABXPePP+RE1b/r3auhrnvHv/Iiat/17tWtH+JH1RlW/hS9GVPhn/wAiFYfRv/QjXEeP5kf4madGrAtHLHuHpkiu2+GX/Ih2P0b/ANCNeeeN1I+L0ZI4MsOP0r0aCvip/M8zEO2Ep/I9ui/1Kf7op1Mi/wBSn+6KfXknsBRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFcf8L/8AkSx/1+XP/o1q7CuP+F//ACJY/wCvy5/9GtQB2FFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFZWueILfQYEluLa7ufMbaqWkPmN+VatZ+t6vY6HpsmoaiwWOIZHGWJ9AO5oAraB4osPEaz/AGJZ4pbdgssNxHskQkZ5Wodf8Zad4duYra5iurm4lUsIbSHzGAHUkZrL8C6bdyXmpeItRi8iTVJFeOEfwKBt5+uAagstg+Lepfa9uTAvkb/7uz5sUAdZpGr2muacl7p7l4mJHIwVI6gjsRS6z/yAr/8A69pP/QTXI/CvP9jal5f+p/tO52fXzDmtfxfYa1daZdPpWsJYwrbv5kbWwk3jac8npQA34b/8k10H/rzT+VdNXMfDbI+GmgZOT9iTn8K6egArz34uxCXw/ACcEzKP516FXm/xiTGi28oYgrIBgH3rqwn8eJyYz+BI73SV2aLZL6W8Y/8AHRVvIzjPNU9HOdDsT620f/oIrhvBupzXXxA1qKW4Z1VtqoW4GCegqFTc+aXY0dVQ5I9z0WvEfjL/AMjZbf8AXsP5mvbq8Q+Mh/4qy3/69h/M105d/H+RyZl/u/zR6L4CvbaPwVo1tJPGs7wZWMty3zHtXVV4dodwzeJPBaKxAWMKQD1+dq9xrLF0uSd+93+Jtg6vtKdu1l+CKGu3Mln4fvriBtskUDuh9CBWH8PtaudV8GR3+rThpTK6lyAOAeK1vFDBfCupZ4zbOP0NeL6frM7fCnUbCMtGLW4jZXRsE725rShR9rSa80Z4iv7Ksn5PQ98VldQyEMpGQR3payvDDFvCumMxJJtkySevFatcUlaTR3RfNFMKKKKkoKKKKACoL4Z0+4B6GJv5Gp6gvf8AkH3H/XJv5U1uJ7Hz/wCBkWP4laciDCicgD/gJr6Hr558Egj4laaWBGZyRnv8pr6Gr08y/iR9Dy8r/hy9Qoooryz1QooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACue8e/wDIiat/17tXQ1z3j3/kRNW/692rWj/Ej6oyrfwpejKfwy/5EOx+jf8AoRrz/wAdN/xdiAekkP8ASuj0DxKPC3wostQMHn/PsCZxySf8K4zxpqUcnxDivycR7YJW284+UEivVw9OX1icraO55GIqR+rQjfVWPYPD3iiw1+a6trLzPMsiEl3rgZ6cflW7XlvwhmW41bXpk5WSQMPoSa9SrzcTTVOq4o9PC1HVpKbCiiiuc6QooooAKKKKACiiigAooooA4Hxf4gvtL8caLbW0u2Gdtjrjrkiu+ryz4g/8lD8P/wDXZf8A0Ja9TrrrxSp02u36nJQk3UqJ9H+gUUUVyHWFFFFABRRRQAUUUUAFFFFABXH/AAv/AORLH/X5c/8Ao1q7CuP+F/8AyJY/6/Ln/wBGtQB2FFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFYHirwbpnjG2gg1d7oRwP5ii3mMfPvjr1rfooA5zTvBNjplu8MF9qjqxB/e3jMRgdBnoKdrvgrS/EMkEl491DNAmxZbacxuR3BI5PSuhooApaTpNpomnJZaemyFOeTkknqSe5PrRrP8AyAr/AP69pP8A0E1dqlrP/ICv/wDr2k/9BNAGN8N/+Sa6D/15p/Kumrmfhv8A8k10H/rzT+VdNQAV5z8YufDsOP8AnqtejV558Xf+QHbf9dl/nXVhP48Tkxn8CR2+j/8AICsP+vaP/wBBFeVeBWx8U9THrNL/ADNeraV/yBrL/r3T/wBBFeSeCWx8XL4es039a2w+sKvoY4jSdH1PUvEmtDw9oFxqTQmYQgfIDjOTivE/iLqg1rUNN1FY/KFxZq+wnO3JPFerfEv/AJJ/qP0X/wBCFeJ+ISfsejZ/58Vx+Zrpy6EdJ9btfgcuZVJaw6WT/E1vC0vmeL/C6/3GA/U19AV84eBXLeO9GBJIW4AGe3Wvo+ssyVqkV5fqbZY705Pz/QxPGP8AyKWof9cW/ka8M0v/AJEHXf8Artb/APoRr2j4g3JtfBl2y/xDZ+YNeL6X/wAiDrv/AF2t/wD0I1rgV+5b81+aMMe/3yX91/kz1r4U3U114Gia4kZykzopJ6KMYFdpXDfCH/kQ1/6+ZP6V3NedidK0vU9PC60IegUUUVznSFFFFABUF9/yDrn/AK5N/I1PVLWZxb6LdyN0ETD9KqOrRMtIs8f8LrGfEHh+VQpf7SVLDr9w8V7bXgngP/kLaKf+n9v/AEWa97rvzBWqJf1ueflzvTb/AK2QUUUV5x6QUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABXO+Pf+RE1b/r3auirnfHv/Iiar/17tWtH+JH1RlW/hS9GeZX1xFN8E7WONwzxXShwOxO41xesQzQXwS4JL+WhyTngqMVq2k0Y+HGowlwJGv4mC55I2msbUL6TUbrz5sBtipwOwGK+loxcZP1f6Hy1aalGPov1PTfgl/rNV+kf9a9arwbwB4k/4RrT9TuhH5jM8Khc9QWINe42F0L7T4LpV2iZA4B7ZrxcfCSrOXR/5Hu5fOLoqHVf5liiiivPPRCiiigAopk0qQQvLKdqIpZj6AVW0vVrPWbP7Vp0wmh3lNwGOR1p2dri5lexcooopDCiiigDyrx+xPxG0Eeky/8AoQr1WvLviEAPiD4eIHPnDP8A30K9RrsxH8Kn6fqcWH/i1fVfkFFFFcZ2hRRRQAUUUUAFFFFABRRRQAVx/wAL/wDkSx/1+XP/AKNauwrj/hf/AMiWP+vy5/8ARrUAdhRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFUtZ/wCQFf8A/XtJ/wCgmrtUtZ/5AV//ANe0n/oJoAxvhv8A8k10H/rzT+VdNXM/Df8A5JroP/Xmn8q6agArzz4u/wDIEtv+uy/zr0OvPPi7/wAgS2/67L/OurCfx4nJjP4Eix4b8YXNz4qg0CS3VYVs0dH78IDzXK+CLaSX4tX8yfcimm3fiTVzw1/yV63/AOwcv/osVW8D3nk/FbUbbbnz5pefTBJrv5FGM+VbxR5/O5yhzvaTO4+Jf/JP9R+i/wDoQrxXxH/x5aJ/14L/ADNe1fEv/kn+o/Rf/QhXi/iBd1roY/6cF/marL/gXq/yIzL436L8xfAhx470g/8ATwK938U+I4fDGjG/njaUbwgVepJr588NXYsPE1hdN0imDGvXfi2+/wACQuP4p4z+hqsZTU8RBS2YsFUcMNUcd0aPjsHU/h/JLGRHuRZcN6YzivINL/5EHXf+u1v/AOhGvXfFCJP8Mxk8C3QjHqFryLS/+RB13/rtb/8AoRpYP+E1/eX5oeN1qp/3X+TPVfhD/wAiGv8A18yf0rua8w+EPiKzGl/2G25boSNKCejA9h+Vd8de00awNLN3GLwjIizya87FQl7eWnmelhKkPYQ18jRooorkOwKKKKACs/XUEmhXat08pv5VoVR1r/kCXf8A1yb+VVD4kTP4WeJeBf8AkJ6Kf+og3/os173XhdldW2g2fhvUGiOxZfMkCdWJUjNe3Wlyl5aR3EX3JF3CvQx93JS6a/medl9lFx66fkTUUUV5p6YUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABXO+Pf+RE1X/r3auirnfHv/ACImq/8AXu1a0f4kfVGVb+FL0Z84UUUV9cfGD42YfKH2gkZr6a8M/wDIrablt/8Ao6fN68V8xV9NeFP+RR0v/r1T+VeTmnwR9T2cq+OXoaMd3BLcPBHKrSx/eUHkVNXnHgyQ/wDC1PFCsx68An/ar0evIrU/Zyt5I9mjU9rHm83+AUUUVibHE/E/X5tH8OGG2yJLr5C3ovQj9ab8I/8AkQ4/+viT+YrI+M+7+zrLA4ycn8RWr8Ij/wAUMg/6byfzr0nFLBJrqzzFJvHNPojuqKKK809MKKwdU8U2+meJtO0WSJ2lvvuuOi845/Kt6qlGUUm+pMZxk2l0PLviF/yUHw9/12H/AKEK9Rry34g/8lC8Pf8AXZf/AEIV6lXVX/hU/R/mcmH/AItX1X5BRRRXGdoUUUUAFFFFABRRRQAUUUUAFcf8L/8AkSx/1+XP/o1q7CuP+F//ACJY/wCvy5/9GtQB2FFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUVS1bVrXRNNkvr9ykKYBwMkk8AAepriF+MujSTBU0zVxH5/kGR7JgqvnoT260AeiUUA5ANc74p8b6Z4QCHVYbx0ddxe3gMioM4yT2oA6KimQTLcW8c0edkih1z6EZrlpviLpUetT6ZHZapcT27KsjQWZdFJ6cigDrKpaz/yAr/8A69pP/QTVuKQSwpIAyh1DAMMEfUVU1n/kBX//AF7Sf+gmgDG+G/8AyTXQf+vNP5V01cz8N/8Akmug/wDXmn8q6agArx34keL9O1fGm2e9pYZhlsfKcdea9ir5y8ZxrH43u1RQo3jgCvRy+EZVG30PMzKpKFJJdTs/DX/JXrf/ALBy/wDosUnhK2iPxav5NvzI7lT6Zzml8Nf8let/+wcv/osVmeG7v7H8Vb+6uJAkUTzswJwSBnGPWuuSbUrfyo5ItLlv/O/0PQ/iX/yT/Ufov/oQrxnWGV49DCkHFioPtya9P8UeIbXxL8K9RvrEMI9wT5xg5DCvF7Rme7iDMTjgZPQYq8BBqm77pv8AIjMKilUXLs0vzLWg263fiKzgk4WSUA16h8SdWstS8EmCwmWU2tzGj7T0+U14+GZJNyMVYHgg4IrqNJBk8B6szHd/pCnJ5/hNdNemnONRvY5cPVahKmlvcS68Y3R8GwaAikBSWkkY8nngfTmq+mNjwJrg9Zbf/wBCNZN/dLe3okRNq7VXA9hinaj9qim8q5O3dGh2pwCMcZFaKmkrLS7uZOpJu71srfgdJ8LY5H8eWjopKorbiOg+U1qaczH47Pkk4vJB19jWT8L2I8fWQBIBD5Gevymun8Nxo/xk1ZmUEpOxU+nNcld2qTf907MOr04L+9+h63RVSXU7ODUI7GWdEuZRlIyeW+lc14k8R32neOdB0m1YLBeMDLxkkbsYrwoU5Tdl6nvzqxgrv0OwormovF6S+OpfDphVfLjLmUt1OBgfrXS0pQlC3N1KhOM78vTQKo61/wAgS7/65N/Kr1Uda/5Al3/1yb+VKPxIc/hZ4XrfHg/Qj7j+Ve0aRe29l4Ptru4lVII4dzOTwBXhevXEp8O6PbmIiJYQ4k9TzxXpUcqyfAd8OGZbEhuc4O6vZxVPmhBP+b8zxMJU5Zza6R/I7uz1G1v7WK4tJ0kilGUZTw1WScda8S02eWO88CxxyuqMDuUMQD+8PUV2PxVu7y10O3NlIYz5yncrYOc8VwywtqkYJ73/ADO+GLvSlNra35XO8oqrpTO+j2bSnLtAhY+p2jNWq42rOx2p3VwooopDCiiigAooooAKKKKACiiigAooooAKKKKACud8ff8AIiar/wBe5roq53x9/wAiJqv/AF7mtaP8SPqjKt/Cl6M+cKKK2fDWhtrt5PCoYmO3kkVVGSWAyBX1spKKuz46MXOXKjGr6b8Kf8ijpf8A17J/Kvm6+0650y8FtexmOXaGKnqAa+kvC4x4V0wf9OyfyryczacItHr5WmqkkzzDSNRnsvjZfQwn5Lq6dJB6gZNera1qaaNotzqMylkt03kDvXjtqcfHST/r+f8Aka9O8ff8iDq//Xuf5iubExTqU13SOrCzapVWujZo6Dqya5odtqMaFFnUsFPbnFaNeUTa5faD8HNGutMl8qVn2FtoPGWr1CxkabT7eSQ5Z4lZj6kgVyVqPI+ZbXa+47KNbnSi97J/ecB8Ysf8I7D67xj86t/CE/8AFEqP+m7/AM6zvjN5n9k2u0/Ju+YfiKv/AAg/5E3/ALbP/Out/wC4r1OOP+/v0Or1fX9N0OEvqN1HCSCVVmwW+lZ2jeONH1kWyQzhJ7g4WFjhs4z0rhfjRCBcWU2TliVx26Vx/wAPyf8AhPtIyf8Alt/7Kaqng4Tw/tL6k1cbUhifZJaaHo3i/wD5K74X+g/9CNej15x4v/5K54X+g/8AQjT/ABlrEifEPw9ZWt1+78wedGjd93f8KxlTdSNOK/lf6m0aqpSqSf8AMvyRQ+IBB+ImgD0mX/0IV6nXlfxA/wCSiaB/12X/ANCFeqVGI/hU/T9TTD/xavqvyCiiiuM7QooooAKKKKACiiozcRCYQmRRIRkJnmgCSiiigArj/hf/AMiWP+vy5/8ARrV2Fcf8L/8AkSx/1+XP/o1qAOwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKAOb8d2lre+GhFfXP2aL7VA2/bu5EgIGPc8VyfiPwtqOnw3yHUYodFu7wXUzGIF0dnHA79QBWp8TvDFlrGjfatQ1W7sYoZEbEUjBSQwwNo7+lc3p+meHNR0GTWL7VNclsbe6EMkVxduRvBGMqR6kUAevr90fSuN+K6Kfhtq7FRuFuQDjmuyH3Rjpiud8V+CdO8YwCHVbm/jh27Wjtbkxq49wOtAGxpX/IHsv+vdP/AEEVwmq6PrvhSbWfEmlavB9mcCaW0eBSWCA8ByeK6rSvCdppEFvFb3uoSJb42+fcl8+x9ao3vw+0zULx57q91R1dstB9rPlH229MUAbujX/9qaHZX5XYbmBJSvpuUH+tZHi+9122026TSNJhvYWt38yR7kRlBtOeCOa6CCCO2t44IFCRxKERR2AGAKraz/yAr/8A69pP/QTQBi/DbJ+GegZGD9iTj8K6euZ+G/8AyTXQf+vNP5V01ABXzp42/wCR6u/98fyr6Lr5z8b8eObv/fH8q9TLf4kvQ8nNP4cfU7Dw9IkXxZhkkYKi6aCST0HliuB12Y3Pii/ktHJDTOQynqMmur3Y8bTn/qDH/wBE1wcb+QqyRuC5yCuOgr06Efe5vJfqeXXn7vL5v9D0PTfl+Bl+D3uD/Na5DwhZpfeKrOCZC0TM2/HptNdfZnHwPux6zn+a1U+E0KS65fM6hmS2JXjoc1mpclOrLzZo489SlHyRwkw2zyAdAxH611Oi/wDJPtX/AOu6/wDoJrLutMEWhz3s0Ukc32zyxuBAK4z0rU0X/kn+r/8AXdf/AEE10VJJxVu6OalFxm79n+Rzt55a3Y8rG3avT6Vs+OIUh1y3WMYBsYG/NBXOV0/j3/kPWv8A2D7b/wBFiqelSK8n+hK1pyfmv1KHhXVJdI8TWd1AAXEgTn0bg/zr0Dwz/wAli1j/AK7t/OvLbOYW99BM3IjkVz+BzXo/gXUI9V+JuoX0IKx3Dl1B7AmufFR92UvI6cJP3ox/vfoaWu3PnfGrRlDZ8tthwenWrXjU4+KvhY/T/wBDNcdrWqf2d8YZrxz8tved+ccf/Xrq/Gcwf4meFpOg2g5/4FXJyOMof4X+R2e0Uoz/AMS/NGDrkjp8b4yjMu65iBwcZGBxXtleIa4wb42QlSCPtMPIPsK9vrlxnw0/Q68F8VT/ABBVHW/+QJd/9cm/lWX4p8Wp4ZudOie1af7dL5YKtjbyBn9a1Nb/AOQJd/8AXJv5VyKElyyezOxzjLmit0eFeIf+RG0T/P8ACaLDWLmx+Gd9BG+UurryGDc4XZnj0o8Q/wDIi6J/n+E1mqf+KCcf9P4/9Ar6KKTgk+/6nzMpOM21/L+h0mn/APIR8CfQ/wDow1o/FLxI0+tx6Gke1IHRnb+8eorlddmkt9B8MSwO0ciWzlXU4IPmGofF159o8UfaS4kPlREsDnJCCojSUqkZvpf8zSVZxpSguvL+R3vwq1q6vdWv4byd5OFVFJOFC56CvU68Z+D25/EF3IB8u3J9s5r2avIx0VGu0j2cBJyoJvzCiiiuI7gooooAKKKKACiiigArj/iVrV7oXhlLnTZBHK06oSRnjBrsK8t+L+vWUmmppEb7rpZhIwH8IAP+NdOFhz1oq1zlxk+ShJ3sz0fS7pLzTLeZJUlLRKWZGBGcc1bryf4P6zDb2t3ZXt1h5ZF8hGPbBzj8a9YqcRSdKo4lYesq1JTCiiisDoCud8ff8iJqv/Xua6Kud8ff8iJqv/XA1rR/iR9UZVv4UvRnzvZ2kt/exWtsN0szBEBOMk13XwmjaDxvJDJw6RyKw9xwa5nwahfxnpe0ZxcoT+ddV8OGx8UrtfUz/wA6+ixUm6c4+R8zhIpVIS8zO+KK4+IEo9Y4/wCVe1eGxjwxpw/6d0/lXjPxTGPiI4/6Zxfyr2jw+MeHLD/rgv8AKvNxf+70z1cH/vNU8a+0x2nxrmmmbai3z5P4GvVPHpz4A1Yj/n3/AKivHtVtPt/xXu7cNt33x5+nNevePPl+H+pj/p3x+oqsQl7Si/QjDN+zrL1PNdduo/8AhTujWxP7wybgMdstXe+JPF58KeHdOlSDznkjj+UnHGBmvJNfun/4RjQbYEeWbdmI995rtPiomfDekN5ijEKDZ3PA5rWdKMpQjLZuRjCtKMZyjulEm+LN4tz4b02U4RrhFkCZ6Zwf61xXh/xTeafHpdhYyGMrdEyejBiBiuu+JyKfB+iMVG5YEAOOnyrXlUcjRSpIhwyMGU+hFb4WnGVDlfdmGMqShiOZdkeqfGk/NYj/AGj/ACri/AP/ACPuk/8AXb/2U1rePtTkvtL0RZ9zSm1SV5D0YkVkeAzjx3pX/Xb/ANlNOlFxwri+zFWkp4tSXdHpPi//AJK54X+g/wDQjXIanLt+MqO7cLdpyT04Fbes6v8A2l8a9Lt/L2fYZxDnP3u+f1rm9YdD8Vi0pAT7Su4k8YwKxoRaST/l/U3ryTba/n/Q6rx6d3xC8Pkcgyqf/Hlr1WvJfG0iv4/8PBMFRImCDweVr1qvOxH8On6fqelhv4tT1X5BRRRXEdwUUUUAFUdavTp+i3d0jBXiiZkJ/vAcVerC8ZqG8J3wP/PMn9DV00nNJkVG1BtHmSfFzWbmSzgiSKNzKqyuUB3gkdB2rfu7qWT41aYPMcI9qpKBjj7rdq8h0/nU7X/rsn/oQr1WRt3xp0nvttVB/wC+Wr3a1GnTfuK3us8ChWqVV77v70T1Siiivnz6IK4/4X/8iWP+vy5/9GtXYVx/wv8A+RLH/X5c/wDo1qAOwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKAMHxhpcet6C1g11FBKZEljMjYyyMGA/MV55p+ieIL9r7QtSuLGG3vL9rud1YbmyQQFGcjlaZ461HQx4+1m28Taibf7Np0UunqyscSkNkrgHnIFc7HqPglfBNhqFreRP4ubyWecRv5zSFgGycY6ZoA+hQMKB6ClpF+4PpS0AFFFFABVLWf+QFf/APXtJ/6Cau1S1n/kBX//AF7Sf+gmgDG+G/8AyTXQf+vNP5V01cz8N/8Akmug/wDXmn8q6agAr5w8ef8AI533+8P5V9H184ePP+Ryvf8AeH8q9XLP4j9DyM1/hL1J/Dl1Jd69cSTOXYadKuT6CPArl88Guh8I/wDIYuf+vCb/ANArJ/sy5OkjUFhY2+4qZOwNexGym/l+p4srygvn+h2tvK4+C0qheGumBPp92pPg1z4jvP8ArgP/AEKntx8Fz/12P/stN+DX/IyXn/XAf+hVxT/gVfVnfD/eKXojb+McMcOj2giQKDLk4Hsa4jRnUeAdWUsATOuAT1+U13Xxn/5BFn/11/oa8dDsEKAnaTkiqwcefDpeZGNlyYlvy/QbXo/xK0+2j0PQ75UAuJbVFZv7wCrivOK9R+Jig+EPD5xyLdcf98rW1ZtVqfzMKCTo1Pl+Z5dXcfCuZYPEskjfwxFsZ64ya4+8sp7GSNLlCjSRrIoPdT0NP0vUZtK1CO8twDImQAenIx/WtqsfaU3FdTGjL2VVSfQveIdYXXPFE9+kAhWWbIXv17+9dX8VLsprWky2s2HjtQQyNypzXnp3B9zAjnmrOoXL3UqyOGC7cKD6VPslzRa2VylWfJNPd2L3h+9ZvGGn3V9MWIuEZ5HPYGvpdHWSNXQ5VgCD6ivk+vqXSP8AkB2P/XtH/wCgivMzSKXLI9XKpt80Tzv4pyu3iDQIz91blSPxK16Frf8AyBLv/rk38q89+Kf/ACMGgf8AXyv81r0HW/8AkCXf/XJv5VyVP4dL5/mdlP8AiVfl+R4X4h/5EXRP8/wmsZbhP+ESa33fvDeB9vttxWt4gb/ijdFX/ZB/Q1yuflx717tKN4/N/mfP1pWn8l+R0XiL/kXPDf8A16yf+jDXOhvmBPNb2vTJJoGgIjAtHbOGA7fOawK0pfD9/wCZnV+L5L8kel/CC6x4guIQjfvI857DANezV4/8I+Nduf8Arkv8q9gr57H/AMdn0eX/AMBBRRRXCegFFFFABRRRQAUUUUAFfOvxGBHj/U8/89B/6CK9+vtWsdNkhS+uEhaZtsYb+I14X8TyD40uCvQ4P6CvUy26qvzR5OaWdJeTMXww2fFWlD0uU/8AQq+mq+UoZpbadJ4HMciNuRh1BHevqDRrj7VollMZPMZoELNnqdozWuaR1jIyyqWkol2iiivGPbCud8ff8iJqv/XA10Vc74+/5ETVf+uBrWj/ABY+qMq38KXozxj4dWz3PjSz8sZ8s7z9ARW38Of+SrXP/bx/OqXwo/5HZP8Ari38xV34c/8AJVrn/t4/nXvYh61F/d/zPnsOtKT/AL3+RW+Kf/JR2/65w/yr1mz1mw0nQtKjv7hYWuIlSIEH5jjpXk3xTIHxGYnoI4c/lVj4g65GYdDsoUJktYUuN5+6wI4H6VhKj7anSh5fodEa3salafn+pUc/8Xkm/wCv1q9N+JEhTwNeAHG5MH3rybRdT/tTxtbXs6Ik892ZHI9x0r1H4oPt8FyD+9x+lTXi1WpJ+RWHknQqyXmeHXF3LdWVukrjbbL5ca47E5rt/ipPun0Nf+edoP5LXBhm+xsuBt3gk984rrPiPP52pWI/uWyj/wAdFehOP76HzPOhL9zP5Gt4q1dPE3hvw7DBE0JuG+zguc4KkLmvP7+0aw1Ce0dgzQSNGSO5BxXVWrA6T4QAIyL2TI9P3gqleaFdaz4m1p7YYjt5pHkc9F5OPzxUUWqfu9NfzKrKVX3t3p+Rm6xrEuqR2cbEiO2t1iC9sjvTdB1MaNr1pqBQuLd9xUd+MVnUV1ckeXl6HLzy5ubqdNP4mh/4WIfEMcLNELgTCPPJ4xisnXNSXV9auL5EMYmbIUnJFZ/TrRSjTjFprtYcqkpJp9Xc7C0upbu+8