{ "cells": [ { "cell_type": "markdown", "id": "36ceaeee-37db-4050-b53d-9026b43f6562", "metadata": {}, "source": [ "# Exercise session week 2 | Preprocessing, Imputation, Statistical feature extraction\n", "\n", "\n", "The goals of this exercise are to learn following techniques:\n", "\n", "1. How to use Pandas to load and manipulate tabular and time series data\n", "2. Data preprocessing and cleaning\n", "3. Missing value imputation\n", "4. Feature extraction: statistical features, one-hot encoding\n", "5. Outlier detection\n", "6. Filtering, smoothing\n", "7. Feature normalization\n", "\n", "---" ] }, { "cell_type": "markdown", "id": "1efd8274", "metadata": {}, "source": [ "> **⚠️ Warning**\n", "> \n", "> This notebook contains the solution to \"Exercise 1\" of [CIVIL-332](https://edu.epfl.ch/coursebook/en/data-science-for-infrastructure-condition-monitoring-CIVIL-332) Spring 2024. On a proper Python installation, it should run in its entirety without any issues (except the very last cell). If the notebook does **not** run, you're most likely having package dependency issues. \n", "> \n", "> Make sure you have a recent version of `pandas`, `matplotlib`, `numpy`, and `scikit-learn`. If you're unsure, you can update the version on your packages by using the following commands:\n", ">\n", "> ```bash\n", "> pip install pandas --upgrade\n", "> pip install matplotlib --upgrade\n", "> pip install numpy --upgrade\n", "> pip install scikit-learn --upgrade\n", "> ```\n", ">\n", "> **⚠️ Note**\n", ">\n", "> If you're not using a [Python virtual environment](https://docs.python.org/3/library/venv.html) (which you should), updating your packages might fail due to other packages (*e.g.* `pytorch` or `tensorflow`) requiring different versions of those packages. If that's the case, I recommend you uninstall Python, start from a clean installation, and create Python virtual environments for each of your courses/applications **before** installing any packages.\n", ">\n", "> For reference, this notebook was ran on Python 3.11.7 with Pandas v2.2.0, Matplotlib v3.8.3, Numpy v1.26.4, and Scikit-Learn v1.4.1." ] }, { "cell_type": "markdown", "id": "7887b546-301d-46a1-8f38-015b9ad8c0e8", "metadata": { "tags": [] }, "source": [ "## 1. Pandas and DataFrames" ] }, { "cell_type": "markdown", "id": "93bfcc97-5c6d-4040-8de3-2cb2c5252943", "metadata": {}, "source": [ "**Previously**: you learned how to use numpy." ] }, { "cell_type": "markdown", "id": "2aab9176-7ddf-4068-b545-2d6ba9d74f03", "metadata": { "jp-MarkdownHeadingCollapsed": true, "tags": [] }, "source": [ "\n", "\n", "http://pandas.pydata.org/\n", "\n", "Pandas is a widely used library to handle **structured, tabular data** using an abstraction called **DataFrame** (type : `pd.DataFrame`) : data is structured into *named columns* (as in a relational table). Allows to load and process structured data files such as CSV, Excel, Parquet, HDF5... One-dimensional data, i.e. a *column* or a *row* has type `pd.Series`.\n", "\n", "Pandas is also based on numpy! `df.values` converts a DataFrame or a Series into a 2D or 1D numpy array.\n", "\n", "**READ THE DOCUMENTATION**\n", "\n", "* http://pandas.pydata.org/pandas-docs/stable/reference/frame.html (pd.DataFrame)\n", "* http://pandas.pydata.org/pandas-docs/stable/reference/series.html (pd.Series)\n", "\n", "" ] }, { "cell_type": "code", "execution_count": 1, "id": "2619c017-c2eb-48af-ae68-fe8b500a9f21", "metadata": {}, "outputs": [], "source": [ "# You should install Pandas (if not done already): `pip install pandas`\n", "import pandas as pd\n" ] }, { "cell_type": "code", "execution_count": 2, "id": "60a878a1-7805-4761-bd96-5f8dae37e1f1", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " A B\n", "0 E420912 1\n", "1 E420913 2\n", "2 E420914 3\n" ] } ], "source": [ "# The DataFrame class is the core data representation used by Pandas\n", "# One would typically load a dataframe with a CSV, but you can also create one manually\n", "df_example = pd.DataFrame({\"A\": [\"E420912\", \"E420913\", \"E420914\"], \"B\": [1, 2, 3]})\n", "\n", "# Take a look at the representation of a DataFrame\n", "print(df_example)\n" ] }, { "cell_type": "markdown", "id": "a7c273dc-3996-4283-a7dc-b81b4341f338", "metadata": { "tags": [] }, "source": [ "## 2. Data loading and cleaning" ] }, { "cell_type": "markdown", "id": "1f19391b-834b-4813-881b-3b00a783ed31", "metadata": {}, "source": [ "Data in the real world is “dirty”:\n", "* Incomplete: lacking attribute values, lacking certain attributes of interest, or containing only aggregate data\n", "* Noisy: containing errors or outliers\n", "* Inconsistent: containing discrepancies in codes or names" ] }, { "cell_type": "code", "execution_count": 3, "id": "611ab073-8254-4fc2-af96-a43ed89dd59a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " t EGT_SEL FMV_SEL HPTC_SEL LPTC_SEL N1_SEL N2_ACTSEL \\\n", "0 datenum deg_C _ % % % %_RPM \n", "1 15/09/2011 14:25:58.125 NaN NaN NaN NaN NaN 0 \n", "2 15/09/2011 14:25:58.375 NaN NaN NaN NaN NaN 0 \n", "3 15/09/2011 14:25:58.625 NaN NaN NaN NaN NaN 0 \n", "4 15/09/2011 14:25:58.875 NaN NaN NaN NaN NaN 0 \n", "\n", " OIL_P OIL_TEMP PS3_SEL ... T3_SEL VBV_SEL VIB_CN1 VIB_CN2 VIB_TN1 VIB_TN2 \\\n", "0 psi _ psi ... _ DEG _ _ _ _ \n", "1 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN \n", "2 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN \n", "3 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN \n", "4 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN \n", "\n", " VSV_SEL WFM_SEL XM FLIGHT_PHASE \n", "0 DEG lb/h mach _ \n", "1 NaN NaN NaN NaN \n", "2 NaN NaN NaN NaN \n", "3 NaN NaN NaN NaN \n", "4 NaN 7679.98 0.15 NaN \n", "\n", "[5 rows x 26 columns]\n" ] } ], "source": [ "# Let's load a CSV file in a DataFrame to process it\n", "df = pd.read_csv(\"flight_data.csv\")\n", "\n", "# Let's take a look at the first few rows to understand the contents\n", "print(df.head())\n" ] }, { "cell_type": "code", "execution_count": 4, "id": "baa591cd-123f-4a9a-9059-72e037d05658", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Number of columns : 26\n", "Number of rows : 22945\n", "Number of columns (alternative): 26\n", "Number of rows (alternative): 22945\n" ] } ], "source": [ "\"\"\"\n", "EXERCISE - Dimensions of a DataFrame\n", "1. Display the number of rows and columns of the DataFrame\n", "\n", "Hints:\n", "- Take a look at the documentation https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.html\n", "- Consider the built-in Python functions learned last week\n", "\"\"\"\n", "print('Number of columns :', df.shape[1])\n", "print('Number of rows :', df.shape[0])\n", "\n", "# You can also use the built-in len function\n", "print('Number of columns (alternative):', len(df.columns))\n", "print('Number of rows (alternative):', len(df))\n" ] }, { "cell_type": "markdown", "id": "44fe6437-a72b-4432-95dd-7e084d5c893a", "metadata": {}, "source": [ "It is important to understand the structure of Pandas' `DataFrame`. A `DataFrame` (short DF) is made of :\n", "\n", "* Named columns (_columns_):\n", "\n", "Column names can be accessed via `df.columns`. They can be renamed. A column can be retrieved using the syntax `df['column_name']` (similar to dictionary indexing) or `df.column_name` (/!\\ the latter only works if column name has no space in it). Multiple columns can be selected using a list of column names as index : `df[['col1', 'col2']]'` (mind the double brackets).\n", "\n", "* Rows (_rows_):\n", "\n", "Rows are associated to an _index_. The default index is 0, 1, 2, etc. but can have different $keys$ (example : a time-based index). The index **is not** a standard column of the DF. Rows can be accessed in two ways. Either **index-based** : `df.loc[idx]`, or **position-based** (i-th row) : `df.iloc[i]`. A set of rows can be retrieved using a list or a _slice_ of indices, e.g. `df.iloc[2:10]` to access rows between 2 and **9**.\n", "\n", "Selection of rows and columns can be combined in loc/iloc. For instance, to select rows 10 to 14 of columns EGT_SEL and FMV_SEL:\n", "```\n", "df.loc[10:15, ['EGT_SEL', 'FMV_SEL']]\n", "```\n", "Or, using position-based indexing for rows and columns:\n", "```\n", "df.iloc[10:15, [1, 3]]\n", "```\n", "\n", "`DataFrame` columns are **strongly typed**, as in a relational database. Column types are displayed with `df.dtypes`. The main types are numerical (int32, int64, float etc.) and \"object\" (e.g. string)." ] }, { "cell_type": "code", "execution_count": 5, "id": "d50c3c03-2cb6-4a81-858b-e77094717e5b", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['t', 'EGT_SEL', 'FMV_SEL', 'HPTC_SEL', 'LPTC_SEL', 'N1_SEL',\n", " 'N2_ACTSEL', 'OIL_P', 'OIL_TEMP', 'PS3_SEL', 'PT2_SEL', 'P0_SEL', 'TAT',\n", " 'TBV_SEL', 'TRA_SEL', 'T25_SEL', 'T3_SEL', 'VBV_SEL', 'VIB_CN1',\n", " 'VIB_CN2', 'VIB_TN1', 'VIB_TN2', 'VSV_SEL', 'WFM_SEL', 'XM',\n", " 'FLIGHT_PHASE'],\n", " dtype='object')" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Let's take a look at our columns\n", "df.columns\n" ] }, { "cell_type": "code", "execution_count": 6, "id": "38230498-5ae5-4fd3-ba39-ee31fe60ece0", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "RangeIndex(start=0, stop=22945, step=1)" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Let's see how many rows we have by checking the DataFrame index\n", "df.index\n" ] }, { "cell_type": "code", "execution_count": 7, "id": "d6e586e9-b925-4026-b3ef-5215ef132c95", "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", "
