{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Targeting Direct Marketing with Amazon SageMaker XGBoost\n", "_**Supervised Learning with Gradient Boosted Trees: A Binary Prediction Problem With Unbalanced Classes**_\n", "\n", "\n", "## Background\n", "Direct marketing, either through mail, email, phone, etc., is a common tactic to acquire customers. Because resources and a customer's attention is limited, the goal is to only target the subset of prospects who are likely to engage with a specific offer. Predicting those potential customers based on readily available information like demographics, past interactions, and environmental factors is a common machine learning problem.\n", "\n", "This notebook presents an example problem to predict if a customer will enroll for a term deposit at a bank, after one or more phone calls. The steps include:\n", "\n", "* Preparing your Amazon SageMaker notebook\n", "* Downloading data from the internet into Amazon SageMaker\n", "* Investigating and transforming the data so that it can be fed to Amazon SageMaker algorithms\n", "* Estimating a model using the Gradient Boosting algorithm\n", "* Evaluating the effectiveness of the model\n", "* Setting the model up to make on-going predictions\n", "\n", "---\n", "\n", "## Preparation\n", "\n", "_This notebook was created and tested on an ml.m4.xlarge notebook instance._\n", "\n", "Let's start by specifying:\n", "\n", "- The S3 bucket and prefix that you want to use for training and model data. This should be within the same region as the Notebook Instance, training, and hosting.\n", "- The IAM role arn used to give training and hosting access to your data. See the documentation for how to create these. Note, if more than one role is required for notebook instances, training, and/or hosting, please replace the boto regexp with a the appropriate full IAM role arn string(s)." ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "isConfigCell": true, "tags": [ "parameters" ] }, "outputs": [], "source": [ "# cell 01\n", "# Define IAM role\n", "import boto3\n", "import sagemaker\n", "import re\n", "from sagemaker import get_execution_role\n", "\n", "region = boto3.Session().region_name\n", "session = sagemaker.Session()\n", "bucket = session.default_bucket()\n", "prefix = 'sagemaker/DEMO-xgboost-dm'\n", "role = get_execution_role() " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now let's bring in the Python libraries that we'll use throughout the analysis" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Requirement already satisfied: smdebug in /opt/conda/lib/python3.7/site-packages (1.0.12)\n", "Requirement already satisfied: boto3>=1.10.32 in /opt/conda/lib/python3.7/site-packages (from smdebug) (1.24.12)\n", "Requirement already satisfied: packaging in /opt/conda/lib/python3.7/site-packages (from smdebug) (20.1)\n", "Requirement already satisfied: protobuf>=3.6.0 in /opt/conda/lib/python3.7/site-packages (from smdebug) (3.20.1)\n", "Requirement already satisfied: numpy>=1.16.0 in /opt/conda/lib/python3.7/site-packages (from smdebug) (1.21.6)\n", "Requirement already satisfied: pyinstrument==3.4.2 in /opt/conda/lib/python3.7/site-packages (from smdebug) (3.4.2)\n", "Requirement already satisfied: pyinstrument-cext>=0.2.2 in /opt/conda/lib/python3.7/site-packages (from pyinstrument==3.4.2->smdebug) (0.2.4)\n", "Requirement already satisfied: botocore<1.28.0,>=1.27.12 in /opt/conda/lib/python3.7/site-packages (from boto3>=1.10.32->smdebug) (1.27.12)\n", "Requirement already satisfied: jmespath<2.0.0,>=0.7.1 in /opt/conda/lib/python3.7/site-packages (from boto3>=1.10.32->smdebug) (1.0.1)\n", "Requirement already satisfied: s3transfer<0.7.0,>=0.6.0 in /opt/conda/lib/python3.7/site-packages (from boto3>=1.10.32->smdebug) (0.6.0)\n", "Requirement already satisfied: pyparsing>=2.0.2 in /opt/conda/lib/python3.7/site-packages (from packaging->smdebug) (2.4.6)\n", "Requirement already satisfied: six in /opt/conda/lib/python3.7/site-packages (from packaging->smdebug) (1.14.0)\n", "Requirement already satisfied: python-dateutil<3.0.0,>=2.1 in /opt/conda/lib/python3.7/site-packages (from botocore<1.28.0,>=1.27.12->boto3>=1.10.32->smdebug) (2.8.1)\n", "Requirement already satisfied: urllib3<1.27,>=1.25.4 in /opt/conda/lib/python3.7/site-packages (from botocore<1.28.0,>=1.27.12->boto3>=1.10.32->smdebug) (1.26.9)\n" ] }, { "data": { "text/html": [ " \n", " " ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# cell 02\n", "import numpy as np # For matrix operations and numerical processing\n", "import pandas as pd # For munging tabular data\n", "import matplotlib.pyplot as plt # For charts and visualizations\n", "from IPython.display import Image # For displaying images in the notebook\n", "from IPython.display import display # For displaying outputs in the notebook\n", "from time import gmtime, strftime # For labeling SageMaker models, endpoints, etc.\n", "import sys # For writing outputs to notebook\n", "import math # For ceiling function\n", "import json # For parsing hosting outputs\n", "import os # For manipulating filepath names\n", "import sagemaker # Amazon SageMaker's Python SDK provides many helper functions\n", "from sagemaker.predictor import csv_serializer # Converts strings for HTTP POST requests on inference\n", "from plotly.offline import init_notebook_mode, iplot # For rendering plots\n", "! python -m pip install smdebug \n", "\n", "init_notebook_mode(connected=True)\n", "%matplotlib inline" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "---\n", "\n", "## Data\n", "Let's start by downloading the [direct marketing dataset](https://sagemaker-sample-data-us-west-2.s3-us-west-2.amazonaws.com/autopilot/direct_marketing/bank-additional.zip) from the sample data s3 bucket. \n", "\n", "\\[Moro et al., 2014\\] S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014\n" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "--2022-07-29 17:24:08-- https://sagemaker-sample-data-us-west-2.s3-us-west-2.amazonaws.com/autopilot/direct_marketing/bank-additional.zip\n", "Resolving sagemaker-sample-data-us-west-2.s3-us-west-2.amazonaws.com (sagemaker-sample-data-us-west-2.s3-us-west-2.amazonaws.com)... 52.218.250.33\n", "Connecting to sagemaker-sample-data-us-west-2.s3-us-west-2.amazonaws.com (sagemaker-sample-data-us-west-2.s3-us-west-2.amazonaws.com)|52.218.250.33|:443... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 432828 (423K) [application/zip]\n", "Saving to: ‘bank-additional.zip.8’\n", "\n", "bank-additional.zip 100%[===================>] 422.68K 1.67MB/s in 0.2s \n", "\n", "2022-07-29 17:24:09 (1.67 MB/s) - ‘bank-additional.zip.8’ saved [432828/432828]\n", "\n", "Collecting package metadata (current_repodata.json): done\n", "Solving environment: done\n", "\n", "# All requested packages already installed.\n", "\n", "Archive: bank-additional.zip\n", " inflating: bank-additional/bank-additional-names.txt \n", " inflating: bank-additional/bank-additional.csv \n", " inflating: bank-additional/bank-additional-full.csv \n" ] } ], "source": [ "# cell 03\n", "!wget https://sagemaker-sample-data-us-west-2.s3-us-west-2.amazonaws.com/autopilot/direct_marketing/bank-additional.zip\n", "!conda install -y -c conda-forge unzip\n", "!unzip -o bank-additional.zip" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now lets read this into a Pandas data frame and take a look." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agejobmaritaleducationdefaulthousingloancontactmonthday_of_week...campaignpdayspreviouspoutcomeemp.var.ratecons.price.idxcons.conf.idxeuribor3mnr.employedy
056housemaidmarriedbasic.4ynononotelephonemaymon...19990nonexistent1.193.994-36.44.8575191.0no
157servicesmarriedhigh.schoolunknownnonotelephonemaymon...19990nonexistent1.193.994-36.44.8575191.0no
237servicesmarriedhigh.schoolnoyesnotelephonemaymon...19990nonexistent1.193.994-36.44.8575191.0no
340admin.marriedbasic.6ynononotelephonemaymon...19990nonexistent1.193.994-36.44.8575191.0no
456servicesmarriedhigh.schoolnonoyestelephonemaymon...19990nonexistent1.193.994-36.44.8575191.0no
..................................................................
4118373retiredmarriedprofessional.coursenoyesnocellularnovfri...19990nonexistent-1.194.767-50.81.0284963.6yes
4118446blue-collarmarriedprofessional.coursenononocellularnovfri...19990nonexistent-1.194.767-50.81.0284963.6no
4118556retiredmarrieduniversity.degreenoyesnocellularnovfri...29990nonexistent-1.194.767-50.81.0284963.6no
4118644technicianmarriedprofessional.coursenononocellularnovfri...19990nonexistent-1.194.767-50.81.0284963.6yes
4118774retiredmarriedprofessional.coursenoyesnocellularnovfri...39991failure-1.194.767-50.81.0284963.6no
\n", "

41188 rows × 21 columns

\n", "
" ], "text/plain": [ " age job marital education default housing loan \\\n", "0 56 housemaid married basic.4y no no no \n", "1 57 services married high.school unknown no no \n", "2 37 services married high.school no yes no \n", "3 40 admin. married basic.6y no no no \n", "4 56 services married high.school no no yes \n", "... ... ... ... ... ... ... ... \n", "41183 73 retired married professional.course no yes no \n", "41184 46 blue-collar married professional.course no no no \n", "41185 56 retired married university.degree no yes no \n", "41186 44 technician married professional.course no no no \n", "41187 74 retired married professional.course no yes no \n", "\n", " contact month day_of_week ... campaign pdays previous \\\n", "0 telephone may mon ... 1 999 0 \n", "1 telephone may mon ... 1 999 0 \n", "2 telephone may mon ... 1 999 0 \n", "3 telephone may mon ... 1 999 0 \n", "4 telephone may mon ... 1 999 0 \n", "... ... ... ... ... ... ... ... \n", "41183 cellular nov fri ... 1 999 0 \n", "41184 cellular nov fri ... 1 999 0 \n", "41185 cellular nov fri ... 2 999 0 \n", "41186 cellular nov fri ... 1 999 0 \n", "41187 cellular nov fri ... 3 999 1 \n", "\n", " poutcome emp.var.rate cons.price.idx cons.conf.idx euribor3m \\\n", "0 nonexistent 1.1 93.994 -36.4 4.857 \n", "1 nonexistent 1.1 93.994 -36.4 4.857 \n", "2 nonexistent 1.1 93.994 -36.4 4.857 \n", "3 nonexistent 1.1 93.994 -36.4 4.857 \n", "4 nonexistent 1.1 93.994 -36.4 4.857 \n", "... ... ... ... ... ... \n", "41183 nonexistent -1.1 94.767 -50.8 1.028 \n", "41184 nonexistent -1.1 94.767 -50.8 1.028 \n", "41185 nonexistent -1.1 94.767 -50.8 1.028 \n", "41186 nonexistent -1.1 94.767 -50.8 1.028 \n", "41187 failure -1.1 94.767 -50.8 1.028 \n", "\n", " nr.employed y \n", "0 5191.0 no \n", "1 5191.0 no \n", "2 5191.0 no \n", "3 5191.0 no \n", "4 5191.0 no \n", "... ... ... \n", "41183 4963.6 yes \n", "41184 4963.6 no \n", "41185 4963.6 no \n", "41186 4963.6 yes \n", "41187 4963.6 no \n", "\n", "[41188 rows x 21 columns]" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# cell 04\n", "data = pd.read_csv('./bank-additional/bank-additional-full.csv')\n", "pd.set_option('display.max_rows',10)\n", "data" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's talk about the data. At a high level, we can see:\n", "\n", "* We have a little over 40K customer records, and 20 features for each customer\n", "* The features are mixed; some numeric, some categorical\n", "* The data appears to be sorted, at least by `time` and `contact`, maybe more\n", "\n", "_**Specifics on each of the features:**_\n", "\n", "*Demographics:*\n", "* `age`: Customer's age (numeric)\n", "* `job`: Type of job (categorical: 'admin.', 'services', ...)\n", "* `marital`: Marital status (categorical: 'married', 'single', ...)\n", "* `education`: Level of education (categorical: 'basic.4y', 'high.school', ...)\n", "\n", "*Past customer events:*\n", "* `default`: Has credit in default? (categorical: 'no', 'unknown', ...)\n", "* `housing`: Has housing loan? (categorical: 'no', 'yes', ...)\n", "* `loan`: Has personal loan? (categorical: 'no', 'yes', ...)\n", "\n", "*Past direct marketing contacts:*\n", "* `contact`: Contact communication type (categorical: 'cellular', 'telephone', ...)\n", "* `month`: Last contact month of year (categorical: 'may', 'nov', ...)\n", "* `day_of_week`: Last contact day of the week (categorical: 'mon', 'fri', ...)\n", "* `duration`: Last contact duration, in seconds (numeric). Important note: If duration = 0 then `y` = 'no'.\n", " \n", "*Campaign information:*\n", "* `campaign`: Number of contacts performed during this campaign and for this client (numeric, includes last contact)\n", "* `pdays`: Number of days that passed by after the client was last contacted from a previous campaign (numeric)\n", "* `previous`: Number of contacts performed before this campaign and for this client (numeric)\n", "* `poutcome`: Outcome of the previous marketing campaign (categorical: 'nonexistent','success', ...)\n", "\n", "*External environment factors:*\n", "* `emp.var.rate`: Employment variation rate - quarterly indicator (numeric)\n", "* `cons.price.idx`: Consumer price index - monthly indicator (numeric)\n", "* `cons.conf.idx`: Consumer confidence index - monthly indicator (numeric)\n", "* `euribor3m`: Euribor 3 month rate - daily indicator (numeric)\n", "* `nr.employed`: Number of employees - quarterly indicator (numeric)\n", "\n", "*Target variable:*\n", "* `y`: Has the client subscribed a term deposit? (binary: 'yes','no')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Transformation\n", "\n", "Cleaning up data is part of nearly every machine learning project. It arguably presents the biggest risk if done incorrectly and is one of the more subjective aspects in the process. Several common techniques include:\n", "\n", "* Handling missing values: Some machine learning algorithms are capable of handling missing values, but most would rather not. Options include:\n", " * Removing observations with missing values: This works well if only a very small fraction of observations have incomplete information.\n", " * Removing features with missing values: This works well if there are a small number of features which have a large number of missing values.\n", " * Imputing missing values: Entire [books](https://www.amazon.com/Flexible-Imputation-Missing-Interdisciplinary-Statistics/dp/1439868247) have been written on this topic, but common choices are replacing the missing value with the mode or mean of that column's non-missing values.\n", "* Converting categorical to numeric: The most common method is one hot encoding, which for each feature maps every distinct value of that column to its own feature which takes a value of 1 when the categorical feature is equal to that value, and 0 otherwise.\n", "* Oddly distributed data: Although for non-linear models like Gradient Boosted Trees, this has very limited implications, parametric models like regression can produce wildly inaccurate estimates when fed highly skewed data. In some cases, simply taking the natural log of the features is sufficient to produce more normally distributed data. In others, bucketing values into discrete ranges is helpful. These buckets can then be treated as categorical variables and included in the model when one hot encoded.\n", "* Handling more complicated data types: Mainpulating images, text, or data at varying grains is left for other notebook templates.\n", "\n", "Luckily, some of these aspects have already been handled for us, and the algorithm we are showcasing tends to do well at handling sparse or oddly distributed data. Therefore, let's keep pre-processing simple." ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "# cell 05\n", "data['no_previous_contact'] = np.where(data['pdays'] == 999, 1, 0) # Indicator variable to capture when pdays takes a value of 999\n", "data['not_working'] = np.where(np.in1d(data['job'], ['student', 'retired', 'unemployed']), 1, 0) # Indicator for individuals not actively employed\n", "model_data = pd.get_dummies(data) # Convert categorical variables to sets of indicators" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Another question to ask yourself before building a model is whether certain features will add value in your final use case. For example, if your goal is to deliver the best prediction, then will you have access to that data at the moment of prediction? Knowing it's raining is highly predictive for umbrella sales, but forecasting weather far enough out to plan inventory on umbrellas is probably just as difficult as forecasting umbrella sales without knowledge of the weather. So, including this in your model may give you a false sense of precision.\n", "\n", "Following this logic, let's remove the economic features and `duration` from our data as they would need to be forecasted with high precision to use as inputs in future predictions.\n", "\n", "Even if we were to use values of the economic indicators from the previous quarter, this value is likely not as relevant for prospects contacted early in the next quarter as those contacted later on." ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "# cell 06\n", "model_data = model_data.drop(['duration', 'emp.var.rate', 'cons.price.idx', 'cons.conf.idx', 'euribor3m', 'nr.employed'], axis=1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "When building a model whose primary goal is to predict a target value on new data, it is important to understand overfitting. Supervised learning models are designed to minimize error between their predictions of the target value and actuals, in the data they are given. This last part is key, as frequently in their quest for greater accuracy, machine learning models bias themselves toward picking up on minor idiosyncrasies within the data they are shown. These idiosyncrasies then don't repeat themselves in subsequent data, meaning those predictions can actually be made less accurate, at the expense of more accurate predictions in the training phase.\n", "\n", "The most common way of preventing this is to build models with the concept that a model shouldn't only be judged on its fit to the data it was trained on, but also on \"new\" data. There are several different ways of operationalizing this, holdout validation, cross-validation, leave-one-out validation, etc. For our purposes, we'll simply randomly split the data into 3 uneven groups. The model will be trained on 70% of data, it will then be evaluated on 20% of data to give us an estimate of the accuracy we hope to have on \"new\" data, and 10% will be held back as a final testing dataset which will be used later on." ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "# cell 07\n", "train_data, validation_data, test_data = np.split(model_data.sample(frac=1, random_state=1729), [int(0.7 * len(model_data)), int(0.9 * len(model_data))]) # Randomly sort the data then split out first 70%, second 20%, and last 10%" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Amazon SageMaker's XGBoost container expects data in the libSVM or CSV data format. For this example, we'll stick to CSV. Note that the first column must be the target variable and the CSV should not include headers. Also, notice that although repetitive it's easiest to do this after the train|validation|test split rather than before. This avoids any misalignment issues due to random reordering." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "# cell 08\n", "pd.concat([train_data['y_yes'], train_data.drop(['y_no', 'y_yes'], axis=1)], axis=1).to_csv('train.csv', index=False, header=False)\n", "pd.concat([validation_data['y_yes'], validation_data.drop(['y_no', 'y_yes'], axis=1)], axis=1).to_csv('validation.csv', index=False, header=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now we'll copy the file to S3 for Amazon SageMaker's managed training to pickup." ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "# cell 09\n", "boto3.Session().resource('s3').Bucket(bucket).Object(os.path.join(prefix, 'train/train.csv')).upload_file('train.csv')\n", "boto3.Session().resource('s3').Bucket(bucket).Object(os.path.join(prefix, 'validation/validation.csv')).upload_file('validation.csv')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "---\n", "\n", "## Training\n", "Now we know that most of our features have skewed distributions, some are highly correlated with one another, and some appear to have non-linear relationships with our target variable. Also, for targeting future prospects, good predictive accuracy is preferred to being able to explain why that prospect was targeted. Taken together, these aspects make gradient boosted trees a good candidate algorithm.\n", "\n", "There are several intricacies to understanding the algorithm, but at a high level, gradient boosted trees works by combining predictions from many simple models, each of which tries to address the weaknesses of the previous models. By doing this the collection of simple models can actually outperform large, complex models. Other Amazon SageMaker notebooks elaborate on gradient boosting trees further and how they differ from similar algorithms.\n", "\n", "`xgboost` is an extremely popular, open-source package for gradient boosted trees. It is computationally powerful, fully featured, and has been successfully used in many machine learning competitions. Let's start with a simple `xgboost` model, trained using Amazon SageMaker's managed, distributed training framework.\n", "\n", "First we'll need to specify the ECR container location for Amazon SageMaker's implementation of XGBoost." ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "# cell 10\n", "from sagemaker.amazon.amazon_estimator import get_image_uri\n", "container = sagemaker.image_uris.retrieve(region=boto3.Session().region_name, framework='xgboost', version='1.0-1')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Then, because we're training with the CSV file format, we'll create `s3_input`s that our training function can use as a pointer to the files in S3, which also specify that the content type is CSV." ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "# cell 11\n", "s3_input_train = sagemaker.TrainingInput(s3_data='s3://{}/{}/train'.format(bucket, prefix), content_type='csv')\n", "s3_input_validation = sagemaker.TrainingInput(s3_data='s3://{}/{}/validation/'.format(bucket, prefix), content_type='csv')" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "# cell 12\n", "base_job_name = \"demo-smdebug-xgboost-regression\"\n", "bucket_path='s3://{}/{}/output'.format(bucket, prefix)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Enabling Debugger in Estimator object\n", "\n", "\n", "#### DebuggerHookConfig\n", "\n", "Enabling Amazon SageMaker Debugger in training job can be accomplished by adding its configuration into Estimator object constructor:\n", "\n", "```python\n", "from sagemaker.debugger import DebuggerHookConfig, CollectionConfig\n", "\n", "estimator = Estimator(\n", " ...,\n", " debugger_hook_config = DebuggerHookConfig(\n", " s3_output_path=\"s3://{bucket_name}/{location_in_bucket}\", # Required\n", " collection_configs=[\n", " CollectionConfig(\n", " name=\"metrics\",\n", " parameters={\n", " \"save_interval\": \"10\"\n", " }\n", " )\n", " ]\n", " )\n", ")\n", "```\n", "Here, the `DebuggerHookConfig` object instructs `Estimator` what data we are interested in.\n", "Two parameters are provided in the example:\n", "\n", "- `s3_output_path`: it points to S3 bucket/path where we intend to store our debugging tensors.\n", " Amount of data saved depends on multiple factors, major ones are: training job / data set / model / frequency of saving tensors.\n", " This bucket should be in your AWS account, and you should have full access control over it.\n", " **Important Note**: this s3 bucket should be originally created in the same region where your training job will be running, otherwise you might run into problems with cross region access.\n", "\n", "- `collection_configs`: it enumerates named collections of tensors we want to save.\n", " Collections are a convinient way to organize relevant tensors under same umbrella to make it easy to navigate them during analysis.\n", " In this particular example, you are instructing Amazon SageMaker Debugger that you are interested in a single collection named `metrics`.\n", " We also instructed Amazon SageMaker Debugger to save metrics every 10 iteration.\n", " See [Collection](https://github.com/awslabs/sagemaker-debugger/blob/master/docs/api.md#collection) documentation for all parameters that are supported by Collections and DebuggerConfig documentation for more details about all parameters DebuggerConfig supports.\n", " \n", "#### Rules\n", "\n", "Enabling Rules in training job can be accomplished by adding the `rules` configuration into Estimator object constructor.\n", "\n", "- `rules`: This new parameter will accept a list of rules you wish to evaluate against the tensors output by this training job.\n", " For rules, Amazon SageMaker Debugger supports two types:\n", " - SageMaker Rules: These are rules specially curated by the data science and engineering teams in Amazon SageMaker which you can opt to evaluate against your training job.\n", " - Custom Rules: You can optionally choose to write your own rule as a Python source file and have it evaluated against your training job.\n", " To provide Amazon SageMaker Debugger to evaluate this rule, you would have to provide the S3 location of the rule source and the evaluator image.\n", "\n", "In this example, you will use a Amazon SageMaker's LossNotDecreasing rule, which helps you identify if you are running into a situation where the training loss is not going down.\n", "\n", "```python\n", "from sagemaker.debugger import rule_configs, Rule\n", "\n", "estimator = Estimator(\n", " ...,\n", " rules=[\n", " Rule.sagemaker(\n", " rule_configs.loss_not_decreasing(),\n", " rule_parameters={\n", " \"collection_names\": \"metrics\",\n", " \"num_steps\": \"10\",\n", " },\n", " ),\n", " ],\n", ")\n", "```\n", "\n", "- `rule_parameters`: In this parameter, you provide the runtime values of the parameter in your constructor.\n", " You can still choose to pass in other values which may be necessary for your rule to be evaluated.\n", " In this example, you will use Amazon SageMaker's LossNotDecreasing rule to monitor the `metircs` collection.\n", " The rule will alert you if the tensors in `metrics` has not decreased for more than 10 steps." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now we'll create the estimator. For this we will include:\n", "1. The IAM role to use\n", "1. The Training instance type and count\n", "1. The `xgboost` algorithm container\n", "1. The timeout in seconds for training\n", "1. The `DebuggerHookConfig` object which saves the specific tensors for debugging\n", "1. The `LossNotDecreasing` rule which detects when the loss is not decreasing in value at an adequate rate\n", "\n", "And then we set the algorithm hyperparameters, as well as specify the `.fit()` function which specifies the S3 location for output data. In this case we have both a training and validation set which are passed in." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "# cell 13\n", "from sagemaker.debugger import rule_configs, Rule, DebuggerHookConfig, CollectionConfig\n", "from sagemaker.estimator import Estimator\n", "sess = sagemaker.Session()\n", "\n", "save_interval = 5 \n", "\n", "xgboost_estimator = Estimator(\n", " role=role,\n", " base_job_name=base_job_name,\n", " instance_count=1,\n", " instance_type='ml.m5.4xlarge',\n", " image_uri=container,\n", " max_run=1800,\n", " sagemaker_session=sess,\n", " debugger_hook_config=DebuggerHookConfig(\n", " s3_output_path=bucket_path, # Required\n", " collection_configs=[\n", " CollectionConfig(\n", " name=\"metrics\",\n", " parameters={\n", " \"save_interval\": str(save_interval)\n", " }\n", " ),\n", " CollectionConfig(\n", " name=\"predictions\",\n", " parameters={\n", " \"save_interval\": str(save_interval)\n", " }\n", " ),\n", " CollectionConfig(\n", " name=\"feature_importance\",\n", " parameters={\n", " \"save_interval\": str(save_interval)\n", " }\n", " ),\n", " CollectionConfig(\n", " name=\"average_shap\",\n", " parameters={\n", " \"save_interval\": str(save_interval)\n", " }\n", " )\n", " ],\n", " ),\n", " rules=[\n", " Rule.sagemaker(\n", " rule_configs.loss_not_decreasing(),\n", " rule_parameters={\n", " \"collection_names\": \"metrics\",\n", " \"num_steps\": str(save_interval * 2),\n", " },\n", " ),\n", " ],\n", ")" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "# cell 14\n", "xgboost_estimator.set_hyperparameters(max_depth=5,\n", " eta=0.2,\n", " gamma=4,\n", " min_child_weight=6,\n", " subsample=0.8,\n", " silent=0,\n", " objective='binary:logistic',\n", " num_round=100)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "# cell 15\n", "\n", "xgboost_estimator.fit(\n", " {\"train\": s3_input_train, \"validation\": s3_input_validation},\n", " # This is a fire and forget event. By setting wait=False, you submit the job to run in the background.\n", " # Amazon SageMaker starts one training job and release control to next cells in the notebook.\n", " # Follow this notebook to see status of the training job.\n", " wait=False\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Result\n", "\n", "As a result of the above command, Amazon SageMaker starts one training job and one rule job for you. The first one is the job that produces the tensors to be analyzed. The second one analyzes the tensors to check if `train-rmse` and `validation-rmse` are not decreasing at any point during training.\n", "\n", "Check the status of the training job below.\n", "After your training job is started, Amazon SageMaker starts a rule-execution job to run the LossNotDecreasing rule.\n", "\n", "**Note that the next cell blocks until the rule execution job ends. You can stop it at any point to proceed to the rest of the notebook. Once it says Rule Evaluation Status is Started, and shows the `RuleEvaluationJobArn`, you can look at the status of the rule being monitored.**" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training job name: demo-smdebug-xgboost-regression-2022-07-29-17-25-00-661\n", "InProgress\n", "17:25:01: InProgress, Starting, InProgress\n", "17:25:16: InProgress, Starting, InProgress\n", "17:25:31: InProgress, Starting, InProgress\n", "17:25:46: InProgress, Starting, InProgress\n", "17:26:01: InProgress, Starting, InProgress\n", "17:26:16: InProgress, Starting, InProgress\n", "17:26:31: InProgress, Starting, InProgress\n", "17:26:46: InProgress, Downloading, InProgress\n", "17:27:02: InProgress, Downloading, InProgress\n", "17:27:17: InProgress, Training, InProgress\n", "17:27:32: InProgress, Training, InProgress\n", "17:27:47: InProgress, Training, InProgress\n", "17:28:02: InProgress, Uploading, InProgress\n", "17:28:17: Completed, Completed, InProgress\n", "17:28:32: Completed, Completed, InProgress\n", "17:28:47: Completed, Completed, InProgress\n", "17:29:02: Completed, Completed, InProgress\n", "17:29:17: Completed, Completed, InProgress\n", "17:29:32: Completed, Completed, InProgress\n", "17:29:48: Completed, Completed, InProgress\n", "17:30:03: Completed, Completed, InProgress\n", "17:30:18: Completed, Completed, InProgress\n", "17:30:33: Completed, Completed, InProgress\n", "17:30:48: Completed, Completed, InProgress\n", "17:31:03: Completed, Completed, InProgress\n", "17:31:18: Completed, Completed, InProgress\n", "17:31:33: Completed, Completed, InProgress\n", "17:31:48: Completed, Completed, InProgress\n", "17:32:03: Completed, Completed, InProgress\n", "17:32:18: Completed, Completed, InProgress\n", "17:32:34: Completed, Completed, InProgress\n", "17:32:49: Completed, Completed, InProgress\n", "17:33:04: Completed, Completed, InProgress\n", "17:33:19: Completed, Completed, InProgress\n", "17:33:34: Completed, Completed, IssuesFound\n" ] } ], "source": [ "# cell 16\n", "import time\n", "from time import gmtime, strftime\n", "\n", "\n", "# Below command will give the status of training job\n", "job_name = xgboost_estimator.latest_training_job.name\n", "client = xgboost_estimator.sagemaker_session.sagemaker_client\n", "description = client.describe_training_job(TrainingJobName=job_name)\n", "rule_job_summary = xgboost_estimator.latest_training_job.rule_job_summary()\n", "rule_evaluation_status = rule_job_summary[0]['RuleEvaluationStatus']\n", "print('Training job name: ' + job_name)\n", "print(description['TrainingJobStatus'])\n", "\n", "if description['TrainingJobStatus'] != 'Completed' or rule_evaluation_status not in ['IssuesFound', 'NoIssuesFound']:\n", " while (description['SecondaryStatus'] not in ['Training', 'Completed']) or (rule_job_summary[0]['RuleEvaluationStatus'] == 'InProgress'):\n", " description = client.describe_training_job(TrainingJobName=job_name)\n", " primary_status = description['TrainingJobStatus']\n", " secondary_status = description['SecondaryStatus']\n", " rule_job_summary = xgboost_estimator.latest_training_job.rule_job_summary()\n", " rule_evaluation_status = rule_job_summary[0]['RuleEvaluationStatus']\n", " print(\"{}: {}, {}, {}\".format(strftime('%X', gmtime()), primary_status, secondary_status, rule_evaluation_status))\n", " time.sleep(15)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Check the status of the Rule Evaluation Job\n", "To get the rule evaluation job that Amazon SageMaker started for you, run the command below. The results show you the `RuleConfigurationName`, `RuleEvaluationJobArn`, `RuleEvaluationStatus`, `StatusDetails`, and `RuleEvaluationJobArn`. If the model parameters meet a rule evaluation condition, the rule execution job throws a client error with `RuleEvaluationConditionMet`.\n", "\n", "The logs of the rule evaluation job are available in the Cloudwatch Logstream `/aws/sagemaker/ProcessingJobs` with `RuleEvaluationJobArn`.\n", "\n", "You can see that once the rule execution job starts, it identifies the loss not decreasing situation in the training job, it raises the `RuleEvaluationConditionMet` exception, and it ends the job." ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'RuleConfigurationName': 'LossNotDecreasing',\n", " 'RuleEvaluationJobArn': 'arn:aws:sagemaker:us-east-1:167814267962:processing-job/demo-smdebug-xgboost-regre-lossnotdecreasing-3291b21e',\n", " 'RuleEvaluationStatus': 'IssuesFound',\n", " 'StatusDetails': 'RuleEvaluationConditionMet: Evaluation of the rule LossNotDecreasing at step 20 resulted in the condition being met\\n',\n", " 'LastModifiedTime': datetime.datetime(2022, 7, 29, 17, 33, 32, 835000, tzinfo=tzlocal())}" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# cell 17\n", "xgboost_estimator.latest_training_job.rule_job_summary()[0]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Data Analysis - Manual\n", "\n", "Now that you've trained the system, analyze the data.\n", "Here, you focus on after-the-fact analysis.\n", "\n", "You import a basic analysis library, which defines the concept of trial, which represents a single training run." ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2022-07-29 17:33:49.594 datascience-1-0-ml-t3-medium-1abf3407f667f989be9d86559395:13708 INFO utils.py:27] RULE_JOB_STOP_SIGNAL_FILENAME: None\n", "[2022-07-29 17:33:49.659 datascience-1-0-ml-t3-medium-1abf3407f667f989be9d86559395:13708 INFO s3_trial.py:42] Loading trial debug-output at path s3://sagemaker-us-east-1-167814267962/sagemaker/DEMO-xgboost-dm/output/demo-smdebug-xgboost-regression-2022-07-29-17-25-00-661/debug-output\n" ] } ], "source": [ "# cell 18\n", "from smdebug.trials import create_trial\n", "\n", "description = client.describe_training_job(TrainingJobName=job_name)\n", "s3_output_path = xgboost_estimator.latest_job_debugger_artifacts_path()\n", "\n", "# This is where we create a Trial object that allows access to saved tensors.\n", "trial = create_trial(s3_output_path)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "You can list all the tensors that you know something about. Each one of these names is the name of a tensor. The name is a combination of the feature name, which in these cases, is auto-assigned by XGBoost, and whether it's an evaluation metric, feature importance, or SHAP value." ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2022-07-29 17:33:51.015 datascience-1-0-ml-t3-medium-1abf3407f667f989be9d86559395:13708 INFO trial.py:198] Training has ended, will refresh one final time in 1 sec.