LSXDl3E+3JPYOAK+ga+anu3sdP0W6iwXgZ3UH1DZr3Twh4jOv8AhaLU7sLCS7I3OBkHFeNj6b5YyW2q/E9vLqi5pRe+j/A3bmYW9rLOw3CNC5A74GayfC3iWDxTpJv7aF4VDlCjnJBFY3xF8WS+HdFg+yRpMb7fHlugGOv61ynw78Yad4e8NxWt6WL3F4w+U/cGBgmuWGGlKg5pa30/U654qMa6pt6W1/Q9eorNsNfsdS1G5sbaUNPbHEienv8ArWlXG4uLsztjJSV0FYPjVtvhG9/65n+RrermviBMIfBt2xBORt4960o61I+pnW0py9D54tpDDdRSKMlHDAeuDXo2i3w1H4r6TcA/M1uN4/una2RXnVowS8hkbhFkUsfQZrs/BMsU3xRS5SQeV5rsG7EEGvpMQrxb8mfL4aTU4rzR7xRQCGGQcj1FFfLH1oVx/wAL/wDkSx/1+XP/AKNauwrj/hf/AMiWP+vy5/8ARrUAdhRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUARSWtvK26WCN29WQE00WNoOlrCP8AtmKnooAKKKKACiiigAqlrP8AyAr/AP69pP8A0E1dqlrP/ICv/wDr2k/9BNAGN8N/+Sa6D/15p/Kumrmfhv8A8k10H/rzT+VdNQAV84eO/wDkcr7/AHh/Kvo+vnDx3/yOV9/vD+Verln8R+h5Ga/wl6ieEf8AkMXP/XjN/wCgVpp/yST/ALeW/wDQhWZ4R/5DFz/14zf+gVqJ/wAkjP8A18t/6EK9Kr8a9V+p5lL4H6P9CGx1Saf4dX1hJgxwsHU9+SBitf4M/wDIx3n/AFwH/oVc3pf/ACKOq/7q/wDoQrpPgz/yMd5/1wH/AKFUV0lRqW/rY0w7br0r/wBbm98Z/wDkD2f/AF1/oa8b617J8Z/+QPZ/9df6GvHEOHH1p4D+Aicx/wB4Zdh07zdEub/fgwSpHt9d2f8ACvV/F3h7Udb0Hw1JpsBnEEcfmIPQhefpXnFsuPA+on1uov619CaF/wAi9p//AF7R/wDoIrnxlWVNxkujf5I6MDRjUUoPql+bPDvidC1v4rihcBWSziUheg4NcjF/rk/3hXbfF3/kfG/69o/61xEX+uT/AHhXdhnejF+RwYlWryXmdffabJeeGbu5tbYyeRqG6V1H3E2Dr7ZqzP4aGuXlpa2rLCy2Zkz6kNWvpZ/4tt4rx/fP/stY3wvd5PEdxvdji1YDJzjkVzc8lGUl9n/JHVyRc4xa+L/NnFSxmKZ4zyUYqfwNfUWj/wDIDsf+vaP/ANBFfMN7/wAhC4/66t/Ovp7R/wDkB2P/AF7R/wDoIrDM/hgdGVfHM85+LEqwaxokshwkc4Zj6AFTXe6hdRXvhia5t23RSwFkYdwRXnPxq/1mnfVv5Cu00z/kmdr/ANeI/wDQa5ZxXsKUjrpyf1irHyR434gb/imNGX/pkD+hrBsLKXUL6K0t+ZJW2rn1rY19/wDiS6Qn/Tup/nTfBADeNdMDf89uPyNe3F8tJv1PCklOqovyMORWSRo3PKEj6U2p7wE6hOAMnzW/nTJ7eW2l8u4jaN8A7WGDg1smc7R1XhDxUnhbXvtFzEzwPEAyr16cV73YXiahp1veRAqk8YkUHqARmvmS/Cb8k/N5aYH4V9HeGP8AkVdM/wCvWP8A9BrxcxpxSjNbs93LKkm5U3sjVooorxz2gooooAKKKKACiiigDxz4xTyp4k06NXYIId2B67jzXN/EPJ8UPn/nmn/oIrQ+KerR6j40ECKVNkPJYnuc5/rVDxl/xM/Ght7bDMQiD0J2ivo8NFxjTv2f6HzOJkpSqW7r9Tm5nja1gVB8yg7vzr1T4NapcSJeWM0jvEmGjU9E65ryq5jjikKRsxKkhsjGDV/THntdMvL21uZIXjKxlV/iDcVviKaq0nHuc+HqulVU+x9OZor5+1jxzNqXhvSrWJ5Ybqzc+YVJwygDac9zxXsHg7xFba5odsFuklvEhUzoDyp968GthJ0YczPoaOMp1p8iOhrnfH3/ACIuq/8AXA10Vc74+/5EXVP+uBrCj/Fj6o6K38KXozyT4VMF8ax5OMxMP1FaHw7Xb8WLke1x/Ok8CadCPiV5MQKJFD5gA9cKak8AEH4t3O05GJ/517lZp+0a/l/zPAoJpU0/5v8AIq/Fq2lTxyZ5UZYJIo1VyODgc1keOQo1PTxGcr/ZsGD68Guo+M8qNqVnGGBdVJI9OBXB61qn9qz20gXHk20cH/fIrTC3lTpy7Iyxdo1Kke7KVtJ5V1FJnG1wSR9a9n8fXg1X4b217agvFKA2fQYxXkEek3k2lPqEVvI9vG215Avyr9TXpupX0EPwT05HYbni8tR/tcnFLFJOdOS3TKwrap1IvZq55UwaOJo3G1twJBrT8T3yX+seZDKJY1iRVI6DCjNZ17OtzdvKg2q2OPwqXTNLutXuHt7CEyzKhk2jqQOtdjSXvM4k27wj1JdBYnxFpoJOBdR4GenzCvbb3wnBotjrt9YvJJJfRlnjIGF6kkfnXieho0fiewSRSrLdxhgex3CvpTVv+QLe/wDXvJ/6Ca8vHzcZxt1/zPWy6EZU5t9P8j5aJJ60gzkY61IYWECzcbGYqKjr1zxR8xkaZjNnf3zTKCc9aKAJpLmSW3ihY/JFnb+NehIzJ8AiUJU/bOoOP4683r0cf8kBP/X7/wCz1y4j7H+JHZhn8f8AhY74hOX8A+FyeTsP/oC153BL5c0TNkqjhsfjXd+OryCTwX4ctVlUzxx7njB5UFRg1wGDjOOPWjCr91Z93+YsW/3t12X5HrXw11KLVPHus3cCsqTRb1DdQMivTTqVmNQFibhPtRXcIs/Nj1r5t8OeI73wzqX2uwYZYbZEPR19K6rwn4ml1j4mQ3t7lGuWCKi8henH04rgxWDcpOfRL8j0MLjYxgodW/zPcHdUXc5AA7mua+IDD/hDLojkEDFZ3xamkg8EFoXZGNygypwcc1F4hvY7z4VLLFIsn7qNSVOeQuK4KNJrkqd3Y9GtVT56fZXPMtMhgb4faxIYh5yvF85HbdXPwzCGOQxuysQMHODnNdTpssbfC/Vo1I8xZYyw9Bv4rjq+ip6uV+/6I+bq6KFu36s+lfBUrzeCdJklYu7W6lmPetysDwL/AMiJpH/Xstb9fLVf4kvVn1dH+HH0QVx/wv8A+RLH/X5c/wDo1q7CuP8Ahf8A8iWP+vy5/wDRrVmanYUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAVR1DW9L0lkXU9QtrRn+6JpQu76Zq9XBfF7S7O58B6lez26SXEFuRG7KCU57elAHeKyugZCGVhkEdxVG513SrK8W0u9RtobhiAsUkoDHPtUmlf8gey/690/9BFeYWWn22s+FfE+sahEkl8vm+XK4y0WzcFKnt0HSgD1oEEAg5B6GqWs/wDICv8A/r2k/wDQTVLwhcSXXhHTZJiWf7OgLH+L5RzVXxffa3baZdJpWjx3sLW7+ZI1yI9g2nPB60AN+G//ACTXQf8ArzT+VdNXMfDbJ+GmgZGD9iTj8K6egAr5w8d/8jle/wC8P5V9H183+O/+Ryvf94fyr1cs/iP0PIzX+FH1E8I/8ha5/wCvGb/0CtVP+SRn/r5P/oQrK8If8ha5/wCvGf8A9ArVT/kkZ/6+T/6EK9Kr8a9V+p5lL4H6P9DM0v8A5FHVf91f/QhXSfBn/kY73/r3H/oQrmtL/wCRR1T/AHV/9CFdN8Gf+Rivf+vcf+hVGI/g1P67F4b+NT/rub3xn/5A9n/11/oa8dhAaZAehNexfGf/AJA9n/11/oa8eg/4+E/3qMB/u6DMP95fyPS/GXhyz8P/AA/hFkDm4eOSQk9Tj/69ep6F/wAi9p//AF7R/wDoIrg/if8A8iDY/SL+Vd5oX/Ivaf8A9e0f/oIryq8nKhFvuz16EVGvJR2sjxb4u/8AI+N/17R/1rhq9U+M2kQRz2mqpnz5sxPzxhRx/OvK69rByUqEbHhY2LjiJXPRvDBLfCPxIWJJJ6n/AIDVD4V/8jJcf9ezfzFX/C3/ACSHxH9f/iao/Cv/AJGW4/69m/mK55fBW9f0R0x/iUfT9Wcdff8AIQuP+urfzNfT2j/8gOx/69o//QRXzDff8hC4/wCurfzNfT2j/wDIDsf+vaP/ANBFYZn8EDfK/jmeX/Gr/Wad9W/kK7XTP+SZ2v8A14j/ANBrivjV/rdP+rfyFdrpn/JM7X/rxH/oNYT/AN2p+p0U/wDeqvoeNeIAP+Ea0Y458oc/gah8Df8AI8aV/wBdx/I1uRaSdVt/DkEsEklvIoVygPoe9afhjSbWy+LN/ZwR/u7U/ug3JU4H+NelKrFU5R62Z5kaUpVYy6XX5XPPJv8AkMS/9dm/nXW/E3SFsdSsL1ZNxvbZSU2427VArK1zwvqmiXv2nUIVjjlmO0hwc5Jrpvi5/q/D/wD16H/2WqdROrT5Xo7kqm1Sqcy1VjgdQ/4+V/65r/KvpLwx/wAirpn/AF7J/wCg1833YzfxA91T+VfSmgDb4dsAOgt0/lXHmXwQO3K/4k2aFFFFeIe6FFFFABRRRQAUUUUAfOPj04+IGrZ/5+P6Cm6eRe+Lra5tVkeIzooJHfFX/idAkPjS6ZBgyHc3ua6b4NQRTJemaJHKSBlLKDtOOor6WVRQwyn5Hy8abninT8zznXdPn0zWri2ugBIG3EA54PIqS0/5FrUP+ukX8zXb6tp8F98ZJ7O6TfFIqhh9QKpePLO30+91W2tIliijFuFVRjtVRrqXLF7tJ/kTKg4801sm1+ZwQBPQZr034J/8hjVP+uCf+hVxOu2S21xa/ZlI8y1RiFHfHJrtvgn/AMhjVP8Argn/AKFSxclLDSa/rUMHFxxUU/60PY653x9/yI2qf9cDXRVzvj7/AJEbVP8Arga+eo/xI+qPpa38KXox/hawtV0izvFhQXBi2mQKMkU3TPBel6T4hm1e1RhPICAMnC56/nVvwv8A8i1Zf9cxWtTnUkpSSe5MKcHGLa2PF/jJarHrlvcgndKm0j6CvNq9V+NUZE2nP2bcP5V5VX0WCd6ET5rHK2Ike3WWmfbfguba1VFkmtlYnpk8Hn8q89u5pJPhjbpJJvEWobFH90bOleveF4g3w1sVA+9ZZP5V42//ACTxv+wqf/QK48NK8pL+8d2KjaEX3j/kc26lGKnqK7j4Q/8AI9D/AK9pP6Vx+op5d/Io7Y/lXYfCH/kex/17Sf0ruxLvQk/I8/Cq2IivMwof+SgL/wBhL/2pX0Vqg3aPeAnAMD8/8BNc3H8NdBTWDqPlymbzfNH7w4DZz0+tdHq3/IFvf+veT/0E14uKrwrShy9D3cLh50Iz5up82vZs+is8ZDJBKSxz1HArPgieaQKiM59FGTV+zLw6TO0vMExCYDdCDk8V7F4Z8MaNZ+DzqVhDve6t94eTkj6Z6V7FbEKgtdbs8Wjh3XlppZHh8EXm3KRn+I4rWh0uB/Bt7qLA+fDeJCpz/CVJP8qo2X/Iaj/66mtuD/km+qf9hOL/ANBatakmrW8vzMacU737P8jC0/TbjU5pY7UKWiiaZtxx8qjJrvMY+AJ/6/P/AGeuc8Ef8hO//wCwbcf+g1QPiK//AOEaGhb1+xCTzNu3knOetZ1IyqTSXRpmlKUacHJ9U1+RW1LUG1GWF3TZ5UKxDBzkL3rR8JeHl8S6ylg9w0AbncFzUGmQo+has7KC0aR7SR0y1dB8Kv8Akcovp/jVVZclKXLpYmlDnqx