EGT_SELFMV_SEL
100336.020
101240.0240
102168.0110
103120.0090
10472.00620
10524.00830
\n", "
" ], "text/plain": [ " EGT_SEL FMV_SEL\n", "100 336.02 0\n", "101 240.024 0\n", "102 168.011 0\n", "103 120.009 0\n", "104 72.0062 0\n", "105 24.0083 0" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Here is how to extract the values of columns \"EGT_SEL\" and \"FMV_SEL\" for rows 100 to 105\n", "df.loc[100:105, ['EGT_SEL', 'FMV_SEL']]\n" ] }, { "cell_type": "code", "execution_count": 8, "id": "5d4547c8-2706-483d-8393-1663d7137627", "metadata": {}, "outputs": [], "source": [ "\"\"\"\n", "EXERCISE - Extraction and removal of the first row.\n", "Notice that the first row contains the physical units of variables.\n", "It must be removed before further processing, but we should keep this information.\n", "\n", "1. Retrieve the units and store them in a variable.\n", "2. Remove this row from the DataFrame using the method \"drop\"\n", "\"\"\"\n", "# 1. \n", "units = df.iloc[0]\n", "\n", "# 2.\n", "df = df.drop(index=0)\n" ] }, { "cell_type": "code", "execution_count": 9, "id": "508f8157-9da0-4e1f-b270-bdac86e023c2", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "t datenum\n", "EGT_SEL deg_C\n", "FMV_SEL _\n", "HPTC_SEL %\n", "LPTC_SEL %\n", "N1_SEL %\n", "N2_ACTSEL %_RPM\n", "OIL_P psi\n", "OIL_TEMP _\n", "PS3_SEL psi\n", "PT2_SEL mb\n", "P0_SEL psi\n", "TAT deg_C\n", "TBV_SEL %\n", "TRA_SEL DEG\n", "T25_SEL _\n", "T3_SEL _\n", "VBV_SEL DEG\n", "VIB_CN1 _\n", "VIB_CN2 _\n", "VIB_TN1 _\n", "VIB_TN2 _\n", "VSV_SEL DEG\n", "WFM_SEL lb/h\n", "XM mach\n", "FLIGHT_PHASE _\n", "Name: 0, dtype: object\n", " t EGT_SEL FMV_SEL HPTC_SEL LPTC_SEL N1_SEL N2_ACTSEL \\\n", "1 15/09/2011 14:25:58.125 NaN NaN NaN NaN NaN 0 \n", "2 15/09/2011 14:25:58.375 NaN NaN NaN NaN NaN 0 \n", "3 15/09/2011 14:25:58.625 NaN NaN NaN NaN NaN 0 \n", "4 15/09/2011 14:25:58.875 NaN NaN NaN NaN NaN 0 \n", "5 15/09/2011 14:25:59.125 NaN NaN NaN NaN 0 0 \n", "\n", " OIL_P OIL_TEMP PS3_SEL ... T3_SEL VBV_SEL VIB_CN1 VIB_CN2 VIB_TN1 \\\n", "1 NaN NaN NaN ... NaN NaN NaN NaN NaN \n", "2 NaN NaN NaN ... NaN NaN NaN NaN NaN \n", "3 NaN NaN NaN ... NaN NaN NaN NaN NaN \n", "4 NaN NaN NaN ... NaN NaN NaN NaN NaN \n", "5 647.998 NaN 575.982 ... NaN 0 0 0 0 \n", "\n", " VIB_TN2 VSV_SEL WFM_SEL XM FLIGHT_PHASE \n", "1 NaN NaN NaN NaN NaN \n", "2 NaN NaN NaN NaN NaN \n", "3 NaN NaN NaN NaN NaN \n", "4 NaN NaN 7679.98 0.15 NaN \n", "5 0 0 4607.86 0.15 NaN \n", "\n", "[5 rows x 26 columns]\n" ] } ], "source": [ "print(units)\n", "\n", "# The first row of the DataFrame should now be correct (no more the units of the columns)\n", "print(df.head())\n" ] }, { "cell_type": "markdown", "id": "3295e2cd-714c-4ac6-851b-4236d030a30e", "metadata": {}, "source": [ "Notice how all columns have been recognized as `object`, meaning strings (text), although it should be numerical values. This was caused by the first row. Columns must be converted to numerical types, with two exceptions:\n", "\n", "* Column 't' should rather be converted to `datetime`.\n", "* Column 'FLIGHT_PHASE' contains text." ] }, { "cell_type": "code", "execution_count": 10, "id": "676f560f-7057-4eb5-91dd-5785ae23ecd8", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "t object\n", "EGT_SEL object\n", "FMV_SEL object\n", "HPTC_SEL object\n", "LPTC_SEL object\n", "N1_SEL object\n", "N2_ACTSEL object\n", "OIL_P object\n", "OIL_TEMP object\n", "PS3_SEL object\n", "PT2_SEL object\n", "P0_SEL object\n", "TAT object\n", "TBV_SEL object\n", "TRA_SEL object\n", "T25_SEL object\n", "T3_SEL object\n", "VBV_SEL object\n", "VIB_CN1 object\n", "VIB_CN2 object\n", "VIB_TN1 object\n", "VIB_TN2 object\n", "VSV_SEL object\n", "WFM_SEL object\n", "XM object\n", "FLIGHT_PHASE object\n", "dtype: object\n" ] } ], "source": [ "# Let's take a look at the columns' types\n", "print(df.dtypes)\n" ] }, { "cell_type": "code", "execution_count": 11, "id": "8c5adb7c-6f2b-451f-a46f-136a84e02c80", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\awei\\AppData\\Local\\Temp\\ipykernel_13512\\4286867465.py:2: UserWarning: Parsing dates in %d/%m/%Y %H:%M:%S.%f format when dayfirst=False (the default) was specified. Pass `dayfirst=True` or specify a format to silence this warning.\n", " df['t'] = pd.to_datetime(df['t'])\n" ] } ], "source": [ "# Let's convert the column \"t\" to the DateTime type (instead of string)\n", "df['t'] = pd.to_datetime(df['t'])\n", "\n", "# Let's convert all the other columns to digits (instead of strings)\n", "df[df.columns[1:-1]] = df[df.columns[1:-1]].apply(pd.to_numeric)\n" ] }, { "cell_type": "code", "execution_count": 12, "id": "42235233-3daf-4bcd-8b22-92cbc6c297c7", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "t datetime64[ns]\n", "EGT_SEL float64\n", "FMV_SEL float64\n", "HPTC_SEL float64\n", "LPTC_SEL float64\n", "N1_SEL float64\n", "N2_ACTSEL float64\n", "OIL_P float64\n", "OIL_TEMP float64\n", "PS3_SEL float64\n", "PT2_SEL float64\n", "P0_SEL float64\n", "TAT float64\n", "TBV_SEL float64\n", "TRA_SEL float64\n", "T25_SEL float64\n", "T3_SEL float64\n", "VBV_SEL float64\n", "VIB_CN1 float64\n", "VIB_CN2 float64\n", "VIB_TN1 float64\n", "VIB_TN2 float64\n", "VSV_SEL float64\n", "WFM_SEL float64\n", "XM float64\n", "FLIGHT_PHASE object\n", "dtype: object\n" ] } ], "source": [ "# Now, the column types should be correct\n", "print(df.dtypes)\n" ] }, { "cell_type": "code", "execution_count": 13, "id": "14bd0d07-c6f7-4596-b838-520d2b7cb10f", "metadata": {}, "outputs": [], "source": [ "# You should install matplotlib (if not done already): `pip install matplotlib`\n", "import matplotlib.pyplot as plt\n" ] }, { "cell_type": "code", "execution_count": 14, "id": "deb7638a", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Let's create a graph to visualize the evolution of the EGT_SEL temperature during the flight \n", "plt.plot(df[\"t\"], df[\"EGT_SEL\"])\n", "plt.xlabel(\"t\")\n", "plt.ylabel(\"EGT_SEL (°C\");\n" ] }, { "cell_type": "markdown", "id": "b63c18a6-64e9-4df6-8f14-d37875b8c892", "metadata": { "tags": [] }, "source": [ "## 3. Missing value imputation" ] }, { "cell_type": "markdown", "id": "aa220874-37fa-48e1-933e-ca6920f1d8e5", "metadata": { "tags": [] }, "source": [ "**NaN = Not a Number**\n", "\n", "NaN values need to be either removed or imputated (i.e. filled with certain values) before further processing. The choice of the imputation method is crucial.\n", "\n", "From today's lecture:\n", "\n", "* Complete case analysis: Delete any record that has missing values from the\n", "data set.\n", "* Nearest neighbors: to impute variable x average the value x of the k closest\n", "data points with no missing values.\n", "* Average method: Average the value of x for the non-missing values.\n", "* Hot deck: pick a “similar” record at random and use its value of x.\n", "* Predictive: Fit a model to the data with variable x as the target and use it to\n", "predict the value (e.g. kernel regression)\n", "* Single imputation: Draw a value at random from the conditional distribution of\n", "x given the other variables\n", "27.02.23\n", "* Multiple imputation: Repeatedly draw values at random from the conditional\n", "distribution of x given the other variables (e.g. as above), creating new data\n", "sets. Make the predictions with these now complete datasets and average the\n", "predictions.\n", "\n", "In this exercise, you will learn to :\n", "\n", "* find missing values in a DataFrame (method `isna`)\n", "* remove missing values (method `dropna`)\n", "* replace missing values with a constant value, forward and backward fill (method `fillna`)" ] }, { "cell_type": "code", "execution_count": 15, "id": "744a7d5b-7b74-45d3-b3f1-102fd854d70c", "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", "
tEGT_SELFMV_SELHPTC_SELLPTC_SELN1_SELN2_ACTSELOIL_POIL_TEMPPS3_SEL...T3_SELVBV_SELVIB_CN1VIB_CN2VIB_TN1VIB_TN2VSV_SELWFM_SELXMFLIGHT_PHASE
1FalseTrueTrueTrueTrueTrueFalseTrueTrueTrue...TrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
2FalseTrueTrueTrueTrueTrueFalseTrueTrueTrue...TrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
3FalseTrueTrueTrueTrueTrueFalseTrueTrueTrue...TrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
4FalseTrueTrueTrueTrueTrueFalseTrueTrueTrue...TrueTrueTrueTrueTrueTrueTrueFalseFalseTrue
5FalseTrueTrueTrueTrueFalseFalseFalseTrueFalse...TrueFalseFalseFalseFalseFalseFalseFalseFalseTrue
..................................................................