\n", "[2022-07-29 17:33:52.046 datascience-1-0-ml-t3-medium-1abf3407f667f989be9d86559395:13708 INFO trial.py:210] Loaded all steps\n" ] }, { "data": { "text/plain": [ "['average_shap/f0',\n", " 'average_shap/f1',\n", " 'average_shap/f10',\n", " 'average_shap/f11',\n", " 'average_shap/f12',\n", " 'average_shap/f13',\n", " 'average_shap/f14',\n", " 'average_shap/f15',\n", " 'average_shap/f16',\n", " 'average_shap/f17',\n", " 'average_shap/f18',\n", " 'average_shap/f19',\n", " 'average_shap/f2',\n", " 'average_shap/f20',\n", " 'average_shap/f21',\n", " 'average_shap/f22',\n", " 'average_shap/f23',\n", " 'average_shap/f24',\n", " 'average_shap/f25',\n", " 'average_shap/f26',\n", " 'average_shap/f27',\n", " 'average_shap/f28',\n", " 'average_shap/f29',\n", " 'average_shap/f3',\n", " 'average_shap/f30',\n", " 'average_shap/f31',\n", " 'average_shap/f32',\n", " 'average_shap/f33',\n", " 'average_shap/f34',\n", " 'average_shap/f35',\n", " 'average_shap/f36',\n", " 'average_shap/f37',\n", " 'average_shap/f38',\n", " 'average_shap/f39',\n", " 'average_shap/f4',\n", " 'average_shap/f40',\n", " 'average_shap/f41',\n", " 'average_shap/f42',\n", " 'average_shap/f43',\n", " 'average_shap/f44',\n", " 'average_shap/f45',\n", " 'average_shap/f46',\n", " 'average_shap/f47',\n", " 'average_shap/f48',\n", " 'average_shap/f49',\n", " 'average_shap/f5',\n", " 'average_shap/f50',\n", " 'average_shap/f51',\n", " 'average_shap/f52',\n", " 'average_shap/f53',\n", " 'average_shap/f54',\n", " 'average_shap/f55',\n", " 'average_shap/f56',\n", " 'average_shap/f57',\n", " 'average_shap/f58',\n", " 'average_shap/f6',\n", " 'average_shap/f7',\n", " 'average_shap/f8',\n", " 'average_shap/f9',\n", " 'feature_importance/cover/f0',\n", " 'feature_importance/cover/f1',\n", " 'feature_importance/cover/f10',\n", " 'feature_importance/cover/f11',\n", " 'feature_importance/cover/f12',\n", " 'feature_importance/cover/f13',\n", " 'feature_importance/cover/f14',\n", " 'feature_importance/cover/f15',\n", " 'feature_importance/cover/f16',\n", " 'feature_importance/cover/f17',\n", " 'feature_importance/cover/f18',\n", " 'feature_importance/cover/f19',\n", " 'feature_importance/cover/f2',\n", " 'feature_importance/cover/f20',\n", " 'feature_importance/cover/f22',\n", " 'feature_importance/cover/f23',\n", " 'feature_importance/cover/f24',\n", " 'feature_importance/cover/f25',\n", " 'feature_importance/cover/f27',\n", " 'feature_importance/cover/f28',\n", " 'feature_importance/cover/f29',\n", " 'feature_importance/cover/f3',\n", " 'feature_importance/cover/f30',\n", " 'feature_importance/cover/f31',\n", " 'feature_importance/cover/f33',\n", " 'feature_importance/cover/f34',\n", " 'feature_importance/cover/f35',\n", " 'feature_importance/cover/f36',\n", " 'feature_importance/cover/f38',\n", " 'feature_importance/cover/f39',\n", " 'feature_importance/cover/f41',\n", " 'feature_importance/cover/f42',\n", " 'feature_importance/cover/f43',\n", " 'feature_importance/cover/f44',\n", " 'feature_importance/cover/f45',\n", " 'feature_importance/cover/f46',\n", " 'feature_importance/cover/f47',\n", " 'feature_importance/cover/f48',\n", " 'feature_importance/cover/f49',\n", " 'feature_importance/cover/f5',\n", " 'feature_importance/cover/f50',\n", " 'feature_importance/cover/f51',\n", " 'feature_importance/cover/f52',\n", " 'feature_importance/cover/f53',\n", " 'feature_importance/cover/f54',\n", " 'feature_importance/cover/f55',\n", " 'feature_importance/cover/f56',\n", " 'feature_importance/cover/f58',\n", " 'feature_importance/cover/f6',\n", " 'feature_importance/cover/f7',\n", " 'feature_importance/cover/f8',\n", " 'feature_importance/cover/f9',\n", " 'feature_importance/gain/f0',\n", " 'feature_importance/gain/f1',\n", " 'feature_importance/gain/f10',\n", " 'feature_importance/gain/f11',\n", " 'feature_importance/gain/f12',\n", " 'feature_importance/gain/f13',\n", " 'feature_importance/gain/f14',\n", " 'feature_importance/gain/f15',\n", " 'feature_importance/gain/f16',\n", " 'feature_importance/gain/f17',\n", " 'feature_importance/gain/f18',\n", " 'feature_importance/gain/f19',\n", " 'feature_importance/gain/f2',\n", " 'feature_importance/gain/f20',\n", " 'feature_importance/gain/f22',\n", " 'feature_importance/gain/f23',\n", " 'feature_importance/gain/f24',\n", " 'feature_importance/gain/f25',\n", " 'feature_importance/gain/f27',\n", " 'feature_importance/gain/f28',\n", " 'feature_importance/gain/f29',\n", " 'feature_importance/gain/f3',\n", " 'feature_importance/gain/f30',\n", " 'feature_importance/gain/f31',\n", " 'feature_importance/gain/f33',\n", " 'feature_importance/gain/f34',\n", " 'feature_importance/gain/f35',\n", " 'feature_importance/gain/f36',\n", " 'feature_importance/gain/f38',\n", " 'feature_importance/gain/f39',\n", " 'feature_importance/gain/f41',\n", " 'feature_importance/gain/f42',\n", " 'feature_importance/gain/f43',\n", " 'feature_importance/gain/f44',\n", " 'feature_importance/gain/f45',\n", " 'feature_importance/gain/f46',\n", " 'feature_importance/gain/f47',\n", " 'feature_importance/gain/f48',\n", " 'feature_importance/gain/f49',\n", " 'feature_importance/gain/f5',\n", " 'feature_importance/gain/f50',\n", " 'feature_importance/gain/f51',\n", " 'feature_importance/gain/f52',\n", " 'feature_importance/gain/f53',\n", " 'feature_importance/gain/f54',\n", " 'feature_importance/gain/f55',\n", " 'feature_importance/gain/f56',\n", " 'feature_importance/gain/f58',\n", " 'feature_importance/gain/f6',\n", " 'feature_importance/gain/f7',\n", " 'feature_importance/gain/f8',\n", " 'feature_importance/gain/f9',\n", " 'feature_importance/total_cover/f0',\n", " 'feature_importance/total_cover/f1',\n", " 'feature_importance/total_cover/f10',\n", " 'feature_importance/total_cover/f11',\n", " 'feature_importance/total_cover/f12',\n", " 'feature_importance/total_cover/f13',\n", " 'feature_importance/total_cover/f14',\n", " 'feature_importance/total_cover/f15',\n", " 'feature_importance/total_cover/f16',\n", " 'feature_importance/total_cover/f17',\n", " 'feature_importance/total_cover/f18',\n", " 'feature_importance/total_cover/f19',\n", " 'feature_importance/total_cover/f2',\n", " 'feature_importance/total_cover/f20',\n", " 'feature_importance/total_cover/f22',\n", " 'feature_importance/total_cover/f23',\n", " 'feature_importance/total_cover/f24',\n", " 'feature_importance/total_cover/f25',\n", " 'feature_importance/total_cover/f27',\n", " 'feature_importance/total_cover/f28',\n", " 'feature_importance/total_cover/f29',\n", " 'feature_importance/total_cover/f3',\n", " 'feature_importance/total_cover/f30',\n", " 'feature_importance/total_cover/f31',\n", " 'feature_importance/total_cover/f33',\n", " 'feature_importance/total_cover/f34',\n", " 'feature_importance/total_cover/f35',\n", " 'feature_importance/total_cover/f36',\n", " 'feature_importance/total_cover/f38',\n", " 'feature_importance/total_cover/f39',\n", " 'feature_importance/total_cover/f41',\n", " 'feature_importance/total_cover/f42',\n", " 'feature_importance/total_cover/f43',\n", " 'feature_importance/total_cover/f44',\n", " 'feature_importance/total_cover/f45',\n", " 'feature_importance/total_cover/f46',\n", " 'feature_importance/total_cover/f47',\n", " 'feature_importance/total_cover/f48',\n", " 'feature_importance/total_cover/f49',\n", " 'feature_importance/total_cover/f5',\n", " 'feature_importance/total_cover/f50',\n", " 'feature_importance/total_cover/f51',\n", " 'feature_importance/total_cover/f52',\n", " 'feature_importance/total_cover/f53',\n", " 'feature_importance/total_cover/f54',\n", " 'feature_importance/total_cover/f55',\n", " 'feature_importance/total_cover/f56',\n", " 'feature_importance/total_cover/f58',\n", " 'feature_importance/total_cover/f6',\n", " 'feature_importance/total_cover/f7',\n", " 'feature_importance/total_cover/f8',\n", " 'feature_importance/total_cover/f9',\n", " 'feature_importance/total_gain/f0',\n", " 'feature_importance/total_gain/f1',\n", " 'feature_importance/total_gain/f10',\n", " 'feature_importance/total_gain/f11',\n", " 'feature_importance/total_gain/f12',\n", " 'feature_importance/total_gain/f13',\n", " 'feature_importance/total_gain/f14',\n", " 'feature_importance/total_gain/f15',\n", " 'feature_importance/total_gain/f16',\n", " 'feature_importance/total_gain/f17',\n", " 'feature_importance/total_gain/f18',\n", " 'feature_importance/total_gain/f19',\n", " 'feature_importance/total_gain/f2',\n", " 'feature_importance/total_gain/f20',\n", " 'feature_importance/total_gain/f22',\n", " 'feature_importance/total_gain/f23',\n", " 'feature_importance/total_gain/f24',\n", " 'feature_importance/total_gain/f25',\n", " 'feature_importance/total_gain/f27',\n", " 'feature_importance/total_gain/f28',\n", " 'feature_importance/total_gain/f29',\n", " 'feature_importance/total_gain/f3',\n", " 'feature_importance/total_gain/f30',\n", " 'feature_importance/total_gain/f31',\n", " 'feature_importance/total_gain/f33',\n", " 'feature_importance/total_gain/f34',\n", " 'feature_importance/total_gain/f35',\n", " 'feature_importance/total_gain/f36',\n", " 'feature_importance/total_gain/f38',\n", " 'feature_importance/total_gain/f39',\n", " 'feature_importance/total_gain/f41',\n", " 'feature_importance/total_gain/f42',\n", " 'feature_importance/total_gain/f43',\n", " 'feature_importance/total_gain/f44',\n", " 'feature_importance/total_gain/f45',\n", " 'feature_importance/total_gain/f46',\n", " 'feature_importance/total_gain/f47',\n", " 'feature_importance/total_gain/f48',\n", " 'feature_importance/total_gain/f49',\n", " 'feature_importance/total_gain/f5',\n", " 'feature_importance/total_gain/f50',\n", " 'feature_importance/total_gain/f51',\n", " 'feature_importance/total_gain/f52',\n", " 'feature_importance/total_gain/f53',\n", " 'feature_importance/total_gain/f54',\n", " 'feature_importance/total_gain/f55',\n", " 'feature_importance/total_gain/f56',\n", " 'feature_importance/total_gain/f58',\n", " 'feature_importance/total_gain/f6',\n", " 'feature_importance/total_gain/f7',\n", " 'feature_importance/total_gain/f8',\n", " 'feature_importance/total_gain/f9',\n", " 'feature_importance/weight/f0',\n", " 'feature_importance/weight/f1',\n", " 'feature_importance/weight/f10',\n", " 'feature_importance/weight/f11',\n", " 'feature_importance/weight/f12',\n", " 'feature_importance/weight/f13',\n", " 'feature_importance/weight/f14',\n", " 'feature_importance/weight/f15',\n", " 'feature_importance/weight/f16',\n", " 'feature_importance/weight/f17',\n", " 'feature_importance/weight/f18',\n", " 'feature_importance/weight/f19',\n", " 'feature_importance/weight/f2',\n", " 'feature_importance/weight/f20',\n", " 'feature_importance/weight/f22',\n", " 'feature_importance/weight/f23',\n", " 'feature_importance/weight/f24',\n", " 'feature_importance/weight/f25',\n", " 'feature_importance/weight/f27',\n", " 'feature_importance/weight/f28',\n", " 'feature_importance/weight/f29',\n", " 'feature_importance/weight/f3',\n", " 'feature_importance/weight/f30',\n", " 'feature_importance/weight/f31',\n", " 'feature_importance/weight/f33',\n", " 'feature_importance/weight/f34',\n", " 'feature_importance/weight/f35',\n", " 'feature_importance/weight/f36',\n", " 'feature_importance/weight/f38',\n", " 'feature_importance/weight/f39',\n", " 'feature_importance/weight/f41',\n", " 'feature_importance/weight/f42',\n", " 'feature_importance/weight/f43',\n", " 'feature_importance/weight/f44',\n", " 'feature_importance/weight/f45',\n", " 'feature_importance/weight/f46',\n", " 'feature_importance/weight/f47',\n", " 'feature_importance/weight/f48',\n", " 'feature_importance/weight/f49',\n", " 'feature_importance/weight/f5',\n", " 'feature_importance/weight/f50',\n", " 'feature_importance/weight/f51',\n", " 'feature_importance/weight/f52',\n", " 'feature_importance/weight/f53',\n", " 'feature_importance/weight/f54',\n", " 'feature_importance/weight/f55',\n", " 'feature_importance/weight/f56',\n", " 'feature_importance/weight/f58',\n", " 'feature_importance/weight/f6',\n", " 'feature_importance/weight/f7',\n", " 'feature_importance/weight/f8',\n", " 'feature_importance/weight/f9',\n", " 'predictions',\n", " 'train-error',\n", " 'validation-error']" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# cell 19\n", "trial.tensor_names()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "For each tensor, ask for the steps where you have data. In this case, every five steps" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{0: array([0.40940192, 0.40940192, 0.40940192, ..., 0.42072025, 0.42072025,\n", " 0.40940192], dtype=float32),\n", " 5: array([0.17423216, 0.17423216, 0.17423216, ..., 0.20525002, 0.20525002,\n", " 0.17011178], dtype=float32),\n", " 10: array([0.09244758, 0.09244758, 0.09244758, ..., 0.14336592, 0.1304271 ,\n", " 0.08529319], dtype=float32),\n", " 15: array([0.06389849, 0.05903047, 0.06389849, ..., 0.11248846, 0.10763057,\n", " 0.0549309 ], dtype=float32),\n", " 20: array([0.05420081, 0.05003211, 0.05420081, ..., 0.09846841, 0.10812173,\n", " 0.0407625 ], dtype=float32),\n", " 25: array([0.04791263, 0.03964589, 0.0486064 , ..., 0.09368774, 0.10400326,\n", " 0.03752989], dtype=float32),\n", " 30: array([0.04766197, 0.06056261, 0.04844233, ..., 0.09047107, 0.0994751 ,\n", " 0.0341584 ], dtype=float32),\n", " 35: array([0.0499336 , 0.05720866, 0.04722781, ..., 0.08356649, 0.09964165,\n", " 0.03486255], dtype=float32),\n", " 40: array([0.05173785, 0.05747067, 0.04266172, ..., 0.08261214, 0.09674504,\n", " 0.03461719], dtype=float32),\n", " 45: array([0.05931778, 0.06785829, 0.04638138, ..., 0.08361725, 0.09038726,\n", " 0.03508312], dtype=float32),\n", " 50: array([0.05538193, 0.06120145, 0.04665741, ..., 0.08237638, 0.09052734,\n", " 0.03513904], dtype=float32),\n", " 55: array([0.05460953, 0.07082538, 0.04600076, ..., 0.0836796 , 0.08932932,\n", " 0.03541474], dtype=float32),\n", " 60: array([0.05313265, 0.06894194, 0.04622852, ..., 0.08410715, 0.08863498,\n", " 0.03559205], dtype=float32),\n", " 65: array([0.05364244, 0.08045801, 0.04653292, ..., 0.07387302, 0.09229486,\n", " 0.03593993], dtype=float32),\n", " 70: array([0.0608957 , 0.08111401, 0.04692643, ..., 0.07440256, 0.09846032,\n", " 0.03795054], dtype=float32),\n", " 75: array([0.06149934, 0.08190059, 0.04838083, ..., 0.07151973, 0.09997997,\n", " 0.03833602], dtype=float32),\n", " 80: array([0.0616881 , 0.08214649, 0.04853141, ..., 0.0717369 , 0.10027424,\n", " 0.03842323], dtype=float32),\n", " 85: array([0.06295961, 0.07733403, 0.04827591, ..., 0.07185908, 0.09033229,\n", " 0.03735269], dtype=float32),\n", " 90: array([0.06326208, 0.07610193, 0.04896875, ..., 0.07286448, 0.08462393,\n", " 0.03701286], dtype=float32),\n", " 95: array([0.0638762 , 0.08147059, 0.04945144, ..., 0.07214621, 0.08227884,\n", " 0.03738234], dtype=float32)}" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# cell 20\n", "trial.tensor(\"predictions\").values()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "You can obtain each tensor at each step as a NumPy array." ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "numpy.ndarray" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# cell 21\n", "type(trial.tensor(\"predictions\").value(10))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Performance metrics\n", "\n", "You can also create a simple function that visualizes the training and validation errors as the training progresses.\n", "Each gradient should get smaller over time, as the system converges to a good solution.\n", "Remember that this is an interactive analysis. You are showing these tensors to give an idea of the data." ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [], "source": [ "# cell 22\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "import re\n", "\n", "\n", "def get_data(trial, tname):\n", " \"\"\"\n", " For the given tensor name, walks though all the iterations\n", " for which you have data and fetches the values.\n", " Returns the set of steps and the values.\n", " \"\"\"\n", " tensor = trial.tensor(tname)\n", " steps = tensor.steps()\n", " vals = [tensor.value(s) for s in steps]\n", " return steps, vals\n", "\n", "def plot_collection(trial, collection_name, regex='.*', figsize=(8, 6)):\n", " \"\"\"\n", " Takes a `trial` and a collection name, and \n", " plots all tensors that match the given regex.\n", " \"\"\"\n", " fig, ax = plt.subplots(figsize=figsize)\n", " sns.despine()\n", "\n", " tensors = trial.collection(collection_name).tensor_names\n", "\n", " for tensor_name in sorted(tensors):\n", " if re.match(regex, tensor_name):\n", " steps, data = get_data(trial, tensor_name)\n", " ax.plot(steps, data, label=tensor_name)\n", "\n", " ax.legend(loc='center left', bbox_to_anchor=(1, 0.5))\n", " ax.set_xlabel('Iteration')" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# cell 23\n", "plot_collection(trial, \"metrics\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Feature importances\n", "\n", "You can also visualize the feature priorities as determined by\n", "[xgboost.get_score()](https://xgboost.readthedocs.io/en/latest/python/python_api.html#xgboost.Booster.get_score).\n", "If you instructed Estimator to log the `feature_importance` collection, all five importance types supported by `xgboost.get_score()` will be available in the collection." ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [], "source": [ "# cell 23\n", "def plot_feature_importance(trial, importance_type=\"weight\"):\n", " SUPPORTED_IMPORTANCE_TYPES = [\"weight\", \"gain\", \"cover\", \"total_gain\", \"total_cover\"]\n", " if importance_type not in SUPPORTED_IMPORTANCE_TYPES:\n", " raise ValueError(f\"{importance_type} is not one of the supported importance types.\")\n", " plot_collection(\n", " trial,\n", " \"feature_importance\",\n", " regex=f\"feature_importance/{importance_type}/.