5tbnNeINLGieILzTVlMotpCgcjG78KZpF+2l6gl9C+yeD54jtzlh0zWx8QonTxzqbMjKGmJBIxniuZHvV03z01fqiKi9nVaj0Z614t1efXfg5a6hd482W5Xdj2LCuZ8NSSSeAtcjZ2YCWIKpbgZzTNb1WeL4c6Fpa48icPK3HOVcgfzrmLK7ngkEcUrLHIwDpnhvqK5qVH924rvf7mdVat+9Un/Kl96O4HhufQ/hdqF3exqHu2iIAbtu4P6158vLD617h46GPhEn+5B/SvD1OGB96eDqOpGUn3JxtNU5xjHsfSvg1dvgvSwOgt1rbrE8GNv8ABelNjGbdeK26+dq/xJerPpqX8OPogrj/AIX/APIlj/r8uf8A0a1dhXH/AAv/AORLH/X5c/8Ao1qzNDsKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAK4/4g+Gdf8V6S+maNqtnYW08ZScT25kZuexBGK7CigDntE07xLY2dpBqeqWNx5KhZDFbFNwHHHPHFYWpeAtXe9vYtG1a3tdJ1Aj7VbSQlnI/i2sCMZye1d9RQBW06yj03Tbeyg/1dvGsa/QDFR6z/AMgK/wD+vaT/ANBNXapaz/yAr/8A69pP/QTQBjfDf/kmug/9eafyrpq5n4b/APJNdB/680/lXTUAFfN/jr/kcr7/AHh/KvpCvm/x1/yOV9/vD+Verln8R+h5Ga/wo+o3wh/yFrn/AK8Zv/QK1k/5JGf+vk/+hCsnwh/yFrn/AK8p/wD0CtaP/kkTf9fJ/wDQhXpVfjXqv1PMo/A/R/oZel/8ijqn+6v/AKEK6b4M/wDIxXv/AF7j/wBCrmdM/wCRS1T/AHV/9CFdN8Gf+Rivf+vcf+hCpxH8Gp/XYrDfx6f9dze+M/8AyBrP/rr/AENePW//AB8J/vV7D8Z/+QNZ/wDXX+hrx63/AOPiP/epYD/d18x5h/vL+R7F8T/+RBsfpF/Ku80L/kXtP/69o/8A0EVwfxP/AORBsvpF/Ku80L/kXtP/AOvaP/0EV5FX/d4+rPZpf7xL0RwXxp/5A+n/APXV/wCQrxqvZfjT/wAgfT/+ur/yFeNV7GX/AO7r5ni5j/vD+R6N4W/5JD4j+v8A8TVH4Vf8jLcf9ezfzFXvC/8AySDxH9f/AImqPwq/5Gaf/r2P8xWcvgrev6I0j/Eo+n6s46+/5CNz/wBdW/ma+ntH/wCQHY/9e0f/AKCK+Yb7/kI3P/XVv5mvp7R/+QHY/wDXtH/6CKwzP4IG+V/HM8v+NX+t0/6t/IV2mm/8kytf+vEf+g1xfxq/1un/AFb+QrtNN/5Jla/9eI/9BrCf+7UvU6Kf+9VfQj+HUaP4LsGZQSqAqSOnFcvon/JbNY/3/wDCuq+HH/Ik2X+4P5Vyuh/8ls1j/f8A8KI/HW9H+Y5fBR9V+Ra+L/8Ax62P++P61g/Fz/V+H/8Ar0P/ALLW98X/APj0sf8AroP61g/Fz/V+H/8Ar0P/ALLW+F/5df8Abxz4v/l7/wBunAX5xcoR18tf5V7n8LdVn1Lwigun3yQyMgOf4RjArwy//wCPhf8Armv8q9k+D0YHheRx1aVga3x6Tw9zny5tYiyPQ6KKK+ePpAooooAKKKKACiiigDyLxdawXGu+JHmjV2hsC8ZYZ2ncORU3wW/1V/8A74/lVvU9Ok1bxd4hsYCFknsCqk9vmFVvg0hi/tKNuqS7T+Ar2ZS/2WS9DxIx/wBri/UgvQR8cmJHBC4/IVn/ABI/5DOsf9u/8q3NX/5LHa/7v+FYnxGRpNe1ZEGWY24A9Tirou9SH+FfmiKytTn/AIn+TM25iM2t6dGgyz2Kqo9SUrofg9ZT2PiDV4LqMxyRxKrA9iGqhJbNa+NtDikGGFrFkeh212nhf/koWv8A+6P/AEI0V6n7lxXVfqGHp/vlJ9H+h29c74+/5EbVP+uBroq5zx9/yI2qf9cDXkUf4sfVHs1v4UvRl3wv/wAi1Zf9cxWtWT4Y/wCRas/+uYrWqanxsqn8C9Dyj42/6vSvrJ/SvK4rdpYJpV6RAE/icV7F8XdGv9UtrCSwtmmS3EjSlSPlGB/hXklpPHHp97G5w8iqEHrg19Dgpf7Orf1qfN4+P+0tv+tD6B8Kf8k50/8A68f6GvGH/wCSen/sLf8Aslez+FP+Sc6f/wBeP9DXiLXcX/CGm03fvf7S8zb7bcVy4RXnP/F/mdeMdqcP8L/QJtLW+1TVSzbfstsZh7kAf410Xwfs5T4ra6MbeWsDrvxxziqEa7dX8RD/AKhzfyWvTPhaijwPbMAASWyfXk1riqrjQa72X4GOFoqVdPtd/idlVbUYnn0u6ijGXkhdVHqSpFWaK8FOzufQtXVj5yPhu/03TZpNThaNDMIVBP8AECM/zr3Gxto7TwRFbwghI7baoPpXP/Fb/kCWf/Xcf0rpoefCi/8AXvXo4itKtThJ9zzMPRjRqTgux842f/IaT/rqa24P+Sb6p/2E4v8A0FqxbIZ1yMf9NT/Ou98UeFT4X+HkymcTfa7yKXgdPlPFevVnFSjF7u35njUYScZSWyT/ACKvw9022l8N+INQYMbiC2aNDngBlOf5VwjxKtnFIPvMSD+Fej/DRd3g3xMCCQY+g6n5WrzeV/lEYBGxjwaVJt1Z+q/IdZJUab8n+Zq6T/yLutf7kX/oVb3wtRk8YQ7hjcuR9Oals9OtR8Grq/WFBctcFGlxyQGGB+tHwyjaPxhbb23bogR7DnioqzUqVS3n+RpSg41aV/L8z13WvDOl65Cy31qjuRw4ADD8a+f/ABL4Zv8Aw1f+TfRbUky0TA53LmvpeuI+Jvhy517SIPsEPmTRyDJ9F5ry8FiZU58rejPWx2FjUg5xWqPD5r24vLe1tXO9LcFYlA55OTUMJ8u5QvxtYZ9ua7L4XafBc+O/IvYUlEUTsA4zhgRzUXxB8MHw1rizK6SRXTNIqAdOckH869r20FV9l8zwvYzdL23nY9a1HTrfWvh0ILjcYvsayjaccquRXzxAM3EYP98fzr6a0RVufC9ikijZJaoGXtgr0rz3x58PrDT9NXVNJC24hkBkjx94EgDFeXgsRGnKVOXV6HrY7DyqRjUj0Wp6H4eVU8O2KoAFEQwB2rSrP0D/AJF+y/65CtCvLn8TPWh8CCuP+F//ACJY/wCvy5/9GtXYVx/wv/5Esf8AX5c/+jWqCzsKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAqlrP8AyAr/AP69pP8A0E1dqlrP/ICv/wDr2k/9BNAGN8N/+Sa6D/15p/Kumrmfhv8A8k10H/rzT+VdNQAV83+Ov+Ryvf8AeH8q+kK+b/HX/I5Xv+8P5V6uWfxH6HkZr/Cj6jPCH/IVuf8Aryn/APQK2I/+SRN/18n/ANCFY/hD/kK3P/XlP/6BWxH/AMkhb/r5P/oQr0qvxr1X6nl0fgfo/wBDJ0z/AJFPVP8AdX/0IV0/wY/5GK9/69x/6EK5jTP+RT1T6L/6EK6f4Mf8jFff9e4/9CFRif4NT+uxphv49P8Arub3xn/5Atn/ANdf6GvH7f8A4+Y/96vYPjP/AMgWz/67f0NeP23/AB8x/wC9RgP93QZh/vL+R7F8T/8AkQLL6Rfyru9C/wCRe0//AK9o/wD0EVwnxP8A+Sf2X0i/lXd6F/yL2n/9e0f/AKCK8ir/ALvH1Z7NL/eJeiOC+NP/ACB9P/66v/IV41Xs3xp/5A2n/wDXV/5CvGa9jL/93XzPFzH/AHh/I9G8L/8AJH/Ef1/+Jqj8Kf8AkZp/+vZv5ir3hf8A5I/4j+v/AMTVL4U/8jNP/wBex/mKzl8Fb1/RGkf4lH0/VnG33/IRuf8Arq38zX09o/8AyA7H/r2j/wDQRXzDff8AIRuf+urfzNfT2j/8gOx/69o//QRWGZ/BA3yv45nl/wAav9dp/wDwL+QrtNN/5Jla/wDXiP8A0GuL+NX+u0/6t/IV2mm/8kytf+vEf+g1hP8A3al6nRT/AN6q+g34cf8AIk2X+4P5Vyuh/wDJbNY/3v8ACuq+HH/Ik2X+4K5bQ/8Aktms/wC9/hSj8db0f5jl8FH1X5Fn4v8A/HpY/wDXQf1rB+Ln+r8P/wDXof8A2Wt74v8A/HnY/wDXQf1rB+Ln+r8P/wDXof8A2WujC/8ALr/t458X/wAvf+3Tz+//AOPhf+ua/wAq9n+D/wDyKbf9dmrxi/8A+Phf+ua/yr2f4Pf8io//AF2aujH/AO7nNl/+8noNFFFfOn0oUUUUAFFFFABRRRQBw2nf8lR1X/r0P/oQrI+EX/Hzq/8A18GtfTv+So6r/wBeh/8AQhWR8Iv+PnV/+vg16kv4M/SJ5Mf40PWQur/8litf93/Csnx3/wAjZf8A/XS1rW1j/ksVp/u/4Vk+O/8Akbb/AP66WtbUfih/h/UxrfBP/F+hPrX/ACUnSf8Ar3i/lXT+F/8Akoev/wC4P/QjXMaz/wAlJ0n/AK94v5V0/hf/AJKHr/8AuD/0I1nV/hf9u/qaUf4v/b36Hb1znj7/AJEbVP8Arga6Ouc8ff8AIjap/wBcDXnUf4sfVHp1/wCFL0Zd8Mf8i3Z/9cxWtWT4Y/5Fuz/65itapqfGyqfwL0KWs/8AICv/APr2k/8AQTXzXY2gn02/lMZZolTaQOmWxX0prP8AyAb/AP69pP8A0E1xHwo0yzuvBDPcQJI0lwwbI6gYIr0MJW9jSlLzR52Mo+3rRh5M6TwpGV+H+nRyAqfsYDD04rwO/aCCaWxgDNtutyue4xX00sarH5aqAuMAD0rwt7GB/jYbNowYDfbSnbG2rwNRc1ST9TPH0nyU4r0GSLt17xKPTTm/9BWvSfhd/wAiJafVv/QjXAatGI/GPi1AMBbFwB+C13/wu/5ES0+rf+hGqxbvQT9PyJwatiGvX8zsKKKK8c9oyfEPh638RWSW90zIEcOpXrn/ACKtTwLBo8kMf3UiIH5VcqG8GbKb/cP8qtSdlHoQ4xTcurPmOx/5D0f/AF2/rXuHj/RbvXPA8cFgm+WMpJsHVgB0FeH2P/Iej/67f1r6dtv+POH/AK5r/KvZx83TnCa6HiZdBVIVIPqeefDjwzfaf4U1L7Wmx74ELEfvLgEc149qERh1K5ibgpKyn8DX1SAAMAYHtXy7rv8AyMOof9fMn/oRp4Gq6tScn1JzCjGlShFdLnd2ClvgLdgDJ+1Hp/vLUHw6Xb4wssjB+zr/AFrsvhPDHP8AD8RzIHQ3MmVI47VkaXGkXxhnSNQqrwAO3WodT+LT9WaKl/BqeiPU6CARg9KKK8U9w5rRfA2maFrs2q2ZfzpQRtOMLnriuQ+Llm19rWh2y8GZimfTJAr1Sq9xYWt1cRTXEKySQ/cY/wANdNPESjVVSWtjlq4aMqTpx0uJptqbHS7a0J3GGJY8+uBisL4hf8iVd/7yf+hCumrmfiF/yJV3/vJ/6EKii71ovzLrK1GSXY1tA/5F+y/65CtCs/QP+Rfsv+uQrQrOfxM0h8CCuP8Ahf8A8iWP+vy5/wDRrV2Fcf8AC/8A5Esf9flz/wCjWqSzsKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKhuru3sbdp7yeOCJfvPIwUD8TQBNRVey1Cz1GHzdPuobmPpvicMPzFQXuu6Vpswi1DUrW2kYZCTTKpP4E0AX6paz/AMgK/wD+vaT/ANBNWbe5huoVmtpUmjbo6NkH8araz/yAr/8A69pP/QTQBjfDf/kmug/9eafyrpq5n4b/APJNdB/680/lXTUAFfN/jr/kcb7/AHh/KvpCvm/xz/yON7/vD+Verln8R+h5Ga/wo+ozwj/yFLn/AK8pv/QK2I/+SQt/18n/ANCFY3hH/kKXP/XlN/6DWzH/AMkhb/r5P/oQr0qvxr1X6nl0fgfo/wBDJ0z/AJFPU/ov/oQrp/gx/wAjFff9e4/9CFcxpn/Ip6n9F/8AQhXUfBj/AJGK+/69x/6EKjE/wan9djTDfx6f9dze+M//ACBbP/rt/Q149bf8fMf+8K9h+M//ACBLP/rt/Q149bf8fUf+8KMB/u6DMP8AeX8j2L4n/wDJP7L6Rfyru9C/5F7T/wDr2j/9BFcJ8T/+Sf2X0i/lXd6F/wAi9p//AF7R/wDoIryKv+7x9WezS/3iXojg/jT/AMgbT/8Arq/8hXjNezfGj/kDaf8A9dW/kK8Zr2Mv/wB3XzPFzH/eH8j0fwv/AMkf8R/X/wCJqj8Kf+Rnn/69j/MVe8L/APJHvEf1/wDiao/Cj/kZ5/8Ar2P8xWcvgrev6I0j/Eo+n6s42+/5CNz/ANdW/ma+ntH/AOQHY/8AXtH/AOgivmG//wCQjc/9dW/ma+ndG/5Adj/17x/+gisMy+CBvlfxzPMPjT/rtP8Aq38hXaab/wAkytf+vEf+g1xfxp/12n/Vv5Cu003/AJJla/8AXiP/AEGsJ/7tS9Top/71V9Bvw4/5Emx/3BXLaH/yWzWf97/Cup+HH/Ik2P8AuCuW0L/ktms/73+FKPx1vR/mOXwUfVfkWvi//wAedl/10H9awPi5/q/D/wD16H/2Wt/4v/8AHlZf9dB/WsD4uf6vw/8A9eh/9lrowv8Ay6+Zz4v/AJe/9unn99/r1/65r/KvZvg9/wAiq/8A12avGb7/AF6/9c1/lXs3we/5Fd/+urV0Y/8A3c5sv/3k9Cooor50+lCiiigAooooAKKKKAOG07/kqOq/9eh/9CFZHwi/4+NX/wCvg1r6d/yVHVf+vQ/+hCsj4Rf8fGr/APXwa9SX8GfpE8qP8aHrIXWP+SxWn+7/APE1k+PP+Ruvv+ulrWvrH/JYbT/d/wDiayPHn/I333/XS1raj8cP8P6mFb4J/wCL9CxrP/JSNJ/694/5V03hj/komvf7g/8AQjXNaz/yUjSf+veP+VdL4Y/5KJr/AP1zX/0I1nV/hf8Abv6mtL+L/wBvfodvXOePv+RG1P8A64GujrnPH3/Ijan/ANcDXnUf4sfVHo1/4UvRl3wx/wAi3Z/9cxWtWV4Y/wCRbs/+uYrVqanxsun8CEdFkjZHGVYEEeoqGzsrewg8m0iWKPOdqjvU9FTd2sVZXuFeMXFo9t8doHcqRNeb1wegx3r2evLvENqlv8aNDdOszb2+vNdmDlZyXdM4cbG8YPtJD/EvhW6s7nxRr07p5NxbMsSqckjA5P5VvfC7/kRLT6t/M1oeO/8AkR9V/wCvdqz/AIXf8iHafVv/AEI1Uqkp4a77pfgKNONPFWj2b/E7CiiiuA9AKiuf+PSb/cb+VS1Fc/8AHpN/uN/KmtxPY+aLF0/tNEx8/wBpznHavpe1/wCPOH/rmv8AKvmSxT/idI//AE3xX03a/wDHnD/1zX+Vevmf2Txsr+0S14j4c0az1PWfFE95F5jW3ntHnsfm/wAK9urgPCfhO+sdW8Qi/ASK+LCNlOeG3f41yYaooQnrbb8zsxNN1Jw0utfyJvhD/wAiGv8A18yf0rIsP+Sy3P1/xruPDHh6Lwzoq6fBIZFDl9xGMk1xFh/yWS5+v+NaRkp1Ksls0zKUHCnSjLdNHp9FFFecemFFFFABXM/EL/kSrv8A3k/9CFdNXM/EL/kSrv8A3k/9CFbUP4sfVGNf+FL0ZraB/wAi/Zf9chWhWfoH/Iv2X/XIVoVnP4mXD4EFcf8AC/8A5Esf9flz/wCjWrsK4/4X/wDIlj/r8uf/AEa1SWdhRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABXD+O1F94g8O6Zcc2s14rSoekgwRtPqPau4rnvFnhybXre1l0+5S1v7KYT28zqWUMAfvAdRz0oAwvD8Eei/ErUNN05BFZ3EfmmJBhUKgAYHbrVTxVomo/8J0msR+HbfWrOOBldZZFG3gdAQc9K2NE8Ka1p091qN7qVrcatdSKXmEJEaoBgqq54zx3q3reneL7m6P9iaxp9rbsgDLPas7ZxyQQRigC54U1ew1rQUudKhWCFXaJolXaEdThl/A1T8Y+KtP0PTbm2vUu2ea3cKYbZ5Byp6kDirnhTw7H4Y0MWMcnmM8rzyv/AHpHOWI9s1d1n/kBX/8A17Sf+gmgDF+Gx3fDPQCO9kn8q6euZ+G//JNdB/680/lXTUAFfN/jn/kcb3/eH8q+kK+bvHP/ACON9/vD+Verln8R+h5Ga/wo+ozwl/yFLn/rym/9Araj/wCSQt/18n/0IVi+Ev8AkKXH/XlN/wCg1tR/8kgf/r5P/oQr0qvxr1X6nl0fgfo/0MfTP+RU1P6L/wChCup+C/8AyMV9/wBe4/8AQhXLaZ/yKmp/Rf8A0IV1PwX/AORhv/8Ar3H/AKEKnE/wan9djTDfx6f9dze+M/8AyBLP/rt/Q149bf8AH1H/AL1ew/Gf/kCWf/Xb+hrx61/4+o/94UsB/u6DMP8AeX8j2P4n/wDJP7L/ALZfyrutC/5F7T/+vaP/ANBFcL8T/wDkn9n/ANsv5V3Whf8AIvaf/wBe0f8A6CK8ir/u8fVns0v94l6I4P40f8gbT/8Arq38hXjNezfGj/kDWH/XVv5CvGa9jL/93XzPFzH/AHh/I9H8Lf8AJHvEf1/+Jqj8KP8AkaJ/+vc/zFXvC3/JHfEf+9/8TVL4T/8AI0T/APXuf5is5fBW9f0RpH+JR9P1Zxt//wAhK5/66t/M19OaN/yArH/r3j/9BFfMd/8A8hK5/wCurfzNfTmjf8gKx/694/8A0EVhmXwQN8r+OZ5h8af9dp//AAL+QrtNN/5Jla/9eI/9BrivjT/rtP8A+BfyFdrpv/JMrX/rxH/oNYT/AN2pep0U/wDeqvoN+HH/ACJNj/uCuW0L/ktms/73+FdT8OP+RJsf9wVy+hf8ls1n/e/wpR+Ot6P8xy+Cj6r8iz8X/wDjxsv+ug/rWB8XP9X4f/69D/7LW/8AF/8A48bL/roP61gfFz/V+H/+vQ/+y10YX/l18znxn/L3/t08/vv9ev8A1zX+Vey/B7/kV5P+urfzrxm9/wBev+4v8q9m+Dv/ACLEn/XVv510Y/8A3c5sv/3k9Dooor50+lCiiigAooooAKKKKAOH07/kqOq/9eh/9CFY/wAIv+PjV/8Ar4NbGnf8lR1X/r0P/oQrH+EX/Hxq/wD18GvUl/Bn6RPKj/Gh6yHax/yWG0/3P/iayPHv/I333/XS1rX1n/ksFn/uf/E1k+Pf+Rwvf+ulrW1H44f4f1MK3wT/AMX6FjWf+SkaR/17x/yrpfDH/JRde/65r/6Ea5vWP+SkaR/17x/yrpPDH/JRte/65r/6Eayq/wAL/t39TWl/F/7e/Q7euc8ff8iNqf8A1wNdHXOeP/8AkRtT/wCuJrz6P8WPqj0a/wDCl6MveGP+Rbs/+uYrVrK8Mf8AIt2f/XMVq1NT42XT+BBRRRUFhXm3ir/ksfhv/dH82r0mvOfFMUjfGDw46oxVVGWA4HLV1YX436P8jkxfwL1X5nTeOv8AkRtV/wCvdqz/AIX/APIh2f1b/wBCNaHjr/kRtW/692qh8L/+RDs/q3/oRpr/AHV/4v0E/wDe1/h/U6+iiiuQ7AqK5/49Jv8Acb+VS02RPMidOm5SKa3E9j5vsEHlh8DP2/Gce1fRtr/x5w/9c1/lXi3iDwq/hWS3he4WZbi7Eq4GNowRg17Ta/8AHnD/ANc1/lXpY6amoyjtqeXl8JU3KMt9CWiiivMPVCvMLD/kslz/AJ7mvT68xsP+SyXP+e5rrw20/Q48VvD1PTqKKK5DsCiiigArmfiF/wAiVd/7yf8AoQrpq5n4hf8AIlXf+8n/AKEK2ofxY+qMa/8ACl6M1tA/5F+y/wCuQrQrP0D/AJF+y/65CtCs5/Ey4fAgrj/hf/yJY/6/Ln/0a1dhXH/C/wD5Esf9flz/AOjWqSzsKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAqlrP/ACAr/wD69pP/AEE1dqlrP/ICv/8Ar2k/9BNAGN8N/wDkmug/9eafyrpq5n4b/wDJNdB/680/lXTUAFfN3jn/AJHG+/3h/KvpGvm7xx/yOF9/vD+Verln8R+h5Ga/w4+ozwl/yFLn/rym/wDQa2o/+SQP/wBfJ/8AQhWJ4T/5Clx/15zf+g1tx/8AJIH/AOvk/wDoQr0q3xr1X6nl0fgfpL9DH03/AJFXU/ov/oQrqfgv/wAjDf8A/XuP/QhXLab/AMirqX0X/wBCFdV8F/8AkYb/AP69x/6EKnE/wan9djTC/wAen/Xc3fjP/wAgOz/67f0NePWv/H1H/vCvYfjP/wAgO0/67f0NePWv/H1H/vClgP8Ad18wzD/eX8j2P4n/APJPrP8A7ZfyrutC/wCRe0//AK9o/wD0EVw3xP8A+SfWf/bL+VdzoX/Ivaf/ANe0f/oIryKv+7x9WezS/wB4l6I4P40f8gWw/wCurfyFeM17N8aP+QLYf9dW/kK8Zr2Mv/3dfM8XMf8AeH8j0fwt/wAkd8R/73/xNUvhP/yNE3/Xuf5ir3hb/kjniP8A3v8A4mqPwn/5Gmb/AK9z/MVnL+HW9f0RpH+JR9P1Zxt//wAhK5/66t/M19OaL/yArH/r3j/9BFfMd/8A8hK5/wCurfzNfTei/wDICsf+veP/ANBFY5l8EDfK/jmeYfGn/X6f/wAC/kK7XTf+SZWv/XiP/Qa4r40/6/T/APgX8hXa6d/yTK1/68R/6DXPP/dqXqdFP/eqvoN+HH/Ik2P+4K5fQv8Aktetf73+FdR8OP8AkSbH/cFcvoP/ACWvWv8Ae/wpR+Ot6P8AMcvgo+q/Is/F/wD48LL/AK6D+tYHxc/1fh//AK9D/wCy1v8Axf8A+QfZf9dR/WsD4uf6vw//ANeh/wDZa6ML/wAuvmc+M/5e/wDbp59e/wCvX/cX+Vey/B3/AJFmT/rq3868avf9cv8AuL/KvZfg7/yLcv8A11b+ddGP/wB3ObL/APeT0SiiivnT6UKKKKACiiigAooooA4fTv8AkqOq/wDXof8A0IVj/CL/AF+r/wDXwa2NO/5Kjqv/AF6H/wBCFZHwi/1+r/8AXwa9SX8GfpE8qP8AGh6yHaz/AMlgs/8Ac/8Aiax/Hv8AyON7/wBdLWtjWf8AksFn/uf/ABNY/j7/AJHK9/37WtqPxw/w/qYVvgn/AIv0Lesf8lH0j/r3j/lXR+GP+Sja9/1zX/0I1zmsf8lH0j/r3j/9Bro/DP8AyUbXv+ua/wDoRrKr/C/7d/U1pfxf+3v0O3rnPH//ACI2p/8AXE10dc54/wD+RG1P/ria8+j/ABY+qPRr/wAKXoy94Y/5Fuz/AOuYrVrK8M/8i3Z/9cxWrU1PjZdP4EFFFFQWFRtbxPMsrRqZF6MRyKkooAwPHP8AyI+rf9ezVn/C/wD5EOz+rf8AoRrQ8c/8iPq3/Xs1Z/wv/wCRCs/q3/oRrrX+6v8Axfocb/3tf4f1OvooorkOwKKKKAPNvip/x+aV/wBdB/WvRLX/AI84f+ua/wAq87+Kn/H5pX/XQf1r0S1/484f+ua/yrrq