22940FalseTrueTrueTrueTrueTrueTrueTrueTrueTrue...TrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
22941FalseTrueTrueTrueTrueTrueTrueTrueTrueTrue...TrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
22942FalseTrueTrueTrueTrueTrueTrueTrueTrueTrue...TrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
22943FalseTrueTrueTrueTrueTrueTrueTrueTrueTrue...TrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
22944FalseTrueTrueTrueTrueTrueTrueTrueTrueTrue...TrueTrueTrueTrueTrueTrueTrueTrueTrueTrue
\n", "

22944 rows × 26 columns

\n", "
" ], "text/plain": [ " t EGT_SEL FMV_SEL HPTC_SEL LPTC_SEL N1_SEL N2_ACTSEL OIL_P \\\n", "1 False True True True True True False True \n", "2 False True True True True True False True \n", "3 False True True True True True False True \n", "4 False True True True True True False True \n", "5 False True True True True False False False \n", "... ... ... ... ... ... ... ... ... \n", "22940 False True True True True True True True \n", "22941 False True True True True True True True \n", "22942 False True True True True True True True \n", "22943 False True True True True True True True \n", "22944 False True True True True True True True \n", "\n", " OIL_TEMP PS3_SEL ... T3_SEL VBV_SEL VIB_CN1 VIB_CN2 VIB_TN1 \\\n", "1 True True ... True True True True True \n", "2 True True ... True True True True True \n", "3 True True ... True True True True True \n", "4 True True ... True True True True True \n", "5 True False ... True False False False False \n", "... ... ... ... ... ... ... ... ... \n", "22940 True True ... True True True True True \n", "22941 True True ... True True True True True \n", "22942 True True ... True True True True True \n", "22943 True True ... True True True True True \n", "22944 True True ... True True True True True \n", "\n", " VIB_TN2 VSV_SEL WFM_SEL XM FLIGHT_PHASE \n", "1 True True True True True \n", "2 True True True True True \n", "3 True True True True True \n", "4 True True False False True \n", "5 False False False False True \n", "... ... ... ... ... ... \n", "22940 True True True True True \n", "22941 True True True True True \n", "22942 True True True True True \n", "22943 True True True True True \n", "22944 True True True True True \n", "\n", "[22944 rows x 26 columns]" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# First, let's check if we have missing values\n", "df.isna()\n" ] }, { "cell_type": "code", "execution_count": 16, "id": "0b19df93", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[1;31mSignature:\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0misna\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m->\u001b[0m \u001b[1;34m'DataFrame'\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;31mDocstring:\u001b[0m\n", "Detect missing values.\n", "\n", "Return a boolean same-sized object indicating if the values are NA.\n", "NA values, such as None or :attr:`numpy.NaN`, gets mapped to True\n", "values.\n", "Everything else gets mapped to False values. Characters such as empty\n", "strings ``''`` or :attr:`numpy.inf` are not considered NA values\n", "(unless you set ``pandas.options.mode.use_inf_as_na = True``).\n", "\n", "Returns\n", "-------\n", "DataFrame\n", " Mask of bool values for each element in DataFrame that\n", " indicates whether an element is an NA value.\n", "\n", "See Also\n", "--------\n", "DataFrame.isnull : Alias of isna.\n", "DataFrame.notna : Boolean inverse of isna.\n", "DataFrame.dropna : Omit axes labels with missing values.\n", "isna : Top-level isna.\n", "\n", "Examples\n", "--------\n", "Show which entries in a DataFrame are NA.\n", "\n", ">>> df = pd.DataFrame(dict(age=[5, 6, np.nan],\n", "... born=[pd.NaT, pd.Timestamp('1939-05-27'),\n", "... pd.Timestamp('1940-04-25')],\n", "... name=['Alfred', 'Batman', ''],\n", "... toy=[None, 'Batmobile', 'Joker']))\n", ">>> df\n", " age born name toy\n", "0 5.0 NaT Alfred None\n", "1 6.0 1939-05-27 Batman Batmobile\n", "2 NaN 1940-04-25 Joker\n", "\n", ">>> df.isna()\n", " age born name toy\n", "0 False True False True\n", "1 False False False False\n", "2 True False False False\n", "\n", "Show which entries in a Series are NA.\n", "\n", ">>> ser = pd.Series([5, 6, np.nan])\n", ">>> ser\n", "0 5.0\n", "1 6.0\n", "2 NaN\n", "dtype: float64\n", "\n", ">>> ser.isna()\n", "0 False\n", "1 False\n", "2 True\n", "dtype: bool\n", "\u001b[1;31mFile:\u001b[0m c:\\users\\awei\\developer\\work\\venvs\\3.11.7\\civil-332\\lib\\site-packages\\pandas\\core\\frame.py\n", "\u001b[1;31mType:\u001b[0m method" ] } ], "source": [ "# You can check the built-in documentation of the isna() method\n", "df.isna?\n" ] }, { "cell_type": "code", "execution_count": 17, "id": "ac992784-d53c-4162-9e30-cf533a8bad19", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Question 2.1\n", "t False\n", "EGT_SEL True\n", "FMV_SEL True\n", "HPTC_SEL True\n", "LPTC_SEL True\n", "N1_SEL True\n", "N2_ACTSEL True\n", "OIL_P True\n", "OIL_TEMP True\n", "PS3_SEL True\n", "PT2_SEL True\n", "P0_SEL True\n", "TAT True\n", "TBV_SEL True\n", "TRA_SEL True\n", "T25_SEL True\n", "T3_SEL True\n", "VBV_SEL True\n", "VIB_CN1 True\n", "VIB_CN2 True\n", "VIB_TN1 True\n", "VIB_TN2 True\n", "VSV_SEL True\n", "WFM_SEL True\n", "XM True\n", "FLIGHT_PHASE True\n", "dtype: bool\n", "Question 2.2\n", "t 0.000000\n", "EGT_SEL 0.348675\n", "FMV_SEL 0.444561\n", "HPTC_SEL 0.422768\n", "LPTC_SEL 0.457636\n", "N1_SEL 0.418410\n", "N2_ACTSEL 0.252789\n", "OIL_P 0.379184\n", "OIL_TEMP 0.383543\n", "PS3_SEL 0.300732\n", "PT2_SEL 0.370467\n", "P0_SEL 0.370467\n", "TAT 0.300732\n", "TBV_SEL 0.296374\n", "TRA_SEL 0.300732\n", "T25_SEL 0.470711\n", "T3_SEL 0.470711\n", "VBV_SEL 0.292015\n", "VIB_CN1 0.292015\n", "VIB_CN2 0.283298\n", "VIB_TN1 0.283298\n", "VIB_TN2 0.283298\n", "VSV_SEL 0.274582\n", "WFM_SEL 0.270223\n", "XM 0.261506\n", "FLIGHT_PHASE 0.444561\n", "dtype: float64\n", "T25_SEL\n", "0.33358813432035184\n", "Question 2.3\n", "99.48134588563458\n" ] } ], "source": [ "\"\"\"\n", "EXERCISE - Method isna\n", "1. Try the isna method on DataFrame df, and on a single column or row. What is the result?\n", "2. Using any(axis=...), mean() and max()/idxmax() methods on the result of isna(), answer following questions :\n", " 2.1 Which columns contain mising values, which don't ?\n", " 2.2 What is the percentage of missing valuesin the DF (a) per column (b) overall ? Which variable containt the most NaN values ?\n", " 2.3 What is the percentage of rows where all variables are present ?