*\")" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# cell 24\n", "plot_feature_importance(trial)" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAqgAAAFzCAYAAADyqfstAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjMsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+AADFEAAAgAElEQVR4nOzde1hU5b83/vdacx4EHGCQgxwEGcZBJYUfWFSCRumWfPKytEi2pr/c196/b2naU+z0KbMTPaWl31J42rUTdilb7DFk88Rvl6mk383+4oHTMAwwchBQOQznmWHWzHr+gDFCQGgrkHxe1+WlrLXu+XwWy/LDfa/7vhme50EIIYQQQshUwU52AoQQQgghhAxGBSohhBBCCJlSqEAlhBBCCCFTChWohBBCCCFkSqEClRBCCCGETClUoBJCCCGEkClFONkJDLVixQr+hx9+mOw0CCGEkInETHYChEwlU64HtaWlZbJTIIQQQgghk2jKFaiEEEIIIWR6owKVEEIIIYRMKVSgEkIIIYSQKYUKVEIIIYQQMqVQgUoIIYQQQqYUKlAJIYQQQsiUQgUqIYQQQgiZUqhAJYQQQgghUwoVqIQQQgghZEqhApUQQgghhEwpVKASQgghhJAp5f4uUG1WwHAGaK2e7EwIIYQQQsgY3d8FKm8HMtYAxZmTnQkhhBBCCBmj+7tAFUoA19nUg0oIIYQQ8gdyfxeoAOAWDLRRgUoIIYQQ8kdx/xeo7sFAqwHg+cnOhBBCCCGEjMH9X6C6BQOWDqC3dbIzIYQQQgghY3D/F6juc/t/p/dQCSGEEEL+EKZBgRrc/3tr1eTmQQghhBBCxuT+L1Bn+gOMgCZKEUIIIYT8Qdz/BapABCgCaIifEEIIIeQP4v4vUAFaaooQQggh5A9kehSotNQUIYQQQsgfxvQoUN2CAWsP0H1jsjMhhBBCCCF3MD0KVPeg/t/pPVRCCCGEkClvmhSoA2uh0nuohBBCCCFT3vQoUF39AIGY1kIlhBBCCPkDmB4FKisAFIE0xE8IIYQQ8gcgnOwE7iXeakPPxZsQ+86A2C0YaDNMdkqEEEIIIeQO7u8eVJZB+6lq9JY09y811WYA7PbJzooQQgghhIzivi5QGQELkZcTrI09gFsQwJmBrsbJTosQQgghhIzivi5QzTY7vg2S4K9dveDdgvsP0nuohBBCCCFT2n1doIpYBvvlfTjrAthEAf0HaakpQgghhJAp7b4uUAUMA3+RCHVOLKwdMwChlHpQCSGEEEKmuPu6QAUAf5EItU4s+poG3kOlApUQQgghZEq7rwtUc7cV5kutuCZnYWns7i9QaYifEEIIIWRKu68LVOkMEYLkEvSxDOpaevqXmjLWAHbbZKdGCCGEEEJGcF8XqACwyF8BAKjhbbDJVYCtD+ion+SsCCGEEELISO77AjVmvhIAUCdnYbUNzOSn91AJIYQQQqas+75ADfRwgsTGo86JRV+ve/9B2vKUEEIIIWTKuu8LVIZhMJsVwiBj0dNgA8QzqAeVEEIIIWQKu+8LVABQK+Soc2LQV98NuM0BWqsmOyVCCCGEEDKCaVGgqlzluClnYbdwsLvMo6WmCCGEEEKmsGlRoAbLJbAzDBrkLNptiwFjLWCzTnZahBBCCCFkGNOiQA2SSwAAtXIGN5vnALwNaK+b5KwIIYQQQshwxlSgMgyzgmGYCoZhqhiGSR7m/A6GYbQMwxQzDPMTwzABg85tZBimcuDXxruZ/FgFyfoLVIMTC3ObrP8gTZQihBBCCJmS7ligMgwjAPA5gJUANACeYxhGM+SyywAieZ5fCCALwP8caOsG4C0A0QCiALzFMIzi7qU/NjNFQriLhKhTiCG2MOixKeg9VEIIIYSQKWosPahRAKp4njfwPN8H4BiA/zb4Ap7nf+Z5vnfgy/8AMHvgz08A+Hee59t4njcC+HcAK+5O6uMTLJegUSGEMwsYuMeoB5UQQgghZIoaS4HqC2Dw3qDXBo6NZAuA//M7294zc2QS1Ev610W9bo2jpaYIIYQQQqaosRSozDDH+GEvZJgNACIBfDSetgzDbGUYppBhmMLm5uYxpDR+wXIJbtrt6BEA1j5vmG5evydxCCGEEELIf81YCtRrAPwGfT0bQOPQixiGeQzALgCreZ63jKctz/P/i+f5SJ7nI5VK5VhzHxfHRKn6mUK4CAQwNPsBnOUOrQghhBBCyEQbS4H6VwAhDMPMYRhGDOBZANmDL2AYZhGANPQXpzcHncoD8DjDMIqByVGPDxybcMEDS001zZbDTQwYTNGAsWYyUiGEEEIIIaO4Y4HK8zwH4E/oLyzLAfwrz/NlDMPsZRhm9cBlHwGYAeA4wzBXGIbJHmjbBuAd9Be5fwWwd+DYhAt09KC6i+HMsmjoWwhzA02UIoQQQgiZaoRjuYjn+VwAuUOOvTnoz4+N0vYrAF/93gTvFpmAha9EhDoxC4YHnFghakquQ/3AZGdGCCGEEEIGmxY7STkEyyWoEfTP0Zol6kV15Zjqc0IIIYQQMoGmVYEaJJfiqtUKiFnMdupBfbMH+szcZKdFCCGEEEIGmV4FqkyMDs6G7tlOcBFLYeOFqC1pney0CCGEEELIINOrQJVLAQANPjIwVlfI2TZUFzZNclaEEEIIIWSwaVWgBg/M5L/mLgJvEyBUWopabRusfbZJzowQQgghhDhMqwLVTyqGkAHq5AIAgL/4JjgrUFdGw/yEEEIIIVPFtCpQhSyDQJkENYwdEDCYIRBDKuFQfenebK9KCCGEEELGb1oVqED/lqcGswUiLydYWTWClPWoKWmBzWqf7NQIIYQQQgimY4Eql+CqyQKhjxOstjkIkl+E1WxDffmkbHBFCCGEEEKGmH4FqkwCs51Hq7cMdrsc3n1FEMuEqL50c7JTI4QQQgghGONWp/eTIHn/TP56NxFCAdh6nDBnviuuFrfAZrNDIJh2NTshhJAp6OLFi55CofCfAMzHNOxQIvc1O4BSjuP+34iIiGF7CKddgRo8UKDWyViEMjz67MEIDu5DxV85NFQY4a9xn+QMCSGEEEAoFP6Tl5fXPKVSaWRZlp/sfAi5W+x2O9Pc3Ky5fv36PwFYPdw10+4nMi+xCDKWxdU+K4QKAax8MPxm1kMkEaD6Ms3mJ4QQMmXMVyqVnVSckvsNy7K8UqnsQP/owPDXTGA+UwLDMAiWS1Dda4F4tius9mAIO6sRuMAdV680w26n/w8QQgiZElgqTsn9auDv9oh16LQrUIH+91ANJjNEfjNhgwds1xsQtMgTpi4rmirbJzs9QgghhJBpbVoWqMEyCerMfeC9nQAA1utmBMx3h1DE0jA/IYQQMuDdd9/1DAoKClu9evWc8bSrqKgQp6amut2rvBy2b9/uc/LkSed7HWewvXv3enZ1dU1o/ZSWlub2+uuve01kzKGxTSYT89BDD6nUarXmiy++UOh0OvHChQvVAQEB81etWhVkNpuZuxl3WhaoQXIJbDxw3U0MAOgziiGSCOA/3x3Vl2+Cp2F+QgghBF9++aUyNze3Mjs7++p42lVWVkoyMzPHXaByHDeu6z/99NPGp556qmu8cX4vjuOQlpY2q7u7e0Lrp7y8PJeEhITOiYzpeBaO2BcuXJBbrVZGp9NpX3zxReOOHTtm/+lPf7pRW1tb6urqyh04cMDjbsafdrP4gf61UAGgxs5hgdwCq9kLMLUjeJEShsvNuH61E97BrpOcJSGEENLvv2cV+emvd8nv5meqvJx7P3o6vH6k84mJif7Xrl2TrF69eu6aNWvaDAaDtLy8XGaz2Zhdu3Y1btiwob2iokKcmJg4x2QysQBw4MCBuvj4+J5du3b5GgwGqVqt1jz33HMtCoXCVlhY6JSenl4HAHFxcXN37tx5IyEhoUsuly/aunXrjdOnT7t89NFH1+RyuX3Hjh1+vb29rEKh4L755puagIAA63A5rl27NjAhIaHjhRdeMPr6+i5Ys2ZN2y+//OLMcRyTmppam5yc7FtbWyt56aWXbrz22mvNOTk5znv27PFRKBScwWCQRkdHd2VkZNQJBAKkpaW57du3z4vneeaxxx5rP3z4cAMADM7v8ccf77h586Zo6dKlKoVCwRUUFOiff/55/6KiIiez2cw++eSTxk8++aQRAHx9fResW7euNS8vz5XjOCYzM9OwaNEic0dHB7tlyxb/4uJiOQC88cYbjZs2bWr/7rvvXPbu3evT19fHBAQEWI4dO1bj6upqt9vtKCsrk8fExPSO1Ha43D/88EPl1atXJampqdcA4ODBg+4XL16UHzlypP7QoUNuhw8fnmW1WpnFixf3pKen1wqFQgx9FvHx8d1lZWXywMDAvpiYGLXRaBSq1WrNiRMnqv/yl784f//99wYA2Lx5c+uePXt8Xn/99bs2DD1te1AB9E+UUrKw8sFAWzUCF3iAFTKovkyL9hNCCJnevv322zpPT0/r2bNn9T09PYK4uLjO0tLS8vz8/Irdu3fP7uzsZH18fLj8/Hy9Vqstz8zMNLzyyiv+APDee+81REZGdut0Ou1bb7016j+qJpOJnT9/vqm4uFgXGxvb8/LLL/t///331WVlZeUbN25sefXVV33HmrOfn1/flStXdNHR0d2bN28OPHXqVHVBQYEuJSXFx3FNSUmJ04EDB+orKirKampqJOnp6YqamhrRnj17fM+cOaPXarVlly9fdsrIyJg5NL+PP/64yfE9KSgo0APA/v37G0pLS8t1Ol3Z+fPnnQsKCmSOWB4eHpxWqy3fvHlzc0pKyiwASE5O9nZxcbHp9XqtXq/Xrlq1qqupqUn4/vvve587d06v1WrLFy9e3PvOO+/MAoALFy7INRpNL8uyw7YdKfekpCRjbm7uTEcuWVlZbomJicZLly5Js7Ky3AoLC3U6nU7LsiyfmprqPvRen3jiiW5HbD8/P+7QoUO1jmfq5uZmc3Z2tolEIgBAYGBg340bN8RjfU5jMS17UBUiIdxEAlw1WSCa7QpTrQj2pqsQ+0bAf54bDJeaEbN2Lhjmrr5OQQghhPwuo/V0ToQzZ8645OXlzTx48KAXAFgsFqaqqkocEBBg3bJlS4BWq5WxLIva2lrJeD9bIBBg06ZNRgAoLi6WVFZWypYtW6YCALvdDqVSOWzv6XDWrVvXDgALFizo7enpYRUKhV2hUNglEom9paVFMHCuR6PR9A1c35afnz9DJBLxS5Ys6fLx8eEAYP369W1nz56dkZSU1D44v+EcOXLE7euvv/bgOI5pbm4WFRUVSaOjo00AkJiYaASAqKio3uzsbAUAnDt3zuXYsWMGR3ulUmk7evSoa3V1tTQqKkoNAFarlYmIiOgGgJycHJcVK1Z0jtQ2Ly/PeaTc/fz8LD/99JNTWFiY2WAwSOPj47tTUlKUpaWl8vDw8HkAYDabWU9PT27osxgaezCev/1VSIZh7ur7kdOyQAX6h/mrey0QBfkC5ythrbsJSSQQtMgTNSXlaK7rgmeAy2SnSQghhEw6nueRlZVVFR4ebhl8fMeOHT6enp7WEydOXLXb7ZDJZBHDtRcKhbzdbr/1tcViuTWCKxaL7UKh0BGHmTt3runKlSu635OnVCrlAYBlWYjF4lsFE8uysFqtDIDbOp8Yhhm24Bouv6F0Op34s88+m3Xx4sVypVJpW7t2baDZbL51b458hEIhz3EcM3CPt+XA8zwefvjhzlOnTt32ru/p06dds7Ozq0ZrO5Knn37aePToUYVarTavXLnSyLIseJ5nnnnmmdbPP/+84U73Ojj2YF5eXlxXV5fAarVCJBKhpqZG7OnpOeYfJMZiWg7xA46lpiwQ+/e/w93XZAYAzAn3AMsyqL5Es/kJIYQQAIiLi+vct2/fLEeRef78eRkAdHR0CLy9va0CgQCHDh1yt9lsAABXV1dbd3e3wNE+ODi4r6ysTG6z2VBVVSUqLi52Gi7OwoULzW1tbcIff/zRCejvqS0sLJTezXspKSlx0ul0YpvNhqysLLdHHnmk69FHH+0pKChwbmpqEnIch+PHj7vFxsZ2D9feycnJ1tHRwQKA0WgUyGQyu5ubm62+vl545syZO05giY2N7dy/f7+n4+vm5mZBbGxsT2Fh4YzS0lIJAHR1dbHFxcWS1tZWgc1mg5eXl22ktqPlvmHDBuMPP/ygOH78uFtiYmIbAKxYsaIzJydH0dDQIASAGzduCPR6/W3D80NjD8ayLJYsWdL1z//8zwoA+Oqrr9wTEhLu6jqd07ZADZZJ0WSxwiwTgBV2w2rsf49C6iSCr1qB6ks3R/2phBBCCJkuUlJSGjmOY9RqtSYkJCRs9+7dvgCwffv2m0ePHnUPDw9X6/V6qUwmswNAVFSUSSgU8qGhoZq3337bMz4+vtvPz88SGhoatm3bNj+NRtM7XBypVMofO3asOjk5eXZoaKgmLCxMc/bs2Rl3814eeOCB7p07d85WqVRh/v7+lqSkpPaAgADrm2++2bB06VLVvHnzwhYuXNi7YcOGYQuujRs3tqxcuTIkOjpa9eCDD5rmz5/fGxISEpaUlBToGJYfzQcffNDU3t4uCAkJCQsNDdXk5uY6+/j4cGlpaTXPPvtskEql0kRERKhLSkqk2dnZLkuXLu0are1ouSuVSltISIipoaFBEhcX1wsAERER5t27dzcsX75cpVKpNMuWLVPV19eLhuY5NPZQ+/btu/bnP//Zy9/ff77RaBRu27atZSzf/7FiploRFhkZyRcWFt7zOKdutuPFshr8GKmC16F/A9dhhdd7zwEMg7L8Bpz5pgLrd0fBY/Zd/e+CEEIIGc5tkx6KiopqwsPD7+o/+tNdTk6O8759+2b9/PPPtw1bT0Xr168P2Lp1a8vy5ct77sfYRUVFHuHh4YHDnZu276AGO2bymyzwUzIwG33Ad7SAmanEnHAlzn5bgerLN6lAJYQQQsikyMzMrJ2OsYFpPMQfOLAWqqHXArGvKwABrFXVAAC5ixjec2fCQLtKEUIIIZMuKSnJX61Wawb/OnDggPt4PychIaHrj9J7Ot1N2x5UuYCFj0QEg8kC0dzZwM8t6Ku5CXFk//ngxZ7Iz9TDeL0HCq9h3+UmhBBCyATIyMiom+wcyMSatj2oQP9SU4ZeCwT+QWDQBet106/nHlACAM3mJ4QQQgiZYNO7QJX3F6iMSAKxuBF9bb9OYpuhkMAryIV2lSKEEEIImWDTukANlktg5Gxos3IQOXfBapoJ3vbrQsLBiz3RUt+NjmbTKJ9CCCGEEELupmldoAYNniilZAFeBO7mr0uz3Rrmp15UQgghhJAJM60L1GB5/+YU1b0WiHz7tzXtMzTdOu/iIYPS35lm8xNCCJmW3n33Xc+goKCw1atXzxlPu4qKCnFqaqrbvcrLYfv27T4nT550vtdxBtu7d69nV1fXhNZPaWlpbq+//rrXRMYcGttkMjEPPfSQSq1Wa7744gvF6tWr5wQGBs4PCQkJe+aZZwItFstta/n+V0zrAtVPKoaQAQwmC4T+fmBghrXmxm+uCV6sxI2rnehqM09SloQQQsjk+PLLL5W5ubmV2dnZt+0RP5rKykpJZmbmuAtUjuPGdf2nn37a+NRTT42429HdxnEc0tLSZnV3d09o/ZSXl+eSkJDQOZExHc/CEfvChQtyq9XK6HQ67Ysvvmh8/vnn2wwGQ2lFRUWZ2WxmPv30U4+7GX/aLjMFACKWgb90YKKUTxBEzI/oa/rtD4nBizzxHycNMFxuRvhyv0nKlBBCyLR28v/zw02t/K5+pqemF099Xj/S6cTERP9r165JVq9ePXfNmjVtBoNBWl5eLrPZbMyuXbsaN2zY0F5RUSFOTEycYzKZWAA4cOBAXXx8fM+uXbt8DQaDVK1Wa5577rkWhUJhKywsdEpPT68DgLi4uLk7d+68kZCQ0CWXyxdt3br1xunTp10++uija3K53L5jxw6/3t5eVqFQcN98801NQECAdbgc165dG5iQkNDxwgsvGH19fResWbOm7ZdffnHmOI5JTU2tTU5O9q2trZW89NJLN1577bXmnJwc5z179vgoFArOYDBIo6OjuzIyMuoEAgHS0tLc9u3b58XzPPPYY4+1Hz58uAEABuf3+OOPd9y8eVO0dOlSlUKh4AoKCvTPP/+8f1FRkZPZbGaffPJJ4yeffNIIAL6+vgvWrVvXmpeX58pxHJOZmWlYtGiRuaOjg92yZYt/cXGxHADeeOONxk2bNrV/9913Lnv37vXp6+tjAgICLMeOHatxdXW12+12lJWVyWNiYnpHajtc7h9++KHy6tWrktTU1GsAcPDgQfeLFy/Kjxw5Un/o0CG3w4cPz7JarczixYt70tPTa4VCIYY+i/j4+O6ysjJ5YGBgX0xMjNpoNArVarXmxIkT1evXr+9wPIfIyMiea9euie/OX8x+07oHFRiYyW8yA67+EAkMsBqF4O2/bv86c5Yc7r5O9B4qIYSQaeXbb7+t8/T0tJ49e1bf09MjiIuL6ywtLS3Pz8+v2L179+zOzk7Wx8eHy8/P12u12vLMzEzDK6+84g8A7733XkNkZGS3TqfTvvXWW6P+A2oymdj58+ebiouLdbGxsT0vv/yy//fff19dVlZWvnHjxpZXX33Vd6w5+/n59V25ckUXHR3dvXnz5sBTp05VFxQU6FJSUnwc15SUlDgdOHCgvqKioqympkaSnp6uqKmpEe3Zs8f3zJkzeq1WW3b58mWnjIyMmUPz+/jjj5sc35OCggI9AOzfv7+htLS0XKfTlZ0/f965oKBA5ojl4eHBabXa8s2bNzenpKTMAoDk5GRvFxcXm16v1+r1eu2qVau6mpqahO+//773uXPn9Fqttnzx4sW977zzziwAuHDhglyj0fSyLDts25FyT0pKMubm5s505JKVleWWmJhovHTpkjQrK8utsLBQp9PptCzL8qmpqe5D7/WJJ57odsT28/PjDh06VOt4pmFhYRbH51osFiYzM9N91apVtwrWu2Fa96ACQLBMgvPGbthZAcQzOtHTLgTXZobIQ/brNYs98Z85V9HTYYGTq2QSsyWEEDItjdLTORHOnDnjkpeXN/PgwYNeQH9RUlVVJQ4ICLBu2bIlQKvVyliWRW1t7bj/kRQIBNi0aZMRAIqLiyWVlZWyZcuWqQDAbrdDqVQO23s6nHXr1rUDwIIFC3p7enpYhUJhVygUdolEYm9paREMnOvRaDR9A9e35efnzxCJRPySJUu6fHx8OABYv35929mzZ2ckJSW1D85vOEeOHHH7+uuvPTiOY5qbm0VFRUXS6OhoEwAkJiYaASAqKqo3OztbAQDnzp1zOXbsmMHRXqlU2o4ePepaXV0tjYqKUgOA1WplIiIiugEgJyfHZcWKFZ0jtc3Ly3MeKXc/Pz/LTz/95BQWFmY2GAzS+Pj47pSUFGVpaak8PDx8HgCYzWbW09OTG/oshsYeycaNG/2XLFnSvWLFiu6xPaWxmfYFapBcApPdjusWKzw8ALQD1sbu3xSoQYuU+M9TV3H1SjPmL509eckSQgghk4DneWRlZVWFh4dbBh/fsWOHj6enp/XEiRNX7XY7ZDJZxHDthUIhb7f/uoyjxWK5NYIrFovtQqHQEYeZO3eu6cqVK7rfk6dUKuUBgGVZiMXiW8OhLMvCarUyAMAwv53LwzAMeJ7HSAbnN5ROpxN/9tlnsy5evFiuVCpta9euDTSbzbfuzZGPUCjkOY5jBu7xthx4nsfDDz/ceerUqdve9T19+rRrdnZ21WhtR/L0008bjx49qlCr1eaVK1caWZYFz/PMM8880/r555833OleB8cezs6dO71bWlqEeXl51SMm8TtN+yH+YPnAUlMmC0Q+CgAcrA2//SHAzdsJM2fJUU2z+QkhhExDcXFxnfv27ZvlKDLPnz8vA4COjg6Bt7e3VSAQ4NChQ+42mw0A4Orqauvu7hY42gcHB/eVlZXJbTYbqqqqRMXFxcPuIb5w4UJzW1ub8Mcff3QC+ntqCwsLpXfzXkpKSpx0Op3YZrMhKyvL7ZFHHul69NFHewoKCpybmpqEHMfh+PHjbrGxscP2CDo5Odk6OjpYADAajQKZTGZ3c3Oz1dfXC8+cOeN6p/ixsbGd+/fv93R83dzcLIiNje0pLCycUVpaKgGArq4utri4WNLa2iqw2Wzw8vKyjdR2tNw3bNhg/OGHHxTHjx93S0xMbAOAFStWdObk5CgaGhqEAHDjxg2BXq+/7f3RobGH2r9/v8fp06ddT548aRAIBMNd8l8y7QtUx1qo1b0WMMo5EDE16Ktr/c01DMMgeLESDfp2mLr7JiNNQgghZNKkpKQ0chzHqNVqTUhISNju3bt9AWD79u03jx496h4eHq7W6/VSmUxmB4CoqCiTUCjkQ0NDNW+//bZnfHx8t5+fnyU0NDRs27ZtfhqNpne4OFKplD927Fh1cnLy7NDQUE1YWJjm7NmzM+7mvTzwwAPdO3funK1SqcL8/f0tSUlJ7QEBAdY333yzYenSpap58+aFLVy4sHfDhg3tw7XfuHFjy8qVK0Oio6NVDz74oGn+/Pm9ISEhYUlJSYGOYfnRfPDBB03t7e2CkJCQsNDQUE1ubq6zj48Pl5aWVvPss88GqVQqTUREhLqkpESanZ3tsnTp0q7R2o6Wu1KptIWEhJgaGhokcXFxvQAQERFh3r17d8Py5ctVKpVKs2zZMlV9fb1oaJ5DYw/12muvBbS0tAgjIyPnqdVqzauvvuo9lu//WDGjdQ1PhsjISL6wsHDC4tl5HsHnSvC3Pu54m9Wj7aufYBY9Du+3HvlNN3pzXRf+9f2/Ii5JDU2MzyifSAghhIzbbWtIFhUV1YSHh7dMRjL3q5ycHOd9+/bN+vnnn0cctp5K1q9fH7B169aW5cuX99yPsYuKijzCw8MDhzs37d9BZRkGc2RiVJssgH8wxMwX6DUzsHX2QThoQpSH3wy4eEhRfamZClRCCCGE3HOZmZm10zE2QAUqgP6JUuXdZsAlECJhHcAB1obu3xSoDMMgaJEnik/Xw9JrhUR+W284IYQQQu6BpKQk/7/+9a+/Ger/+7//+xvbtm1rHanNcBISEroSEhImbGF/8vtRgYr+LfdVQocAACAASURBVE9/aOmAFQxE7gzQwMPa2A2Zxv231y1W4sq/16GmuAWhS+7qqxaEEEIIGUFGRkbdZOdAJta0nyQF9E+U4nig3twH1sMPQuFN9DXc/p7zrAAXzFBIaDY/IYQQQsg9RAUqfl1qqrrXDLgHQcRXwNp4e4HKsAyCHlCiTtuGPvP49gsmhBBCCCFjQwUq+t9BBfrXQoX7XIiZStg6+mDruX3ziuDFnrBZ7agtHddrL4QQQgghZIyoQAXgJhJCIRSgutcCuAVDxPRviDBcL6pXsCtkLmJUX6JhfkIIIYSQe4EK1AFBcgkMvRbAPRhitr9AHe49VJZlMHeREjUlLbD0jnl7YEIIIeQP59133/UMCgoKW7169ZzxtKuoqBCnpqa63au8HLZv3+5z8uRJ53sdZ7C9e/d6dnV1TWj9lJaW5vb66697TWTMobFNJhPz0EMPqdRqteaLL75QrF69ek5gYOD8kJCQsGeeeSbQYrEwAHD48GE3lUqlUalUmkWLFqn/8pe/yO4UYzhUoA6YI5PgqskCOHuDFfMQSHuH7UEFgHkxPrBZ7dD/540JzpIQQgiZOF9++aUyNze3Mjs7+7Y94kdTWVkpyczMHHeBynHjm9/x6aefNj711FMTtmwUx3FIS0ub1d3dPaH1U15enktCQkLnRMZ0PAtH7AsXLsitViuj0+m0L774ovH5559vMxgMpRUVFWVms5n59NNPPQBg7ty5lvPnz1fo9XrtP/7jPzb+3d/9XcDviU/LTA0IlkuQdcOIXjsPuVsQxMZGWBvdh71W6e8MD78Z0J5vxILY2ROcKSGEkOnmf5z/H35Vxir53fzMuYq5ve/EvFM/0vnExET/a9euSVavXj13zZo1bQaDQVpeXi6z2WzMrl27Gjds2NBeUVEhTkxMnGMymVgAOHDgQF18fHzPrl27fA0Gg1StVmuee+65FoVCYSssLHRKT0+vA4C4uLi5O3fuvJGQkNAll8sXbd269cbp06ddPvroo2tyudy+Y8cOv97eXlahUHDffPNNTUBAwLBDlmvXrg1MSEjoeOGFF4y+vr4L1qxZ0/bLL784cxzHpKam1iYnJ/vW1tZKXnrppRuvvfZac05OjvOePXt8FAoFZzAYpNHR0V0ZGRl1AoEAaWlpbvv27fPieZ557LHH2g8fPtwAAIPze/zxxztu3rwpWrp0qUqhUHAFBQX6559/3r+oqMjJbDazTz75pPGTTz5pBABfX98F69ata83Ly3PlOI7JzMw0LFq0yNzR0cFu2bLFv7i4WA4Ab7zxRuOmTZvav/vuO5e9e/f69PX1MQEBAZZjx47VuLq62u12O8rKyuQxMTG9I7UdLvcPP/xQefXqVUlqauo1ADh48KD7xYsX5UeOHKk/dOiQ2+HDh2dZrVZm8eLFPenp6bVCoRBDn0V8fHx3WVmZPDAwsC8mJkZtNBqFarVac+LEier169d3OJ5DZGRkz7Vr18QAEB8ff2vnqbi4uJ4//elP4t/z95N6UAc4JkrVmCyAW/9Mfq7FBPsIs/U1MT5oqe9Gcx2t90sIIeT+8+2339Z5enpaz549q+/p6RHExcV1lpaWlufn51fs3r17dmdnJ+vj48Pl5+frtVpteWZmpuGVV17xB4D33nuvITIyslun02nfeuutm6PFMZlM7Pz5803FxcW62NjYnpdfftn/+++/ry4rKyvfuHFjy6uvvuo71pz9/Pz6rly5oouOju7evHlz4KlTp6oLCgp0KSkpt7aALCkpcTpw4EB9RUVFWU1NjSQ9PV1RU1Mj2rNnj++ZM2f0Wq227PLly04ZGRkzh+b38ccfNzm+JwUFBXoA2L9/f0NpaWm5TqcrO3/+vHNBQcGtIW0PDw9Oq9WWb968uTklJWUWACQnJ3u7uLjY9Hq9Vq/Xa1etWtXV1NQkfP/9973PnTun12q15YsXL+595513ZgHAhQsX5BqNppdl2WHbjpR7UlKSMTc3d6Yjl6ysLLfExETjpUuXpFlZWW6FhYU6nU6nZVmWT01NdR96r0888US3I7afnx936NChWsczDQsLszg+12KxMJmZme6rVq26VbA6/PnPf/aIi4u77fhYUA/qgGCZY6kpCzTuwRBpLwBYBWtTDyRzXG+7XhU1C+dPVEH7SyOWJoZOcLaEEEKmk9F6OifCmTNnXPLy8mYePHjQC+gvSqqqqsQBAQHWLVu2BGi1WhnLsqitrZXc6bOGEggE2LRpkxEAiouLJZWVlbJly5apAMBut0OpVI55wse6devaAWDBggW9PT09rEKhsCsUCrtEIrG3tLQIBs71aDSavoHr2/Lz82eIRCJ+yZIlXT4+PhwArF+/vu3s2bMzkpKS2gfnN5wjR464ff311x4cxzHNzc2ioqIiaXR0tAkAEhMTjQAQFRXVm52drQCAc+fOuRw7dszgaK9UKm1Hjx51ra6ulkZFRakBwGq1MhEREd0AkJOT47JixYrOkdrm5eU5j5S7n5+f5aeffnIKCwszGwwGaXx8fHdKSoqytLRUHh4ePg8AzGYz6+npyQ19FkNjj2Tjxo3+S5Ys6V6xYsVv3os8deqU87/8y794XLhwQTda+5FQgTpgzkCB2j9Rai7E+BpA/0Sp4QpUiVyEuYs9of/P63jo6bkQiQUTmS4hhBAyYXieR1ZWVlV4eLhl8PEdO3b4eHp6Wk+cOHHVbrdDJpNFDNdeKBTydrv91tcWi+XWCK5YLLYLhUJHHGbu3LmmK1eu/K6iRiqV8gDAsizEYjHvOM6yLKxWKwP0b10+GMMw4HkeIxmc31A6nU782Wefzbp48WK5Uqm0rV27NtBsNt+6N0c+QqGQ5ziOGbjH23LgeR4PP/xw56lTp2571/f06dOu2dnZVaO1HcnTTz9tPHr0qEKtVptXrlxpZFkWPM8zzzzzTOvnn3/ecKd7HRx7ODt37vRuaWkR5uXlVQ8+XlBQIPuHf/iHgH/7t3+r9PLyso2Y4ChoiH+Ak1AAb4kI1SYz4BYMAWMEK+NHnCgFAJqHvdFntqH60qijF4QQQsgfWlxcXOe+fftmOYrM8+fPywCgo6ND4O3tbRUIBDh06JC7zdZfi7i6utq6u7tv9dwEBwf3lZWVyW02G6qqqkTFxcVOw8VZuHChua2tTfjjjz86Af09tYWFhdK7eS8lJSVOOp1ObLPZkJWV5fbII490Pfrooz0FBQXOTU1NQo7jcPz4cbfY2NhhCwAnJydbR0cHCwBGo1Egk8nsbm5utvr6euGZM2du79EaIjY2tnP//v2ejq+bm5sFsbGxPYWFhTNKS0slANDV1cUWFxdLWltbBTabDY4ib7i2o+W+YcMG4w8//KA4fvy4W2JiYhsArFixojMnJ0fR0NAgBIAbN24I9Hr9be+JDo091P79+z1Onz7tevLkSYNA8GsnXWVlpfiZZ54J/uqrr64uXLjQMlzbsaACdZAg2a9LTQGA2KV71ALVe+5MuHrKUH6+aaJSJIQQQiZcSkpKI8dxjFqt1oSEhITt3r3bFwC2b99+8+jRo+7h4eFqvV4vlclkdgCIiooyCYVCPjQ0VPP22297xsfHd/v5+VlCQ0PDtm3b5qfRaHqHiyOVSvljx45VJycnzw4NDdWEhYVpzp49O+Nu3ssDDzzQvXPnztkqlSrM39/fkpSU1B4QEGB98803G5YuXaqaN29e2MKFC3s3bNjQPlz7jRs3tqxcuTIkOjpa9eCDD5rmz5/fGxISEpaUlBToGJYfzQcffNDU3t4uCAkJCQsNDdXk5uY6+/j4cGlpaTXPPvtskEql0kRERKhLSkqk2dnZLkuXLu0are1ouSuVSltISIipoaFBEhcX1wsAERER5t27dzcsX75cpVKpNMuWLVPV19eLhuY5NPZQr732WkBLS4swMjJynlqt1rz66qveALB7927v9vZ24UsvvRSgVqs18+fPn3fnp3I7ZrSu4ckQGRnJFxYWTkrs1yrqkdPcDm3MfOADP3S4vo2uBhV8344BIxq+lr+UV4u//O9qPP/2EsycdVcnWBJCCJk+mKEHioqKasLDw1smI5n7VU5OjvO+fftm/fzzzyMOW08l69evD9i6dWvL8uXLe+589R8vdlFRkUd4eHjgcOeoB3WQOTIJ2qw2GDkb4B4EESoAO2C9PvKzCV3iBZZloD3fOIGZEkIIIeR+l5mZWTsZxelkxwbGWKAyDLOCYZgKhmGqGIZJHub8owzDXGIYhmMY5ukh52wMw1wZ+JV9txK/F4IHlpq6OrDlqdjc35PbN8owv5OrBIELPaD7SxNsNvuI1xFCCCHk90lKSvJXq9Wawb8OHDgw/GLlo0hISOj6o/SeTnd3nMXPMIwAwOcA4gFcA/BXhmGyeZ7XDrqsDsAmAK8O8xEmnucfuAu53nOOtVCrTRYsdg+GoOwkGKlg1PdQAWBejDcMV5pRW9yKoEXKiUiVEEIImTYyMjLqJjsHMrHG0oMaBaCK53kDz/N9AI4B+G+DL+B5vobn+WIAf+guRH+pGALm16WmGNghVgrQ1zh6D7d/mDucZkpomJ8QQggh5C4YS4HqC2DwAsHXBo6NlZRhmEKGYf6DYZinhruAYZitA9cUNjc3j+Oj7y4xy8JfKka1qX+IHwBELj2wNvWAt408mYxlGcx7yBt1Za3oajNPVLqEEEIIIfelsRSot80sBDCeqf/+PM9HAkgE8CnDMMG3fRjP/y+e5yN5no9UKid3iDxIJv3tUlOSJoCzg2sedkWMW+Y95A2eB3R/oSWnCCGEEEL+K8ZSoF4D4Dfo69kAxjyWzfN848DvBgBnACwaR34TLlgugcFkAS9TANKZ/TP50b+j1GhcPGSYrVag/HwTePvUWrqLEEIIIeSPZCwF6l8BhDAMM4dhGDGAZwGMaTY+wzAKhmEkA3/2ABADQDt6q8k1Ry5Br82OG30c4B4MYW8RGBF7x4lSAKB52AddbWZc0424ZS8hhBDyh/Huu+96BgUFha1evXrOeNpVVFSIU1NT3e5VXg7bt2/3OXnypPO9jjPY3r17Pbu6uiZ0mc60tDS3119/3WsiYw6NbTKZmIceekilVqs1X3zxhWLdunUBoaGhGpVKpVmxYkWQY3etu+WOH8bzPAfgTwDyAJQD+Fee58sYhtnLMMxqAGAY5v9hGOYagGcApDEMUzbQfB6AQoZhigD8DCBlyOz/KSdYNjCTv7d/y1PGWA2Rt9OoS005BIUrIXES0mQpQggh94Uvv/xSmZubW5mdnX3bHvGjqayslGRmZo67QOU4blzXf/rpp41PPfXUiLsd3W0cxyEtLW1Wd3f3hBaoeXl5LgkJCZ0TGdPxLByxL1y4ILdarYxOp9O++OKLxtTU1PqKigqtXq/Xzp49u+/DDz/0vMNHjssdl5kCAJ7ncwHkDjn25qA//xX9Q/9D210AsOC/mOOEciw1ZTBZEOMeDJQch2ihDL1FreDtPBh2uFdy+wlELNTR3ig5dw2m7j7IZty2tS0hhBAybo1v7PKzVFbe1e0KJSEhvT7vv1c/0vnExET/a9euSVavXj13zZo1bQaDQVpeXi6z2WzMrl27Gjds2NBeUVEhTkxMnGMymVgAOHDgQF18fHzPrl27fA0Gg1StVmuee+65FoVCYSssLHRKT0+vA4C4uLi5O3fuvJGQkNAll8sXbd269cbp06ddPvroo2tyudy+Y8cOv97eXlahUHDffPNNTUBAgHW4HNeuXRuYkJDQ8cILLxh9fX0XrFmzpu2XX35x5jiOSU1NrU1OTvatra2VvPTSSzdee+215pycHOc9e/b4KBQKzmAwSKOjo7syMjLqBAIB0tLS3Pbt2+fF8zzz2GOPtR8+fLgBAAbn9/jjj3fcvHlTtHTpUpVCoeAKCgr0zz//vH9RUZGT2Wxmn3zySeMnn3zSCAC+vr4L1q1b15qXl+fKcRyTmZlpWLRokbmjo4PdsmWLf3FxsRwA3njjjcZNmza1f/fddy579+716evrYwICAizHjh2rcXV1tdvtdpSVlcljYmJ6R2o7XO4ffvih8urVq5LU1NRrAHDw4EH3ixcvyo8cOVJ/6NAht8OHD8+yWq3M4sWLe9LT02uFQiGGPov4+PjusrIyeWBgYF9MTIzaaDQK1Wq15sSJE9VhYWEWALDb7TCZTCzDjFwf/R60k9QQPhIRpCyD6l7HTH4eYtde8BYbbGOYoT8vxht2joe+4Ma9T5YQQgi5R7799ts6T09P69mzZ/U9PT2CuLi4ztLS0vL8/PyK3bt3z+7s7GR9fHy4/Px8vVarLc/MzDS88sor/gDw3nvvNURGRnbrdDrtW2+9dXO0OCaTiZ0/f76puLhYFxsb2/Pyyy/7f//999VlZWXlGzdubHn11VfHvHKQn59f35UrV3TR0dHdmzdvDjx16lR1QUGBLiUlxcdxTUlJidOBAwfqKyoqympqaiTp6emKmpoa0Z49e3zPnDmj12q1ZZcvX3bKyMiYOTS/jz/+uMnxPSkoKNADwP79+xtKS0vLdTpd2fnz550LCgpkjlgeHh6cVqst37x5c3NKSsosAEhOTvZ2cXGx6fV6rV6v165ataqrqalJ+P7773ufO3dOr9VqyxcvXtz7zjvvzAKACxcuyDUaTS/LssO2HSn3pKQkY25u7kxHLllZWW6JiYnGS5cuSbOystwKCwt1Op1Oy7Isn5qa6j70Xp944oluR2w/Pz/u0KFDtY5n6ihOn3766UClUhleVVUlTU5OHvU5j9eYelCnE5ZhMEcm+c1MfpGkCYAz+hq7IfSQjdre3XcGZs1xgfZ8IxYum427/RMFIYSQ6We0ns6JcObMGZe8vLyZBw8e9AIAi8XCVFVViQMCAqxbtmwJ0Gq1MpZlUVtbKxnvZwsEAmzatMkIAMXFxZLKykrZsmXLVEB/75xSqRy293Q469ataweABQsW9Pb09LAKhcKuUCjsEonE3tLSIhg416PRaPoGrm/Lz8+fIRKJ+CVLlnT5+PhwALB+/fq2s2fPzkhKSmofnN9wjhw54vb11197cBzHNDc3i4qKiqTR0dEmAEhMTDQCQFRUVG92drYCAM6dO+dy7Ngxg6O9Uqm0HT161LW6uloaFRWlBgCr1cpERER0A0BOTo7LihUrOkdqm5eX5zxS7n5+fpaffvrJKSwszGwwGKTx8fHdKSkpytLSUnl4ePg8ADCbzaynpyc39FkMjT2crKysGo7jsGnTJv+vvvpKsW3bttaxPqs7oQJ1GEFyCSp6zL8WqPYqgF3cP1Fq4Z2XwdLE+ODnf9HhxtVOeAW53ut0CSGEkHuK53lkZWVVhYeHWwYf37Fjh4+np6f1xIkTV+12O2QyWcRw7YVCIW+3/7qXj8ViuTWCKxaL7UKh0BGHmTt3runKlSu635OnVCrlAYBlWYjF4ltL6rAsC6vVygC4reOIYRjw/Mir7wzObyidTif+7LPPZl28eLFcqVTa1q5dG2g2m2/dmyMfoVDIcxzHDNzjbTnwPI+HH36489SpU7e963v69GnX7OzsqtHajuTpp582Hj16VKFWq80rV640siwLnueZZ555pvXzzz9vuNO9Do49EqFQiOeee67t448/9rqbBSoN8Q8jWCZBjckCTuwCyD3AtFdCNEt+xx2lHOZGekIoEdBkKUIIIfeFuLi4zn379s1yFJnnz5+XAUBHR4fA29vbKhAIcOjQIXebzQYAcHV1tXV3dwsc7YODg/vKysrkNpsNVVVVouLiYqfh4ixcuNDc1tYm/PHHH52A