/wACn8zjo/x6nyJaKKK5DsCvMrD/AJLJc/57mvTa8ysP+Sx3P0/qa68NtP0OPFbw9T02iiiuQ7AooooAK5n4hf8AIlXf+8n/AKEK6auZ+IX/ACJV3/vJ/wChCtqH8WPqjGv/AApejNbQP+Rfsv8ArkK0Kz9A/wCRfsv+uQrQrOfxMuHwIK4/4X/8iWP+vy5/9GtXYVx/wv8A+RLH/X5c/wDo1qks7CiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKpaz/wAgK/8A+vaT/wBBNXapaz/yAr//AK9pP/QTQBjfDf8A5JroP/Xmn8q6auZ+G/8AyTXQf+vNP5V01ABXzd44/wCRwvv94fyr6Rr5u8cf8jhe/wC8P5V6uWfxH6HkZr/Dj6kfhP8A5Clx/wBec3/oNbcX/JH3/wCvk/8AoQrE8J/8hO4/685v/Qa3Iv8Akj7/APXyf/QhXpVvjXqv1PLo/A/R/oYum/8AIq6l9F/9CFdX8Fv+Rhv/APr2H/oQrlNN/wCRW1L6L/6EK6v4Lf8AIw3/AP17D/0IVOJ/g1P67GmF/j0/67m98Z/+QFaf9dv6GvHbX/j6j/3hXsXxn/5AVp/12H8jXj1r/wAfcf8AvClgP93XzDMP95fyPY/if/yT6z/7ZfyrudC/5F7T/wDr2j/9BFcN8T/+Se2f/bL+VdzoX/Ivaf8A9e0f/oIryKn+7x9WezS/3iXojhPjR/yBbD/rq38hXjFez/Gf/kC2H/XVv5CvGK9jL/8Ad18zxcx/3h/I9I8Lf8kc8R/73/xNUfhN/wAjTN/17n+Yq94X/wCSOeI/97/4mqPwm/5Gqb/r3P8AMVnL+HW9f0RrD+JR9P1Zxt//AMhK5/67P/M19N6L/wAgGx/694//AEEV8yX/APyErn/rs/8AM19N6J/yAbH/AK94/wD0EVjmXwQNsr+OZ5h8af8AX6f/AMC/kK7XTv8AkmNr/wBeI/8AQa4r40/6/T/+BfyFdrp3/JMbX/rxH/oNc8/92pep0U/96q+g34cf8iTY/wC4K5jQf+S161/vf4V0/wAOP+RJsf8AcFcxoP8AyWvWv97/AApR+Ot6P8xy+Cj6r8iz8X/+QfZf9dR/Wuf+Ln+r8P8A/Xof/Za6D4v/APIPsv8ArqP61z/xc/1fh/8A69D/AOy10YT/AJdfM58Z/wAvf+3Tz69/1y/7i/yr2T4O/wDIty/9dG/nXjd5/rl/3F/lXsfwc/5F2X/rof5104//AHc5cv8A95PRqKKK+cPpgooooAKKKKACiiigDh9O/wCSo6r/ANeh/wDQhWR8Iv8AXav/ANfBrX07/kqOq/8AXof/AEIVkfCL/Xav/wBfJr1JfwZ+kTyo/wAaHrIdrP8AyWCy/wBz/Csjx/8A8jle/wC/a1r61/yV+y/3P/iax/H/APyOd5/v2tbUfjh/h/UwrfBP/F+hc1j/AJKPpH/XvH/6DXReGf8Ako+vf9cl/wDQjXO6v/yUfSP+veP/ANBrovDP/JSNe/65L/6Eayqfwv8At39TWl/F/wC3v0O3rnPH/wDyI2p/9cTXR1zfj/8A5EbU/wDria8+j/Fj6o9Gv/Cl6Mv+Gf8AkW7P/rmK1ayvDP8AyLdn/wBcxWrU1PjZdP4EFFFFQWFFFFAGB45/5EbVv+vZqz/hf/yIVl9W/wDQjWj44/5EbVv+vZqz/hh/yINl9W/9CNda/wB1f+L9Djf+9r/D+p11FFFch2BRRRQB5t8VP+PzSv8ArqP616Ja/wDHnD/1zX+VeefFT/j80r/rqP616Ha/8ecP/XNf5V11f4FP5nHR/j1PkS0UUVyHYFeZ2H/JY7n6f1NemV5nY/8AJY7n6f1NdeG2n6HHid4ep6ZRRRXIdgUUUUAFcz8Qv+RKu/8AeT/0IV01cz8Qv+RKu/8AeT/0IVtQ/ix9UY1/4UvRmtoH/Iv2X/XIVoVn6B/yL9l/1yFaFZz+Jlw+BBXH/C//AJEsf9flz/6Nauwrj/hf/wAiWP8Ar8uf/RrVJZ2FFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFRXN1b2cDTXc8cES9XkYKB+JqWuH8eKL7X/D2l3HzWk14pljPSQYI2n1HtQB2Npf2moRebY3UNzH/AHoXDD8xTL3VLDTtv9oXtva7vu+dKEz+dcX4egi0T4k6hpenIIrOePzTCgwqFQBwO3Wmf2ZaeJviZrFvrMK3MFjFGkMcgyBvTJIB78UAd/HKk0ayQurowyrKcgiqms/8gK//AOvaT/0E1y3wruZZ/C91HM5cW+o3MMZPZFkIUfgBWh4w8U6domm3NtfC5Mk1u4Xyrd5Byp6kDigA+G//ACTXQf8ArzT+VdNXMfDY7vhnoBHQ2Sfyrp6ACvm7xx/yOF7/ALw/lX0dNIYoWcLuKjOB3r5z8UWmpX3iK6uf7NuUDtwBGW6e4Ferluk5NnkZprTil3IfCn/ITuP+vOb/ANBrci/5I/J/18n/ANCFZejaXqunTS3LabO6vbumNhB+ZceldJbaFqMnwmeFbWTzTcFghGDjcO1ejWlHmTv1X6nm0Yy5WrdH+hyum/8AIral9F/9CFdX8Fv+Rg1D/r2H/oQrmrLTdVj0m9s/7NnJkwN2wjGDn0rsPg9pd7aaxfz3NtJDGYQgLqVydw9ajEyXsZ6/1oXhYy9vT0/rU0/jP/yArT/rt/Q149af8fcX+8K9t+K2k3mq6Pax2MJlYTZIHbg15HbaBqi6pFAbGcPvAz5Zx+dLAyiqFr9ysfCTxF0ux6l8T/8Akntp/wBsv5V3Ohf8i9p//XtH/wCgiuT+IWlXmoeB7W2tITJKpiBUdsCuv0iJ4NEsopBh0t0Vh6EKK8io17CK82evTT+sSfkjgfjP/wAgWx/66t/IV4xXufxX0q81TRrQWMLSmORiwHbOK8ibwvrKzJEbCbc5wPkOK9fATiqCTfc8fMISddtLsdl4X/5I34j/AN7/AOJql8Jv+Rqm/wCvc/zFdB4d8P6lb/C3XbCW3ZbmZj5aHv0rO+Fuh6jaeIpZrm1kij8grlxjnIrOU48lXXr+iNYwl7Sjp0/Vnnt//wAhK5/67P8AzNfTeif8gGx/690/9BFfO2q+HtVh1KfdYzkNK2CsZPevWNP8b3tppttbnw/dMYolTOeuBj0pY6Lqwjyajy+SpTnz6GD8af8AX6f/AMC/kK7XTv8AkmNr/wBeI/8AQa84+IN/qHiU20iaPcwCHOflLZz9BXQ2Xim+j8IwaYNCuSy2wi38jPGM4xWM6cnQpx6pm0KsViKkujR0vw5/5Emx/wCuYrl9B/5LXrX1/wAK67wHZz2PhCyhukMcgjGVPauf0bRr6D4tatfSwFbaXlH7HpWEZLnq69H+ZvKL5KOnVfkRfF//AJB9l/11H9a5/wCLn+r8P/8AXof/AGWut+J2k3mqWNmllCZCJRnHbrWD8UtD1C8ttGktbd5RBb+W+0ZIJx/hXRhZRXs7vuc+LhJ+1sux5def65f9xf5V7J8HP+Rdm/66H+deYS+GdZnkBWwmGFA+6fSu38D6rqPhbTZLabRbiYsxOV4/pXXjLVKPLF6nHgr06/NJWR69RXE/8J/ef9C9df8AfX/1qP8AhP7z/oXrr/vr/wCtXifVqvb8Ue99Zpd/wZ21FcT/AMJ/ef8AQvXX/fX/ANaj/hP7z/oXrr/vr/61H1ar2/FB9Zpd/wAGdtRXE/8ACf3n/QvXX/fX/wBaj/hP7z/oXrr/AL6/+tR9Wq9vxQfWaXf8GdtRXE/8J/ef9C9df99f/Wo/4T+8/wCheuv++v8A61H1ar2/FB9Zpd/wY3Tv+So6r/16H/0IVkfCL/Xav/18mtDwu95qXjXUNTnsZLWKS2KKH9cim/DHSL3TJdV+2wmLfcErnuK65tKnOL3tE4oJyqwktryKmtf8lesv9z/4msb4gf8AI6Xn+/a10uraTey/FCzvI4SYFQ5fsOlYvjrStRufG0rW1o8kUzW5EgHA29a1oyjzx1+z+plXjLknp9r9B2r/APJR9H/690/9BrofDP8AyUjXv+uS/wDoRrO1TRL+Tx5pVykBMSQqrN6ELzSte33hzxzql4NLmu47pAqlDjGGJ9KiVpw5Y78v6mkbwnzS25v0PR65v4gf8iNqf/XE1m/8J/ef9C9df99f/WrL8R+Kb/W9AutPj0K5jadCoYnOP0rmpUKkakW117o6auIpypySfTsztfDP/It2f/XMVq1naBBJb6FaxTLtdYxkelaNc0/jZ1U/gQUUUVBYUUUUAYPjj/kRtX/69mrP+GH/ACINl9W/9CNavi62lvPB+p29uu+WS3ZVUdzVL4e2Vxp/gu0t7uMxyqWyp7cmupNfVmvP9Dkaf1pP+7+p01FFFcp1hRRRQB5v8VP+PvSv+uo/rXodr/x5w/8AXNf5VxHxG0m81K60w2cJkCyjdjt1ruLdStrErdQgB/Kuqq06MF6nJSTVeb9CSiiiuU6wrzSx/wCSxXP+7/U16XXA2ek3ifFS4vGhIgK5D9uprqw7SU79jkxCbcLdzvqKKK5TrCiiigArmfiF/wAiVd/7yf8AoQrpq57x1bS3fhG6ht0LyMyYUDr8wrWjpVj6oxr60pejNHQP+Rfsv+uQrQqjokbRaHaJINrLGAQe1XqifxMuHwoK4/4X/wDIlj/r8uf/AEa1dhXH/C//AJEsf9flz/6NapLOwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigArnvFnhyfXYbSbT7hLW/sZhPbyyKSoYA/eA6jmuhooA47RPCutafcXWpX2o2lxqt1IpeVYmEaoBgqq5yM8Ua74U1mXW/7W8NalbWV1NF5dz58TOr8YBABHIrsaKAMbwt4fTw1ogsUfzHaRppXHRpHOWP51c1n/kBX/8A17Sf+gmrtUtZ/wCQFf8A/XtJ/wCgmgDG+G//ACTXQf8ArzT+VdNXmvgf4g+FtK+H+j22o6vHbzQWqJIjxv8AKfQ8V0X/AAsrwj/0Gov+/b//ABNAHUUVy/8Awsnwj/0Gov8Av2//AMTR/wALJ8I/9BqL/v2//wATQB1FFcv/AMLJ8I/9BqL/AL9v/wDE0f8ACyfCP/Qai/79v/8AE0AdRRXL/wDCyfCP/Qai/wC/b/8AxNH/AAsnwj/0Gov+/b//ABNAHUUVy/8Awsnwj/0Gov8Av2//AMTR/wALJ8I/9BqL/v2//wATQB1FFcv/AMLJ8I/9BqL/AL9v/wDE0f8ACyfCP/Qai/79v/8AE0AdRRXKt8TfByuqtrkIZvugxvz/AOO07/hZPhH/AKDUX/ft/wD4mgDqKK5f/hZPhH/oNRf9+3/+Jo/4WT4R/wCg1F/37f8A+JoA6iiuX/4WT4R/6DUX/ft//iaP+Fk+Ef8AoNRf9+3/APiaAOoorl/+Fk+Ef+g1F/37f/4mj/hZPhH/AKDUX/ft/wD4mgDqKK5f/hZPhH/oNRf9+3/+Jo/4WT4R/wCg1F/37f8A+JoA6iiuX/4WT4R/6DUX/ft//iaP+Fk+Ef8AoNRf9+3/APiaAOoorlY/id4OlXdHrkLDOMhH6/8AfNO/4WT4R/6DUX/ft/8A4mgDqKK5f/hZPhH/AKDUX/ft/wD4mj/hZPhH/oNRf9+3/wDiaAOoorl/+Fk+Ef8AoNRf9+3/APiaP+Fk+Ef+g1F/37f/AOJoA6iiuX/4WT4R/wCg1F/37f8A+Jo/4WT4R/6DUX/ft/8A4mgDqKK5f/hZPhH/AKDUX/ft/wD4mj/hZPhH/oNRf9+3/wDiaAOoorl/+Fk+Ef8AoNRf9+3/APiaa/xN8HJt365Cu44GY35P/fNAHVUVy/8Awsnwj/0Gov8Av2//AMTR/wALJ8I/9BqL/v2//wATQB1FFcv/AMLJ8I/9BqL/AL9v/wDE0f8ACyfCP/Qai/79v/8AE0AdRRXL/wDCyfCP/Qai/wC/b/8AxNH/AAsnwj/0Gov+/b//ABNAHUUVy/8Awsnwj/0Gov8Av2//AMTR/wALJ8I/9BqL/v2//wATQB1FFcv/AMLJ8I/9BqL/AL9v/wDE0f8ACyfCP/Qai/79v/8AE0AdRRXL/wDCyfCP/Qai/wC/b/8AxNNX4m+DnLBNchYqcMBG/B/75oA6qiuX/wCFk+Ef+g1F/wB+3/8AiaP+Fk+Ef+g1F/37f/4mgDqKK5f/AIWT4R/6DUX/AH7f/wCJo/4WT4R/6DUX/ft//iaAOoorl/8AhZPhH/oNRf8Aft//AImj/hZPhH/oNRf9+3/+JoA6iiuX/wCFk+Ef+g1F/wB+3/8AiaP+Fk+Ef+g1F/37f/4mgDqKK5f/AIWT4R/6DUX/AH7f/wCJo/4WT4R/6DUX/ft//iaAOoorlj8SvCABJ1uIAdT5b/8AxNInxM8HyIHj1yFlYZBEb8/+O0AdVRXL/wDCyfCP/Qai/wC/b/8AxNH/AAsnwj/0Gov+/b//ABNAHUUVy/8Awsnwj/0Gov8Av2//AMTR/wALJ8I/9BqL/v2//wATQB1FFcv/AMLJ8I/9BqL/AL9v/wDE0f8ACyfCP/Qai/79v/8AE0AdRRXL/wDCyfCP/Qai/wC/b/8AxNH/AAsnwj/0Gov+/b//ABNAHUVx/wAL/wDkSx/1+XP/AKNarH/CyfCP/Qai/wC/b/8AxNVfhXIs3gWOWMko91cMpIIyDI2DzQB2VFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUEZGDyKztetr670eWLS7xrK4OCsyqCVHfg8Vg/DXUNS1Dw5df2xetfXFvfzW/nuoUsqkAcDigC5400I6t4Su7Kwt4/Pk2bcIOzgn9BW3HZwLEgMEWQoB+QVwXxG12703X9Fs4/EJ0K1upSs04VTxtJ/i9xXQWNre3nhZk07xI99LMP3eobEyPcAcUAdB9kt/+eEX/AHwKPslv/wA8Iv8AvgVw+mXes6H4+ttCv9Zk1mK6tWnLSoqNEQwHRR0rvaAIvslv/wA8Iv8AvgUfZLf/AJ4Rf98CpaKAIvslv/zwi/74FH2S3/54Rf8AfAqWigCL7Jb/APPCL/vgUfZLf/nhF/3wKlooAi+yW/8Azwi/74FH2S3/AOeEX/fArk/iMutw6DLqGiavJp32SF5HEaK3mEDIHIrotBuJbvw7p1zcNvlmtY3dvVioJNAGTregtd+KvD95Bbx+RZyTGb5B0ZMD9a6D7Jb/APPCL/vgV5be6/dXHxJ1DTLvxo2i28MUbQQBIz5hLEEfMM9hXba/rR8P+G1ZZTd3ki7IMj5pm9QB+dAG59kt/wDnhF/3wKPslv8A88Iv++BXHfDLU9Y1HTNRTX7s3VzbXZi34AwNoOOPrXbUARfZLf8A54Rf98Cj7Jb/APPCL/vgVLRQBF9kt/8AnhF/3wKPslv/AM8Iv++BUtFAEX2S3/54Rf8AfAo+yW//ADwi/wC+BUtB6HHWgCL7Jb/88Iv++BR9kt/+eEX/AHwK4LSLnX9P+Ka6VqesyX1pcWUlwsLxqBGQwAAIGT1rofHWo3OleDb68srg200cZKygA7eDzzQBX8DeH30fQri31C3jEr31xMuUH3WkJX9DXSfZLf8A54Rf98CuK8BXhvreO7bxm2tkwK0tvsQCNiuT93niseDxNL4h1u4ZvFy6FHDdNbxWahGabY2MncM80Aem/ZLf/nhF/wB8Cj7Jb/8APCL/AL4FOhDLCodt7Act60+gCL7Jb/8APCL/AL4FH2S3/wCeEX/fAqWigCL7Jb/88Iv++BR9kt/+eEX/AHwKlooAi+yW/wDzwi/74FH2S3/54Rf98Cpa5/xjbarcaKzaNqcmmyRAu8kaKxIx0waANv7Jb/8APCL/AL4Fc/4p0FtSm0Y2lvGRa6jHPLhB9wZzT/AOo3ereAtJvtRmM91NDukkIA3HcRnj6VyPizX7qL4iRaXN4tbQLM2rOPkQ72BGPvCgD0v7Jb/88Iv++BR9kt/+eEX/AHwK4vxfq9/oXgyzls9UaXzbiOObUiq5jjbOXx04HNV/AevXeoeIL6zh1z/hIdOiRGW+2qMMRkr8vHXigDvPslv/AM8Iv++BR9kt/wDnhF/3wKlooAi+yW//ADwi/wC+BR9kt/8AnhF/3wKlooAi+yW//PCL/vgUfZLf/nhF/wB8CpaKAIvslv8A88Iv++BR9kt/+eEX/fAqWvPrqfX9K+J2kwz61LPp+oySj7GY1CoFXI5xmgDvPslv/wA8Iv8AvgVznhjQH07VvEM13bx7LzUDNDlB9zYB/MVtazqSaRo9zfS/dhTP49q4Twlq11rWoWt3c+MVM7nzJdHjCFUH93ON1AHon2S3/wCeEX/fAo+yW/8Azwi/74FebX+q+JNZudfv9H1V7K30d9kFsqKVuflB+YkZHPHFd34d1T+2dBtr3GGdcN/vDg/rQBe+yW//ADwi/wC+BR9kt/8AnhF/3wKlooAi+yW//PCL/vgUfZLf/nhF/wB8CpaKAIvslv8A88Iv++BR9kt/+eEX/fAqWigCL7Jb/wDPCL/vgUfZLf8A54Rf98CqHiG1v7zR5ItKvmsLjIInRQSo78HisT4ZanqOq+EXl1i7a8uYr2eAzMoBYI5A4H0oA6HUtPiuNKu4YrePfJC6r8g6lSBWd4O0X+yvBulWN7bxi4t7ZUkyg6isPxx4ne01e00a31VNIEgL3F62MxLjK4B4OSMVo6ba3994VePTvFD38sr5j1EImVHHAAGKAOl+yW//ADwi/wC+BR9kt/8AnhF/3wK4nRbzWNI8eHQNQ1aTWIpLTz/MlRVaM7sYwvau7oAi+yW//PCL/vgUfZLf/nhF/wB8CpaKAIvslv8A88Iv++BR9kt/+eEX/fAqWigCL7Jb/wDPCL/vgUfZLf8A54Rf98CpaKAIvslv/wA8Iv8AvgVIiLGu2NQq+ijApaKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAo6zqUelaVLdSw3E6qMbLeMyOc+gFcB8NfES2+nalbXWk6tA76hNcL5tkygo5GPx4r02igDlvEGu6VbLA+paJeXwkTdH5dj5xT6jtXN+HrnUPDPhjxHrMemXTxXFyZ7CxCMXCbQMbeq854r02igDzX4eXsM+pS3epWOq/2zefNLLc2bJHGOm1SeAOlelUUUAFFFFABRRRQAUUUUAcb8TNVFn4Tu7JLG+u5ruB0jFrbmTBxjnHSpfCPiWGbwzpkLafqUMkcEcLLNashDKoB69s9662igDz/AMV6tpUn22wbw7e3F/IhRJ0sCVycgHzO2DVa18A61deG9AaXXZLC/wBOtQrL5ImBfaQfvfWvSaKAPPPhbous6VNrZ1e9lmWS7O1ZLcR7zgfOP5V6HRRQAUUUUAFFFFABQTgZoooA8qk8Sq3xhtb0aPrH2aOzktWl+wtt3lgRz6cda7q91u0k0meefT7uaGMgPCbYlmB9F71t0UAeaaYia78QrC/0TSrrTLC3t5o7rzrcweYWXC4Xocc1hf2Wmiafquhz6Jd3OoXd/JPBcx25ZArvlf3nbFe0UUAZ3h+1ubLw9Y218++5ihVZGznLVo0UUAFFFFABRRRQAVg+MNXj0nQJjJa3lyZlZFS0gMrZx3AreooA89+G3iFLfwHp1jdaZqkE9qnlyLLaMvOSePUc1oeJdc0e2upIdQ8P3t9MyfLJFYGUY9N3auyooA8iOi6zY/DvSlvbWW5ihv8Az57VQXfyjIWAx1OFPStrwpF9v8dXGqaTpk+maZ5Ko0c0BhMjbcfc9jXodFABRRRQAUUUUAFFFFABXl3inxIo+JGhyppGryxafLKJpI7JmX5l2gg9xmvUaKAOd1cx+KPD9/psUNzEzxdZYigPPQV55YWT3UfhvSdP0a7s9Q064zd3LwFE24YcP/H1HWvZaKAPJp5tR8MN4k0oaZd3UmpOGsZIYS6H5APnYfd5zXoPhXTH0jw3a2kv3wu5h6E8kfrWxRQAUUUUAFFFFABRRRQBna7qcek6RLdSwXE6j5dltEZHOfYVwXwu18Wfh67tLvStVgl+3TzASWbKCruSuPwr06igDznxbp0UHi/TfE9zp1xfWhjKSwxwmRlG3j5O/JqrpF/qHhzw3r2tWmlXbR3Fy8lnZCJt4BIwdn8P09q9QooA85+HN3DJdTT31nqn9sXnz3E91aNGi/7Kk9uK9GoooAKKKKACiiqlzqun2cyw3l/bW8rfdSWZVY/QE0AW6KKZNPFbQtLcSpFGoyzuwUD8TQA+iq9pqFnfqzWN3BchTgmGQPj8qsUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAV5EfHGuR3Hi1dQ0W5lsbKRQXgu1RoV2Z4Pv14r12vJte0bxDbzeLbGx0Oe+i1ra0NxHIqqmI9uCCc9aAOhufH0tpf2Gk6ZotxqFzcWa3CL54U7dgPJI681Uh+Kj3Ni15b6BO9vDP9nun84DyX3bT2+bBz0q1pGg6jbeMtMvZrYrBDpywu+R8r+Wox+YrO0vwxq1v4E1ixls2W5uNSnmjTI+ZGkJB/KgDZ1f4hW1leJZ6bbLfXLQrOyNcrDtRuhy3Xoagf4mWv9i293b2Rmup7g2wthMoAkAyRv6dO9czdeB57LWbbWb3wyniBZdPhtZLQ7d0LJkk5Y45z+lbU+lxJ4Tjih8BEJJOXNhE0YaPj72c4z2oAj8XeMPENt4RW+t9Ea1uDcBPL+1I+VxndkcdeK3ZPFGrWmgW93caDtuHC7oZL2NMcddx4rj4/DHiS48H6qsltcrm482ysLiQM6JgDZkcdc1c8Q2eta2mk3d34ZuLm0t0CT6U8qEu2fvZzjp/OgDaj+JNs3hm+1V7JhLYOFntkmD7SQSPmHB4FVR8S7pLu0tbrw3cQzX8Xm2afaFbzhgHsPl6jrXOaR4N1iHRfE0K6ItgL24he2to9oG0IwPQ+9dZc6FqD+L/Cd2tsTBY2MsVw+R+7YooA/MUAMk+JUdv4bvdRu9KlhubKYRS2fmgsMttB3YxVjSvHsl5q1lZ6no02mrqA/wBDleUOJeM4wBxx61x3jLSNRsNN8Q3c1uUjuJ7fyGJGHIl//VWzp9pr3iTXPD0upaTJp9tozNKZnZSLgshX5QDx680Aek0UUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAV518W9GsJdDXU5LZGvEnhVJSASo8xen516LXFeP/C/iTxTbLZ6PqWn2lpuR2FxCzPuU56g9OBQBn+OPHt1pHiNNE025WzmFuLh5ns2uQQSRjavT61jXWvan4s8IxzXVvNLDp98FvtsDRfaotuSVQ84yRxz0rpJvCfif+0YtbttV0+PWvJEE7+S3kyIDnG3OevvWzHZeKl0SRX1KwbU2bKy+S3lDjptzmgDiPDGsWB+K9pZeHLN7PTptNkkmjMRjDyBlAO0gdBmvWK5bQPDGowa2+t+JLyC81LyzFE1uhVI0OMgA+4rqaACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigCtf6daapam21CBLiEsGKOOMg5B/OrCIsaBEG1VGAB2paKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooA//Z"}}},{"cell_type":"markdown","source":"# Summary\n\nBased