\n", "\"\"\"\n", "print('Question 2.1')\n", "print(df.isna().any(axis=0))\n", "\n", "print('Question 2.2')\n", "print(df.isna().mean()*100)\n", "print(df.isna().mean().idxmax())\n", "print(df.isna().mean().mean()*100)\n", "\n", "print('Question 2.3')\n", "print((1-df.isna().any(axis=1).mean())*100)\n" ] }, { "cell_type": "code", "execution_count": 18, "id": "03b5883e-7b6e-4f89-8af7-aa8679aad7fc", "metadata": { "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[1;31mSignature:\u001b[0m\n", "\u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdropna\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m\n", "\u001b[0m \u001b[1;33m*\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", "\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;34m'Axis'\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", "\u001b[0m \u001b[0mhow\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;34m'AnyAll | lib.NoDefault'\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m<\u001b[0m\u001b[0mno_default\u001b[0m\u001b[1;33m>\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", "\u001b[0m \u001b[0mthresh\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;34m'int | lib.NoDefault'\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m<\u001b[0m\u001b[0mno_default\u001b[0m\u001b[1;33m>\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", "\u001b[0m \u001b[0msubset\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;34m'IndexLabel | None'\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", "\u001b[0m \u001b[0minplace\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;34m'bool'\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", "\u001b[0m \u001b[0mignore_index\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;34m'bool'\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", "\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m->\u001b[0m \u001b[1;34m'DataFrame | None'\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;31mDocstring:\u001b[0m\n", "Remove missing values.\n", "\n", "See the :ref:`User Guide ` for more on which values are\n", "considered missing, and how to work with missing data.\n", "\n", "Parameters\n", "----------\n", "axis : {0 or 'index', 1 or 'columns'}, default 0\n", " Determine if rows or columns which contain missing values are\n", " removed.\n", "\n", " * 0, or 'index' : Drop rows which contain missing values.\n", " * 1, or 'columns' : Drop columns which contain missing value.\n", "\n", " Only a single axis is allowed.\n", "\n", "how : {'any', 'all'}, default 'any'\n", " Determine if row or column is removed from DataFrame, when we have\n", " at least one NA or all NA.\n", "\n", " * 'any' : If any NA values are present, drop that row or column.\n", " * 'all' : If all values are NA, drop that row or column.\n", "\n", "thresh : int, optional\n", " Require that many non-NA values. Cannot be combined with how.\n", "subset : column label or sequence of labels, optional\n", " Labels along other axis to consider, e.g. if you are dropping rows\n", " these would be a list of columns to include.\n", "inplace : bool, default False\n", " Whether to modify the DataFrame rather than creating a new one.\n", "ignore_index : bool, default ``False``\n", " If ``True``, the resulting axis will be labeled 0, 1, …, n - 1.\n", "\n", " .. versionadded:: 2.0.0\n", "\n", "Returns\n", "-------\n", "DataFrame or None\n", " DataFrame with NA entries dropped from it or None if ``inplace=True``.\n", "\n", "See Also\n", "--------\n", "DataFrame.isna: Indicate missing values.\n", "DataFrame.notna : Indicate existing (non-missing) values.\n", "DataFrame.fillna : Replace missing values.\n", "Series.dropna : Drop missing values.\n", "Index.dropna : Drop missing indices.\n", "\n", "Examples\n", "--------\n", ">>> df = pd.DataFrame({\"name\": ['Alfred', 'Batman', 'Catwoman'],\n", "... \"toy\": [np.nan, 'Batmobile', 'Bullwhip'],\n", "... \"born\": [pd.NaT, pd.Timestamp(\"1940-04-25\"),\n", "... pd.NaT]})\n", ">>> df\n", " name toy born\n", "0 Alfred NaN NaT\n", "1 Batman Batmobile 1940-04-25\n", "2 Catwoman Bullwhip NaT\n", "\n", "Drop the rows where at least one element is missing.\n", "\n", ">>> df.dropna()\n", " name toy born\n", "1 Batman Batmobile 1940-04-25\n", "\n", "Drop the columns where at least one element is missing.\n", "\n", ">>> df.dropna(axis='columns')\n", " name\n", "0 Alfred\n", "1 Batman\n", "2 Catwoman\n", "\n", "Drop the rows where all elements are missing.\n", "\n", ">>> df.dropna(how='all')\n", " name toy born\n", "0 Alfred NaN NaT\n", "1 Batman Batmobile 1940-04-25\n", "2 Catwoman Bullwhip NaT\n", "\n", "Keep only the rows with at least 2 non-NA values.\n", "\n", ">>> df.dropna(thresh=2)\n", " name toy born\n", "1 Batman Batmobile 1940-04-25\n", "2 Catwoman Bullwhip NaT\n", "\n", "Define in which columns to look for missing values.\n", "\n", ">>> df.dropna(subset=['name', 'toy'])\n", " name toy born\n", "1 Batman Batmobile 1940-04-25\n", "2 Catwoman Bullwhip NaT\n", "\u001b[1;31mFile:\u001b[0m c:\\users\\awei\\developer\\work\\venvs\\3.11.7\\civil-332\\lib\\site-packages\\pandas\\core\\frame.py\n", "\u001b[1;31mType:\u001b[0m method" ] } ], "source": [ "# You can check the built-in documentation of the dropna() method\n", "df.dropna?\n" ] }, { "cell_type": "code", "execution_count": 19, "id": "4c026180-7ba3-445f-8aee-5ec58b0375cd", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "119\n" ] }, { "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", "
t
12011-09-15 14:25:58.125
22011-09-15 14:25:58.375
32011-09-15 14:25:58.625
42011-09-15 14:25:58.875
52011-09-15 14:25:59.125
......
229402011-09-15 16:01:32.875
229412011-09-15 16:01:33.125
229422011-09-15 16:01:33.375
229432011-09-15 16:01:33.625
229442011-09-15 16:01:33.875
\n", "

22944 rows × 1 columns

\n", "
" ], "text/plain": [ " t\n", "1 2011-09-15 14:25:58.125\n", "2 2011-09-15 14:25:58.375\n", "3 2011-09-15 14:25:58.625\n", "4 2011-09-15 14:25:58.875\n", "5 2011-09-15 14:25:59.125\n", "... ...\n", "22940 2011-09-15 16:01:32.875\n", "22941 2011-09-15 16:01:33.125\n", "22942 2011-09-15 16:01:33.375\n", "22943 2011-09-15 16:01:33.625\n", "22944 2011-09-15 16:01:33.875\n", "\n", "[22944 rows x 1 columns]" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\"\"\"\n", "EXERCISE - Method dropna\n", "The dropna method can be used to remove missing values (NaN). Start by reading its documentation.\n", "1. What is the meaning of arguments \"axis\" and \"how\" ?\n", "2. Remove the rows containing ONLY missing values.\n", "3. Remove the rows containing AT LEAST one missing value. How many additional rows were removed?\n", "4. Remove the columns containing AT LEAST one missing value.\n", "\n", "Note: do not change the actual DataFrame df (you can create new variables df2, df3, ...)\n", "\"\"\"\n", "# 1. axis=0 for rows ; axis=1 for columns ; how=\"all\" for only NaN ; how=\"any\" for at least 1 NaN\n", "\n", "# 2.\n", "df.dropna(how='all')\n", "\n", "# 3. \n", "df.dropna(how='any')\n", "print(df.dropna(how='all').shape[0]-df.dropna(how='any').shape[0])\n", "\n", "# 4. \n", "df.dropna(axis=1, how=\"any\")\n" ] }, { "cell_type": "code", "execution_count": 20, "id": "32cf8940", "metadata": {}, "outputs": [], "source": [ "# Now, update the actual DF by removing the rows containing AT LEAST one missing value\n", "df = df.dropna(how='any')\n" ] }, { "cell_type": "code", "execution_count": 21, "id": "bf434e2d-0c78-4609-a3a6-2ae93c05a49b", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " nom age\n", "0 Alice 24.0\n", "1 Bob NaN\n", "2 Charlie 99.0\n", "3 David 24.0\n", "nom Bob\n", "age 0.0\n", "Name: 1, dtype: object\n", "nom Bob\n", "age 24.0\n", "Name: 1, dtype: object\n", "nom Bob\n", "age 99.0\n", "Name: 1, dtype: object\n", "nom Bob\n", "age 49.0\n", "Name: 1, dtype: object\n", "nom Bob\n", "age 24.0\n", "Name: 1, dtype: object\n" ] } ], "source": [ "\"\"\"\n", "EXERCISE - Method fillna\n", "The fillna() method can be used to fill missing values (NaN). Start by reading its documentation.