/p7awsJC6d28l5KSEiedTie22WzIyspye+SRR7oeffTRnoKCAuempiYhx3E4fvy4W2xs7LCzo52cnGyOGetGo1Egk8nsbm5utvr6euGZM2fu2CsVGxvbuX///lsTipqbmwWxsbE9hYWFM0pLSyUA0NXVxRYXF0taW1sFNpsNXl5etpHajpb7hg0bjD/88IPi+PHjbomJiW0AsGLFis6cnBxFQ0ODEABu3Lgh0Ov1t02aGRp7MLvdDkeudrsd33///cyQkJC7ulMRFajDCJJLwPHANUtffy9qqwEinxmwNnSP+pOKg1gqREikJyoLb6LPPL4ZiYQQQshUk5KS0shxHKNWqzUhISFhu3fv9gWA7du33zx69Kh7eHi4Wq/XS2UymR0AoqKiTEKhkA8NDdW8/fbbnvHx8d1+fn6W0NDQsG3btvlpNJphd7+RSqX8sWPHqpOTk2eHhoZqwsLCNGfPnp1xN+/lgQce6N65c+dslUoV5u/vb0lKSmoPCAiwvvnmmw1Lly5VzZs3L2zhwoW9GzZsaB+u/caNG1tWrlwZEh0drXrwwQdN8+fP7w0JCQlLSkoKdAzLj+aDDz5oam9vF4SEhISFhoZqcnNznX18fLi0tLSaZ599NkilUmkiIiLUJSUl0uzsbJelS5d2jdZ2tNyVSqUtJCTE1NDQIImLi+sFgIiICPPu3bsbli9frlKpVJply5ap6uvrRUPzHBp7MJ7n8bd/+7dzVCqVJjQ0NOz69euilJSUu9orx4yl4JpIkZGRfGFh4aTm8J/t3Vh9uQrfLAzC8nOvA4af0f3gabRnV8P7H6MgcL3zKzbXDR048T8vIm6DGpqHfe54PSGEkGnttgkLRUVFNeHh4S2Tkcz9Kicnx3nfvn2zfv7551GHraeK9evXB2zdurVl+fLlYxvC/YPFLioq8ggPDw8c7hy9gzqMIHn/aIKh14Ll7kFA0bcQKftHKvoauiEbQ4E6a44L3HycoD3fSAUqIYQQQsYtMzOzdjrGBmiIf1juIgFchQJUmxxLTQEiyQ2AwZh2lAL6X7rWxPjgxtVOtN5hm1RCCCGEjCwpKclfrVZrBv86cOCA+3g/JyEhoeuP0ns63VEP6jAYhkGQTAJDrxmYNRcAwHYZIPSYPeaJUgCgip6FC/+7CtrzjXhknepepUsIIYTc1zIyMuomOwcysagHdQTBcsnAYv1B/QfaqvsnSo2xBxUAZDPECHpAiYqC67BZ7XduQAghhBBCqEAdSZBcggaLFSahHJjhBbQaIPaZAVu7BbaeMa8ZDE2MDyw9HAxFzfcwW0IIIYSQ+wcVqCMIkvVPhKoxDewo1VoFkW//sm3j6UWdHaqAs7sU2l9oTVRCCCGEkLGgAnUEwfL+AtVgGhjmb6uG2Kd/KbbxFKgMy2DeQ964pjOis8V0T3IlhBBCCLmfUIE6gjkDPaiG3oEe1J5msKwJgpmScU2UAgD1g95gGKD8QtO9SJUQQgi5J959913PoKCgsNWrV88ZT7uKigpxamqq273Ky2H79u0+J0+edL7XcQbbu3evZ1dX14TWT2lpaW6vv/6610TGHBrbZDIxDz30kEqtVmu++OILxbp16wJCQ0M1KpVKs2LFiiDH7lp6vV784IMPqlQqlSYqKiq0urr6tk0AxoIK1BHMEAowSywcmCjVv9TUrYlS41w2ytlNCv8wd5RfaILdRpOlCCGE/DF8+eWXytzc3Mrs7Ozb9ogfTWVlpSQzM3PcBSrHjW/3xU8//bTxqaeeGna3o3uB4zikpaXN6u7untD6KS8vzyUhIaFzImM6noUj9oULF+RWq5XR6XTaF1980ZiamlpfUVGh1ev12tmzZ/d9+OGHngCwbdu22YmJia16vV67e/fuxp07d87+PfFpmalRBMkl/UP8vgMFams1xL5RMJe3wm7hwErG/u3TxPjg/6SVoE7bhsAFHvcoY0IIIfejn9LL/doauuV38zPdfGf0Lv/befUjnU9MTPS/du2aZPXq1XPXrFnTZjAYpOXl5TKbzcbs2rWrccOGDe0VFRXixMTEOSaTiQWAAwcO1MXHx/fs2rXL12AwSNVqtea5555rUSgUtsLCQqf09PQ6AIiLi5u7c+fOGwkJCV1yuXzR1q1bb5w+fdrlo48+uiaXy+07duzw6+3tZRUKBffNN9/UBAQEDDs7ee3atYEJCQkdL7zwgtHX13fBmjVr2n755RdnjuOY1NTU2uTkZN/a2lrJSy+9dOO1115rzsnJcd6zZ4+PQqHgDAaDNDo6uisjI6NOIBAgLS3Nbd++fV48zzOPPfZY++HDhxsAYHB+jz/+eMfNmzdFS5cuVSkUCq6goED//PPP+xcVFTmZzWb2ySefNH7yySeNAODr67tg3bp1rXl5ea4cxzGZmZmGRYsWmTs6OtgtW7b4FxcXywHgjTfeaNy0aVP7d99957J3716fvr4+JiAgwHLs2LEaV1dXu91uR1lZmTwmJqZ3pLbD5f7hhx8qr169KklNTb0GAAcPHnS/ePGi/MiRI/WHDh1yO3z48Cyr1cosXry4Jz09vVYoFGLos4iPj+8uKyuTBwYG9sXExKiNRqNQrVZrTpw4UR0WFmYBALvdDpPJxDJM/2ZolZWVsr/5m7+pB/rXnU1MTJz7e/5+Ug/qKIJl0iFLTRkg8nECeMDaNL5h/oCF7pA5i2iyFCGEkD+Eb7/9ts7T09N69uxZfU9PjyAuLq6ztLS0PD8/v2L37t2zOzs7WR8fHy4/P1+v1WrLMzMzDa+88oo/ALz33nsNkZGR3TqdTvvWW2/dHC2OyWRi58+fbyouLtbFxsb2vPzyy/7ff/99dVlZWfnGjRtbXn31Vd+x5uzn59d35coVXXR0dPfmzZsDT506VV1QUKBLSUm5taVjSUmJ04EDB+orKirKampqJOnp6YqamhrRnj17fM+cOaPXarVlly9fdsrIyJg5NL+PP/64yfE9KSgo0APA/v37G0pLS8t1Ol3Z+fPnnQsKCmSOWB4eHpxWqy3fvHlzc0pKyiwASE5O9nZxcbHp9XqtXq/Xrlq1qqupqUn4/vvve587d06v1WrLFy9e3PvOO+/MAoALFy7INRpNL8uyw7YdKfekpCRjbm7uTEcuWVlZbomJicZLly5Js7Ky3AoLC3U6nU7LsiyfmprqPvRen3jiiW5Hiue1agAAIABJREFUbD8/P+7QoUO1jmfqKE6ffvrpQKVSGV5VVSVNTk6+CQDz5s3r/fbbbxUAkJGRMbOnp4e9fv26YKzP0IF6UEcRJJeg1cqhHSLMdJnd34O6aGCiVEM3JIGuY/4sgYCF+kFvXPmxHj0dFjiNYbtUQgghBABG6+mcCGfOnHHJy8ubefDgQS8AsFgsTFVVlTggIMC6ZcuWAK1WK2NZFrW1teP+x00gEGDTpk1GACguLpZUVlbKli1bpgL6e+eUSuWY13Zct25dOwAsWLCgt6enh1UoFHaFQmGXSCT2lpYWwcC5Ho1G0zdwfVt+fv4MkUjEL1mypMvHx4cDgPXr17edPXt2RlJSUvvg/IZz5MgRt6+//tqD4zimublZVFRUJI2OjjYBQGJiohEAoqKierOzsxUAcO7cOZdjx44ZHO2VSqXt6NGjrtXV1dKoqCg1AFitViYiIqIbAHJyclxWrFjROVLbvLw855Fy9/Pzs/z0009OYWFhZoPBII2Pj+9OSUlRlpaWysPDw+cBgNlsZj09Pbmhz2Jo7OFkZWXVcByHTZs2+X/11VeKbdu2tf75z3++tnXrVv958+Z5LFmypMvT09MqEo3/NVQqUEcxeCb/YvcgoLUKrLMY7AzRuCdKAf3D/Jf//zpU/Md1LH4i4G6nSwj5v+zdeVhT17438O/eCZmYDJAIwQACGQhIVCxYJ0BLq6162jpTOFq99T3nfXuq1Q7eyrVqB+mgrd6qcHt663BapGKPRcqRc1orTpUWlZkQBhlElHlMCBn2+wfGgwgoFqjD+jxPnpZkr71+O/GBX9ba67cIghgWDMMgKSmpRK1WG3o+v27dOolYLDYeOXLkssViAZ/PD+qrPZvNZiyWf6/BMBgMN2dwORyOhc1mW/uhfH199VlZWZp7iZPH4zEAQNM0OBwOY32epmkYjUYK6N4tsieKosAwDPrTM77eNBoN57PPPht94cKFQpFIZF6wYIFXZ2fnzWuzxsNmsxmTyUTduMbbYmAYBtOmTWs9duzYbff6njhxwjE5OblkoLb9WbhwYVNCQoJQqVR2zpkzp4mmaTAMQy1atKhh9+7d1Xe61p5994fNZmPZsmWNH3/8seuaNWsavLy8jP/85z9LAaClpYVOTU0VOjs7mwc6R1/IFP8ArLVQL1sXSjWWgqIo2Ejs0FU1+HuyR40WQCIbhYIzVwf8B0UQBEEQ95Pw8PDW7du3j7YmmWfPnuUDQEtLC8vNzc3IYrGwZ88eZ7O5Ow9xdHQ0t7e335zW9fHx6crPzxeYzWaUlJTY5OTk2PbVT2BgYGdjYyP7hx9+sAW6R2ozMzN5Q3ktubm5thqNhmM2m5GUlOQ0ffr0thkzZnRkZGTY19TUsE0mEw4fPuwUFhbW54poW1tbs3XFelNTE4vP51ucnJzMVVVV7JMnT95xajUsLKx1x44dYuvPdXV1rLCwsI7MzEy7vLw8LgC0tbXROTk53IaGBpbZbIarq6u5v7YDxR4VFdV0/Phx4eHDh50iIyMbAWD27NmtKSkpwurqajYAXL9+naXVajm94+zdd08WiwXWWC0WC7777rtRMpmsEwBqamrY1n8HMTExbsuWLau/03vSF5KgDsCTzwENoNRarF/fBOgawVMIYarVwXj9XkZR3dBSp8fV4uahD5ggCIIghkFsbOxVk8lEKZVKlUwm84+JiXEHgLVr19YmJCQ4q9VqpVar5fH5fAsABAcH69lsNqNQKFRbtmwRR0REtEulUoNCofBfs2aNVKVS6frqh8fjMYcOHSrdsGHDGIVCofL391elp6fbDeW1jB8/vn39+vVj5HK5v4eHhyE6OrrZ09PTuGnTpurQ0FC5n5+ff2BgoC4qKqrPP9TLly+vnzNnjiwkJET++OOP6wMCAnQymcw/OjrayzotP5Bt27bVNDc3s2Qymb9CoVClpqbaSyQSU3x8fPnSpUu95XK5KigoSJmbm8tLTk52CA0NbRuo7UCxi0Qis0wm01dXV3PDw8N1ABAUFNQZExNTPWvWLLlcLlfNnDlTXlVVddscfO++e2IYBn/84x/HyuVylUKh8L927ZpNbGzsVQA4fvy4vbe3d4CXl1dAbW0te9u2bfdUY5O630byJk2axGRmZv7eYdwU8nMBJjgIEMcqAA4tA/7jR5gdA1GzLQP2oVI4PuU1qPMZu8zY98YZjFWL8MSLquEJmiAIgnjQUL2fyM7OLler1fc0+kT0LSUlxX779u2jf/rppwGnre8XS5Ys8Vy9enX9rFmzBj8i9gD0nZ2d7aJWq736eo3cg3oH3gJud7F+r3+XmmKNmQSurxC6S7VwiPAERd/2e6VfNhwW5MGuKPy5BtOXyMAV3FP9WoIgCIIgHnKJiYkVj2LfAJnivyMfARelegOYUZ4ARQONpQAAwQQxzM0GdFUOvm6uapoEZqMF2l+uD3W4BEEQBPHQiY6O9lAqlaqej507dzoP9jxz585te1BGTx91ZAT1Drz5XHSYLai1sDDaUQo0dCeofJUzmm1o6C7VDqrcFACIPOzhIrVDwdmrGBd2TxssEARBEMQj4+DBg5W/dwzEyCIjqHfgI+hePFiqu7FQ6sYIKs1lge/vDF1OPRjT4LcvVU2VoL6qHXWVI7ZDG0EQBEEQxAOBJKh34H2jFupl/Y1SUw2lwI2FZfwJYjB6EzqL+q3f2y958GiwbGiysxRBEARBEEQvJEG9A3euDbg09e8RVEMr0NG9qJLnKwRtawNd1oC7uPWJK7CB70QxtL9cg7Fr0PVrCYIgCIIgHlokQb0DmqLgxeeiTN/ZPYIK3Jzmp1gUBGoR9IUNsHSaBn1u1TQ3dHWaUXpx8AkuQRAEQRDEw4okqHfBh8/99wgqcHOhFNC9mh8mBvrcwZeqc/MdBUcxn0zzEwRBEPeld999V+zt7e0/f/78sYNpV1RUxImLi3Marris1q5dKzl69Kj9cPfT09atW8VtbW0jmj/Fx8c7vfnmm64j2WfvvvV6PTVlyhS5UqlUff7550Lr68uXL5cKBIIJ1p937drlLBQK1dZqCzt27HC5l35JgnoXvAVclOu7YHaUAjT75ggqANiMsQPbmXdP0/wURUE1VYKakhY0XRvxGrwEQRAEMaAvvvhClJqaWpycnHzbHvEDKS4u5iYmJg46QTWZBjcb+emnn1599tlnR2y1sclkQnx8/Oj29vYRzZ/S0tIc5s6dO/i6lr+B9bOw9n3u3DmB0WikNBpNwUsvvdQEAKdOnRK0tLTcVhFq3rx5TRqNpkCj0RSsW7funjabIGWm7oK3gAsjw+CKkYHnKM9bRlApioJgghitP1bC3GIAy5E7qHMrJrvi/HdlKDxbgykLfIc6dIIgCOIhkLb3U2l9VYVgKM/pIvXUPfXntVX9vR4ZGelx5coV7vz5832fe+65xrKyMl5hYSHfbDZTGzduvBoVFdVcVFTEiYyMHKvX62kA2LlzZ2VERETHxo0b3cvKynhKpVK1bNmyeqFQaM7MzLQ9cOBAJQCEh4f7rl+//vrcuXPbBALBhNWrV18/ceKEw0cffXRFIBBY1q1bJ9XpdLRQKDR99dVX5Z6ensa+YlywYIHX3LlzW1588cUmd3f3cc8991zjmTNn7E0mExUXF1exYcMG94qKCu5f/vKX62+88UZdSkqK/ebNmyVCodBUVlbGCwkJaTt48GAli8VCfHy80/bt210ZhqGeeOKJ5r1791YDQM/4nnzyyZba2lqb0NBQuVAoNGVkZGhfeOEFj+zsbNvOzk563rx5TZ988slVAHB3dx+3ePHihrS0NEeTyUQlJiaWTZgwobOlpYVetWqVR05OjgAA3nrrrasrVqxo/vbbbx22bt0q6erqojw9PQ2HDh0qd3R0tFgsFuTn5wumTp2q669tX7F/8MEHosuXL3Pj4uKuAN0jmxcuXBDs37+/as+ePU579+4dbTQaqYkTJ3YcOHCggs1mo/dnERER0Z6fny/w8vLqmjp1qrKpqYmtVCpVR44cKVUoFIbXX399zDfffHPZz89v1FD+2wTICOpd8eF3J529S01ZCcaLAQbQZdcN+ty2jlx4jXOG5nwNzObBl6siCIIgiOHw9ddfV4rFYmN6erq2o6ODFR4e3pqXl1d4+vTpopiYmDGtra20RCIxnT59WltQUFCYmJhY9uqrr3oAwHvvvVc9adKkdo1GU/D2228POMWo1+vpgIAAfU5OjiYsLKzjlVde8fjuu+9K8/PzC5cvX17/2muvud9tzFKptCsrK0sTEhLSvnLlSq9jx46VZmRkaGJjYyXWY3Jzc2137txZVVRUlF9eXs49cOCAsLy83Gbz5s3uJ0+e1BYUFORfunTJ9uDBg6N6x/fxxx/XWN+TjIwMLQDs2LGjOi8vr1Cj0eSfPXvWPiMjg2/ty8XFxVRQUFC4cuXKutjY2NEAsGHDBjcHBwezVqst0Gq1Bc8880xbTU0N+/3333c7deqUtqCgoHDixIm6d955ZzQAnDt3TqBSqXQ0TffZtr/Yo6Ojm1JTU28mjklJSU6RkZFNFy9e5CUlJTllZmZqNBpNAU3TTFxcnHPva33qqafarX1LpVLTnj17Kqyfqb+/v2Hbtm3ip59+urmvLw//+Mc/RsnlctXs2bO9S0pK7mnLTDKCehespabK9AbMdPIBys92l5qiurc4ZbvwwZHaQ3epFvYzBl94XzVNgsvZ9ajIaYD3BNGQxk4QBEE8+AYa6RwJJ0+edEhLSxu1a9cuVwAwGAxUSUkJx9PT07hq1SrPgoICPk3TqKioGNw0IgAWi4UVK1Y0AUBOTg63uLiYP3PmTDkAWCwWiESiPkdP+7J48eJmABg3bpyuo6ODFgqFFqFQaOFyuZb6+nrWjdc6VCpV143jG0+fPm1nY2PDTJ48uU0ikZgAYMmSJY3p6el20dHRzT3j68v+/fud9u3b52Iymai6ujqb7OxsXkhIiB4AIiMjmwAgODhYl5ycLASAU6dOORw6dKjM2l4kEpkTEhIcS0tLecHBwUoAMBqNVFBQUDsApKSkOMyePbu1v7ZpaWn2/cUulUoNP/74o62/v39nWVkZLyIioj02NlaUl5cnUKvVfgDQ2dlJi8ViU+/PonffPZWXl9scPXpUeP78+aK+PoOXXnqpkc/nMx9++KEoKipq7Pnz57V38/n1RBLUu+Biw4YDm0aZdQTV2AG0XQMc3G4eI5ggRnNyKYzXOmDjajuo83uonGA7iouCs1dJgkoQBEHcdxiGQVJSUolarTb0fH7dunUSsVhsPHLkyGWLxQI+nx/UV3s2m81YLP+eJTQYDDdncDkcjoXNZlv7oXx9ffVZWVmae4mTx+MxAEDTNDgcDmN9nqZpGI1GCui+Na8niqLAMAz60zO+3jQaDeezzz4bfeHChUKRSGResGCBV2dn581rs8bDZrMZk8lE3bjG22JgGAbTpk1rPXbs2G33+p44ccIxOTm5ZKC2/Vm4cGFTQkKCUKlUds6ZM6eJpmkwDEMtWrSoYffu3dV3utaeffd0/vx5QUVFBc/Ly2sc0J3kenh4BFRWVua5urrerJ25bt26unfeeeeuR8B7IlP8d4GiKHjzed0JqpN395O9pvn5gS4AjXtaLEWzaPhNcUNlfgNKLtQO+I+NIAiCIEZaeHh46/bt20dbk8yzZ8/yAaClpYXl5uZmZLFY2LNnj7PZ3J2bODo6mtvb21nW9j4+Pl35+fkCs9mMkpISm5ycnD5HcgIDAzsbGxvZP/zwgy3QPVKbmZnJG8pryc3NtdVoNByz2YykpCSn6dOnt82YMaMjIyPDvqamhm0ymXD48GGnsLCw9r7a29ramltaWmgAaGpqYvH5fIuTk5O5qqqKffLkyTvufR4WFta6Y8cOsfXnuro6VlhYWEdmZqZdXl4eFwDa2tronJwcbkNDA8tsNsOa9PXVdqDYo6Kimo4fPy48fPiwU2RkZCMAzJ49uzUlJUVYXV3NBoDr16+ztFotp3ecvfvuaenSpS319fXZ1dXVudXV1bk8Hs9SWVmZBwAVFRU3p/S//vrrUd7e3p13ek/6QhLUu+Qt4KJU33epKQBg2XHAkwmhy6oDYxl8gjkubAyc3O2Q9nkeUj7LQUudbijCJgiCIIjfLDY29qrJZKKUSqVKJpP5x8TEuAPA2rVraxMSEpzVarVSq9Xy+Hy+BQCCg4P1bDabUSgUqi1btogjIiLapVKpQaFQ+K9Zs0aqUqn6/CPH4/GYQ4cOlW7YsGGMQqFQ+fv7q9LT0+2G8lrGjx/fvn79+jFyudzfw8PDEB0d3ezp6WnctGlTdWhoqNzPz88/MDBQFxUV1dxX++XLl9fPmTNHFhISIn/88cf1AQEBOplM5h8dHe1lnZYfyLZt22qam5tZMpnMX6FQqFJTU+0lEokpPj6+fOnSpd5yuVwVFBSkzM3N5SUnJzuEhoa2DdR2oNhFIpFZJpPpq6urueHh4ToACAoK6oyJiameNWuWXC6Xq2bOnCmvqqq67T7R3n3frQ8//FDs6+vrr1AoVLt37xbv27evfLDnAADqfhutmzRpEpOZmfl7h3Gbjy9fw/bya7g83R+8bRJg8p+BiK23HKPLqkXjoSKIVgeC633HL1G3sZgtyD1ZjYzkMlgsDIJme2Lik55g2ZDvEQRBEA85qvcT2dnZ5Wq1+p5K9BB9S0lJsd++ffvon3766bZp6/vRkiVLPFevXl0/a9asEa9FORJ9Z2dnu6jVaq++XiP3oN4lHwEXDIBygwlK4djbRlABgKdyBsWhocuqvacElWbRUM+SwmeiGGeTivHLscsoyriG0KUKSFXDXu+YIAiCIIj7SGJiYsWj2DdApvjv2s2V/DoD4OwLXMsFLLfelkFzWOD7u0CXUw/GdO8lo+yEXDz1UgDmvaIGGCB5VxbS/pqHjmbDnRsTBEEQxEMmOjraw7ozkfWxc+dO58GeZ+7cuW0Pyujpo46MoN4l7561UMctAIq+B3KTAPWSW44TTBBDd6kWnZpG8APuaXevmzxUzli6KRiX/lmJC/+oQEVeA0LmeWNcmDtoFvluQRAEQTwaDh48WPl7x0CMLJLl3CV7NgtiDhuX9QZA9RzgGgj89B5g6rrlOK7PKNB2Nve0mr8vbBsWHntmLJa9HQw3H0ecOVyMb7Zl4lpZy5CcnyAIgiAI4n5DEtRB8OZzu6f4aRp44m2guQK4uP+WYygWBYFaBH1hIyz6we0pPBBHkQBzX1Zj9uoAdLYbceTDC/jpYCE62++6fjFBEARBEMQDgSSog3Cz1BQA+MwCPKcB6R8ChlurSggmiAEzA33e0C6+pCgKPhPFiNwcgvFPSFH48zV89fZ5FJy9ek+lrQiCIAiCIO5HJEEdBG8+F3VdJrSazN3bnD7xNtBRC2TsveU4G3c7sF340F0ammn+3jg8NqYulGHJxscgdBXgp4Ma/H37RdRfuWP5NYIgCIIgiPveQ52gmswWXKhoRGXD0BS99+m5kh8ApMGA4hng7C5A13jzOIqiIJgghuFyC0zDuPLe2d0Oz62fiJl/VKLpmg7fvP8rziQVo6tz6G4tIAiCIB5d7777rtjb29t//vz5YwfTrqioiBMXFzfs9RHXrl0rOXr0qP1w99PT1q1bxW1tbSOaP8XHxzu9+eabriPZZ+++9Xo9NWXKFLlSqVR9/vnnQuvry5cvlwoEggk92/z1r38V+vj4+Pv6+vrPmzdvUP92rB7qBFVvNGNx/HkkZg7N4j9vQfdua2X6HknnzBjA0Aac+eSWYwXjRQAD6LOHZxTViqIp+E2R4IUtk+E3xQ3ZP1Th680ZZMtUgiAI4jf74osvRKmpqcXJycm37RE/kOLiYm5iYuKgE1STaXADLJ9++unVZ599dtC7Hd0rk8mE+Pj40e3t7SOaP6WlpTnMnTu3dST7tH4W1r7PnTsnMBqNlEajKXjppZeaAODUqVOClpaWWypC5ebmcrdv3+52/vx5TUlJSX5cXFzVvfT/UJeZsufZYIJ0FM6UNOD1p377+bz4HFAASnU9tpUdrQLUS4Ff/gcI+RPg6A4AYDvzwfGwh+5SLexDpb+98zvg2dkgPEoJvyluOPl1EdI+z4OHvxOmL5FjlFgw7P0TBEEQw6cxSSs1XusY0l/mNq62OqeF8n6Th8jISI8rV65w58+f7/vcc881lpWV8QoLC/lms5nauHHj1aioqOaioiJOZGTkWL1eTwPAzp07KyMiIjo2btzoXlZWxlMqlaply5bVC4VCc2Zmpu2BAwcqASA8PNx3/fr11+fOndsmEAgmrF69+vqJEyccPvrooysCgcCybt06qU6no4VCoemrr74q9/T07HNF8IIFC7zmzp3b8uKLLza5u7uPe+655xrPnDljbzKZqLi4uIoNGza4V1RUcP/yl79cf+ONN+pSUlLsN2/eLBEKhaaysjJeSEhI28GDBytZLBbi4+Odtm/f7sowDPXEE0807927txoAesb35JNPttTW1tqEhobKhUKhKSMjQ/vCCy94ZGdn23Z2dtLz5s1r+uSTT64CgLu7+7jFixc3pKWlOZpMJioxMbFswoQJnS0tLfSqVas8cnJyBADw1ltvXV2xYkXzt99+67B161ZJV1cX5enpaTh06FC5o6OjxWKxID8/XzB16lRdf237iv2DDz4QXb58mRsXF3cFAHbt2uV84cIFwf79+6v27NnjtHfv3tFGo5GaOHFix4EDByrYbDZ6fxYRERHt+fn5Ai8vr66pU6cqm5qa2EqlUnXkyJFShUJheP3118d88803l/38/EZZP5Pdu3eLXnrppVqRSGS+8T7c07TuQz2CCgDTZC7IvdKMFt1vX+3OpWlIeRxc1t9aWgph/9ldtD/9g1ueFkwQw3hNh66akduhzNXbEYv/cxKmLZahprQFh7b+gotpFWQRFUEQBDEoX3/9daVYLDamp6drOzo6WOHh4a15eXmFp0+fLoqJiRnT2tpKSyQS0+nTp7UFBQWFiYmJZa+++qoHALz33nvVkyZNatdoNAVvv/32gFOJer2eDggI0Ofk5GjCwsI6XnnlFY/vvvuuND8/v3D58uX1r732mvvdxiyVSruysrI0ISEh7StXrvQ6duxYaUZGhiY2NlZiPSY3N9d2586dVUVFRfnl5eXcAwcOCMvLy202b97sfvLkSW1BQUH+pUuXbA8ePDiqd3wff/xxjfU9ycjI0ALAjh07qvPy8go1Gk3+2bNn7TMyMvjWvlxcXEwFBQWFK1eurIuNjR0NABs2bHBzcHAwa7XaAq1WW/DMM8+01dTUsN9//323U6dOaQsKCgonTpyoe+edd0YDwLlz5wQqlUpH03SfbfuLPTo6uik1NfVm4piUlOQUGRnZdPHiRV5SUpJTZmamRqPRFNA0zcTFxTn3vtannnqq3dq3VCo17dmzp8L6mfr7+xu2bdsmfvrpp5t7f3koKSnharVa3sSJE5VqtVqZlJTkcLefX08P9QgqAEzzdcGnPxTj57J6zA5w+83n8xFwbx1BBQChJ/DYKuCXz4EprwAuvgAA/jgXNB8rgy6rFhy3e7oF457QLBrqmVL4ThTjVKIWP/+9FFWFjXjiRRVsHbkjFgdBEAQxNAYa6RwJJ0+edEhLSxu1a9cuVwAwGAxUSUkJx9PT07hq1SrPgoICPk3TqKioGPQfGRaLhRUrVjQBQE5ODre4uJg/c+ZMOQBYLBaIRKK7HmFavHhxMwCMGzdO19HRQQuFQotQKLRwuVxLfX0968ZrHSqVquvG8Y2nT5+2s7GxYSZPntwmkUhMALBkyZLG9PR0u+jo6Oae8fVl//79Tvv27XMxmUxUXV2dTXZ2Ni8kJEQPAJGRkU0AEBwcrEtOThYCwKlTpxwOHTpUZm0vEonMCQkJjqWlpbzg4GAlABiNRiooKKgdAFJSUhxmz57d2l/btLQ0+/5il0qlhh9//NHW39+/s6ysjBcREdEeGxsrysvLE6jVaj8A6OzspMVisan3Z9G7757Ky8ttjh49Kjx//nxR79fMZjNVWlrK/fnnn4suX75sExoaqgwLC8t3cXEx9z52IA99gqqWjoIdl43TxUOToHrzuchs6QDDMKAo6t8vTH8NuHgQ+OldYNE+AADLjgOeXAh9Vi0cn/ICRVN9n3SY2I7iYvbqABSercHpRC0OvfMLZi33g9e437bDFUEQBPFoYRgGSUlJJWq1+paVv+vWrZOIxWLjkSNHLlssFvD5/KC+2rPZbMZi+fcW4AaD4eYMLofDsbDZbGs/lK+vrz4rK0tzL3HyeDwGAGiaBofDuTl1SNM0jEYjBeDWv903fh5ozUbP+HrTaDSczz77bPSFCxcKRSKRecGCBV6dnZ03r80aD5vNZkwmE3XjGm+LgWEYTJs2rfXYsWO33et74sQJx+Tk5JKB2vZn4cKFTQkJCUKlUtk5Z86cJpqmwTAMtWjRoobdu3dX3+lae/bd0/nz5wUVFRU8Ly+vcUB3kuvh4RFQWVmZ5+bm1jV58uQOLpfLKJXKLm9v7878/HxuaGjooFasP/RT/DYsGpO9nXCmZGhqko4VcNFmtqDe2OuWCjsR8Pj/A/L/DlzNuvm0YIII5pYuGC7/Pjs/URQF1TQJFr31GGwdufh+dw5Of6OF2Wi5c2OCIAiCABAeHt66ffv20dYk8+zZs3wAaGlpYbm5uRlZLBb27NnjbDZ3D5I5Ojqa29vbWdb2Pj4+Xfn5+QKz2YySkhKbnJwc2776CQwM7GxsbGT/8MMPtkD3SG1mZiZvKK8lNzfXVqPRcMxmM5KSkpymT5/eNmPGjI6MjAz7mpoatslkwuHDh53CwsL6rN1oa2trbmlpoQGgqamJxefzLU5OTuaqqir2yZMnHe/Uf1hYWOuOHTvE1p/r6upYYWFhHZmZmXZ5eXlcAGhra6NzcnK4DQ0NLLPZDFdXV3N/bQeKPSoqVAMbAAAgAElEQVQqqun48ePCw4cPO0VGRjYCwOzZs1tTUlKE1dXVbAC4fv06S6vVcnrH2bvvnpYuXdpSX1+fXV1dnVtdXZ3L4/EslZWVeQDw/PPPN588edIeAGpqatiXL1/mKRSKQZc0eugTVKB7mr+iQYeqxt9ebsqH3z17Uarr472e8jLAdwJ+3HrzKZ6fMygOC/qsut/c92/h5GaLhRuCEBg+BjknriDpw0w0XRu5e2MJgiCIB1dsbOxVk8lEKZVKlUwm84+JiXEHgLVr19YmJCQ4q9VqpVar5fH5fAsABAcH69lsNqNQKFRbtmwRR0REtEulUoNCofBfs2aNVKVS9fkHmcfjMYcOHSrdsGHDGIVCofL391elp6fbDeW1jB8/vn39+vVj5HK5v4eHhyE6OrrZ09PTuGnTpurQ0FC5n5+ff2BgoC4qKqq5r/bLly+vnzNnjiwkJET++OOP6wMCAnQymcw/OjrayzotP5Bt27bVNDc3s2Qymb9CoVClpqbaSyQSU3x8fPnSpUu95XK5KigoSJmbm8tLTk52CA0NbRuo7UCxi0Qis0wm01dXV3PDw8N1ABAUFNQZExNTPWvWLLlcLlfNnDlTXlVVZdM7zt59363nn3++1cnJyeTj4+MfGhoq37p1a1VfSe6dUPdbKaJJkyYxmZmZQ3rOkto2PLHjFLY9Pw7Lgj1+07kq9AaEnC/EDoUUkRLn2w8499/AP2OA5ceAsTMAAI3fFEFf0ADJxsmgbH7/7wSXc+pxYn8hTEYzpi+Rw2+K221TBgRBEMSIuu2XcHZ2drlarR7aLQkfcSkpKfbbt28f/dNPP902bX0/WrJkiefq1avrZ82aNeIjSiPRd3Z2totarfbq67XfP1saAT4iO7g68IZkmn8MjwMORf17y9PeHvsPwMEd+GELcCP5F0wQg+k0o7Oose82I2xsoAuWxARj9FgH/HRQg39+kQ+DnhT3JwiCIIj7SWJiYsXvkZz+3n0Dj0iCSlEUpslccK6kHpbfWG6JRVHw4nP/vZtUbzZ8IGwDUJ0JaL4HAHB9RoG2t0HHMG19ei/shFzMXzMBk5/1RunFOiS++wuulf0+98kSBEEQxECio6M9lEqlqudj586dfUxjDmzu3LltD8ro6aPuoV/FbzXN1wVJF66goKYVAe53vId5QL4CLrLbdDBaGNj0tTJfHdm9/emJdwDFHFA0CwK1GO0/X4VFZwQtuO1Wj98FTVMImu0Fd7kQ//wiH99+fBHB88Zi4lOeoEe44gBBEARB9OfgwYNDsyUk8cC4qxFUiqJmUxRVRFFUCUVRG/p4fQZFURcpijJRFLWw12vLKYoqvvFYPlSBD9ZU3+7SSqeLf/s0/1I3J1QbjNh/tZ9zsdjdW6DWaYCcRADd0/wwM9Dl3X+3E7l6O2JJTDB8JoqQ8V0ZkndeQnvToBfcEQRBEARBDIk7JqgURbEA7AYwB4AKwDKKolS9DqsEsALA173aOgF4G0AIgGAAb1MUJfztYQ+eyJ4Lpas9zpT89tX0Ec4OmC60w8eXr6Gpd7kpK9UfALfxwE/vAyYDbCS2YIv40N1H0/w9cflsPLnKHzP/qMT1y61IfPcXXM65/5JpgiAIgiAefnczghoMoIRhmDKGYboAHALwh54HMAxTzjBMDoDexTWfAvAvhmEaGYZpAvAvALOHIO57Ms3XBb+WN6HTOOhqB7egKApbfN3RajLjk/Lr/R0EPLEZaKkCMr8ERVEQTBCj63IrTM2dfbf5nVEUBb8pEix+6zHYOXGRuicHpw5pYfqN7xdBEARBEMRg3E2C6g6g5xZrV248dzfuqi1FUaspisqkKCqzrm746oVOlbmgy2TBr+W/fTW9yo6PSDdn/G913e1bn1r5hANjQ4FTHwGGNgjGd9fW1f3ONVHvROhqi4VvTIJ6lhS5J68gKfYCGq+SmqkEQRAEQYyMu0lQ+1otc7dL4e+qLcMw/8MwzCSGYSaJRKK7PPXghYx1AodFD9muUm96u4JH09haerX/g2a9DejqgZ/3gO3EA8fTAbpLtQNuTXY/YNnQmLZIhmf+XyB0rQYc3vYr8k9X3/dxEwRBEEPn3XffFXt7e/vPnz9/7GDaFRUVceLi4pyGKy6rtWvXSo4ePWo/3P30tHXrVnFbW9uIVkGKj493evPNN11Hss/efev1emrKlClypVKp+vzzz2/errl8+XKpQCCYYP151apVUmulBS8vrwB7e/vx99Lv3bzBVwBIe/w8BsAAGdmQtR1yAg4bEz1H4cwQLJQCABHHBms8RyOtvhVnmvrZbGFMEOA3r7uAf0cDBBNEMF3XwVjzYIxIeo3rrpnq6uOIk18VIe3zPHR2GH/vsAiCIIgR8MUXX4hSU1OLk5OTb9sjfiDFxcXcxMTEQSeoJtPganJ/+umnV5999tlB73Z0r0wmE+Lj40e3t7ePaIKalpbmMHfu3NaR7NP6WVj7PnfunMBoNFIajabgpZdeagKAU6dOCVpaWm6pCPXFF19UaTSaghvH1c6ePbvPHbnu5G7KTP0KQEZR1FgA1QCWAoi8y/OnAXi/x8KoJwH856CjHELTfF3w8T+1aGg3wNmO+5vP99IYEQ5cbcCm4mr86zEFWH3tyDTzv7prop7ZAf60zWhOLoMuqw4cyZDu3jZsbB25mP/KeFz6VyUyvivD9fJfMDPKD2OUQlCkHBVBEMSwO3r0qLS2tlYwlOcUi8W6Z599tqq/1yMjIz2uXLnCnT9/vu9zzz3XWFZWxissLOSbzWZq48aNV6OiopqLioo4kZGRY/V6PQ0AO3furIyIiOjYuHGje1lZGU+pVKqWLVtWLxQKzZmZmbYHDhyoBIDw8HDf9evXX587d26bQCCYsHr16usnTpxw+Oijj64IBALLunXrpDqdjhYKhaavvvqq3NPTs8+RkQULFnjNnTu35cUXX2xyd3cf99xzzzWeOXPG3mQyUXFxcRUbNmxwr6io4P7lL3+5/sYbb9SlpKTYb968WSIUCk1lZWW8kJCQtoMHD1ayWCzEx8c7bd++3ZVhGOqJJ55o3rt3bzUA9IzvySefbKmtrbUJDQ2VC4VCU0ZGhvaFF17wyM7Otu3s7KTnzZvX9Mknn1wFAHd393GLFy9uSEtLczSZTFRiYmLZhAkTOltaWuhVq1Z55OTkCADgrbfeurpixYrmb7/91mHr1q2Srq4uytPT03Do0KFyR0dHi8ViQX5+vmDq1Km6/tr2FfsHH3wgunz5MjcuLu4KAOzatcv5woULgv3791ft2bPHae/evaONRiM1ceLEjgMHDlSw2Wz0/iwiIiLa8/PzBV5eXl1Tp05VNjU1sZVKperIkSOlCoXC8Prrr4/55ptvLvv5+Y3q6/NJSkpy2rRp0z0NTN7xGwDDMCYAL6M72SwE8A3DMPkURW2lKGo+AFAU9RhFUVcALAIQT1FU/o22jQDeQXeS+yuArTee+91Mk3XfQnCutGFIzsdj0YjxcUNBRycO1fRzaSJFd23UXz4Hy3gNPIUQ+qxaML9x04CRRNEUJj7liedfDwLNopG8KwtfbjiLEwcKUXapDl2dZCcqgiCIh8nXX39dKRaLjenp6dqOjg5WeHh4a15eXuHp06eLYmJixrS2ttISicR0+vRpbUFBQWFiYmLZq6++6gEA7733XvWkSZPaNRpNwdtvvz1g+Rq9Xk8HBAToc3JyNGFhYR2vvPKKx3fffVean59fuHz58vrXXnvtbte9QCqVdmVlZWlCQkLaV65c6XXs2LHSjIwMTWxsrMR6TG5uru3OnTurioqK8svLy7kHDhwQlpeX22zevNn95MmT2oKCgvxLly7ZHjx4cFTv+D7++OMa63uSkZGhBYAdO3ZU5+XlFWo0mvyzZ8/aZ2Rk8K19ubi4mAoKCgpXrlxZFxsbOxoANmzY4Obg4GDWarUFWq224Jlnnmmrqalhv//++26nTp3SFhQUFE6cOFH3zjvvjAaAc+fOCVQqlY6m6T7b9hd7dHR0U2pq6s3EMSkpySkyMrLp4sWLvKSkJKfMzEyNRqMpoGmaiYuLc+59rU899VS7tW+pVGras2dPhfUz9ff3N2zbtk389NNPN/f35UGr1XKuXLnCmTdv3j2N/N5VoX6GYVIBpPZ6blOP//8V3dP3fbX9XwD/ey/BDYdx7o5