on what we have inferred about the *Target-Methodology*, both the beta and market-return have random jumps based on whether or not there is missing price data in the future(15 mins period future). If the scoring process calculates the Target using the *Target-Methodology*, in order for our models to correctly predict the Target, our models needs to predict whether or not there will be missing data for each asset in the future. It is unlikely that there is any pattern in when missing data occurs. Predicting missing data may not be impossible but seems very difficult to do using the features in the training data. \n \nTo summarize,the *Target-Methodology* G-Research uses makes training a high-scoring model difficult. Moreover, the prediction from this model might match the (strangely calculated) Target but won't match the actual returns from the crypto market. All of above problems can be simply solved if the Target we are trying to predict calculated based on G-Research Tutorial (padding missing data with previous available row instead of padding with NaN).","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport math as math\n\ndata = pd.read_csv(r\"../input/g-research-crypto-forecasting/train.csv\")\nasset_details = pd.read_csv(r\"../input/g-research-crypto-forecasting/asset_details.csv\")\n\nasset_df_Dict = {}\nAsset_IDs = asset_details.Asset_ID.to_numpy()\nasset_details['Normalized_Weight'] = asset_details['Weight'] / asset_details['Weight'].sum()\n\nall_timestamps = np.sort(data['timestamp'].unique())\n##insert January 1, 2018 12:00:00 to all_timestamps to better match the target.\nall_timestamps = np.insert(all_timestamps, 0, 1514764800, axis=0)","metadata":{"execution":{"iopub.status.busy":"2021-12-23T11:48:04.849859Z","iopub.execute_input":"2021-12-23T11:48:04.850333Z","iopub.status.idle":"2021-12-23T11:49:00.87861Z","shell.execute_reply.started":"2021-12-23T11:48:04.850242Z","shell.execute_reply":"2021-12-23T11:49:00.877071Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for i in Asset_IDs:\n    data_asset_i = data[data['Asset_ID']==i].copy()\n\n    ##calculate Return for each timestamp\n    data_asset_i.sort_values(by = 'timestamp', inplace = True)\n    data_asset_i.set_index('timestamp', inplace = True)\n    \n    data_asset_i = data_asset_i.reindex(all_timestamps)\n    \n    data_asset_i['P1'] = data_asset_i.shift(periods=-1)['Close']\n    data_asset_i['P16'] = data_asset_i.shift(periods=-16)['Close']\n    data_asset_i['Log_Return'] = (data_asset_i['P16']/data_asset_i['P1'])-1\n    \n    weight_i = asset_details[asset_details['Asset_ID']==i]['Normalized_Weight'].iloc[0]\n    data_asset_i['Weighted_Log_Return'] = (data_asset_i['Log_Return']) * weight_i\n    asset_df_Dict[i] = data_asset_i","metadata":{"execution":{"iopub.status.busy":"2021-12-23T11:49:00.880303Z","iopub.execute_input":"2021-12-23T11:49:00.880519Z","iopub.status.idle":"2021-12-23T11:49:13.57655Z","shell.execute_reply.started":"2021-12-23T11:49:00.880491Z","shell.execute_reply":"2021-12-23T11:49:13.575883Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"market_return = asset_df_Dict[Asset_IDs[0]]['Weighted_Log_Return']\n\nfor i in Asset_IDs[1:]:\n    market_return = market_return.add(asset_df_Dict[i]['Weighted_Log_Return'], fill_value = 0)\n\nfor i in Asset_IDs:\n    asset_df_Dict[i]['Market_Return'] = market_return\n    \n    num = pd.DataFrame(asset_df_Dict[i]['Log_Return'] * asset_df_Dict[i]['Market_Return']).rolling(3750).mean().values  #numerator of linear regression coefficient\n    denom = pd.DataFrame(asset_df_Dict[i]['Market_Return']*asset_df_Dict[i]['Market_Return']).rolling(3750).mean().values  #denominator of linear regression coefficient\n    beta = np.nan_to_num( num / denom, nan=0., posinf=0., neginf=0.)  #if regression fell over, use beta of 0\n    asset_df_Dict[i]['Beta'] = beta\n    asset_df_Dict[i]['Re_Calc_Target'] = asset_df_Dict[i]['Log_Return'] - (asset_df_Dict[i]['Beta'] * asset_df_Dict[i]['Market_Return'])\n    \n    original_timestamp= np.sort(data[data['Asset_ID']==i].timestamp.unique())\n    asset_df_Dict[i] = asset_df_Dict[i].reindex(original_timestamp)\n    \n    asset_df_Dict[i]['Abs_Diff'] = np.absolute(asset_df_Dict[i]['Re_Calc_Target'] - asset_df_Dict[i]['Target'])","metadata":{"execution":{"iopub.status.busy":"2021-12-23T11:49:13.577712Z","iopub.execute_input":"2021-12-23T11:49:13.578529Z","iopub.status.idle":"2021-12-23T11:49:30.622716Z","shell.execute_reply.started":"2021-12-23T11:49:13.578495Z","shell.execute_reply":"2021-12-23T11:49:30.621757Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for i in Asset_IDs:\n    print(f'Asset_ID: {i}:')\n    print(f'Average absolute error {asset_df_Dict[i].Abs_Diff.mean()}')\n    print(f'Max absolute error {asset_df_Dict[i].Abs_Diff.max()}')\n    print()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T11:49:30.624488Z","iopub.execute_input":"2021-12-23T11:49:30.624723Z","iopub.status.idle":"2021-12-23T11:49:30.722583Z","shell.execute_reply.started":"2021-12-23T11:49:30.624694Z","shell.execute_reply":"2021-12-23T11:49:30.721654Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n%matplotlib inline\n\np = plt.plot(asset_df_Dict[3].Beta.index, asset_df_Dict[3].Beta.values)\nplt.xlabel(\"timestamp\")\nplt.ylabel(\"Beta\")","metadata":{"execution":{"iopub.status.busy":"2021-12-23T11:49:30.723913Z","iopub.execute_input":"2021-12-23T11:49:30.724189Z","iopub.status.idle":"2021-12-23T11:49:31.179794Z","shell.execute_reply.started":"2021-12-23T11:49:30.724149Z","shell.execute_reply":"2021-12-23T11:49:31.178951Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}}]}