\n", "1. What are the different strategies to fill missing values?\n", "2. Fill the missing value of \"age\" in the provided toy DataFrame using :\n", " - 0\n", " - the last or next non-empty value\n", " - the mean\n", " - the most frequent value (mode)\n", "\n", "Complete the exercise on the \"example\" DataFrame declared below\n", "\"\"\" \n", "example = pd.DataFrame({'nom': ['Alice', 'Bob', 'Charlie', 'David'], 'age': [24, None, 99, 24]})\n", "print(example)\n", "\n", "# 1. Check https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.fillna.html\n", "\n", "# 2.\n", "print(example.fillna(0).iloc[1])\n", "print(example.ffill().iloc[1]) # Previous non-empty value\n", "print(example.bfill().iloc[1]) # Next non-empty value\n", "print(example.fillna(example[\"age\"].mean()).iloc[1]) # Mean\n", "print(example.fillna(example[\"age\"].dropna().mode()[0]).iloc[1]) # Mode\n" ] }, { "cell_type": "markdown", "id": "e3cff224-1b61-4546-8bcd-1861e77e0fd2", "metadata": {}, "source": [ "**Question**: How would you handle a temporal variable, such as temperature 'EGT_SEL' in the flight data?" ] }, { "cell_type": "markdown", "id": "c37db8ee-6cfe-42a4-9441-fb466cc81042", "metadata": {}, "source": [ "## 4. Feature extraction: statistical features, one-hot encoding" ] }, { "cell_type": "markdown", "id": "c25e3d02-2be6-4281-9e20-6be1b892b335", "metadata": {}, "source": [ "Now that we have some clean data to work with, let's analyze it and extract meaningful information:\n", "\n", "* Transform raw signals into more informative signatures (or fingerprints)\n", "of a system\n", "* Reduce size / complexity of the dataset\n", "* Provide a physical description / representation\n", "* Reduce resources necessary for further processing\n", "* Achieve intended objectives\n", "* Features are known to be the most crucial point in machine learning" ] }, { "cell_type": "code", "execution_count": 22, "id": "124a9a47-f873-4b94-87c9-a19d370cdd51", "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
EGT_SELFMV_SELHPTC_SEL...VSV_SELWFM_SELXM
meanstdminmaxmeanstdminmaxmeanstd...minmaxmeanstdminmaxmeanstdminmax
FLIGHT_PHASE
approach546.49046214.642402509.281000604.84325.7851564.90209921.00032.75068.02849225.548291...5.88867026.630902012.232731618.345232707.9993296.00.2297410.0142500.1866250.259875
begin_climb527.56870749.3071840.000000684.87511.7372883.3356110.00019.62515.58112814.956426...-0.96680538.05630872.421668663.7980150.00010752.10.1500000.0000000.1500000.150000
climb756.21249415.205915689.219000772.68748.74635425.24594417.75070.37599.4248860.113250...-1.4941403.867187231.375021341.8881806544.0007754.00.2353590.0398720.1500000.274000
cruise627.12996715.107123571.969000714.68834.2311291.80034421.25042.00089.90081627.462222...-1.2304705.932622590.441446136.2626761714.0003488.00.7777140.0055680.7470000.791000
cruise_climb775.24985520.252909680.281000800.00059.3913735.28994438.25064.62579.36349211.867054...-2.0214804.262695723.930024820.2219112230.0006656.00.5837190.1437650.2591250.749000
descent464.34357640.471346391.531000601.28115.8215596.3995547.87533.87522.89662230.414487...1.31836026.894501153.696377511.345119384.0002830.00.5733200.1698870.2563750.783000
flare556.40291040.397556507.094000644.21922.68578111.1096719.37532.75027.95813831.633174...-0.52730431.904301332.4718401432.197240356.0004854.00.1531700.0076190.1500000.184375
landing555.95158736.018719401.564000675.15510.8288094.960601-12.50019.37512.69403310.826525...16.61140038.40820730.567227310.4167620.0002030.00.1500000.0000000.1500000.150000
take_off205.285706154.2336750.000000538.9491.0078112.9599210.00010.75015.11724017.328247...-5.80078038.408201819.4532153194.9715560.00010752.10.1500000.0000000.1500000.150000
taxi333.585900160.495227-0.003114641.432-9.8099715.092670-12.5000.0005.41812012.452663...-5.71289038.408201947.3736803438.4198350.00010752.10.1500000.0000000.1500000.150000
\n", "

10 rows × 96 columns

\n", "
" ], "text/plain": [ " EGT_SEL FMV_SEL \\\n", " mean std min max mean \n", "FLIGHT_PHASE \n", "approach 546.490462 14.642402 509.281000 604.843 25.785156 \n", "begin_climb 527.568707 49.307184 0.000000 684.875 11.737288 \n", "climb 756.212494 15.205915 689.219000 772.687 48.746354 \n", "cruise 627.129967 15.107123 571.969000 714.688 34.231129 \n", "cruise_climb 775.249855 20.252909 680.281000 800.000 59.391373 \n", "descent 464.343576 40.471346 391.531000 601.281 15.821559 \n", "flare 556.402910 40.397556 507.094000 644.219 22.685781 \n", "landing 555.951587 36.018719 401.564000 675.155 10.828809 \n", "take_off 205.285706 154.233675 0.000000 538.949 1.007811 \n", "taxi 333.585900 160.495227 -0.003114 641.432 -9.809971 \n", "\n", " HPTC_SEL ... VSV_SEL \\\n", " std min max mean std ... min \n", "FLIGHT_PHASE ... \n", "approach 4.902099 21.000 32.750 68.028492 25.548291 ... 5.888670 \n", "begin_climb 3.335611 0.000 19.625 15.581128 14.956426 ... -0.966805 \n", "climb 25.245944 17.750 70.375 99.424886 0.113250 ... -1.494140 \n", "cruise 1.800344 21.250 42.000 89.900816 27.462222 ... -1.230470 \n", "cruise_climb 5.289944 38.250 64.625 79.363492 11.867054 ... -2.021480 \n", "descent 6.399554 7.875 33.875 22.896622 30.414487 ... 1.318360 \n", "flare 11.109671 9.375 32.750 27.958138 31.633174 ... -0.527304 \n", "landing 4.960601 -12.500 19.375 12.694033 10.826525 ... 16.611400 \n", "take_off 2.959921 0.000 10.750 15.117240 17.328247 ... -5.800780 \n", "taxi 5.092670 -12.500 0.000 5.418120 12.452663 ... -5.712890 \n", "\n", " WFM_SEL XM \\\n", " max mean std min max mean \n", "FLIGHT_PHASE \n", "approach 26.63090 2012.232731 618.345232 707.999 3296.0 0.229741 \n", "begin_climb 38.05630 872.421668 663.798015 0.000 10752.1 0.150000 \n", "climb 3.86718 7231.375021 341.888180 6544.000 7754.0 0.235359 \n", "cruise 5.93262 2590.441446 136.262676 1714.000 3488.0 0.777714 \n", "cruise_climb 4.26269 5723.930024 820.221911 2230.000 6656.0 0.583719 \n", "descent 26.89450 1153.696377 511.345119 384.000 2830.0 0.573320 \n", "flare 31.90430 1332.471840 1432.197240 356.000 4854.0 0.153170 \n", "landing 38.40820 730.567227 310.416762 0.000 2030.0 0.150000 \n", "take_off 38.40820 1819.453215 3194.971556 0.000 10752.1 0.150000 \n", "taxi 38.40820 1947.373680 3438.419835 0.000 10752.1 0.150000 \n", "\n", " \n", " std min max \n", "FLIGHT_PHASE \n", "approach 0.014250 0.186625 0.259875 \n", "begin_climb 0.000000 0.150000 0.150000 \n", "climb 0.039872 0.150000 0.274000 \n", "cruise 0.005568 0.747000 0.791000 \n", "cruise_climb 0.143765 0.259125 0.749000 \n", "descent 0.169887 0.256375 0.783000 \n", "flare 0.007619 0.150000 0.184375 \n", "landing 0.000000 0.150000 0.150000 \n", "take_off 0.000000 0.150000 0.150000 \n", "taxi 0.000000 0.150000 0.150000 \n", "\n", "[10 rows x 96 columns]" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\"\"\"\n", "EXERCISE - Compute statistical features for each phase of this flight\n", "For each FLIGHT_PHASE, compute and display the mean, standard deviation, max and min of the numerical features.\n", "Hint: a DataFrame or Series can be aggregated using methods such as \".mean()\".\n", "Hint: A DF can be grouped on a key using df.groupby(column), before being aggregated.\n", "\"\"\"\n", "df.drop(\"t\", axis=1).groupby(\"FLIGHT_PHASE\").agg([\"mean\", \"std\", \"min\", \"max\"])\n" ] }, { "cell_type": "code", "execution_count": 23, "id": "2ce6a0df", "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", "