w4LFxprge89SSOze4C/NFo/BXh3rEXq7BH8SjYMdm3X5Q2AYg9xsgPRaCCZvRWNgIQ1kLeL59fum4b40e64AlGx/D5ex6lOfWo/RSHQrP1YBmUxgjF8Ir0AWe45zh4My/88kIgiCIuzLQSOdIOHnypENaWtqoXbt2uQKAwWCgSkpKOJ6ensZVq1Z5FhQU8GmaRkVFxaCnJlksFlasWNEEADk5Odzi4mL+zJkz5QBgsVggEonu+r6yxYsXNwPAuHHjdB0dHbRQKLQIhUILl8u11NfXs2681qFSqbpuHN94+vRpOxsbG2by5MltEonEBABLlixpTE9Pt4uOjm7uGV9f9u/f77Rv3z4Xk8lE1dXV2WRnZ/NCQkL0ABAZGdkEAMHBwbrk5GQhAJw6dcrh0KFDZdb2IpHInJCQ4FhaWsoLDg5WAoDRaKSCgoLaASAlJcVh9uzZrf21TUtLs+8vdqlUavjxxx9t/f39O8vKyngRERHtsbGxory8PIFarfYDgM7OTlosFpt6fxa9++6pvLzc5ujRo8Lz588XDfS+PP30001s9r3tCfXI7CRlxaIpTPFxwZmSejAMA6qvKflBoigKW2QSPH2hGLsqruMtnz4S31FS4LGXgIy94D/2CiguC7qs2gcuQQUADo8NRYgrFCGuMJstqClpQXluPcpz6nHqkBY4BDi728JznAvGBrpA7OVAdqYiCIJ4gDEMg6SkpBK1Wn3LLi7r1q2TiMVi45EjRy5bLBbw+fygvtqz2WzGYvl3JUqDwXBzBpfD4VisSQzDMJSvr68+KytLcy9x8ng8BgBomgaHw7k5TUnTNIxGIwXgtr/7FEUNuAC4Z3y9aTQazmeffTb6woULhSKRyLxgwQKvzs7Om9dmjYfNZjMmk4m6cY23xcAwDKZNm9Z67Nix2+71PXHihGNycnLJQG37s3DhwqaEhAShUqnsnDNnThNN02AYhlq0aFHD7t27q+90rT377un8+fOCiooKnpeX1zigO8n18PAIqKyszLMe8+233zrt2rWrot/g7mBEb/K9X0yVuaC6WY/yBt2QnXOigy0WjBYi/kodKvX97MI0fR1gYwvq9LvgB7hAn1sPxti7dOyDhcWiMUYhxLSFMkRtfRwvbJmMKQt8wbO1waV/VuLIhxew780z+HFfAUov1qJLT24FIAiCeNCEh4e3bt++fbQ1yTx79iwfAFpaWlhubm5GFouFPXv2OJvN3XWzHR0dze3t7TenE318fLry8/MFZrMZJSUlNjk5ObZ99RMYGNjZ2NjI/uGHH2yB7pHazMxM3lBeS25urq1Go+GYzWYkJSU5TZ8+vW3GjBkdGRkZ9jU1NWyTyYTDhw87hYWFtffV3tbW1tzS0kIDQFNTE4vP51ucnJzMVVVV7JMnT95xL/WwsLDWHTt2iK0/19XVscLCwjoyMzPt8vLyuADQ1tZG5+TkcBsaGlhmsxmurq7m/toOFHtUVFTT8ePHhYcPH3aKjIxsBIDZs2e3pqSkCKurq9kAcP36dZZWq+X0jrN33z0tXbq0pb6+Pru6ujq3uro6l8fjWXomp9nZ2dzW1lbWrFmz7nlF+COZoE6/se3pmeKhrUf6lrcbaADvldX0fYCtCzDlZaAwGQJpMxiDGXrN0NwLe78YNVqACREeeHbdRKz8aBqeXOWPMUonXM6px/H/ycMXr51G8s5LyD5RhdZ6/e8dLkEQBHEXYmNjr5pMJkqpVKpkMpl/TEyMOwCsXbu2NiEhwVmtViu1Wi2Pz+dbACA4OFjPZrMZhUKh2rJlizgiIqJdKpUaFAqF/5o1a6QqlarPESIej8ccOnSodMOGDWMUCoXK399flZ6ePqQrisePH9++fv36MXK53N/Dw8MQHR3d7Onpady0aVN1aGio3M/Pzz8wMFAXFRXV5+rz5cuX18+ZM0cWEhIif/zxx/UBAQE6mUzmHx0d7WWdlh/Itm3bapqbm1kymcxfoVCoUlNT7SUSiSk+Pr586dKl3nK5XBUUFKTMzc3lJScnO4SGhrYN1Hag2EUikVkmk+mrq6u54eHhOgAICgrqjImJqZ41a5ZcLperZs6cKa+qqrLpHWfvvgdj//79zn/4wx8aafre00zqfqtrOWnSJCYzM3NY+2AYBtM//An+EgfER08a0nN/UFaDTyqu49hEGR5z7OMLoqEN2KkGMzoQNVf+ExypPVz+2Hvn2IePxWzBtbIWlOc0oDy3Hk3Xun83Cd1sMTbQGV7jXDDa25HcCkAQxKPqtl9+2dnZ5Wq1muw5PYRSUlLst2/fPvqnn366bdr6frRkyRLP1atX1/+Wkcj7ue/s7GwXtVrt1ddrj9w9qED3/SbTfF3wfW4NTGYL2KyhG0h+2UOMr2u6y059HyQD3fseV649MON1UMc3QCB7Fe0FRlh0RtCC2768PFRoFg2JTAiJTIgpC3zRXKtDRW53spr1rypcTKsE394GT/1HANwVwjufkCAIgiAecomJifd8D+eD3DfwiE7xA8A0mQvaOk3IrW4Z0vPasln4T283XGrT4WhtP7VpJ60EHKUQNMYBZga63EfvC/IosQDqWVL8Ye0ErNw+HU+9FACerQ2+35uDusoRq7lMEARBPACio6M9rLsTWR87d+50Hux55s6d2/agjJ4+6h7JEVQAmOLjAooCzhTXY4LH0I7YLXZ1wv9eqcd7pVcx28URgt4jtGwuEPafsDn6f8F2XA3dpVrYhbgNaQwPEi6fDd8gMVy9HXDkows49t9ZeP71IIwSD2lNaoIgCOIBdfDgwcrfOwZiZD2yI6hOthz4SxxwumToRy9pisIWmTuqDUbEV/VTn1i9FJRYCQGThq7yVpiaOoc8jgeNnZCH+a+MB2MBju3KQkdLP9UQCIIgCIJ4qD2yCSoATPV1waXKJnQYhr700eOj7PCMyBH/XVmLa4Y+agzTLGDmf0FgSAIA6LKGtqLAg0roaou5L6uhazPi2H9nw6C76/rMBEEQBEE8JB7pBHW6rwhGM4NfLg/P7qv/5SOBycIgtr+yU8pnwB7jCY5NMXQXrw1YbPdRMnqsA57+P+PQVNOB1L25MHXdVoKNIAiCIIiH2COdoE7yEoLLpnFmGKb5AcCLz8WqMS5IvNaInLY+Sr5RFPDE2xAwaTDVdcJ4dcSrSNy3pConPPGiCldLmvHPL/JhMT/YGxoQBEE8iN59912xt7e3//z588cOpl1RUREnLi7Oabjislq7dq3k6NGj9sPdT09bt24Vt7W1jWj+FB8f7/Tmm2+6jmSfvfvW6/XUlClT5EqlUvX555/fXLyzfPlyqUAgmGD9ubi4mBMSEiL38/NTyeVyVWJi4h03L+jLI52g8mxYeMzLCWeKh28V/VrP0RDasPB2SXXfI6RjZ0DgQwMwQZd5ZdjieBDJJo3G9MVyXM6ux8mvisgIM0EQxAj74osvRKmpqcXJycm3bcE5kOLiYm5iYuKgE1STaXC33H366adXn3322REr/WIymRAfHz+6vb19RPOntLQ0h7lz57aOZJ/Wz8La97lz5wRGo5HSaDQFL730UhMAnDp1StDS0nLLgvtNmza5Pf/8802FhYUFCQkJZevWrfO4l/4f6QQV6C43VXS9DbWtw7NIydGGjdfHuuHn5g78o77vklb0U2+AR/8K3cUr0Bc1Qq+58ShsgL7gxiO/Afr8eujzuh+6XOujDrqcG4/sOuiya6HLuvG41P0wVLQ+sFuqBoaPwaSnvVB4rgbnvyv7vcMhCIJ4ZERGRnpcuXKFO3/+fN8333zTddGiRV4BAQF+fn5+qr/97W+jgO6R0qCgIIVKpfJTqVR+//rXv2wBYOPGje6ZmZl2SqVStWXLFvGuXbuc//jHP95MVMLDw31TUlLsAUAgEExYu3atJDAwUPnjjz/anT59WvDYY48p/P39/aZNmyarqKjot1D4ggULvL788kshALi7u497+eWX3cePH68MCAjwO3PmjGDatGkyqVQa8OGHH4qA7kL9kyZNUkRERPj4+Pj4R0ZGeli3Z42Pj3eSy+UqmUzm/+c//9nd2kfP+DZs2OBWW1trExoaKg8JCZEDwAsvvOAREBDg5+vr6//qq69KrO3c3d3HvfrqqxKVSuUnl8tVly5d4gFAS0sLvXDhQi+5XK6Sy+Wqffv2jQKAb7/91mH8+PFKlUrlN2fOHG/rdqoWiwX5+fmCqVOn6vpr21fsH3zwgehPf/rTGGs8u3btcl6+fLkUAPbs2eM0btw4P6VSqYqMjPS0JqO9Pwtr315eXl0vvvjiWI1Gw1cqlar8/HyuyWTC66+/Pmbnzp23jK5RFIXW1lYW0L0VrFgsvqfFJI9smSmraTe2PT1bWo/nJoy5w9H3JtrNGV9eqcfW0quY5ewAbu+tvyQTYOv1d3SWcdHwZf6wxAAWBRuJHbhSe3A87cGROoAl5ILqvZHAfSh43ljo27pw8XgF+HY2GP/EPX0ZIwiCeGAVFL4p7WjXDmntPVs7uU7l90FVf69//fXXlenp6Y7p6ena9957b3R4eHjr4cOHy+vr61mTJk3ymz9/fqtEIjGdPn1aKxAImNzcXO6yZcu88/LyCt97773qnjs27dq1q9+apXq9ng4ICNB/+umnVw0GAzV58mTF999/XyKRSEyff/658LXXXnM/fPhw+d1ck1Qq7crKytKsWrVKunLlSq+MjAzNjfP7v/HGG3UAkJuba3vp0qU8uVzeNWPGDNmBAweE4eHh7Zs3b3a/cOFCoUgkMk2fPl1+8ODBUdHR0c094wOAhIQEl/T0dK2bm5sJAHbs2FE9evRos8lkwpQpUxQZGRn8kJAQPQC4uLiYCgoKCmNjY0WxsbGjExMTKzZs2ODm4OBg1mq1BQBQV1fHqqmpYb///vtup06d0jo4OFg2btzo+s4774z++OOPa86dOydQqVQ6mqbRV9vy8nKbfmJvmjx5shLAFQBISkpy2rhxY83Fixd5SUlJTpmZmRoul8tERUV5xMXFOb/88ssNva/1zJkzApVKpZNKpaY9e/ZU9PxM33nnHfHTTz/d7OnpeUsCum3btqsRERGyv/71r2K9Xk9///332rv57Hp75BNUlZsDhAIbnC4evgSVTVPY7CtBZE4Z/vdKPf7sIb7tGN7ClRB/+yEYgw4UwwCMBYCl+7+MBWCYHj+bAVhAMT1eB9PjNebmMTAZYTII0cWdDEPnNHT82oH2c1cBALS9DThSB3BvJKw2Y+xAc1jD8h78FhRFYcYyBTrbjTibVAK+PQeKkN/lVhyCIIhH0smTJx3S0tJG7dq1yxUADAYDVVJSwvH09DSuWrXKs6CggE/TNCoqKriDPTeLxcKKFSuaACAnJ4dbXFzMnzlzphzoHj0UiUR3PQK3ePHiZgAYN26crqOjgxYKhRahUGjhcrmW+vp61o3XOlQqVdeN4xtPnz5tZ2Njw0yePLlNIpGYAGDJkiWN6enpdtHR0c094+vL/v37nfbt2+diMpmouro6m+zsbJ41QY2MjGwCgODgYF1ycrIQAE6dOuVw6NChm1OCIpHInJCQ4FhaWsoLDg5WAoDRaKSCgoLaASAlJcVh9uzZrf21TUtLs+8vdqlUavjxxx9t/f39O8vKyngRERHtsbGxory8PIFarfYDgM7OTlosFpt6fxa9++6pvLzc5ujRo8Lz588X9X7tyy+/dFq2bFnDli1brv/www+2K1asGKvVavNZrMHlF498gkrTFKb4uuBsST0Yhhm2EcWZzg4Id7LHJxXXsMjVCS6cW996yskLnP/YM/QdW8ywKTwG/untwLVPwYySwui/Hl124eiqNqCrshWdBQ3dx9KAjZsdOFJ7cDwdwJXag+XMuy9GWWmaQsRKf3R+loUT+wvBs7WBZ8CgNxEhCIJ4IA000jkSGIZBUlJSiVqtvqVA9bp16yRisdh45MiRyxaLBXw+P6iv9mw2m7FY/n2rmcFguDmVyOFwLGw229oP5evrq8/KytLcS5w8Ho8BAJqmweFwbi5coGkaRqORAnDb3zSKogZc49Azvt40Gg3ns88+G31j9NK8YMECr87OzpvXZo2HzWYzJpOJunGNt8XAMAymTZvWeuzYsdvu9T1x4oRjcnJyyUBt+7Nw4cKmhIQEoVKp7JwzZ04TTdNgGIZatGhRw+7du6vvdK09++7p/PnzgoqKCp6Xl9c4oDvJ9fDwCKisrMz729/+5nL8+HEtADzxxBMdBoOBvnbtGtvd3X1QNxg/8vegAsB0XxdcbzWgpLZ9WPvZ7OuODrMFH5dfG9Z+bkGzAP9ngf9zCog6AsrJA5zza2F3biacXJPh+rIv3GJC4LxcBftQKWgeC7qLtWhKLMK1jzNR8+551O/LR+tPlegsaYZlGGrG3i2WDY2n/xQIJ3dbHI/PxbWyod2mliAIguhbeHh46/bt20dbk8yzZ8/yAaClpYXl5uZmZLFY2LNnj7P1fk5HR0dze3v7zSEzHx+frvz8fIHZbEZJSYlNTk6ObV/9BAYGdjY2NrJ/+OEHW6B7pDYzM5M3lNeSm5trq9FoOGazGUlJSU7Tp09vmzFjRkdGRoZ9TU0N22Qy4fDhw05hYWF9JgW2trZm6/2hTU1NLD6fb3FycjJXVVWxT548eccV62FhYa07duy4OZVaV1fHCgsL68jMzLTLy8vjAkBbWxudk5PDbWhoYJnNZri6upr7aztQ7FFRUU3Hjx8XHj582CkyMrIRAGbPnt2akpIirK6uZgPA9evXWVqtltM7zt5997R06dKW+vr67Orq6je6QlcAACAASURBVNzq6upcHo9nqayszAMAiUTSlZqa6gAAFy9e5HV1dVHW2yEGgySo6F4oBWDYyk1ZKWx5iJa44ODVehR1jPDOURQF+D4BvJgKrEwD3CcBP70LfDIOrJ/fA19qhuNTXhC9FAjJ5schXjMRo57zBU/pDFODHq1pFaj/ay6ubv4Z1z+9iObkUhjKWsBYRnZlPYfPxry/jIftKC5SPstGw9Xh/VJBEARBALGxsVdNJhOlVCpVMpnMPyYmxh0A1q5dW5uQkOCsVquVWq2Wx+fzLQAQHBysZ7PZjEKhUG3ZskUcERHRLpVKDQqFwn/NmjVSlUrVR+3F7hHHQ4cOlW7YsGGMQqFQ+fv7q9LT0+2G8lrGjx/fvn79+jFyudzfw8PDEB0d3ezp6WnctGlTdWhoqNzPz88/MDBQFxUV1dxX++XLl9fPmTNHFhISIn/88cf1AQEBOplM5h8dHe1lnZYfyLZt22qam5tZMpnMX6FQqFJTU+0lEokpPj6+fOnSpd5yuVwVFBSkzM3N5SUnJzuEhoa2DdR2oNhFIpFZJpPpq6urueHh4ToACAoK6oyJiameNWuWXC6Xq2bOnCmvqqq6bSFa777v1ieffFK1b98+kUKhUEVGRnrHxcWV073X3twF6n4r3TNp0iQmMzNzxPsN++gn+Ijs8MWKx4a1n4YuEx7PKMAkB1t8rfYZ1r7uqCYHOPMJUHAUYHGACVHAlFcAoedth1p0RnRVtcFQ2YauylZ0lXdXBqDtOeAHOEMQKALH0wEUPTK3A7TW63HkwwugaAoL3giCvdOQfsEmCIIYabf98szOzi5Xq9XDO3LyiElJSbHvudDnfrdkyRLP1atX18+aNWvEC6WPRN/Z2dkuarXaq6/XHvl7UK2myVzw94vVMJotsGEN38CyM4eNVz1dsaX0Kn5qaEW4s8Ow9XVHboHAoi+Bhhjg7KfAhf1A5pdA4GJg6lpArLx5KC2wAU/hBJ6iu6ydxWBGZ1Ej9Dl16Pj1Ojp+rgHtwIEgwAX8QBdwPIY3WXVw4WPeK+Px9+0XcWxXFp57bSL4drfNUBAEQRDEAysxMbHiUewbICOoNx3Pq8Gf/nYRh//0OB7zGt7NLwwWC0J/0YBD0TjxmALsERp1vKOWauDn3cCFLwGjDlDOBaavA9z7vOf9JovBjE5NA3Q59egsagRMDFgOHPDHuYAfKAJHaj9syerV4mYk78qCs7sd/rB2PDg88p2LIIgHEhlBHUB0dLTHr7/+estU/5///Ofra9asafi9YiJ+u4FGUEmCekOLzogJ7/wTL8+UYV2EfNj7S61rxsq8csTKx2CFu8uw9zcoHQ3AL/FARhzQ2QJ4hwHT1wNe07vvZR2AxWBCZ2Fjd7KqvZGsOnLAHycCf5zLsCSrl7Pr8I/4PIxRCvHM/w0Ei01urSYI4oFDElTikTNQgkr+kt/gKLDBuDGjcHaYF0pZzXFxxOOjbPHh5Rq0GH+/lfF9snUGwt8C1uYBEVuB6wXA/nnAFxGAJhWw9L8rFc1lQzBeDJc/qiCJmQynJQrYSOzQ/vNV1O3NxrUPfkVzShkMla1DtnXpWLUI4VEKVBU04sf9hSO+cIsgCIIgiKFFEtQepvu6IKuqGa2d97Qr16BQFIUtvu5oMprxacX1Ye/vnvAcgKlr8P/ZO/PwKKrs73+rqvdOOumQztZkA7IHQoAJkT0CDozIyCJIgBFBmdHBAUGBAXQQUeMICIgsovxYRoEh8DIIKo4iYdMICCQhK2QjC1k7nd67a3n/qE4IoRMChGW0Ps9TT62376nuTudb5557DuZlAk+uAYxVwJ4pwOaBQMY+gGlfWJMyERTxPvB+LgYBbyRCPSkcYn8lL1Y3OsXqkULYrxnuWaxGDQjAY+O6o+BsFU7uK+g08SsgICAgICDw4BEEagsGhXmDYTn8dPXBhLT0cldgkp8XPi2rRbHFdvsGDwuxDPjdLOCVC8D4rXxVqwMvABv6Ab/sBGj7bV+ClImg7OML7xkxCFiWCPUz4RD7KWE8U4Hqjy/yYvWrIjhqXGYe6RDxTwQhbkQgMn8ow/mvH2pst4CAgICAgMA9IAjUFsQHeUIuph7YMD8A/L2bP8QkgbevVjywPu8aSsTP8H/pDDD5c0DmARx6BVgfD6R/AjgsHXoZUi6Csq9TrC7tD/XEcIh9FTCeKkfV6vOo2ZYFS07dHQ/VEwSBgeN7IKK/H9IPFeLyyVuKZAgICAgICAj8DyAI1BZIRRT6d/PCyQcoUP2kYswJ8sGRGj3O6P5Hks6TJBA1Bph9HJi2H/AMBL5+HVjbCzi9DrB1PK8vqRBD2c8X3s/Hwv/vCVCNDIbjugl1O7JxfdU5GE6UgTV3POSCIAkk/SkSwbFdkPZFHq5eqL7z+xMQEBAQAACsXLnSp1u3bjFjx44NvZN2eXl5ks2bN9/flDgA5s2bF3Dw4EH3+91PS1asWOFjMBgeqH7asmWL16JFi/weZJ+t+7ZYLMSAAQPCIyMjo7du3apuOv/cc88FKhSK+Kb9/Px8yWOPPRYeHh4enZCQEHH16tVbigB0BEGgtmJQD28U1phQ0dAxb2Bn8JdAHwRIxXjzSjlO6QzIN1mhc9CPfhxlU3Wqmd8AM74CfGOA/74JrO0JpP0TsLgswtEmlLsEquFB8F/0O3glR4LykED/VREq3v0Z9an5sHewahRFkfj97Fj4hqrw7WeXkXm8DLrrpkf//RQQEBB4xPjss880X331VcGhQ4duqRHfHgUFBdK9e/fesUCl6TubNLx27dqKp59++o6rHd0tNE1jy5Ytvkaj8YHqp6NHj6rGjBnT+CD7bPosmvo+c+aMwuFwELm5udkvvviiDgBOnDih0Ov1N+V3nDt3btfk5OS6/Pz87GXLllUsWLCg6930L6SZakXu9UaMWnsS/5zYC5P6BT6wfv9TrcOfL98cNykhCGgkInhLRPCRiKFpsdZIxPBpse9GkSBukwLqgVB2Hji5Csj7CpC4AwkvAo/9FVDeXSote4URpp8qYb5QDc7BQhKigttjAZDHdgFxm4IKVpMD/1l7AbXXeGErVYrg380Dft094NfNAz4hKoglVLuvISAgIPCAaDfN1Lyc0sBck1XRmR1GKmXmtVFB19o6n5ycHLRv3z7v0NBQ67hx4+oLCwtlOTk5coZhiKVLl1ZMmzatIS8vT5KcnBxqsVhIAFi3bl3pyJEjTXFxcZGFhYUyrVZrnzJlSq1arWbOnTun3LlzZykAJCUl9ViwYEHVmDFjDAqFIn727NlVx44dU33wwQdlCoWCnT9/fqDZbCbVajX9+eefFwcHB7scSpswYULImDFj9M8//7xOq9X2HDduXP2pU6fcaZomNm/eXLJ48WJtSUmJ9JVXXqlauHBhzeHDh92XL18eoFar6cLCQln//v0Nu3btKqUoClu2bPFavXq1H8dxxIgRIxo2bdpUDgAt7XviiSf069at8w8NDbWq1Wo6PT09f+rUqUGXLl1SWq1W8qmnntJ9+OGHFQCg1Wp7Tpo0qe7o0aMeNE0Te/fuLYyPj7fq9Xpy1qxZQRkZGQoAWLJkScWMGTMaDhw4oFqxYkWA3W4ngoODbXv27Cn28PBgWZZFVFRUdE5OTrbBYHDZ1pXt77//vqaoqEi6efPmMgBYv359l/Pnzyt27NhxbePGjV6bNm3ydTgcRJ8+fUw7d+4sEYlEaP1ZjBw50hgVFRX93Xff5Q8cODBSp9OJtFqtff/+/VcjIiJsAwcODP/3v/9dFBUVFWs2my8AQI8ePWKOHj2a3717dwfLslCpVPFGo/GCq89PqCR1B0T4usPbTYpTBbUPVKD+0UeN3u4KXLPaUW2nUWN3NK9r7DQqbHZcMphRa6fhKsmTnCSguUXE8kJWJaIgIwnISRIyioSMJCEjCShabMspEmKCuHeR27UvMGU3cD0TOLmaL6X60yag3/PAgFcAVcAdvZwkwA2S8WHwGBUC0/kqGH+sRP3uXJDuErj194Oyvz8od9cVpGRKMSb9/XfQVZlxvVCP61f1uF6oR3EmPwmOJAl4B7rBr4VoFUqmCggICPB88cUXpWlpaR5paWn577zzjm9SUlLjvn37imtra6l+/fpFjR07tjEgIIA+efJkvkKh4DIzM6VTpkzplpWVlfPOO++Utywpun79+i5t9WOxWMjY2FjL2rVrK2w2G5GYmBhx5MiRKwEBAfTWrVvVr732mnbfvn3FHbE5MDDQfvHixdxZs2YFzpw5MyQ9PT3X+foxCxcurAGAzMxM5YULF7LCw8PtQ4YMCdu5c6c6KSnJuHz5cu358+dzNBoNPXjw4PBdu3Z5Tp8+vaGlfQCwe/du77S0tHx/f38aANasWVPu6+vL0DSNAQMGRKSnp8v79+9vAQBvb286Ozs7JyUlRZOSkuK7d+/eksWLF/urVComPz8/GwBqamqoyspK0bvvvut/4sSJfJVKxS5dutTv7bff9l21alXlmTNnFNHR0WaSJOGqbXFxsbgN23WJiYmRAMoAIDU11Wvp0qWVv/zyiyw1NdXr3LlzuVKplJs2bVrQ5s2bu8yZM6eu9b2eOnVKER0dbQ4MDKQ3btxY0vIzffvtt33+8Ic/NLR+eIiKijJ/8cUX6jfeeKN6165dniaTibx+/Trl5+fHdPzbJwjUWyAIAoN6dMHJglqwLAfyAVZ5CpZLESyXtnsNw3God9CosdOodorXaud2rXNdaLEhXW9EveOOvgsgAaeA5cWs3ClgeWFLOMUsCTlFIFgmxXNab3hL2vgK+fUEntkODMvnRWr6FuDsp0DvqcCgeYA65M5sU4jhPrgr3AZqYc3XwfRjBRq/K0XjD9cgj/WG24AASILcbxHYBEnAy18JL38logfy4thqcvCC1blkn65Axg9lAAClpxR+3Tzg7xSs3oFuQuJ/AQGBh057ns4HwfHjx1VHjx71XL9+vR8A2Gw24sqVK5Lg4GDHrFmzgrOzs+UkSaKkpKT9f2IuoCgKM2bM0AFARkaGtKCgQP7444+HAwDLstBoNB2eiDBp0qQGAOjZs6fZZDKRarWaVavVrFQqZWtraynnOVN0dLTdeX39yZMn3cRiMZeYmGgICAigAWDy5Mn1aWlpbtOnT29oaZ8rduzY4bV9+3ZvmqaJmpoa8aVLl2RNAjU5OVkHAAkJCeZDhw6pAeDEiROqPXv2FDa112g0zO7duz2uXr0qS0hIiAQAh8NB9O3b1wgAhw8fVo0aNaqxrbZHjx51b8v2wMBA2/fff6+MiYmxFhYWykaOHGlMSUnRZGVlKeLi4qIAwGq1kj4+PnTrz6J13y0pLi4WHzx4UP3TTz/ltT730Ucflc2ePTsoKirKOzEx0eDj4+MQi+88DFUQqC4YFKbBwYsVyL1uQHSA6pbzdosZtMMBhcrjgdtGEU2eUjGiIW/3WgfLoc5Bw0AzsLIsrCwHK8PCwvKLleFgZVlYGLb5PH/ced55PX8NhwaHA1aWhZlhsc+mw4bSavxJ2wUvB/rAV9rGl08TDozbBAxbxE+guvAvPjVVr0nAoPn8+TuAIAnII70gj/SCo9YC048VMJ2vguVSDcRaN7g95g9FnAaEuO2he5lSjJCe3gjpyYcdsAyLunITKp0e1utX9bj6Cz+5ihKT8Al2bxasft08IG/DYysgICDwa4XjOKSmpl6Ji4u7KSfi/PnzA3x8fBz79+8vYlkWcrncZW1skUjEsS2KvNhstuYnf4lEwopEoqZ+iB49elguXryYezd2ymQyDgBIkoREImmOYSRJEg6HgwBwqyODINqdo9DSvtbk5uZKNmzY4Ov0XjITJkwIsVqtzffWZI9IJOJomiac93iLDRzHYdCgQY1ffvnlLbG+x44d8zh06NCV9tq2xcSJE3W7d+9WR0ZGWkePHq0jSRIcxxHPPPNM3ccff3xLqpvW99qy75b89NNPipKSEllISEhPgBe5QUFBsaWlpVkhISGOb7/99ioA6PV68quvvlJ36dLlzjxmEASqSwb14IXL6Su1LgXqd59uxJVz6Zjw97egjYx+0OZ1GDFJwE8qhl9b4vEeKDBZsa6kCluv1WB7eS2m+nfBnCAfBMjaEG/qEGDMh8CQ14EzG4Bz24BLe4CYp/kyqn4979gGsbccnk91h+qJEJgvVsN4pgK61ALovyqC4nd+cOvvD1EHhuxJioQmyB2aIHf0SuJjuY06201e1ovfXQPLlAIAPHzk0IZ5okc/X2gj1A/Uyy4gICDwMEhKSmpcvXq17/bt20tJksTp06flAwcOtOj1eqpr1652iqKwYcOGLgzD6xAPDw/GaDQ2ewq6d+9u37p1q4JhGBQVFYkzMjKUrvrp1auXtb6+XvTdd98pR4wYYbLZbERmZqa0X79+1s66l8zMTGVubq4kLCzMnpqa6vXCCy/UDBkyxLRo0aLAyspKkUajofft2+f18ssvu0wDo1QqGb1eT/r7+0On01FyuZz18vJirl27Jjp+/LjH0KFD2520NWzYsMY1a9b4bNu27RrAD9MPGzbMtGDBgqCsrCxpbGyszWAwkEVFRWKtVkszDIOm4XFXbduzfdq0abr4+PjozMxMW0pKShkAjBo1qnH8+PE9lixZUqXVaumqqipKr9dT4eHhNyU1r6uro1r23ZJnn31W/+yzz15q2lcoFPGlpaVZAFBZWSny8fGhKYrCsmXL/KdMmXJXqZGEsUsX+HnI0MPHzWW6KY7jUJJ5EQ6rBfvffRNl2VkPwcKHT5hShg3RwTjdPwrjfdXYWVGLxJ9ysDDvGkrbKzqgCgBGvQu8mgUMng8UfAdsHgR88SxQdneT40gpBbf+/vCd1wea2T0h7eYB48kyXP/gLGp3ZsOSXQeObrs8qyvc1FL06OuDQc+EYeKifnjxwyEY91ofPDauO7z8lSg4X41D6y5ix99P49S+AlSXdF7pVgEBAYFHjZSUlAqaponIyMjosLCwmGXLlmkBYN68edW7d+/uEhcXF5mfny+Ty+UsACQkJFhEIhEXERER/dZbb/mMHDnSGBgYaIuIiIiZO3duYHR0tMuqLDKZjNuzZ8/VxYsXd42IiIiOiYmJTktLc+vMe+ndu7dxwYIFXcPDw2OCgoJs06dPbwgODna8+eab5UOHDg2PioqK6dWrl3natGkuU9E899xztaNHjw7r379/+GOPPWaJjY01h4WFxUyfPj2kaVi+Pd57773KhoYGKiwsLCYiIiL6q6++cg8ICKC3bNlS/Oyzz3YLDw+P7tu3b2RmZqbs0KFDqpaC11Xb9mzXaDRMWFiYpby8XJqUlGQGgL59+1qXLVtWPnz48PDw8PDoxx9/PPzatWu3eLJa991RvvnmG/du3brFhoSExFZXV4vee++9yjt9DUCYxd8myw9dxp6zpbj45hOQtRgurq8ox/+9+mcMeGYqck+nobGuBuMX/QOBMb0eorUPn1KLDRtKq7Gnsh4sOEz09cLcYF+EKm4TjmTRAT9vBX7ayG93fxwYuggISrwne+gGG0zplTD9fB2syQFCSkEe5QV5Tw1k4WoQ4nt7NqPtDIoz65D/83WUZNWBZTh4+ioQnuCL8ARfeGg6dbKtgIDAr592Z/ELdA6HDx92bznR51Fn8uTJwbNnz64dPny46dfYd3uz+AWB2gbfZVfhhZ3n8MWL/TGg+40USZk/fItvN6/HjNWbIHNzw763l0JfXYWnF76B4J69H6LFjwYVVjs2XqvGvyrqYGc5jPNVY26wL8KVtxlqtxmBc58Bp9cD5logdCgvVEMG3pM9HM3CdrUB5sxaWLPrwJppEBIKsigvKHp6QxahbjdetSNYTQ5c/aUa+T9XoaKAf+D2DVUhPMEPYf18hJhVAQGBjiAI1AfA/5pA/bUjCNS7wGB1oPeK/+LPQ7ph4ajI5uPfbFyLq7/8jJe3fg6CIGDWN2DfymVoqKzAH19fhpC4Pg/R6keHapsDG69VY0d5Hawsi6d8PPFqsC+i3Nqf2AW7CTj3f/yEKlM1EDIYGLqQX99jCiyOYWEr1MOSWQvL5VqwJhqEhIQs0gvynt6QRXiBvMe8qIZ6KwrOViH/5+uoKzeBIAkERnkhPMEX3XprIJYKeVcFBARcIgjUdpg+fXrQ2bNnbxrqf+mll6rmzp1b97BsErh3BIF6l0zcdAYOhsV/5gxqPvbZ3BfRpWswnn59WfMxc6MeqSuXob6iDH98bRlCe7ucxPibpNZO45Nr1dhWXgsjw2K0twdeDfFFL/fbDIE7LMD57cCptYDxOhA0gBeq3Ybds1AFAI7hYCtq4MVqVh0fBiBuJVbvUUzWlRuR//N15P9cBaPOBpGERGicBuEJvgiM9gJ1m0IDAgICvykEgSrwm0MQqHfJ2u/yse77Alx4YyQ8FRKYGnTY/OfpGDptJvo9Nf6may2GRqSufAN1ZSUYu2ApuvX53UOy+tFE56DxaVkNPi2rhZ5mMKKLCvODfdHHw+VEzhs4rMCFXcDJNYChAgjszwvV7sM7RagCAMdysBU5PatZtWCNTrEarubFapQXSOndJ7zgWA6VVxuQ93MVrp6vhs1MQ+4uRo++fLyqb6jq0agCJiAg8DARBKrAbw5BoN4l54rrMXHzj9g0tQ9G9/RH/k+n8OWHKUheuRr+YRG3XG81GpH6zhuoKSnCU/P/jh79+j8Eqx9tGmkG28pq8ElZDeodDIaq3fFqiC8SPW8zSZO2OYXqh0BjGaDtx8eoho3sNKEK8GLSXqyHucmzarADIgKycGfMapQXSNndi1XGwaLkch3yf65CcWYtGAcLlbcM4Ql+CE/whdrvNoJdQEDg14ogUAV+cwgC9S5xMCziV/wXY3sH4N1xPfHD9k+Q8f1RzPm/PaBErnOLWk1G7H/3TVQXFWLMvIUISxjwgK3+38BEM9heUYdNpdWoddB4zFOJ+cF+GKR2a9+bSNuBS1/wZVQbSoGAeF6oho/qVKEKOMVqaSMsGbxnlWm0AxTBe1aju0AS6gFRF9ldez/tFhpXL9Qg/+frKM/TgeMArwAlQnt5IzROA59gdxBCjlUBgd8KgkAV+M0hCNR74IUdZ5FfZcSJhUnYtXgupAolJr35brttbGYT9r/7JqoKr+DJv72O8MRB7V7/W8bMsPi8og4fl1bjut2BMIUUyf5dMNFPDY2knQIDjINP9H9yFaArBvx68UP/EU8CZOfHdnIsB/s1Ax8GkFkLRs/neiWVIkiCVJAEqyANcoe4q/tdTbQy6W24cq4aRZdqUHFFD47loPCQNIvVrhFqUPeYGktAQOCRRhCoAr852hOown+82zCohzdK6824Wl6HmuKiDlWOkiqUmLDkbfj1iMDhdf9E7pkTD8DS/00UFIkXAzX4KTEKayID4SGi8NbVCsSfuYxZWUX4vq4RjKuHKEoM9JkOzDkHPL0JsBuBvdOALYOBywcB9s4S898OgiQgDVbBc0w3+C36HXzn9YHn+B6QRXYBXWtB4zfFqPkkExXLf0TVRxfQcOgqzJeqQeusHUrgr/SQIm54IJ6e3wcz/zkII2ZEwb+bB/J+rsLhDZfw2Wsn8c0nmchLvw6rqcNlqQUEBATuiZUrV/p069YtZuzYsaF30i4vL0+yefNmr/tlVxPz5s0LOHjwoPv97qclK1as8DEYDA9UP23ZssVr0aJFfg+yz9Z9WywWYsCAAeGRkZHRW7duVU+YMCFEq9X2jIyMjI6MjIw+c+aMHAA2bdrkFR4eHh0eHh4dHx8f+eOPP94mfY9rBA/qbbhSbcCINSfwj3gK9Qc2YMLStxHSK75Dbe0WMw6kvIWKvByMnjMfUYOG3V9jfyXkmazYXVmHf1+vR72DQYBUjMl+XnjW3wvB8jYS/zM0kLUfOPEBUFcAaKKAoa8D0U8D5P1P7cSYHLCXNsJeaoC9pBH2awZwDl4kkyoJpMEqSILcIQlWQRLgBkLUsd822sGgLFeHoku1KMqohaXRDoIkEBDmidA4b4TGeUPV5a7+9gUEBB4tHkkPamhoaMzXX39dEBkZab/91Te423yjNE2jrbr3jwI0TSM4OLjnuXPncvz9/ekH1e/48eNDXn311erBgwe7rMB1P2j6LJr6ttvtxOLFi7uePXs2DwAmTJgQMmbMGP3zzz+va9nuv//9r7J3795WjUbD/Pvf/1atXLkyICMjI9dVH8IQ/z3AcRwee+8YRlh+gVfBScz5vz2QyDteJchhteL/vf8WynIuY9TL8xA95PH7aO2vCzvL4tvaRnxeWYfj9QZwAAar3ZDs3wWjvT0gc5WmiWWAy/8PSPsnUJsHeEcAcc8C/r34MAA3nwdiO8dwcFw3wV7aCFtJI+wljWB0zhKwIgISrTskwe6QOsMDqA4k8+dYDlXFjbxYvVQD3XX+d6pLVzeExnmjW5wG3oG3ieEVEBB4VGlXoL6eeikw/7qhU0vUhfu5mz+YGHetrfPJyclB+/bt8w4NDbWOGzeuvrCwUJaTkyNnGIZYunRpxbRp0xry8vIkycnJoRaLhQSAdevWlY4cOdIUFxcXWVhYKNNqtfYpU6bUqtVq5ty5c8qdO3eWAkBSUlKPBQsWVI0ZM8agUCjiZ8+eXXXs2DHVBx98UKZQKNj58+cHms1mUq1W059//nlxcHCwy6GjliJJq9X2HDduXP2pU6fcaZomNm/eXLJ48WJtSUmJ9JVXXqlauHBhzeHDh92XL18eoFar6cLCQln//v0Nu3btKqUoClu2bPFavXq1H8dxxIgRIxo2bdpUDvB15pvse+KJJ/Tr1q3zDw0NtarVajo9PT1/6tSpQZcuXVJarVbyqaee0n344YcVAKDVantOmjSp7ujRox40TRN79+4tjI+Pt+r1enLWrFlBGRkZCgBYsmRJxYwZMxoOHDigWrFiRYDdbieCg4Nte/bsKfbw8GBZlkVUVFR0Tk5OtsFgcNnWle3vv/++pqiosm8UDwAAIABJREFUSLp58+YyAFi/fn2X8+fPK3bs2HFt48aNXps2bfJ1OBxEnz59TDt37iwRiURo/VmMHDnSGBUVFf3dd9/lDxw4MFKn04m0Wq19//79V998801/VwK1JTU1NVRMTExMdXV1hqvz7QnUR/cx5RGBIAgMCvOG7eur0IR0uyNxCgBimQzjFv8DB//5Nr7e+CFYlkXssBH3ydpfFxKSxBgfT4zx8US51Y691+vxRWUdXsougaeIwgRfNZIDuiCmZfJ/kgJ6TgRixgM5/+EnU33/1o3zbr6AX88WSy/Aq1une1kJioBE6waJ1g1ujwUAAJhGOy9YSxthLzHAeLoCxhPlAADKSwZpkDukYWrIwtUuBStBEvDr5gG/bh54bFx3NFSZm8Xqua+Kce5IMdzUUoTGaRAa542AcE8h16qAgMBd88UXX5SmpaV5pKWl5b/zzju+SUlJjfv27Suura2l+vXrFzV27NjGgIAA+uTJk/kKhYLLzMyUTpkypVtWVlbOO++8U97Sg7p+/foubfVjsVjI2NhYy9q1aytsNhuRmJgYceTIkSsBAQH01q1b1a