tEGT_SELFMV_SELHPTC_SELLPTC_SELN1_SELN2_ACTSELOIL_POIL_TEMPPS3_SEL...T25_SELT3_SELVBV_SELVIB_CN1VIB_CN2VIB_TN1VIB_TN2VSV_SELWFM_SELXM
count2282522825.00000022825.0000002.282500e+042.282500e+042.282500e+042.282500e+042.282500e+0422825.00000022825.000000...22825.00000022825.00000022825.0000002.282500e+0422825.0000002.282500e+0422825.00000022825.00000022825.00000022825.000000
mean2011-09-15 15:13:47.615284736580.90553927.9610355.504560e+014.223039e+016.285678e+018.192068e+013.825420e+01102.055101115.628227...54.088825342.35610111.5569471.582161e-010.0706272.378445e-010.14740810.9158792437.9779230.535795
min2011-09-15 14:26:02.875000-0.003114-12.500000-2.364350e-54-5.461640e-43-2.793460e-40-2.118610e-31-1.554120e-200.0000000.000000...-128.000000-512.000000-0.175781-2.995200e-080.000000-4.351020e-080.000000-5.8007800.0000000.150000
25%2011-09-15 14:50:01.375000064501.96900011.3750007.999510e+002.525000e+013.012500e+017.190630e+012.700000e+0196.90630045.750000...34.500000218.000000-0.0219744.875010e-020.0300003.000000e-020.0612501.274410768.0000000.246375
50%2011-09-15 15:13:47.875000064613.00000033.3750007.100000e+013.783980e+018.487890e+019.200000e+014.100000e+01103.281000118.000000...57.250000411.0000000.0000001.487500e-010.0437502.812500e-010.0712502.2412102542.0000000.657625
75%2011-09-15 15:37:34.375000064628.00000034.0105009.936130e+016.393750e+018.612500e+019.275000e+014.100000e+01107.969000120.500000...59.500000417.46900033.8379002.712500e-010.1000004.100000e-010.21000026.5430002592.0000000.776875
max2011-09-15 16:01:20.875000800.00000070.3750009.955420e+016.478470e+011.000000e+029.937500e+017.440030e+02746.1550001345.530000...111.000000532.00000034.3652006.000000e-010.3200006.987500e-010.46000038.40820010752.1000000.791000
stdNaN125.83596418.1034544.173754e+011.856232e+013.037419e+011.926020e+013.616953e+0127.560810105.081767...27.919786131.01694215.3335181.141368e-010.0578191.886181e-010.13699112.9092611902.8601220.260862
\n", "

8 rows × 25 columns

\n", "
" ], "text/plain": [ " t EGT_SEL FMV_SEL \\\n", "count 22825 22825.000000 22825.000000 \n", "mean 2011-09-15 15:13:47.615284736 580.905539 27.961035 \n", "min 2011-09-15 14:26:02.875000 -0.003114 -12.500000 \n", "25% 2011-09-15 14:50:01.375000064 501.969000 11.375000 \n", "50% 2011-09-15 15:13:47.875000064 613.000000 33.375000 \n", "75% 2011-09-15 15:37:34.375000064 628.000000 34.010500 \n", "max 2011-09-15 16:01:20.875000 800.000000 70.375000 \n", "std NaN 125.835964 18.103454 \n", "\n", " HPTC_SEL LPTC_SEL N1_SEL N2_ACTSEL OIL_P \\\n", "count 2.282500e+04 2.282500e+04 2.282500e+04 2.282500e+04 2.282500e+04 \n", "mean 5.504560e+01 4.223039e+01 6.285678e+01 8.192068e+01 3.825420e+01 \n", "min -2.364350e-54 -5.461640e-43 -2.793460e-40 -2.118610e-31 -1.554120e-20 \n", "25% 7.999510e+00 2.525000e+01 3.012500e+01 7.190630e+01 2.700000e+01 \n", "50% 7.100000e+01 3.783980e+01 8.487890e+01 9.200000e+01 4.100000e+01 \n", "75% 9.936130e+01 6.393750e+01 8.612500e+01 9.275000e+01 4.100000e+01 \n", "max 9.955420e+01 6.478470e+01 1.000000e+02 9.937500e+01 7.440030e+02 \n", "std 4.173754e+01 1.856232e+01 3.037419e+01 1.926020e+01 3.616953e+01 \n", "\n", " OIL_TEMP PS3_SEL ... T25_SEL T3_SEL \\\n", "count 22825.000000 22825.000000 ... 22825.000000 22825.000000 \n", "mean 102.055101 115.628227 ... 54.088825 342.356101 \n", "min 0.000000 0.000000 ... -128.000000 -512.000000 \n", "25% 96.906300 45.750000 ... 34.500000 218.000000 \n", "50% 103.281000 118.000000 ... 57.250000 411.000000 \n", "75% 107.969000 120.500000 ... 59.500000 417.469000 \n", "max 746.155000 1345.530000 ... 111.000000 532.000000 \n", "std 27.560810 105.081767 ... 27.919786 131.016942 \n", "\n", " VBV_SEL VIB_CN1 VIB_CN2 VIB_TN1 VIB_TN2 \\\n", "count 22825.000000 2.282500e+04 22825.000000 2.282500e+04 22825.000000 \n", "mean 11.556947 1.582161e-01 0.070627 2.378445e-01 0.147408 \n", "min -0.175781 -2.995200e-08 0.000000 -4.351020e-08 0.000000 \n", "25% -0.021974 4.875010e-02 0.030000 3.000000e-02 0.061250 \n", "50% 0.000000 1.487500e-01 0.043750 2.812500e-01 0.071250 \n", "75% 33.837900 2.712500e-01 0.100000 4.100000e-01 0.210000 \n", "max 34.365200 6.000000e-01 0.320000 6.987500e-01 0.460000 \n", "std 15.333518 1.141368e-01 0.057819 1.886181e-01 0.136991 \n", "\n", " VSV_SEL WFM_SEL XM \n", "count 22825.000000 22825.000000 22825.000000 \n", "mean 10.915879 2437.977923 0.535795 \n", "min -5.800780 0.000000 0.150000 \n", "25% 1.274410 768.000000 0.246375 \n", "50% 2.241210 2542.000000 0.657625 \n", "75% 26.543000 2592.000000 0.776875 \n", "max 38.408200 10752.100000 0.791000 \n", "std 12.909261 1902.860122 0.260862 \n", "\n", "[8 rows x 25 columns]" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# The describe() method also provides similar capabilities\n", "df.describe()\n" ] }, { "cell_type": "markdown", "id": "465e7863-b926-4fd3-bc32-0493c3f9fb4d", "metadata": {}, "source": [ "The `FLIGHT_PHASE` feature is categorical (text, with finite number of different values). One way to transform it into a numerical feature is through one-hot encoding.\n", "\n", "![one-hot colors](rc/onehot-color.png)" ] }, { "cell_type": "code", "execution_count": 24, "id": "57af14fc-d01a-475a-a612-2776ca52d0bb", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['approach' 'begin_climb' 'climb' 'cruise' 'cruise_climb' 'descent'\n", " 'flare' 'landing' 'take_off' 'taxi']\n" ] }, { "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", "
tEGT_SELFMV_SELHPTC_SELLPTC_SELN1_SELN2_ACTSELOIL_POIL_TEMPPS3_SEL...FLIGHT_PHASE_approachFLIGHT_PHASE_begin_climbFLIGHT_PHASE_climbFLIGHT_PHASE_cruiseFLIGHT_PHASE_cruise_climbFLIGHT_PHASE_descentFLIGHT_PHASE_flareFLIGHT_PHASE_landingFLIGHT_PHASE_take_offFLIGHT_PHASE_taxi
202011-09-15 14:26:02.875335.98400.00.00.00.00.00.0177.3740959.980...0.00.00.00.00.00.00.00.00.01.0
212011-09-15 14:26:03.125239.98600.00.00.00.00.00.0133.6240575.982...0.00.00.00.00.00.00.00.00.01.0
222011-09-15 14:26:03.375167.99100.00.00.00.00.00.089.8743191.984...0.00.00.00.00.00.00.00.00.01.0
232011-09-15 14:26:03.625119.99400.00.00.00.00.00.068.00000.000...0.00.00.00.00.00.00.00.00.01.0
242011-09-15 14:26:03.87572.00110.00.00.00.00.00.068.00000.000...0.00.00.00.00.00.00.00.00.01.0
\n", "

5 rows × 36 columns

\n", "
" ], "text/plain": [ " t EGT_SEL FMV_SEL HPTC_SEL LPTC_SEL N1_SEL \\\n", "20 2011-09-15 14:26:02.875 335.9840 0.0 0.0 0.0 0.0 \n", "21 2011-09-15 14:26:03.125 239.9860 0.0 0.0 0.0 0.0 \n", "22 2011-09-15 14:26:03.375 167.9910 0.0 0.0 0.0 0.0 \n", "23 2011-09-15 14:26:03.625 119.9940 0.0 0.0 0.0 0.0 \n", "24 2011-09-15 14:26:03.875 72.0011 0.0 0.0 0.0 0.0 \n", "\n", " N2_ACTSEL OIL_P OIL_TEMP PS3_SEL ... FLIGHT_PHASE_approach \\\n", "20 0.0 0.0 177.3740 959.980 ... 0.0 \n", "21 0.0 0.0 133.6240 575.982 ... 0.0 \n", "22 0.0 0.0 89.8743 191.984 ... 0.0 \n", "23 0.0 0.0 68.0000 0.000 ... 0.0 \n", "24 0.0 0.0 68.0000 0.000 ... 0.0 \n", "\n", " FLIGHT_PHASE_begin_climb FLIGHT_PHASE_climb FLIGHT_PHASE_cruise \\\n", "20 0.0 0.0 0.0 \n", "21 0.0 0.0 0.0 \n", "22 0.0 0.0 0.0 \n", "23 0.0 0.0 0.0 \n", "24 0.0 0.0 0.0 \n", "\n", " FLIGHT_PHASE_cruise_climb FLIGHT_PHASE_descent FLIGHT_PHASE_flare \\\n", "20 0.0 0.0 0.0 \n", "21 0.0 0.0 0.0 \n", "22 0.0 0.0 0.0 \n", "23 0.0 0.0 0.0 \n", "24 0.0 0.0 0.0 \n", "\n", " FLIGHT_PHASE_landing FLIGHT_PHASE_take_off FLIGHT_PHASE_taxi \n", "20 0.0 0.0 1.0 \n", "21 0.0 0.0 1.0 \n", "22 0.0 0.0 1.0 \n", "23 0.0 0.0 1.0 \n", "24 0.0 0.0 1.0 \n", "\n", "[5 rows x 36 columns]" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\"\"\"\n", "EXERCISE - Perform a one-hot encoding of the categorical feature \"FLIGHT_PHASE\".\n", "The simplest way is to use the OneHotEncoder provided by the scikit-learn library.\n", "1. Fit the encoder to the FLIGHT_PHASE column.\n", "2. Print out the categories of the encoding.\n", "3. Append the new encoded features to the DF (FLIGHT_PHASE_cruise, FLIGHT_PHASE_climb, etc.).\n", "\n", "Hint: Check the OneHotEncoder class from Scikit-Learn https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.OneHotEncoder.html\n", "\"\"\"\n", "\n", "# You should install scikit-learn (if not done already): `pip install scikit-learn`\n", "from sklearn.preprocessing import OneHotEncoder\n", "\n", "# 1. \n", "onehot = OneHotEncoder().fit(df[[\"FLIGHT_PHASE\"]])\n", "\n", "# 2.\n", "categories = onehot.categories_[0]\n", "print(categories)\n", "\n", "# 3.\n", "result = onehot.transform(df[[\"FLIGHT_PHASE\"]]).toarray()\n", "for j, cat in enumerate(onehot.categories_[0]):\n", " #print(j)\n", " df.loc[:, \"FLIGHT_PHASE_\" + cat] = result[:, j]\n", "df.head()\n" ] }, { "cell_type": "code", "execution_count": 25, "id": "59aa1f8b", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " t EGT_SEL FMV_SEL HPTC_SEL LPTC_SEL N1_SEL \\\n", "20 2011-09-15 14:26:02.875 335.9840 0.0 0.0 0.0 0.0 \n", "21 2011-09-15 14:26:03.125 239.9860 0.0 0.0 0.0 0.0 \n", "22 2011-09-15 14:26:03.375 167.9910 0.0 0.0 0.0 0.0 \n", "23 2011-09-15 14:26:03.625 119.9940 0.0 0.0 0.0 0.0 \n", "24 2011-09-15 14:26:03.875 72.0011 0.0 0.0 0.0 0.0 \n", "\n", " N2_ACTSEL OIL_P OIL_TEMP PS3_SEL ... FLIGHT_PHASE_approach \\\n", "20 0.0 0.0 177.3740 959.980 ... 0.0 \n", "21 0.0 0.0 133.6240 575.982 ... 0.0 \n", "22 0.0 0.0 89.8743 191.984 ... 0.0 \n", "23 0.0 0.0 68.0000 0.000 ... 0.0 \n", "24 0.0 0.0 68.0000 0.000 ... 0.0 \n", "\n", " FLIGHT_PHASE_begin_climb FLIGHT_PHASE_climb FLIGHT_PHASE_cruise \\\n", "20 0.0 0.0 0.0 \n", "21 0.0 0.0 0.0 \n", "22 0.0 0.0 0.0 \n", "23 0.0 0.0 0.0 \n", "24 0.0 0.0 0.0 \n", "\n", " FLIGHT_PHASE_cruise_climb FLIGHT_PHASE_descent FLIGHT_PHASE_flare \\\n", "20 0.0 0.0 0.0 \n", "21 0.0 0.0 0.0 \n", "22 0.0 0.0 0.0 \n", "23 0.0 0.0 0.0 \n", "24 0.0 0.0 0.0 \n", "\n", " FLIGHT_PHASE_landing FLIGHT_PHASE_take_off FLIGHT_PHASE_taxi \n", "20 0.0 0.0 1.0 \n", "21 0.0 0.0 1.0 \n", "22 0.0 0.0 1.0 \n", "23 0.0 0.0 1.0 \n", "24 0.0 0.0 1.0 \n", "\n", "[5 rows x 36 columns]\n" ] } ], "source": [ "# You should now have additional columns at the end of the DataFrame with the proper encoding \n", "print(df.head())\n" ] }, { "cell_type": "markdown", "id": "34bcd830-8449-4999-828a-3be4952ff12e", "metadata": {}, "source": [ "## 5. Outlier detection\n", "\n", "One way to analyze data is to look at its distribution. This is often done by computing the mean/average and the standard deviation. However, quantiles are also important metrics and help to identify outliers, which can potentially indicate abnomral operating conditions.\n", "\n", "Let's see how we can compute quantiles on a Pandas `DataFrame`." ] }, { "cell_type": "code", "execution_count": 26, "id": "0bfdadb2-fcd8-431f-8d3f-f2a02a4ab82b", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "EGT_SEL 798.000000\n", "FMV_SEL 70.375000\n", "HPTC_SEL 99.478500\n", "LPTC_SEL 64.051500\n", "N1_SEL 99.750000\n", "N2_ACTSEL 99.156300\n", "OIL_P 51.031300\n", "OIL_TEMP 116.000000\n", "PS3_SEL 308.750000\n", "PT2_SEL 1031.000000\n", "P0_SEL 14.328100\n", "TAT 34.468700\n", "TBV_SEL 100.711000\n", "TRA_SEL 71.930200\n", "T25_SEL 110.850080\n", "T3_SEL 530.000000\n", "VBV_SEL 34.277300\n", "VIB_CN1 0.391250\n", "VIB_CN2 0.250000\n", "VIB_TN1 0.650000\n", "VIB_TN2 0.450000\n", "VSV_SEL 36.595864\n", "WFM_SEL 7521.040000\n", "XM 0.785000\n", "FLIGHT_PHASE_approach 1.000000\n", "FLIGHT_PHASE_begin_climb 1.000000\n", "FLIGHT_PHASE_climb 1.000000\n", "FLIGHT_PHASE_cruise 1.000000\n", "FLIGHT_PHASE_cruise_climb 1.000000\n", "FLIGHT_PHASE_descent 1.000000\n", "FLIGHT_PHASE_flare 0.000000\n", "FLIGHT_PHASE_landing 1.000000\n", "FLIGHT_PHASE_take_off 1.000000\n", "FLIGHT_PHASE_taxi 1.000000\n", "Name: 0.99, dtype: float64\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "\"\"\"\n", "EXERCISE - Quantiles\n", "1. Compute the 99th-percentile values for each variable in the DF.\n", "2. Compute this value for a specific variable, for example \"VIB_CN1\", and highlight the outlier values in the plot.\n", "\n", "Hint: Take a look at the documentation https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.html\n", "\"\"\"\n", "\n", "# 1. Print the 99th percentile for each column\n", "print(df.quantile(q=0.99, numeric_only=True))\n", "\n", "# 2. Compute the 95th percentile for the VIB_CN1 column (q95 should be a single float value)\n", "var = \"VIB_CN1\"\n", "q95 = df[var].quantile(0.99)\n", "\n", "# Automatic plot (you shouldn't have to modify this code)\n", "plt.figure(figsize=(10,5))\n", "plt.plot(df[\"t\"], df[var])\n", "plt.plot([df[\"t\"].iloc[0], df[\"t\"].iloc[-1]], [q95, q95], \"r-\")\n", "outlier = df[df[var] > q95]\n", "plt.plot(outlier[\"t\"], outlier[var], \"ro\")\n", "plt.xlabel(\"t\")\n", "plt.ylabel(var);\n" ] }, { "cell_type": "markdown", "id": "5c99655e-326f-4ad2-9c54-8df9161184ee", "metadata": {}, "source": [ "## 6. Filtering & Smoothing\n", "\n", "As sensors are inherently noisy, their measurements often need some filtering and smoothing. In this section, we will explore a moving-average smoothing method.\n", "\n", "### 6.1 Time-based index\n", "\n", "For now, each row is identified by its index. However, the `DataFrame` contains time-series data (*i.e.* data which evolves over time). To compute a moving-average smoothing over time, we should first index each row with a time value, instead of a simple integer index." ] }, { "cell_type": "code", "execution_count": 27, "id": "d055d85b-80be-411f-9054-199ef81eb6c8", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index([ 20, 21, 22, 23, 24, 25, 26, 27, 28, 29,\n", " ...\n", " 22883, 22884, 22885, 22886, 22887, 22888, 22889, 22890, 22891, 22892],\n", " dtype='int64', length=22825)\n", "DatetimeIndex(['2011-09-15 14:26:02.875000', '2011-09-15 14:26:03.125000',\n", " '2011-09-15 14:26:03.375000', '2011-09-15 14:26:03.625000',\n", " '2011-09-15 14:26:03.875000', '2011-09-15 14:26:04.125000',\n", " '2011-09-15 14:26:04.375000', '2011-09-15 14:26:04.625000',\n", " '2011-09-15 14:26:04.875000', '2011-09-15 14:26:05.125000',\n", " ...\n", " '2011-09-15 16:01:18.625000', '2011-09-15 16:01:18.875000',\n", " '2011-09-15 16:01:19.125000', '2011-09-15 16:01:19.375000',\n", " '2011-09-15 16:01:19.625000', '2011-09-15 16:01:19.875000',\n", " '2011-09-15 16:01:20.125000', '2011-09-15 16:01:20.375000',\n", " '2011-09-15 16:01:20.625000', '2011-09-15 16:01:20.875000'],\n", " dtype='datetime64[ns]', name='t', length=22825, freq=None)\n" ] }, { "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", "