+99pp23759xR2xOTAw0H7x4sXcWbNmBc6cOTMkPT091/n6MQsXLqwBgMzMTOWFCxeywsPD7UOGDAnbuXOnOikpybh8+XLt+fPnczQaDT148ODwXbt2eU6fPr2hpX0AsHv3bu+0tLT8Jg/qmjVryn19fRmapjFgwICI9PR0ef/+/S0A4O3tTWdnZ+ekpKRoUlJSfPfu3VuyePFif5VKxeTn52cDvIirrKwUvfvuu/4nTpzIV6lU7NKlS/3efvtt31WrVlWeOXNGER0dbSZJEq7aFhcXi9uwXZeYmBgJoAwAUlNTvZYuXVr5yy+/yFJTU73OnTuXK5VKuWnTpgVt3ry5y5w5c+pa3+upU6cU0dHR5sDAQHrjxo0lrb3ib731lva9997zHzx4sGHDhg1lcrn8Jq/nRx995J2UlKTv2DfuZgSB2gEGhnoiz3wdsq7D76q9WCrD04vexH8+WImjm9eBY1n0fPyJTrby141WJsH8ED/MC/bFKZ0RX1TWYVdFHT4rr0WcuxzJ/l0wzlcNlcgpNEkSiBnHLxYdUHUZuJ7pXDKAM2kA63wgFysA3xhesPrG8qLVNxqQdG7KJ0olgTzWG/JYvnQuR7OwVxj5kIBSA6xXG2C+WMOb1NUNsggvyCLUkHR1PZvf01eB+CeCEP9EEMyNdhRn1qLoUi1yTlcg83gZJHIRgmO7wL+7B9zUUripZXBTSyFzEwteVgGB/zHa83Q+CI4fP646evSo5/r16/0AwGazEVeuXJEEBwc7Zs2aFZydnS0nSRIlJSVtxGG1DUVRmDFjhg4AMjIypAUFBfLHH388HABYloVGo+lw4P2kSZMaAKBnz55mk8lEqtVqVq1Ws1KplK2traWc50zR0dF25/X1J0+edBOLxVxiYqIhICCABoDJkyfXp6WluU2fPr2hpX2u2LFjh9f27du9aZomampqxJcuXZI1CdTk5GQdACQkJJgPHTqkBoATJ06o9uzZU9jUXqPRMLt37/a4evWqLCEhIRIAHA4H0bdvXyMAHD58WDVq1KjGttoePXrUvS3bAwMDbd9//70yJibGWlhYKBs5cqQxJSVFk5WVpYiLi4sCAKvVSvr4+NCtP4vWfbdmzZo15YGBgQ6bzUZMnTo1+I033vBbtWpVZdP5L7/80v1f//qX95kzZ1wO798OQaB2gAhxIwo5GtflAXf9GmKJFH98fRkOrX4X325ZD45l0WvEqE608rcBSRAY4uWOIV7uqHfQOFClw+cVdViUX4blV8oxxscTyf5dkOihvCHC5GogZBC/NEHb+RCAZtGaycewntvmvIAAuvS42dPq1xNw9+20eyFEJKRBKkiDVAD4cBJHpQnWvHpYc3UwHCuF4ftSkEoRZOG8WJWGqUEpb81uoFBJED0wANEDA+CwM7iWXY+ijFoUZ9Si4GzVze+hiICbJy9YlZ5SuHtJofSUOUWsFEpPKRTuEiHFlYCAQDMcxyE1NfVKXFycreXx+fPnB/j4+Dj2799fxLIs5HK5y1KKIpGIY1tMXrXZbM3DOxKJhG2KO+U4jujRo4fl4sWLdyVqZDIZBwAkSUIikTR780iShMPhIADc8oBOEES7k1lb2tea3NxcyYYNG3yd3ktmwoQJIVartfnemuwRiUQcTdOE8x5vsYHjOAwaNKjxyy+/LGrdx7FjxzwOHTp0pb22bTFx4kTd7t271ZGRkdbRo0frSJIEx3HEM888U/fxxx+X3+5eW/bdmqawC7lczs2cObNu9erVzf8g09PT5S+//HLwkSNHCvz8/Jg2DWwHQaB2AFNpAQDgrMXjnl5HLJHijwuW4ssP38N/t24AyzDo/fsnO8PE3yReYhFe6KrBLK03Lhos2F1ZhwNVOuy7rkM3uRRT/L0w2c8LPlIX6apEkhviswmOA/TXbhat5eeAywduXKP04dsEJgB9/gSo7v6hpTUEQUAS4AZJgBtUSUFgzQ5YC3Sw5upgza+H+UI1QACSIBVkEWrIIrwgDlDe8mMlllDo1luDbr014FgOZoMdRp0NJp0NxgYrjPU2GBtsMOqsqCrS4+ovNrDMzT9wJEVA6ckLVjdPKZTqGwLWzZMXtnKVWAghEBD4jZCUlNS4evVq3+3bt5eSJInTp0/LBw4caNHr9VTXrl3tFEVhw4YNXRiG1yIeHh6M0Whsjp3q3r27fevWrQqGYVBUVCTOyMhwOUTVq1cva319vei7775TjhgxwmSz2YjMzExpv379rJ11L5mZmcrc3FxJWFiYPTU11euFF16oGTJkiGnRokWBlZWVIo1GQ+/bt8/r5ZdfrnbVXqlUMnq9nvT394dOp6Pkcjnr5eXFXLt2TXT8+HGPoUOHGtrrf9iwYY1r1qzx2bZt2zWAH6YfNmyYacGCBUFZWVnS2NhYm8FgIIuKisRarZZmGAZNIs9V2/ZsnzZtmi4+Pj46MzPTlpKSUgYAo0aNahw/fnyPJUuWVGm1WrqqqorS6/VUeHj4TRPh6urqqJZ9t6akpEQcHBzsYFkWBw4c8IyKirIAQEFBgeSZZ57pvm3btqJevXrZXLXtCIJA7QDludlg3bvgp0oHLHYG8rvIc9mESCLBU/OX4MsP38P32zaBZVn0Gf1UJ1r724MgCMSrFIhXKfCPHgE4XK3H7so6vFNYiZSiSvR2VyBKKUeUm6x5rRa7+OoTBOAZxC+RLR4cXIUIpL3PZwyIfhp47GVA69JpcE+QCjEUcT5QxPmAYzk4yo2w5NbDmlePxm9L0PhtCUh3SbNYlYV53lLliiAJKD2kUHpIgRDX/XAsB4vRAaPOygvZBhuMLcRsVYkBpou1YOhbU3dJFSIoVBLI3SWQu4uhcJdA7txXOI/J3SVQqCQQyyghtEBA4H+UlJSUitmzZwdFRkZGcxxHdO3a1fbDDz9cmTdvXvWECRO6Hzx4UD1o0CCDXC5nASAhIcEiEom4iIiI6OTk5No33nij+uOPP7ZFRETEREREWKKjo13ORpfJZNyePXuu/u1vfwsyGAwUwzDESy+9VNWZArV3797GBQsWdM3NzZX379/f0DSM/+abb5YPHTo0nOM4Yvjw4fpp06Y1uGr/3HPP1Y4ePTrMx8fHkZ6enh8bG2sOCwuLCQoKsjUNy7fHe++9V/n8888HhYWFxZAkyS1ZsqTiueeea9iyZUvxs88+281utxMA8I9//KP8/PnzZEvB21bbtmzXaDRMWFiYpaCgQJ6UlGQGgL59+1qXLVtWPnz48HCWZSEWi7n169eXthaohw4dUrUntidPnhxaX18v4jiOiI6ONu/cubMEAJYtW+bf0NAgeuWVV4IB3nuclZWVc/tP5maEWfy3gWNZbJw9DcoevbC8oSd2zkzAkHDNPb8uQztweO37uHL2Jwz70wvo++TTnWCtQEuumK3YW1mPc40m5BitaKBvPAT6ScQ3CdYopQxhShmkHU3yrysG0j8BftkJ2A1AYH8g8WUgcgxA3f/nPsZghzVfx4cD5OvAWRmAJCANUfFiNVINkY+i0wQhx3GwmhwtPLE2WAx2WBrtMBsc/LbBDrPBDpvJdeYVSkTyIraloG3elkDuJgZBEmAZDizLgWM4MAwLjuWaj7EMv3Bsq3MtznMMB5Zh+X2WA0WRkLmLIXcTQ+4mgcxNDLm7GDIl36dQAEHgEeGRTDP1a+Nu0189LCZPnhw8e/bs2uHDh5t+jX0Ls/jvgfqKclgNjUjs2xuS4xxOXantFIFKicQYM28xjqz/J47v/BQsy+J3T42/d4MFmumhkGFpd34InuM4XLc7kGO0IsdkRY7RghyTBad1RtidD2kUAXSTSxHlJke0UoYoNzkilTIEyiQgWws9dQgw6l1g2GLgwr+A9M3AvucAjyCg/2x++F92byEh7UG5S6Ds6wtlX19wDF+StSl2Vf91EfRfF4HylEIW6QWxvxKkhAIhIUFIqOaFbLkvJtuNOSUIAnI3CeRuEmgC28+JzdAsrEYHzI32G8K18WYRa260o7bMCIvBfkt4wd1CUgRIkgBJESAoAiRFgiQJMA4WVrMDaKMbsYyC3E0MmZvEKWLFkDkXubsEMqW4WUDL3MSQykVCfK6AgMADYe/evSW/xb4BwYN6WzK+/wb//WQDZq7dgpe+LEWjhcZXcwd32uszNI2vN6xG3o8nMWjKc+j/9DOd9toCt8fBcii02JBjtCDXZEW20YIckxXXrDdGOpQUiUil7KYwgUg3GbxahgmwDJD3FfDTJqDkNCBxA3pPBfr/GejS/YHeE623NYtV2xUdOHvHqmoR4ibBSroUsS1FLimjQHnKQKmlEKllIO8yMwDHcbBbaF7MGvmJuk0ik6QIECQBiuLFc9OxZhHadM55rD1YloPN7IDF4IDV6IDFaHeuHbAaHLCY7Py6xTm6jfeNIAnI3cXw0Mih9lXA01cJTz8F1L4KqLxlIIW4XIG7Q/CgtsP06dODzp4969by2EsvvVQ1d+7cuodlk8C9I3hQ74HynMtQeHjC0y8Ag3qYserbfNQabfB2u+NMGi6hRCL84ZXXQJAkTu3egfryaxg+8y93nG9V4O4QkwQilDJEKGU3HTfQDPJMVuSYLMgx8sL1cE0D/lV5I0zAU0QhRC5FqFyCUIUUoeqBCB3/OEL1+fA6txnEuW3Az58AEaP54f+QQXyc631G5CGFW4I/3BL8wdEsWJMDrJ0BZ2fB2RlwdgZsi23OzjrP39jnr3GeM9tubuNggFbajRCTzWKVUssgUkuda17EkkrXApYgCEgVYkgVYqjv43tCkjc8wB3FYWdgNToFrYEX0E3i1qy3o6HazFf3MjRnVQFJElBp5PD05QWrp5+ieVtI7yUgcPfs2rWr9GHbIPBgEQTqbSjPy4Y2MtqZsF+DVd/m48zVOoyN67zZ2yRFYfSc+fD0C0D6gb2oyMvBH/72Gvx7RHRaHwJ3hruIQj8PJfp53Jho2jJMIN9kRZHFhiKLDecazThY3dBiBJmASvNXhP7+FYSaShBacRqh33yEUPknCO01Bl16/hGEWOaq206HEJGgPKTozDIEHMeBszFgGmygdVYw9VbQOhsYnRV0gw32awaw5pvjUHkB20K4esluErSkQnRr6hSW74e10eCsDFgrDdbG8NtNx2wMOCsN1sqAs7k+DwCkQgRSKQapEINSiEAqxM590Y218xilEIEQUxBLKIi9KLh7tf9ZWU0ONFSZ0VBlhs65bqgyozS7Dix941shVYhuEa6evgp4ahRCHKyAgIBAKwSB2g6G+lroq6sQP2osAKCn1gMqmQinCmo6VaACAElSGDhpKoJ7xuGrj1Zjz5sLMWDSNPxu7HiQD6CWvMDtIQgC/lIJ/KUSPN5FddM5G8ui1GJvFq1FFjuKzTb8wobikFZ7w+GoB9yP/4JQkQOhXn4IdVchtIUXViNxkRLrEYMgCBAyEUg/EcR+rosZsFb6hmjVWcHonGJWZ4WtxADO2krASihQnlKA45rFZodCEwg0hxwQUhG/llEQe0pBSCk+qwHHgTXTYEwOsGYH6FoLWJMDnK3t1HyEmHQK1lZi1ilwCQU/oQskAYIEPEgCnl5ShHjLgJ5d+LyKBGA22GHQ2WDQ2dBYb0VjnQW1OXUo/fk6WKd25QhAqZZC5aOEwkvKZ0Fwk0Cu4id1NU0ok7kJab0EBAR+OwgCtR3Kc7MBANrIaAAARRIY0N0bpwpqXSbL7Qy6RsXiT//8CP/dugGndu9AScYFjJ4zH+5e3p3el0DnISVJhDkzAbTGzrK4ZrWj0GxD8bUsFJZlo9jO4pLFiMMyfzDEDdERLJNggNoNAz3dMMDTDQGyjg9JP0qQMhEk/iLAvw0Ba6FvEa5Mgw2gCJBSEQgZBVJK8UJYSjn3bxwnZfw2IabuesISR7NgLTRYs4MPg2gWsbRz37ltdsChs4Ix0+AsrjMUtAcFwNO5AOAjDVWtHkQYFqg0AJUG0BwHmgNoDtBzQB04OJz7HEUAEgqElAIlE4FSiCBSiiF2F0PiLoHMQwqZWgq5lwwyTyko8d093HIcx08qa163Ogbw7z0lhCwICAjcHzokUAmCGAVgHfjf2k85jktpdV4KYCeAvgDqAEzmOK6YIIgQADkA8pyX/sRx3F86x/T7T3nuZYilMviEdGs+NjDMG99cvo6iWhO6adzaaX33yNzcMGbeImQd74Nj/7cFO19/Bb//y1z0+F3ifelP4P4iIUl0V8jQXSEDvAcC8QOBmjwgfTPsP+5DmUiFopDRKOjxNNLFWnxdo8fuynoAQIhcggGeTsGqdoO/9H9TsLaGlIsgkbsBAffnb6gjECISlLsElHvH31OO4cBaHGAtNMDygo1jOIDjU1/BufDbuPkY13QOra67sc3ZWd77bHLAYXKAMdPNoQ2wMyBoFgTDgjSzgNkB1N9qo9W5ALyoZQk+9JkkiOYQ6OZ1yzmyLcRoh9/Dpol1UucDRattUsrvt3msdVuR4CEWEBDgua1AJQiCAvAxgJEAygCcJQjiEMdx2S0umwVAx3FcD4IgngXwPoDJznNXOY7r3cl2PxDKc7PhHx4JkrrhhRjcg/dknrpSe98EKsAPo/ZMegLaiGgcWf8B/rNqJeJG/gFDp8+EWPpg4hcF7iOaCGDMh5A8/ga6nd+Obj9vxfCcT/EXhTfYyCeR3WM8zigjcabRjCM1enzhFKyhTYJV7Y4Bnm7wc1UlS+C+QVAEKDcJqDuYbHU/4GiWj7e1MWAsNGx6G6wNVtj1dtgNdtAmGrSZF9KMjYHDzoC2s3DYGD5XLFrpUIKASEpCLKUgkoogllEQSymIZSKIZSJI5BTEMgoSmQikmOSFedNEOqcdrM05Ac/sAKOz8tvOcx0WvRTRLGD5tah9wXvTWnSLGBbSgd07K1eu9Nm2bZsmNjbWfOjQoVvKcLZFXl6e5IcffnD7y1/+4uIxqvOYN29ewLBhwwxPP/10u9WbOpMVK1b4vPrqq7Xu7u4dS5HSCWzZssWrsLBQ8v77719/UH227nv58uVVw4cPD6uvrxctWLCg8ptvvvH46aef3N3d3RkA2LZtW9GAAQMsAJ9v9rXXXgukaZpQq9X02bNn89rv5VY64kFNAHCF47hCACAIYg+APwJoKVD/CGC5czsVwAbif3y6qs1sQk1pMQZMTL7peHAXBbqq5TiRX4s/PRZy3+3wCuiK5JWrcGrPLpz78gDKcrLw5N9ehyY49L73LfAAUHgBg+cDA14Bco8A2f8BmZmK2F92IFbmidkRfwATNRbZvo/hjNGO0zojvqxpwOdOwdpNLsVANR8O8JggWH8zECISlIgElGKIAEi1blDdthU/TO+wMjDpbTA38vlozfqmtQ0NjXaYGu0wX7fAYrC7FJYSuQhydzFEYt4GkiJBiQiQIhIURYASi0DKJaAo5zGSL9IgAp9rWMQBFDhQHD8kR7IcSA4gGRYkw4FhON5TTLMg7AzvKXawzoXh1x0UvISYBCkXgXR6yil3CUh3MSgV/5BBqm4cF7y3rvnss880X3/9dUFkZKT99lffoKCgQLp3716vOxWoNE2jrbr3rli7dm3Fnbz+vULTNLZs2eL74osv1j9IgXr06FHVq6++6rL06v2i6bNo6vvMmTMKh8NB5Oby8Y/ffPONx8qVK8uef/55Xct2tbW11Ny5c4O++eabgrCwMHt5efldhZN2pJEWwLUW+2UA+rd1DcdxNEEQegBdnOdCCYK4AKARwDKO40627oAgiNkAZgNAUFDQHd3A/aIiLwfguOb40yYIgsDoWD98eqoI3+dUYXiU7323hRKJMXTaTAT3isc3H6/B50vnY8jUmYgfNUZIW/NrgRIDMU/zi8MCXD0GZB8Cco+AuvQFekrc0TP89/hz9FgwCSNw2U7gjM6I0w1GHKzSYVcFnwqweyvB6isIVoEWEAQBiVwEiVwEdRsT3JpgGRYWo+OGgG20weTcthjsYBwsWIYDQ7NgaBa0hQZD33yMpfmKXy3XnQEFQES0WEDcvE84960MJGYaikY75BQBCQeIWO7WhKMACLnIKVbFvJB1ilhKJblJ4BIPq2Tvwb8Gojq7c/MP+kSb8fTH19o6nZycHFRWViYdO3Zsj3HjxtUXFhbKcnJy5AzDEEuXLq2YNm1aQ15eniQ5OTnUYrGQALBu3brSkSNHmpYuXaotLCyURUZGRk+ZMqVWrVYz586dU+7cubMUAJKSknosWLCgasyYMQaFQhE/e/bsqmPHjqk++OCDMoVCwc6fPz/QbDaTarWa/vzzz4uDg4MdrmycMGFCyJgxY/TPP/+8TqvV9hw3blz9qVOn3GmaJjZv3lyyePFibUlJifSVV16pWrhwYc3hw4fdly9fHqBWq+nCwkJZ//79Dbt27SqlKApbtmzxWr16tR/HccSIESMaNm3aVA4ALe174okn9NXV1eKhQ4eGq9VqOj09PX/q1KlBly5dUlqtVvKpp57SffjhhxUAoNVqe06aNKnu6NGjHjRNE3v37i2Mj4+36vV6ctasWUEZGRkKAFiyZEnFjBkzGg4cOKBasWJFgN1uJ4KDg2179uwp9vDwYFmWxeXLlxUDBw40t9XWle3vv/++pqioSLp58+YyAFi/fn2X8+fPK3bs2HFt48aNXps2bfJ1OBxEnz59TDt37iwRiURo/VmMHDnSePnyZUVISIh94MCBkTqdThQZGRm9f//+q219bz799FOvJ598UhcWFmZ3vg93HryPjglUV3+JrX9l2rqmEkAQx3F1BEH0BXCQIIgYjuMab7qQ4z4B8AnAJ+rvgE33nfK8bJAU5TLV04InIvBjYR3m7bmIg3MGovt9HOpvSUivePzpgw04umktfti+BSUZv+D3L82DQnX/KhYJPATEciDySX6h7UDRCSD7IO9hzUoFJZKjV9hI9Ir+I/4S/gQYaSiyjHxVrDMNRhyo0mGnU7D2UEgRppBBTpGQk4RzTUJOkZA51y2PK246TkJOEZCT/DEpSQgPRL8hSIqE0kMKpUfn5HwGeA9uk4BtvWbom8vack3la1tutyh121zatvU2w4Flb7yWw8agxnDDU2zR28GaHZCRgJQgICMBGUFAamOgNNGQ1xKQEoDY6dm9BREByl0C9bgwyMLvZ/beh88XX3xRmpaW5pGWlpb/zjvv+CYlJTXu27evuLa2lurXr1/U2LFjGwMCAuiTJ0/mKxQKLjMzUzplypRuWVlZOe+88055y5Ki69ev79JWPxaLhYyNjbWsXbu2wmazEYmJiRFHjhy5EhAQQG/dulX92muvafft21fcEZsDAwPtFy9ezJ01a1bgzJkzQ9LT03Odrx+zcOHCGgDIzMxUXrhwISs8PNw+ZMiQsJ07d6qTkpKMy5cv154/fz5Ho9HQgwcPDt+1a5fn9OnTG1raBwC7d+/2TktLy/f396cBYM2aNeW+vr4MTdMYMGBARHp6urx///4WAPD29qazs7NzUlJSNCkpKb579+4tWbx4sb9KpWLy8/OzAaCmpoaqrKwUvfvuu/4nTpzIV6lU7NKlS/3efvtt31WrVlWeOXNGER0dbSZJEq7aFhcXi9uwXZeYmBgJ3rGI1NRUr6VLl1b+8ssvstTUVK9z587lSqVSbtq0aUGbN2/uMmfOnLrW93rq1ClFdHS0OTAwkN64cWNJ6zKxb731lva9997zHzx4sGHDhg1lcrmcy8/PlzkcDiIhISHCZDKRL730UvWcOXPuuKBCRwRqGYDAFvtdAbR2qTddU0YQhAiAB4B6ji9TZQMAjuPOEwRxFUA4gEenVFQblOVchk9od4hlt8Z7ysQUtkzvh7EfncLsnedw8K8D4S57MJ4qhcoDTy98ExePHkbav7Zh5+tzMOrlVxES1+eB9C/wgBFJgLAR/DJmLV+lKucQkPMlv6YkoLoPR1z0WMRFjMbLQd1AsxwyjRacaTDijM6IYosNFpaFhWFhYVlYGa65vOudQAA3CVm1iIJaLIKnmF/z+xQ8m7dF/L6Iv4a6T+KW4TiYGBYmhoGRZpu3+TULdxGFvioF1GIhacnDhiAIUCKCD094iDA02yLE4Ua4g0FvR1XTfoMNdqMDYpaFjORFa9NabmFgrTQh9EEK1HY8nQ+C48ePq44ePeq5fv16PwCw2WzElStXJMHBwY5Zs2YFZ2dny0mSRElJyR0/0VAUhRkzZugAICMjQ1pQUCB//PHHwwGAZVloNBqX3lNXTJo0qQEAevbsaTaZTKRarWbVajUrlUrZ2tpaynnOFB0dbXdeX3/y5Ek3sVjMJSYmGgICAmgAmDx5cn1aWprb9OnTG1ra54odO3Z4bd++3ZumaaKmpkZ86dIlWZNATU5O1gFAQkKC+dChQ2oAOHHihGrPnj2FTe01Gg2ze/duj6tXr8oSEhJDrwcxAAAgAElEQVQiAcDhcBB9+/Y1AsDhw4dVo0aNamyr7dGjR93bsj0wMND2/fffK2NiYqyFhYWykSNHGlNSUjRZWVmKuLi4KACwWq2kj48P3fqzaN13a9asWVMeGBjosNlsxNSpU4PfeOMNv1WrVlXSNE1kZGQoTp48mW8ymcjExMTIIUOGGHv16mXr6OcIdEygngUQRhBEKIByAM8CSG51zSEAzwH4EcBEAMc4juMIgtCAF6oMQRDdAIQBKMQjDu1w4PrVfPR+4sk2r9F6yrEhuQ+mfZaOV/dewifT+9623GJnQRAE4kc9ha5RsTiy/gPsf/dN9B0zDoOn/AmUSBjS/dVCiYBuQ/ll9AdA2c9A9n/4UID8rwFSBIQOgShqLOIjxyA+yAd/DfJx+VI0y8HK8oLV3EK4thSyFhfHzc61iWHR4GCgo2lcs9rRQNPQOZh2QwM9nAJW7RSsXmIRPFuIXE8RBUeT2KRviExjK8FppG9smxgGFrZjYjtcIUOChxK/81AiwUOJELlE8Aj/RqFEJNy9ZLctwtBUitfUIszBrOe9sR6/cu9paziOQ2pq6pW4uLibRMb8+fMDfHx8HPv37y9iWRZyubyvq/YikYhj2RshmzabrfkpRSKRsE1xpxzHET169LBcvHgx927slMlkHACQJAmJRNL840CSJBwOBwHglr97giDQXtn3lva1Jjc3V7JhwwZfp/eSmTBhQojVam2+tyZ7RCIRR9M04bzHWwuTcBwGDRrU+OWXX94yEe3YsWMehw4dutJe27aYOHGibvfu3erIyEjr6NGjdSRJguM44plnnqn7+OOPy293ry37bk1T2IVcLudmzpxZt3r1al8A6Nq1q93b25tWqVSsSqVi+/fvbzh37pyi0wWqM6Z0DoCj4EN/tnEcd5kgiBUAznEcdwjAZwB2EQRxBXzik2edzYcAWEEQBA2AAfAXjuPu64y+zqDqagEYhwPaqJh2r3usexe88WQUln+ZjXXfF+DVkeEPyEIeTXAopr73IdJ2bcP5w/8P1y5n4Mm/vQ6vgK4P1A6BhwBJAkGJ/PL7d4GKX3ihmv0f4PA84Mh8IHggEDUWCEwA5J6AzBOQqgCShIgk4EZScOvEGlMsx6GRZqBzCledg0GDg4aOZqBzOPdbbBdZbNA5GOhp1wnzRQTgRlFQUrzHtmk7SC6B0rnNLxTcKBJKEeny+iq7A2f1JvysN+FQjQ7/quRHmrzFIvyuhWDt6S6HlBQmygjcoGUpXq82cvr+VkhKSmpcvXq17/bt20tJksTp06flAwcOtOj1eqpr1652iqKwYcOGLgzD/z17eHgwRqOx+Qeme/fu9q1btyoYhkFRUZE4IyPD5Rvaq1cva319vei7775TjhgxwmSz2YjMzExpv379rK6uvxsyMzOVubm5krCwMHtqaqrXCy+8UDNkyBDTokWLAisrK0UajYbet2+f18svv+xyUpJSqWT0ej3p7+8PnU5HyeVy1svLi7l27Zro+PHjHkOHDm03o8CwYcMa16xZ47Nt27ZrAD9MP2zYMNOCBQuCsrKypLGxsTaDwUAWFRWJtVotzTAM/Pz8mLbatmf7tGnTdPHx8dGZmZm2lJSUMgAYNWpU4/jx43ssWbKkSqvV0lVVVZRer6fCw8NvmghXV1dHtey7NSUlJeLg4GAHy7I4cOCAZ1RUlAUAJk6c2PDXv/41yOFwwGq1khcuXHB7/fXXq+7sU+pgHlSO474C8FWrY2+22LYCeMZFu/0A9t+pUQ+b8jxngv6I6NtcCTw3IASZ5Y1Y930BYgJUeCLG736bdxNiiRQjZr2EkLg+OLp5HXYtnovHn/8zYoeNFLxDvxUIAtD25ZcRy4GqLF6s5hwCvn691bUkIPPgxWqTaJV7AnL17Y9J3W8k0HQBSRDwFIvgKRYhFB0f5WM4Dg1OoSoiwAtOEQkJ0Tkxr2FKGQap3QHwIjrPZG0WrGf1JnxdqwcASEkCvd0VzYK1n4cSXkJYgIAAACAlJaVi9uzZQZGRkdEcxxFdu3a1/fDDD1fmzZtXPWHChO4HDx5UDxo0yCCXy1kASEhIsIhEIi4iIiI6OTm59v+z9+Zxdl5nnef3vNvd19pLJVmyVkuOpNhW4sQJdnAgCUkgnQA2IZmwNAzBGdJ0pqEDpAP0zAeY7hmahDSEDjAJPWTphCUBmgAdHMYhdmwnlm3Z2q2t9uXuy7ue/uN9761bi2TZKqkk1fl+dD5nfd976q2rur/7nOc85yMf+cjMJz7xCXv37t37du/e3dq7d29ztdeJx+Pyc5/73Kmf+7mf21Kr1XTf98X73//+6bUUqAcPHqx/6EMfGjt69Gji1a9+da2zjP/v/t2/G7/33nt3SSnF/fffX3nPe95TXu36973vfXNvectbdg4ODrqPPfbY8dtvv725c+fOfVu2bLE7y/KX4jd+4zcmf/zHf3zLzp0792maJn/pl35p4n3ve1/5k5/85JkHH3zwVsdxBMBHP/rR8SeffFLrFbwXu/Zicx8YGPB37tzZOnHiROINb3hDE+DOO+9s/8qv/Mr4/fffvysIAkzTlB/72MfOLReoX/7yl7OXEtsPPPDAtoWFBUNKKfbu3dv8zGc+cxbgjjvuaL/xjW+s7NmzZ5+mabz3ve+dPXTo0Ev+/YlLmYbXg7vuuks+8cT6uqj++W/9GuWpSX78t3//ssa3XZ8HPvlNTs7U+csP3MOOwcxVnuHq1Bbm+NtP/D+ce/Zpdt39Or7npz5APL1+gdAV1wFzJ2DuOLTK0C5Dq9RTjuqdcrsMwSU2Wwp9Uawmi5AeClNmeGWeGoAb5IjeaTu0sHZE6zP1Jp3N5juTsSVW1lsTMfXFT3G1WPHGOnz48JkDBw7Mrcdkblb+6q/+KrN8o8/1zAMPPHDLT//0T8/df//9jZvxtQ8fPtx/4MCBrav1KfPAMmQQMHHseXa++rWXfU3c1Pn9997J2z/+CD/1mSf5i4fuIZe49r6gmWI/P/jL/wePf+XP+Mbn/4TJk8f4vg98iLHbbu+OkVLiuy6u3Q5T28Ztt6K6HbWFfU67jdc7Lmpz7TaarpMbHCY/NEx+aITc0DD5weFVN5Up1pH+nWG6HKQEp7FStK4malsLMH8q3LTVWmXvgNBCkXoxAZsehkwkcI212yX+chiKmbxtMM/bBsPDSFt+wFO1Zlew/k3PQQl9psGhXJKDmSR9lkFG18kYOllDJ2NoZPWwnNQ1NCVkFQrFFfL5z3/+7EZ8bVAW1BXMnTvDp6Od8fvuvf8lXfutFxZ49395lO/aNcCn/pe7rtmmqdWYOnmcv/74f6AyPU1uaCgUn+1QfEr5EmILC4EZi2PGYljxBGYshhGPE3ge5elJ7MbSL1apfIHc0EhXuOaHhrv1RDanrE83I54N9WmoTUN9CmpTUX1Z3piF1d57icKiYE0UQxeERH7RFWFFPSrr1+b7dSAlJ5p2JFjrPF5p8ELr0jHLBZAxNDJ6R7zqUVlbFLR6JGqNxTEd/9lkFCkhpeuY6jSkjYKyoF6C9773vVsef/zxJUuC73//+6c/+MEPvuTwRYrrB2VBfQlcOBr5n+659Aap1XjVtiIffftePvKXR/jtfzjOh753ZQzVa8Xwjl289zd/h29+6XPUF+Yx4/FIaIZis1vvbY/HMGNxrHgCIxpjmJfe6dyu1ylPT1KenqQyPdUtnzvyNM/909eWjLUSicjqGllch0bCNDxMpm9gyZGyihsIIwb5LWG6FIEfitSLCdjaFFQuXJ67AYCVXkXAriJqc2MwchDil3PW0ko0IdidirM7Fec9o2Eox4YX+sxWo9BWVc+n6vnUfJ+aF1CL6lXfp+aFbbOOy6lWNM4LcC/TOGAKEYrWJcI1jFXb257S9cV6T3ve1BmNWYzETBK62gSmuDH5kz/5k3PrPQfFtUUJ1GWMHz1CulAkN/jyToh6z9238Ox4lY9/7ST7RrO8+faRNZ7h5WMlktz7np+4qq8RT6cZTu9kePvKZWTPcajMTEfidZJyJGDnLpzj9Le/he8tCpDQZWCIwa3bGdm5h5Gduxjcuh3DWt8zzxVriKaHy/uZy9hIKCW4TWhXwtQqR+Xyxevl89B+Jqzby8P2CRjYE24kG4s2lA3ue9lW2JShkzJ0Rl/W1aGrjR1Ian4kZCNR2/B9mlE4r6a/NDWWtZdcn/G2G4XaCtvaLxJyqxiJ1dGYyWg8ymMmozGLTXGT4ZipIhlcXwRBEAhNW/XIAIXihiYIAgFcdElXCdRljB99jtE9+172UrQQgl9/xz6OTdf41184zLb+NLuH12fT1HpjWBZ9Y5vpG9u8oi8IfOoL85HVNRSupYlxJo4f5dg3w9NwNd1gcOs2hnfsZmRnmPJDI8pNYCMgBFipMGVfhgwM/EUBO38axp+A8Sfh2N/AU/81HGMkYOQAjN21GAUhv+WSkQrWCiEEcV0Q1zUGrLXzV/elDOPVRmK24QeUXI8J22Wi7YS57XKh7fCtSoPyKiG++k2D0fiicB2NmWyKhxbY0ZjJSMxSbgfXjmdnZ2f3DgwMVJRIVdxMBEEgZmdnc8CzFxujfFB7qM7N8F8e+gne8GP/K3e85e1XdK+pSpu3/+4jJC2dLz/0OnJJFUD/cqkvzDN58hiTJ48zeeIo06dO4tphhIp4JsvI9p0M79jN6M7dDO/YrSIVKC4fKaF0JhSr40/ChSdg8jD4Ufzo1EAkVu+CTXeEKXHzBmRv+D6TtstE22XcdpaUJ2yXSduh6i01cAigaBoYkUbtfIL0fpL0fqws9q/+WdM7VgjQhUBHoIvQvcKI2rSozRACLWozhEAjuqZzbadMWI5pgqJpUIwOh+ikgqnTZxoUTON6EdwrJvHkk08OGobxKeB2QJm2FTcTAfCs53n/8s4771w13qwSqD08/8jD/M3H/yPv/a2PMbj11iu+35NnF3jwDx7ltdv7+aMfO4R+ffwRvOEIfJ/5C+dC0XoiTPPj57ufbIWRTYzs2BW5Buymf8tW9Iuc+qFQrMBzYOZIJFgj4Tp3bLG/b0ckWCP3gKFXhEfQbhDqns94ZIGdtEPxOut4BMuEJayisFja3rv6IVbpDwg3pXlS4svQIhxAVJcEcmnZJxwbRGM9GV7vs3h9KwjdIRr+xTeHZg0tFK1GJGCtUMz2RUK2V9gWo9PQjLX/e64+IBSKHpRA7eEfPvUJnn/k6zz0R59FW6MYjn/62Dl+6c+f4f33becX37xnTe6pALvZZOrUcaZOHu8K12YljKlsmBaDt+6IROtuiqNjJHN5Etnsmv1eFTc57QqMf3uppbURfcnXLRjeD6OvhNGDYd6/+5pFFVC8POxIqC64Hguux3x0olmnvuCGp5zN99SblxC1f3T7Vr5vIL+WU1QCVaHoQQnUHj79vz9Euq+fd33419b0vh/+s2f47LfO8bvvfiVv2/9yt1UoLoWUkursDJMnjzF18hgTJ44x88IpfNftjhFCI5HNksrlSeYL3TyZy5Pq5Lm8ErOKlUgZRhgYfzLyZ/126BrgRIfGGAkYvj0UqyMd0bpLidYbnLYfUPJCsbrgeCz0lN8xlGd7ck3jPiuBqlD0oARqRKte4z//5I9wzwPv5e53PrCm97Y9n3f/l8d4bqLKn/3sa7lt5OWFu1G8NHzPZe7cWSozUzQqZZqVMo1yiWalTLNcplEp0SyX8dyVMS0vJmYX8wKpfJ5UoUg8nVEbtzYiQQALp2DiOzDxVJhPPb1MtL5imaV11w1zwpbimqP+iCgUPSiBGnHqyW/xF//Xr/PAR3+Tsb23v/gFL5GZarhpyjI0vvKB15FPbhwftusZKSVOq0WzUuqK10alTLNcWlXUriZmNd0gmc+TzhdI5guk88UwLyzWOxZaFTbrJifwwxO2Jr4Dk5FonXwa3OhACzMZuQccXLS29u9UolUBSqAqFEtQAjXin/6/P+bJv/5LPvD/fh7TujpHL377XIkHP/kor761yB//2CEMFTT7hiIUs00a5Y6ADUVto7RAo1ymUV4I6+USzWpl6fbkiHgqvShecwVShVC8pvNhubhpM6l8QVlkbyYCH+ZPrrS0us2w30zByP5QrBZuCSMJJPvCvFNWrgIbAfWfXqHoQf3Vixg/+hxD23dcNXEKcMeWAv/+Hfv4xS89w3/46jE+/H23XbXXUqw9QghiyRSxZIri6KZLjg18n2a1EorXSolGKRKzXRFbZvLkMRqlEp5jL7k2kc0xcMs2Bm7ZxmCUFzeNoRsqVNkNiabDwO4wHXgwbAt8mDvRY2l9Cr796UXRupxEIRKr/ZDqj8RrT57sXxS0iQKoYPsKheIGRwlUwHVspk6d4M63/sBVf60HDm3h2fEqn/yn0+wdzfIDBy8tdBQ3Jpquky4USReKlxzXcTFolEvUF+aYO3+W2bMvMHv2BZ766l91N3lpukHf2OaucO2kZDZ3LX4cxVqj6TC4J0wHfyRsC4LwYIHGHDTnwmNhG7PQmF8sN+dh7jic/QY0F2C12KJCW7TAJvsglg3HySCy6suefLU2uXrb8vEdlqwUXEH74g8QZSIsXyx/0TERZgLSQ5AZgUwnHw7z1KCyTisU1ynqfyYwffIEge+xac/ea/J6H3nbXo5OVfnFLz3NjsE0+0aVyNiohFbZJLFkkuLoJrbcfqDbF/g+pclxZiLBOnv2Bc4+8xTP/dPXumPSheIy0XorhZFRNF35NN5waBoki2Fi14uPD/xQpHbF61wobhuzS/PyuUjPLRNwQlvZRtTeKXcssRcd36GnfCXtXfF6KZF8sTEs1oNgcUx9OvQDbsyEAnsJIhTyHcG6XMB2hG1qQAlZheIao3xQgcf+/As88rnP8LN/+FkS6WtzLOlszebtH38EXRN85X97HcWU2jyjuDya1QqzZ15g9uzprnCdHz9P4IfHVhqmRd/mLV3RmunrRzdNdN1ENw10wwzrholuGFE5zDXDwDBMhFoiVtxs+F4o2utTUJuC2mSUL6s3Zllh2RVaaG3tFbB3/WToO7x2KB9UhaIH9ZUQuHD0CH1jW66ZOAUYyMT45Hvv5Ic++U0+8Kff5jM/8Sq1aUpxWSSzOW7Zf5Bb9h/stvmey/yF813BOnv2BU498RjP/uPfv6zX0HS9K1a1XhHbEbemiRVPYMUTmPE4ZjyBlUhgxRbLZjy+ckw8HvbF4koEK64tugHZkTBdCt8Lra21SahN9wjZydAaWx0P4+He9v3XZt4KxQZlwwvUIPCZOPY8t73u3mv+2gc25/k/33E7/+aLT/Mb//0oH3nbtXExUNx86IbJ4NZblxzRK6WkUVqgWa3guy6+5+K7Hr7vRnVvMfdcAs/Dc8Pc93r7o+u8TtnFc90wokFpAafdxmm3cNutJQcjvBhGLLZEwIaiNqxbicW8t81M9PYnwzwSw+pgBcWaoBuQHQ2TQqFYNza8QJ07dxan1WTT7vURhz9012aOTFT5w0de4PZNWf7FK8fWZR6Kmw8hBOliH+li3zV7Td/zcLuCtY3TboZ5KxSwvWLWabdxW62wbodjWtUqlZlp3FYTJxqzWriu1egK3mWiNpHOkO7rJ1Psj/LwmSSzOWXFVSgUiuuUDS9Qx48eAWDTbfvWbQ6//NbbeH6yyr/5b0/zO/9wglzSopA0ySdM8kmLXMIkn4xSwiLX05eNG8o1QHHdoBsGejpNPJ1ek/tJKfFsOxSrrSZOJGg7uXvReihwG+USc+fP0igtdH10O2i6QbrYR6avj3SxPywX+7v1TF8/qXxBbThTKBSKdUAJ1KPPkekbINs/uG5zMHWN33vPnfz+108xVWlTbrmUGg6nZxuUmw7VtnfJ6zNxoyteQyFrRQLWJJcweeWWPHdsUcHfFTceQojIfzVOKl942feRQUCzWqE2P0dtYY76/By1hXnq83PUF+aZPn2CU48/uuKkMCE0Uvl8jwW2j3Shj0yxj3gmSyKdIR6lWDKpLLIKhUKxRmxogSqlZPzoEcb2vmK9p0IxZfFLFwnc7weSasul3HIpNx3KLZdKc7FcbrpUevrGS63u2CBaHd2UT/C2AyN8/4FR9o5klVhVbCiEppHKF0jlCwxv37nqGCkl7XqNWiRa6wvz1BbmuvX58fOcfeYpnNbqwfSF0Iil05FoTRNPZ5YI2Hgms6ItkclgJZLq/6NCoVAsY0ML1OrsNPXSApv2rN/y/uWga4JCyqKQsoDUZV8XBJJyy+XhYzN85fAEf/j/v8Anv36aWwdSvH3/KN9/cJTtA2uzFKtQ3OgIIUhksiQy2SWbzZZjN5vUS/O063Xa9Vo3tWo95XqNRrnE/IXztOtVnFbr4q+racRTaeKZLKYVC0OBmSaGaS2GA+vJDXO1uoVuhlEX9J5+w7QQug5SIrtB+OmWQ/deiVzWDkTX0HNtKOLD8ct+iFX8hOXyUE3Lx1wkRr8QGkITUa4hhOhpE1Fbz5hOW3fs0rphxUjm8ujGhv64UyhuODb0/9gLz0f+p9coQP+1RtMExZTFO+8Y4513jLHQcPjbZ6f48uFxPva1E/zO/zjB3pEs339wlLftH2GskFzvKSsU1z2dgxVeCr7nReK13hWw7WWpVavhOTaeG0ZKaDfqYRSFKJJCp71TX+5Tq7gEQpDK5UkVipGvceiqkSoWyRT6os2E/cRSKWXNViiuEzZ0oP6/+4OPc/zRR3joU5/dcL5j09U2f/X0JF85PMFT58sA3HlLgbfvH+Gt+0cZyMTWeYYKheJSBIG/GArMXQz/1QkFFtYdpO9HJ0EJBCKyUoanQYXZYvtiORRpIjqBSojouqhvVRG3StuLib3l/VJ2rLmSIPCRgYzaAggkQRAgZRCOCQICGbzoGKfdpl5aoL4wT6MUuW6UFmjXqivmY1ix8IjiYt9SMRvVM8U+UoU+DNO8vF/SS0MpY4Wihw0tUP/453+G/PAI/+IXP3pNXu965dx8k688PcFXDk9wdKqGJuA12/v4/gOjvHnfCLnkVfljrFAoFOuG5zg0ygvhZrmFeRqlxXKnXl+YX7FxDiCRyfLmh36eW195aC2npASqQtHDhl3ib1YrLExcYN99b1zvqaw7W/qSPPSGHTz0hh0cn67xlcMTfPnwBL/4pWf4lb94lnt3DfD2A6O88bYhUrEN+5ZRKBQ3EYZlkRscJjc4fNExUkrajXooWBfmqZUWxWu2b+Aazlah2HhsWLUxcex5gHUL0H+9smsow4e+dzf/+nt28cx4ha8cnuArhyf5h+dniJsa9982xPcfGOXeXQPETRUfUqFQ3LwIIUhEkRcGtmxd7+koFBuKDStQLxw9gm6aDF0k5MxGRwjB/rE8+8fyfPgtt/HE2RJfPjzO3zwzxV8/PUnM0Ng3muXA5jwHN+c5MJbnlj4VLkehUCgUCsWVs2EF6sTR5xjevutqObvfVGia4FXbirxqW5Ffffs+vnFqnn86Psvh82U++61z/PE3zgCQT5rsH8tzcCzHgc15DmzO059Wm60UCoVCoVC8NDakQHXbbaZfOMldb3/nek/lhsPQNe7dNcC9u0L/K9cPOD5d4/D5CofPlzl8oczv/uPskgMCDm7Oc2BzjgNjeW7flFN+rAqFQqFQKC7JhlQKkyePE/g+Y9d5gP4bAVPX2DeaY99ojne/egsADdvjyESVw+fLPHWhzOHzZf76mUkANBH6uR4Yy0dW1hy7hzIY+sYK86VQXAuklLS8FrITjJ8wgH4niH5vFBcp5Yq+3mD7S66/nMD8LzKviyGEQBMaIgpv1SlrnaD8rN4vhEBjcYxyN1Iobmw2pEAdP3oEhGBk1571nspNSSpmdF0COszVbZ6+UOapyNL61eem+PwT5wGImxq3j+Z4xViOsUKSoWyMoWycoUycwWxMbcZSKC4D27c5WT7J8YXjHF04ytGFoxwvHafu1td7autCR6TG9BhDySGGUkMMJ4fDPDXMUHIxz1rq+GeF4npjYwrUY88xsGUr8ZQ65vOlUq/XmZiYoFqtEovFiMfjK3LLslb8se9Px/juPUN8954hILSgnFto8tT5cugecCH0Z227wYrXzCXMrmgdzMQXBWw2xmA2zlA2zkA6hmUoK6xiY7DQXuDYwrEwlY5xdOEoL1RewJfh6VIJI8Huwm7eeutbGU2Pdi2LHXotjMutjSv66ATt7xkjFtt7Wa1t+bWXGtuxzgYE3aD9AWFAfoBALi1LZJhH1t7l5UAGtLwW081pppvTfHPym8y15rr36JAwEksEqxKxCsX6s+EEauD7TBw/yr57v3u9p3Ld02w2mZiYWJKq1ZWnryxHCEEsFlsiXC8mZrfFYty2O8779m8iHt+Oi0HV05hreExX28zUbKar7SjZnJqZY6Zm4wUrlwiLKYvBzKJ4HcrGGczGycYNYoZOzNDCZGrEDB2rU+/0mRqWril3A8V1QyADzlXPcawUitGjC0c5tnCMmdZMd8xQcojdxd28YfMb2FPcw+7ibjZnNqMJ9T5eDS/wmGvNMdWYYqo5xXRjmqnGVChiG5cvYt9927vZ26fCFCoUV4sNJ1Bnz76A226p+KfLaLVaTE5OLhGj5XK529/X18ctt2xheDgglT6Hps2DjCFlHN838X0LzzNwPQPX1XFsDdsWtFpg2wG1Wo25uTna7Ta2bRMEKy2lvViWRSKRIJlMsiORYH8ySbIvSSKRIJHoI9BNWtKg4etUHcG8DTN1j+maw0ytzdGpKrM1m1V07Iuia2JRzPYK2Y6w1TVMQ4ssPB2rDxcv0/HnI5xPVO4dE8jQP3cgE2OskGBTPhnmhQRjhQQD6Ziy3lwHuIFLxa5QdaogWeLv2LU2Chb9IpdZIzt+lJ16r9+klJJztXNdEXqsdIzjpeO0vBYAhjDYlt/Gq0deze7i7jAVdlOIF9btedyIGJrBcGqY4dTFA/Rfjoh9661vvYazVig2HhtOoI4fPQLApg28Qcq2bV4bNIUAACAASURBVKamppiYmGB8fJyJiQkWFha6/YVCgU2bNnHo0CEGBy1isVPUat9iofRfadtztG0wjCy+30RKb9XXsGJhymRBCB1dT2PoKXQjjaGn0fQUggSIBDKwCGSMwI/h+SkcO0G7HaPVsmg2A5rNJuVymWazSbvdvujPFdd1bksmuSORIDmaJJFIIkwLI5bAjKewEim0WBLNSuJrJo4f4HgBthdgu36Ye522qO6GZcfvlMN6s+WjdY8vF51jzCPRAZoGAq1zBHq3fenYzoYQgFCgTNfaPHW+TLnpLvnZYobGpvyiYB0rJNmUT3RF7GAmjq4pAftSkFLScBuU7BKldomyXWahvUC5XWbBDvNSu0TJXuyrObVrMreMmWF3cTfv2vkudhV2sae4h+357Vi6dU1ef6NzOSJWoVBcXTacQL1w9AjZgSEyff3rPZWrjpQSx3GYmZlZYhmdnZ3tjslms4yOjnLw4EFGR0cZHMxiO8+wsPAICwuf4tz5kwCYZpFi8R6KhddRLL6WeHw09A8LHHy/huc18P06nlfH8+v43rJyT+55dXyvgueP43uNsM9vLJm7aYWpUEwRiw1iWYPEYoOY5gCaVkDKHIGfwfVSOHacVkvSarVoNps0m01arRazszPd+nIMwyCTyZDNZslms/R1ygPZbns6nUbX12eDVt32GC+1uFBqMl5ucaHU6tb/bqLKfGPp+eCmLhjJRYI1HwnYSMwWUxaWvujCEDNDlwZDu752OledKnWnjh/4eNLDCzx86XfrfuDjSx83cLvl3r7luS99vMCj6Ta7IrQrRttlSnYJN3BXnYupmRRiBQrxAvl4nr2pveTjeQrxAoVYoeuP2OsvCYs+lKvmnfLyes+u+dH0KLuLuxlNjV7ydxMENp5XW5bqYe4vbQ+Cdmiup3en/bKlhSU79pfly3bzr3r9sntdtOsydvqHVmhtWbljnRZLyoKwL/zXKXfaCcvCQNMsNC3Wk6wlub6kL7bK+MU2oVwnFIprwoYSqFJKxo8+x9b9r1zvqbxkfN/vCq+OEOvNL9bm+373Hul0mtHRUfbt28fo6Cijo6MkkzGq1cMslP6ZhYXf5dz5w0jpoWlx8vlDjI7+EMXCPaTTu1f8YRZCoOsxdD2GZV2Z4JfSx/PqOM4stj2N7cziRLltT2PbM1Srh7HtmfADdxm6niKdGaTYFwrZmDVILDaEZW3BNAfwvDTtdoJ63aZarVKr1ahWq1SrVS5cuEC1Wl3yrDo/XyqV6orYXkGbSqWwLAvTNFckwzCuWPilYwa7hzPsHs6s2t9yfMbLTS6UIvHaFbFNvn58lpma/aKvIURome2I1tVEbCdZxqJ7Q+jqoJEwdRKWQdLSo3KYJy2duBXmSdMgbmkkLYOEqa+w8jq+w8PnH+bPT/45/zzxzyv8/tYKkxRxPUtSz5I284zGtrI3G4rP/kSRgWSRoVQfI+k+RjL95OOZayLegyCgaS9Qa5yh0TiD65yiPP4U814d36/h+4t54NfCsldDSudF761pCTQ9g6bFo59l6Wan5Zuflv7/XjqGnutX9PXQlbJSLHFxYYnLS9jHMvcXGQ0Mxb4EgsU2gmhAlLqieWkbBCzK4AAR3UfDReAgWH3F56UghImmxbh933+iv/8NV3w/hUKxOhtKoJanJmhWytfV8n6z2WR+fp75+XlKpdJFhafjXPwDSdM0kslk12ezr6+vW08kEvT39zM6Okomk4le8zQLC49w6vQ/Uyo9iu/XAUE28wq2bPkpisV7yOfuQNOu3SlQQuiYZg7TzJFK7bjoOCklnlfDcWa6wjUsz2BHebVyGNuZJghWEWlaGt0skioMUhgeIh4bJpXYRCp+O0IUcewkjQZdAdvJ5+fnOXPmzCVdDHoxDGNV8RomA9MUWJaHaboYhothOOi6Szw+QDq9mWx2K5lMgVQqhWGs/G+asHR2DGbYMbi6gG27PpOVNhdKTSotd4krQ8ddwfFXcWnwFt0eHM+nbnvM1ztj/Z77BLRcf5VXDqWB6Kn3yhrL0EiaGlZiCtJP4sS+Q6A1MYMCY+ItmHIAxyNKAtsD24W2C0EgkGggdSRaVA7rQU8ZdCzdIGmZJE0LpEnTlszZ4c++Oj4wE6VwnumYQSqmk46ZpGM6qZhBKmaQtgwSlo4XhM/K9SWOH+B64XNy/QDXk92y4wXoVMmZ02StKQrWNMX4DAPxGQaSs6TM1srfnxej6cVpeQlandwt0vRGl7Z5cZpL6glabpyWHyMmPdK0iAtnye9EdH9HckW7EGCIjuuJQBcy/CIqQh9pXRNd95QgkPiBxAsCvAACGdY7912Ny5H8ko6IFcvKy+udd5cgkKv3g8DBoEaSAA1BgKF5mJqHqbmYepRr7tJ2zcPUF9ss3SNheMQNj5jhE9M9RH+Ce2/+hTiFYt3YUAJ1/OhzwLX3P2232ywsLHSFaG95ueCJx+NdcZlOpxkYGOgKz968t7xaWKdebGeO0sLDXLjwCAulb2DbUwAkElsYHno7xeLrKBTuxjTzV/U5rAVCCEwzi2lmLylka3aN//tb/55Hzv01OV2S1yU5XZIz2uT0cfL6eXK6JK3BctdNVwoa0qQlY9ipBE46iRzLktRzJEUO/AK6nyYmJEbgYkoXAwddOuiBjUYbQRshw1yjjRAthGijaWESYqlQCiQEHrh1qNVhcorQF9dO4nlZZJBH0/oxjEEsa4RkcoxUaphMJkMqlSKVSpFOp7Gs0Ecxbups60+xrT910WckpcS2bdrtdvfLUKfcbrvL6ktzRzhIsyf4+yWWdVe+MNAEmv3A9yz/zV3+fSBy5F3tZ4O2a1GyE7jCRBdgxkOhpWsCXQt9f/WOX7CIFoVFZIjrLN9LCGzw2uAG4PowE4AX+EgMfGEQ6Ca+MNBNn3S8RjpWIxGrE9NrmFoDQ9QJZIDjmziBhe1ZnKncyvOlO2j7OZwggxMkcYMEYJAQHmnRIk2LlGySpkWSFhnZYChqS8o6STlLUjZIyiYJ2SRBk4TeJCEaJIImGmtsjZaEOn45WpSuYyQC18zgmDkcKxfmUdk2sjhWjraRwzaLtPQsbTNLU8vS0NK0fB3H93u+uAXUvYC+/Lb1/rEUipuajSVQjz1HPJOluGlsze/tOA4LCwurCtFGY6l/ZS6Xo1gscvvtt9PX10exWKSvr498Pr+qteyl4nk1SuVvUSp9k1Lpm9TrRwEwjDzF4mspFl5Lsfg6EonNV/xa1yNPTj/JLz/yy0w2JvmXr/gZfmjXD2H7Nk23SctrLUklt45tz+A5cwTePNIroflVjKCGJRukqZJgFkNKlqwOdkTRRT6YnQBaUtAKoBUIWj60A0FLClwsXEw8LAItTiBiIBJoJCgIkwIBaVySooUVb5DSKpjaeTRtcQJ+AOWKxvRMCrudom2nsO0UnpdF1/owjCEsa5h0uogQ4qJi88VO9EkkEsTj8e6XomKx2A0T1hF2nbG95U4upeR8/TzPzT/HqcopfOkzmBxkX98+buu/jYSRWHINsEL0XiqXUlJqB4zXJeM1n4lGWJ6oBzSvfDW3MyO2iikOacd4vXacO8RxdmoTna7F94VLKLwjQqveahY/oLcuFq19MWz0y/DTbGFRl0nqJKjJBHMkqMk+amymJhPUSVCP8ra0erxKxbJ8aTvL2i/vmtWe2KX6Lk74faPzxJaXg5VtYtFWqi2xtS6Os/DIiQY5r06+XSdPg7yYIsdJ+kSDHA00cfFZ1WWCikhTI01Ny9CIkrftIdj0XZf4aRQKxZWwsQTq0SNs2r33in3LZmdnOXHixBIhujw+aDqdplgssmvXriUitFgsYprmFb3+cny/Sbn8ZFeQVmvPAgGaFiOfu4vtt/4bisV7yGT2IsTNeyqT67t84qlP8EfP/hFjmTE+/eZPc3Dw4BXfN3QrKNO2p7HtKez2FLZbBi3RFZg+MVxh4mJgSx098BF+G92zMX0by2sT923ifhvbs2n7bWzfXlJue23OunVqTo2aU1t2ApBJUjMp6JK8HtCnQ7+mM2BKCokamUyJId1m+VvbdWP4vkUypZHO6AgRJk3T0YSO0IywrBnomo6mG+iaga6baJqO0HRAC69DgNARQgsjFGgGQoRJE2ZU1xHCpOY0OFo6zpH5Y1TcOrF8gjfteAUHB+9gJD0WjhcthPC612li6f+LJcdsBgGzdcmpOZ8X5gNOzfucngs4PR9Q7/HkyCVge5/GwVt0tvVpbO8X5BMejtui7bZx3DaO18ZxHWzPxvEcXM/B8Vwcz8P1XXzXpr85x+bWDLe059nqzJGN/J4bwuKUOcSX9TsJNDB1HUs3MXUTQ4thaBaGsNCEiSZBSB+kh/B9kD4EPtL3kIFH4Pv4nofvewSBjwAcTGysVVKsJzcJ0NF0bZnvs4lhmmiGSdo0yRomum4iIfpCElnJW21se/UvJ523TyIRX1zNicdJdPJo5SYejyGDAM/z8TwvTH6Y+57XbfejtrDsL/b73tJroxSGnxPLBDJL2nodE3rbJKLHZrw4viUFC5G89dHCXAoCNPzoS0RS98noLinNIa05pEVotU7RIkWTlGySkg1yQZ1ROU/arTPefNeK56dQKNaODSNQG+USpckJXnH/m1/+PRoNHn74YZ544gmklCQSCfr6+ti6dSt9fX1LhGgsdvX8N4PAplJ5ilLpmyyUvkm1ehgpXYQwyWUPsm3rQxQKryGXO3hN/UjXk5Olk3z4kQ9zdOEo79r5Ln7h0C+QNJNrcu/QraCAaRbIpK/d8bh+4FPvEazd5C6tTzrVUNA6FQK3hO6XMYMaCVoUDJ+YaKIJ0AJBykyQMpKkDIuUmSBpJEjoMXQhkNKPNrL4BNKm2jIot+KUbZ1SK0G5HafcTlJuJ2i6FqbuENNtYrqNpTUxNRtTa2JpbeKGjaU7DOqDbNbzobwqHeOFyjNM6A4x3UHXVi5BSwklO89EfZiJxjAT9ZGoPETLW/x9ps06m9KT3DUwxab0FKPpKUZTk2Rjy471LEMjCuerAwkggYauJzGSaXQ9iRVYZCttsqU66YUSidIcWrRhzs0Uccb2Uxndiz/6ChjYzS1Ghu1Ghnh8DF1fm/9fQRDguu6K5DjOqu0vlpxmvVsGSCQS5JNJRorZF3UZisfjaNrSpQHp+7iTUzhnz+CcPoE7EVqQhaaDriF0I8w1HWHo0JvrGsRMhB7vae+5RtcRejiWwEe6LtJ1CRwnzF0X6UR5p891kY4T5p632BbVe9t9KfETcbx4Ai9m4VkxPMvENUxcQ8fTDVxdwxUxHBHHBZwgoCIls74fLu+7Lv6y2M0PDu9fk9+9QqFYnQ0jUMePRf6nLyNAv+d5PP7443z961/Htm0OHTrE61//+u6mo7UgaLdpfec7iFgMPZNBy+bQsxlEPI6UPrXaM5RKj1IqfZNy5YloA5BGNnM7Wzb/BIXCa8jn70TX10aU3SgEMuBPn/9TfvvJ3yZtpfnYGz7GG7bcHDtrdU0nF8uRi+Ve1vWBDKi7dSbrk5wqn+J05TTPzZ/hxMw0FypVXCeJ9NJIP0OcQWIMIPwsjhOn3tbwVvE3NHVBfzpGNm5it32ajk/ddmi5AVK+tJUJUxfETUHCFCRMsHSYrAbU7UX7WSEpuLXP4M7tBrf2G2zvN9gxYFJMjgC7olG9O81X7i4XwsQwUuh6El1LoVUmEecfg/OPwrnHYPb5cKBmwPB+OPQu2Pxq2HI3ZmaYtV3vWB1N07onrq0XUkr8uTnaR45gnzmDe/ZsN3fOnkP2bNQUpgmahgwC8LxLhpa6KpgmwjTRTBOssLyYLIyeOgJkvUEwP49stQnsdpTbyHYbXuTQkA6+puEZBp5p4Bom/XffDXuu3RdWhWKjsXEE6tHnMKwYQ7duv+xrpJScOHGCr371q8zPz7N9+3be9KY3MTg4uGbzsk+dovT5z1P5i78kiNwEpJB4myT2Lol9GzjbA2Q8/ACwSilypU2km1vIyJ1YqX60bBY926CdfQotk0XPZsK2TAaxzKdVSgkd60JkYejmrgu9bZ6HdDrlnn7PA6Gh57Lo2Sx6LoeWy636eleTqcYUH/nGR3h08lHuHbuXX33tr9Kf2Jjbal0/YKZmM1VpMVlpM1Vpd/PpapvZeoLZ2g6azmobOyRazMUz6nhigsCooOVrxPQ66UTAplyW7X0D7O0f5o54nG1BDb0+y3fmn+VbM99hoj2H0GPsH3oVd4y8ntHMTmxp0Ap0WoFO09dp+RpNX6Pu6zQ8jYYraHqSluPTdDxabkDL8bl7e5xdQ2l2DmXYOZimL/0igk1KkAEEfphLf1k9gNJZOP81OPdomBrRMaGxHGw+BLe/C7bcDZvuACsV3VaC7yNbre7/jSXJ87piSFgmmmWFdcuCNQgzdjXxKxWcM2dwzp4N8zNncM6E5aA3ZrBpYm3ZgnXLLaRe/11Yt9yCtXUr1tatGIMDK/2GfR/p+2EeCVcZBCvapedBECy2+eHvS3o+QtcQnWd5kYRprtnzlVKGv892m6DdXpnbNkGrFebt9qLAbdtkdu1ekzkoFIrVES9p9+014K677pJPPPHEmt/3v374X2HFE/zwR3/jssbPzMzw1a9+lVOnTtHX18eb3vQmdu7cuSZ/GAPHofb3f0/5c5+n+fjjYJok3/Z6vO/tp8IxqsERfBF+UFjtPKmFQRITWWJnYog5m6BSwa/V8KvV0HpxCbRUKrR0RB+qLzb+StHS6UiwhsJVz+bCPJdDz2VDIZtdrOu5HFo2h5ZKrni2UspFwbxMSP/TC1/jk9/+zwjP4327fpT7hl4HvreKmPAQlhWK9kwmsk5H4j2ReFm/T88PKLdcYoZG3NSvesB7xwuYroaCc7LSWiI+J6ttpiqtVY91TZg6I/k4g5kYg5k4A5kY/ekYA5kopWP0ZyyKSQtDD5d0A6/N7MSTzI0/RmPqaVg4Tbw6SbFZZth11vYbrWaAbi1NXExwBqsL0MvYUNTB85K0mwXajRytWga3ZiGd1d4z0Zexl/u3UYhFkWVZi6lbN9EiYRsK3MV+jNDHN1wu18Jlb01EbTpCE4ttvf1atGy+pD9sC+q1rgB1zpzB7znCGE3D3LRpifi0brkFa9tWzJGRcOldca24fr/VKBTrwIYQqE6rye/++IO8+p0/zD0//J5Lju31M43FYtx3330cOnRoTU4Ucs6fp/yFL1D+0p/hLyxg3DIK7ztAfeccpfqjSOkTj41SKLwmSncTj49c9H5SSmSrhV+t4lerBNUqfrVGUKviV6r4tbBNSokwIguEYSBMo1vG6JTNy2oXUbsMAvxKBb9SCV+3XAnnUakQVCtL6p0cd/VTewAwDPR0etGi4bqXHr8WRK/ZEaxaNoOeyaJl0uiZLE46ywUrz1k9xQt+jKlWm3z9Wba3n2IHF/DQcTHwMAg0g0AzCYSJ1AykZiJ1C/RFESZ0E023EIaFZphohoVmxtANC9200PQYC67OVEsw3tAYrwvO1gQXGmBj0vv5lYkZDOfiDOfijOTiDOcSjETlkVyC4VycbPwiljzPhtIZWDgdpvlTi+XK+Uj4RcSyULwV2bedVmaYqXiKUzrMGyavH72HTYkB8J1Vkhu+ju++SH9Ylr4NTjvyJfSQdvjlIrAdpO0QOA5B20G2HYJ2aM0KWna47CxFN4Z7mItQt1oWWiJFoKWxnX4CkbmkZa6bViwZm90l5W7SdaTrIR0H6TrhSoPrhH6RjgMdH0qn0+dG5Sj11qPrA9cBP0AGfhh3zPfDL2kdK6Rc2XbZb/WhoaUidGtYNsfG0Cx1fOp1ghKoCkUPG2KJf/LEcaQMLul/2vEzffjhh3Ech0OHDnHfffeRTF6ZT6f0POoPP0zpc5+n8cgjSF3D+MGDuPftZkb7Np7/l8ScYbZs+SmGh99BKrnjsq1xQghEMomWTGIOX/0zoxu2x7PjFQ6fKzNZaZMwEyTMNInCFhJDPacImZ2yQcLSSFkGcUMj7juYjRpBrRYJ2EpoDa5EwrZeCzdRdIV0j1gwDM40x/nzM1+hHNS5b9sb+e5bvxfDivcIB2OpiDAMMEyk64Sv2RHv1RpBfbFeqrY41pSccU3ONOOctTOcqxUoJVK8Uj/FPdqzvFl7hv3iNLqQOMJgtpFDCgiNWBJNk2hCookAXQQYwkcnTKa4fCGxKvHwTBxfxJDCQggLgYGsGwQ1neCshvQ1Ak8QuBC44DuSeTvAtwM03cVKuZgJBzPRxrCW7vYPAhPXy+AFWXz245HHF0V8ow+cDMybiEr4PDOmyStNA4SGfOIpZi4iuC4pzpYJteAyvoxoqRR6oYCeHw7zvjx6Po9RKETtBfR8PiwXwr6NILw6opUgWBSwQWSFjsSsFouhXeHfMYVCobjWbAiBeuHoEYTQGN210qFdSsnx48f5u7/7uzX1M3UnJyn/ty9S/uIX8WZmYE8//q/dSWXTOdrOo2giweDAmxgZfieFwt3XXfgn1w84NlXj8IUyh8+XefpChePTte4ycjpmYHs+rv/SLfBLhKw1QNIaJp7SSRZ0UtHRmanoFJ+kZRA34RuTX+Ofq88wvOcgP3vHT7J3cBc1KxyTihnEDO2Swl5KyXTV5uRMnZMzNU7O1jnp1znZaDBn2JAN4yzuN87ztvRx7tGeZWf7aczARgodv7AXv/Bu2vFduIwQr7cIWk1ks0nQbOI1wrybGo2eegNptxGaRGh0czSJb+i4ho5v6ASGRiZoEhcumhGgGRJhSDRDhiLYkAjDQzPcsG6BZgo0Uy6OtQKE5q0INxXIGJ6fxfH7aDZSuE4S107gtmIEtrbUH9lrI72zSPckuEt9lVdY7XS9Zxm7s3HFWrq0bVloyWTPMne41B36bS4dp+eyodDMd4RnHr2wMcTmy0EIAZHftzK/KRSKm4kNIVAnjh1hYOs2rMRSK8LMzAx/+7d/y+nTp+nv7+dHf/RH2blz58t+Hen7NL7xDUqf+zz1hx8miAUEP7yd1quT1DgOTFBI3s2t2z/IwMCbMIz0Ff5ka4OUkjPzTZ6+UOap86EgPTJRxfbCpd5iyuLAWI437Rvm4OY8+8dy3c0rrh8eedl2wh3dLTfM264fboDp9nU2wnjdMS03HNd0wrELDYfzC81oZ7hHw/Z6/Co3Ae/hDPALx6aB6SU/g66JUNj2iNaO2J1rOJyeqVOzF/1vM3GDHYNp3rnN5R7tOfY0n6R/9jH09gK0gYE98Iofh1vvQ9xyD0Y8C8DLlUnS9wlaLYJGKFiD5qK4XUytUOAl4oh4IsrjaInkkjYtHrZf1D9QynD53G2C0wArhZYsYl3B/Lu37tn80lnqVigUCoVirbmpfVCllPzg7/0z88efZXCgyM69e8gmTOKaZPLcaSbPniJtabzmrgPcfccB8qkwfI5lvLRz+7y5Ocpf+jPKX/gCzsQF3FdlcN/eT63vLIG0SSS2MjLyToaH3kEisWlNfrYrYaba5vCFCofPlzl8IbSOVlpRvERT5xWbchzYnGP/WJ6Dm/OMFV7eZqIrwQ98Pn3kM3z8279HxujnX73y33Jb4SBNx6Nh+zRsj0YkfOu2R9P2aThet70RtdVtj3zSZMdgmh2DafZkHHa3nyI78Q3ECw+HvpgAmRG49b4wbbsXshf3/VUoFIqrgDKCKxQ93NQC1fEC3vO7X+PsmXMYfcO0MKk0HV5sVTpuamTjJtmESTZuRLlJNmF02xOmhnf2LK0nnsB5/jmCtIe8I4OzqU0gGuh6nELuIIXCq0glt3bP/oYw14RA08IlOk0stolOX9QmevqW9GssG7P6PQBOz9U5fH5RkE5WwlNxdE2weyjDgc15DkaCdOdgOtzRLSU0F6A6DtUJqF6I8omwrV0BoYc7sTUj2jncWw/9FC/a3712eW5Q8Vr89dmvcqZ+gR3F23jrjneQiueiXd8maGaUG8vajKV9nXz6CJx+OExTzwAy3Pyz9fWLorR/JyvWxRUKheLaof4AKRQ93NQCNfB9/vt99/D8aD/7FmyOvGI/tUyGvukZtp44ifAkdStJPZbAjsdxLBMnZuFZJp6hRX6BgkATSA2kFoCQWCK0NjZknAZxGiRoyhh1EjSJU5dxmsRxrkmI78vnlr4kB8byHBjLcteAx+5EjXhzalF09grQ6gT49tIbCD20NOY2QTwfhfvxotQ5yrGnHiyve5cYc5V37GtmGHz91vvCNPrKUNAqFArF9YESqApFDzf1J7TnNDjwlgu8UkygIzkkj2AGLvqojz4i0aVER3K1vOhcBG3NoKWZtHUTW7OwdQtbj+HoFraewNXjOHocT0/gGvFuqJzuOeRSEh4wLaN/QTekTqet29ctR+3Rl4+iVmWIBQpOlezZOpnjdQy59PQUT2hUYinKsSTlWIrSyA7KVpKFWIKSlWDBilMxY/hEc5OgCe1Fky70le2sPuaF8im+ceHr3NV/gI+++pfYlBhcFK++G5b9zjb13vaeeuCt7MtvhVte0w3CrlAoFAqF4vrmphaobccna7YINAg0jUAX2JpGoOkEGvi6iPoEvga+tlgPeurhuN6xgkBL45m7sLWteIGFsBsIt4nuNNHcFrrbRPfamK6N4dtYroPpO8S8JmmnQtz3iPseicAndpWt2LYQzJgWc6bF8bjFfHqYOSvGnBljwYyzYMWpmRZEglEI0RWREAlRPITnIxDd9kAGK5Ivw9A2fnSuux9EufQvPVZKTM3koTt/nh/b92Pomtp8o1AoFArFRuWyBKoQ4s3A7wA68Ckp5W8u648BnwHuBOaBB6SUZ6K+DwM/CfjAz0kpv7pms38RYqbFn3of5I7X3MOB++6/onstukJ08jU8Pch3w93WbueYQdHjD9kpL8873cv6VmmLmQk2C8HmtZmtQqFQKBQKxVXlRX1QRRig8zjwPcAF4HHgR6SUz/WM+Vlgv5TyZ4QQDwL/Qkr5gBBiL/BZIA2pNwAAB+tJREFU4FXAKPAPwC4p5UUjl1+to04VCoVCobiOUT6oCkUPlxNP6VXASSnlaSmlA3wO+IFlY34A+HRU/iJwvwjNiz8AfE5KaUspXwBORvdTKBQKhUKhUChW5XIE6ibgfE/9QtS26hgppQdUgL7LvBYhxE8LIZ4QQjwxOzt7+bNXKBQKhUKhUNx0XI5AXW3ZYblfwMXGXM61SCn/QEp5l5TyroGBgcuYkkKhUCgUCoXiZuVyBOoFWLK/ZgyYuNgYIYQB5ICFy7xWoVAoFAqFQqHocjkC9XFgpxBimxDCAh4EvrxszJeB90XlHwS+JsPdV18GHhRCxIQQ24CdwLfWZuoKhUKhUCgUipuRFw0zJaX0hBAfAL5KGGbqj6SUR4QQvw48IaX8MvCHwJ8IIU4SWk4fjK49IoT4AvAc4AEPXWoHv0KhUCgUCoVCcVMfdapQKBQKxQ2CCjOlUPRwOUv8CoVCoVAoFArFNUMJVIVCoVAoFArFdYUSqAqFQqFQKBSK6wolUBUKhUKhUCgU1xVKoCoUCoVCoVAoriuUQFUoFAqFQqFQXFdcd2GmhBCzwNk1vm0/MLfG99zoqGd6dVDPde1Rz3TtUc907ZmTUr55vSehUFwvXHcC9WoghHhCSnnXes/jZkI906uDeq5rj3qma496pgqF4mqjlvgVCoVCoVAoFNcVSqAqFAqFQqFQKK4rNopA/YP1nsBNiHqmVwf1XNce9UzXHvVMFQrFVWVD+KAqFAqFQqFQKG4cNooFVaFQKBQKhUJxg3BTC1QhxJuFEMeEECeFEP92vedzoyKE2CyE+EchxPNCiCNCiA9G7UUhxN8LIU5EeWG953qjIYTQhRDfEUL8VVTfJoR4LHqmnxdCWOs9xxsJIUReCPFFIcTR6P36GvU+vXKEED8f/d9/VgjxWSFEXL1XFQrF1eSmFahCCB34BPAWYC/wI0KIves7qxsWD/iQlPI24G7goehZ/lvgf0gpdwL/I6orXhofBJ7vqf8W8NvRMy0BP7kus7px+R3gb6WUe4ADhM9WvU+vACHEJuDngLuklLcDOvAg6r2qUCiuIjetQAVeBZyUUp6WUjrA54AfWOc53ZBIKSellN+OyjXCD/1NhM/z09GwTwPvWJ8Z3pgIIcaAtwKfiuoC+G7gi9EQ9UxfAkKILPBdwB8CSCkdKWUZ9T5dCwwgIYQwgCQwiXqvKhSKq8jNLFA3Aed76heiNsUVIITYCrwSeAwYklJOQihigcH1m9kNyX8CfgEIonofUJZSelFdvWdfGrcCs8AfR24TnxJCpFDv0ytCSjkO/EfgHKEwrQBPot6rCoXiKnIzC1SxSpsKWXAFCCHSwJeAfyWlrK73fG5khPif7d1biFVVHMfx7w8vZRJFlwdDwwIrKEgDw1shJT2EVEQhZCRFdIEKggjzrYdACIKegqDoxYIwK5+yhzTLKMXb2PUlo4bwAkaUQZj9e9h76jiM6Dhjc87h+3mZ2WvvvWadw+Kc36y1zllZDhyqqp2dxSNcap89fZOBG4BXqmoecBSn88esXbN7J3AFcBkwnWbp1HD2VUnjpp8D6iAwq+N4JvDzBLWl5yWZQhNO11XVhrb4YJIZ7fkZwKGJal8PWgzckeQHmuUnt9CMqF7YTqOCfXa0BoHBqvqiPV5PE1jtp2OzDNhfVYer6hiwAViEfVXSWdTPAXUHMKf9pOlUmkX9Gye4TT2pXRv5GvBNVb3UcWojsKr9fRXw/v/dtl5VVc9V1cyqmk3TNz+qqpXAZuCe9jKf01GoqgPAT0mubotuBb7GfjpWPwILkpzXvhYMPa/2VUlnTV9/UX+S22lGpSYBr1fVCxPcpJ6UZAnwCbCP/9ZLrqFZh/o2cDnNm9i9VXVkQhrZw5IsBZ6pquVJrqQZUb0I2A3cX1V/TmT7ekmSuTQfOpsKfA88SPOPuP10DJI8D6yg+UaP3cDDNGtO7auSzoq+DqiSJEnqPf08xS9JkqQeZECVJElSVzGgSpIkqasYUCVJktRVDKiSJEnqKgZUqYcl+b39OTvJfeNc95phx5+NZ/2SJJ2MAVXqD7OBUQXUJJNOcckJAbWqFo2yTZIknREDqtQf1gI3JdmT5Okkk5K8mGRHkoEkj0KzKUCSzUnepNl4gSTvJdmZ5Kskj7Rla4FpbX3r2rKh0dq0dX+ZZF+SFR11b0myPsm3Sda1Ow9JkjQqk099iaQesJp2NyqANmj+WlXzk5wDbEvyYXvtjcB1VbW/PX6oqo4kmQbsSPJOVa1O8kRVzR3hb90NzAWuBy5p79nanpsHXEuzL/s2YDHw6fg/XElSP3MEVepPtwEPJNlDsyXtxcCc9tz2jnAK8FSSvcDnwKyO605mCfBWVR2vqoPAx8D8jroHq+pvYA/N0gNJkkbFEVSpPwV4sqo2nVCYLAWODjteBiysqj+SbAHOPY26T6ZzL/bj+BojSToDjqBK/eE34PyO403A40mmACS5Ksn0Ee67APilDafXAAs6zh0bun+YrcCKdp3rpcDNwPZxeRSSJOHohtQvBoC/2qn6N4CXaabXd7UfVDoM3DXCfR8AjyUZAL6jmeYf8iowkGRXVa3sKH8XWAjsBQp4tqoOtAFXkqQxS1VNdBskSZKkfznFL0mSpK5iQJUkSVJXMaBKkiSpqxhQJUmS1FUMqJIkSeoqBlRJkiR1FQOqJEmSuooBVZIkSV3lHxNygfhB77khAAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# cell 25\n", "plot_feature_importance(trial, importance_type=\"cover\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### SHAP\n", "\n", "[SHAP](https://github.com/slundberg/shap) (SHapley Additive exPlanations) is\n", "another approach to explain the output of machine learning models.\n", "SHAP values represent a feature's contribution to a change in the model output.\n", "You instructed Estimator to log the average SHAP values in this example so the SHAP values (as calculated by [xgboost.predict(pred_contribs=True)](https://xgboost.readthedocs.io/en/latest/python/python_api.html#xgboost.Booster.predict)) will be available the `average_shap` collection." ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# cell 26\n", "plot_collection(trial,\"average_shap\")" ] } ], "metadata": { "celltoolbar": "Tags", "instance_type": "ml.t3.medium", "kernelspec": { "display_name": "Python 3 (Data Science)", "language": "python", "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-east-1:081325390199:image/datascience-1.0" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.10" }, "notice": "Copyright 2017 Amazon.com, Inc. or its affiliates. All Rights Reserved. Licensed under the Apache License, Version 2.0 (the \"License\"). You may not use this file except in compliance with the License. A copy of the License is located at http://aws.amazon.com/apache2.0/ or in the \"license\" file accompanying this file. This file is distributed on an \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License." }, "nbformat": 4, "nbformat_minor": 4 }