EGT_SELFMV_SELHPTC_SELLPTC_SELN1_SELN2_ACTSELOIL_POIL_TEMPPS3_SELPT2_SEL...FLIGHT_PHASE_approachFLIGHT_PHASE_begin_climbFLIGHT_PHASE_climbFLIGHT_PHASE_cruiseFLIGHT_PHASE_cruise_climbFLIGHT_PHASE_descentFLIGHT_PHASE_flareFLIGHT_PHASE_landingFLIGHT_PHASE_take_offFLIGHT_PHASE_taxi
t
2011-09-15 14:26:02.875335.98400.00.00.00.00.00.0177.3740959.9800.0...0.00.00.00.00.00.00.00.00.01.0
2011-09-15 14:26:03.125239.98600.00.00.00.00.00.0133.6240575.9820.0...0.00.00.00.00.00.00.00.00.01.0
2011-09-15 14:26:03.375167.99100.00.00.00.00.00.089.8743191.9840.0...0.00.00.00.00.00.00.00.00.01.0
2011-09-15 14:26:03.625119.99400.00.00.00.00.00.068.00000.0000.0...0.00.00.00.00.00.00.00.00.01.0
2011-09-15 14:26:03.87572.00110.00.00.00.00.00.068.00000.0000.0...0.00.00.00.00.00.00.00.00.01.0
\n", "

5 rows × 35 columns

\n", "
" ], "text/plain": [ " EGT_SEL FMV_SEL HPTC_SEL LPTC_SEL N1_SEL \\\n", "t \n", "2011-09-15 14:26:02.875 335.9840 0.0 0.0 0.0 0.0 \n", "2011-09-15 14:26:03.125 239.9860 0.0 0.0 0.0 0.0 \n", "2011-09-15 14:26:03.375 167.9910 0.0 0.0 0.0 0.0 \n", "2011-09-15 14:26:03.625 119.9940 0.0 0.0 0.0 0.0 \n", "2011-09-15 14:26:03.875 72.0011 0.0 0.0 0.0 0.0 \n", "\n", " N2_ACTSEL OIL_P OIL_TEMP PS3_SEL PT2_SEL ... \\\n", "t ... \n", "2011-09-15 14:26:02.875 0.0 0.0 177.3740 959.980 0.0 ... \n", "2011-09-15 14:26:03.125 0.0 0.0 133.6240 575.982 0.0 ... \n", "2011-09-15 14:26:03.375 0.0 0.0 89.8743 191.984 0.0 ... \n", "2011-09-15 14:26:03.625 0.0 0.0 68.0000 0.000 0.0 ... \n", "2011-09-15 14:26:03.875 0.0 0.0 68.0000 0.000 0.0 ... \n", "\n", " FLIGHT_PHASE_approach FLIGHT_PHASE_begin_climb \\\n", "t \n", "2011-09-15 14:26:02.875 0.0 0.0 \n", "2011-09-15 14:26:03.125 0.0 0.0 \n", "2011-09-15 14:26:03.375 0.0 0.0 \n", "2011-09-15 14:26:03.625 0.0 0.0 \n", "2011-09-15 14:26:03.875 0.0 0.0 \n", "\n", " FLIGHT_PHASE_climb FLIGHT_PHASE_cruise \\\n", "t \n", "2011-09-15 14:26:02.875 0.0 0.0 \n", "2011-09-15 14:26:03.125 0.0 0.0 \n", "2011-09-15 14:26:03.375 0.0 0.0 \n", "2011-09-15 14:26:03.625 0.0 0.0 \n", "2011-09-15 14:26:03.875 0.0 0.0 \n", "\n", " FLIGHT_PHASE_cruise_climb FLIGHT_PHASE_descent \\\n", "t \n", "2011-09-15 14:26:02.875 0.0 0.0 \n", "2011-09-15 14:26:03.125 0.0 0.0 \n", "2011-09-15 14:26:03.375 0.0 0.0 \n", "2011-09-15 14:26:03.625 0.0 0.0 \n", "2011-09-15 14:26:03.875 0.0 0.0 \n", "\n", " FLIGHT_PHASE_flare FLIGHT_PHASE_landing \\\n", "t \n", "2011-09-15 14:26:02.875 0.0 0.0 \n", "2011-09-15 14:26:03.125 0.0 0.0 \n", "2011-09-15 14:26:03.375 0.0 0.0 \n", "2011-09-15 14:26:03.625 0.0 0.0 \n", "2011-09-15 14:26:03.875 0.0 0.0 \n", "\n", " FLIGHT_PHASE_take_off FLIGHT_PHASE_taxi \n", "t \n", "2011-09-15 14:26:02.875 0.0 1.0 \n", "2011-09-15 14:26:03.125 0.0 1.0 \n", "2011-09-15 14:26:03.375 0.0 1.0 \n", "2011-09-15 14:26:03.625 0.0 1.0 \n", "2011-09-15 14:26:03.875 0.0 1.0 \n", "\n", "[5 rows x 35 columns]" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\"\"\"\n", "Exercise - Time-based index\n", "As our data are multivariate time series, we would like to use a time-based index.\n", "1. Create a copy of df, called df2, using the appropriate method.\n", "2. Set the time column ('t') the be the index of the DataFrame.\n", "3. Remove column 't' of the resulting DF.\n", "\"\"\"\n", "print(df.index)\n", "\n", "# 1.\n", "df2 = df.copy()\n", "\n", "# 2. & 3.\n", "df2.set_index(\"t\", inplace=True)\n", "print(df2.index)\n", "\n", "df2.head()\n" ] }, { "cell_type": "markdown", "id": "b37d52ef-9b93-448f-9818-d105251e9a38", "metadata": {}, "source": [ "We notice that pandas has automatically recognized a `DatetimeIndex`, suited for time series processing (such as time-based window operations, etc) !\n" ] }, { "cell_type": "markdown", "id": "2e009388-0087-431e-bd83-fbc39488dd70", "metadata": {}, "source": [ "### 6.2 Moving average smoothing\n", "\n", "Now that each row is properly indexed and represents a moment in time, let's compute a 30 seconds moving-average to smooth a sensor's data. " ] }, { "cell_type": "code", "execution_count": 28, "id": "211f746e-4635-4d8c-8498-30f8f8bd404e", "metadata": {}, "outputs": [], "source": [ "\"\"\"\n", "EXERCISE - Moving average smoothing.\n", "Pandas provides rolling window functions that can be applied as follows:\n", " data.rolling(window=).()\n", "Window size can be provided as a integer (number of steps), or a time unit if index is time-based.\n", "1. Perform a moving average of 30 seconds.\n", "\n", "Hint: Again, take a look at the documentation https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.html\n", "\"\"\"\n", "# This is the column to smooth\n", "var = \"VIB_CN1\"\n", "\n", "# The variable below should be an array of floats\n", "var_smoothed = df2[var].rolling(window=\"30s\").mean()\n" ] }, { "cell_type": "code", "execution_count": 29, "id": "7831d50d-da44-49f2-b8cd-37445846fcc1", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Automatic plot (you shouldn't have to modify it)\n", "plt.figure(figsize=(10,5))\n", "plt.plot(df2.index, df2[var])\n", "plt.plot(df2.index, var_smoothed, \"r-\", label=\"moving average\")\n", "plt.xlabel(\"t\")\n", "plt.ylabel(var)\n", "plt.legend();\n" ] }, { "cell_type": "markdown", "id": "ed438236-34f5-4cee-b606-be3aaf141d9f", "metadata": {}, "source": [ "**Question** : why would you sometimes want to use a moving median instead of a moving average ? Try it yourself!" ] }, { "cell_type": "code", "execution_count": 30, "id": "e7ab2737", "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAA04AAAHACAYAAACVhTgAAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAADsfElEQVR4nOydd5hTZdrG75zU6cNQhqEOvTdpgmJFsXfFrqjs2gvurqKu+tld66qoa0GsKyr2gqsIKkUQkCK99xna9JnUc74/Ts1JMklmMpMQ7t91cXFy6ptMynuf53nuxyJJkgRCCCGEEEIIIRERkj0AQgghhBBCCEl1KJwIIYQQQgghJAoUToQQQgghhBASBQonQgghhBBCCIkChRMhhBBCCCGERIHCiRBCCCGEEEKiQOFECCGEEEIIIVGgcCKEEEIIIYSQKNiSPYDmRhRF7N69Gzk5ObBYLMkeDiGEEEIIISRJSJKEqqoqtGvXDoJQf0zpsBNOu3fvRseOHZM9DEIIIYQQQkiKsGPHDnTo0KHefQ474ZSTkwNAfnFyc3OTPBpCCCGEEEJIsqisrETHjh01jVAfh51wUtPzcnNzKZwIIYQQQgghMZXw0ByCEEIIIYQQQqJA4UQIIYQQQgghUaBwIoQQQgghhJAoHHY1ToQQQgghJLlIkgS/349AIJDsoZDDALvdDqvV2ujzUDgRQgghhJBmw+v1Ys+ePaitrU32UMhhgsViQYcOHZCdnd2o81A4EUIIIYSQZkEURWzZsgVWqxXt2rWDw+GIyc2MkIYiSRL27duHnTt3okePHo2KPFE4EUIIIYSQZsHr9UIURXTs2BGZmZnJHg45TGjdujW2bt0Kn8/XKOFEcwhCCCGEENKsCAKnoKT5SFRUk+9aQgghhBBCCIkChRMhhBBCCCEpyoMPPojBgwcnexgJ5eqrr8Y555yjPT7uuONw++23J208sZJ04TRlyhQUFxfD5XJh5MiRWLRoUb37l5eX46abbkJRURGcTid69uyJb7/9tplGSwghhBBCSPPxt7/9DbNmzUr2MJqUTz/9FA8//HCyhxGVpJpDTJ8+HZMmTcKrr76KkSNH4vnnn8e4ceOwbt06tGnTJmR/r9eLk046CW3atMEnn3yC9u3bY9u2bcjPz2/+wRNCCCGEENLEZGdnN9pGO9UpKChI9hBiIqkRp2effRYTJ07EhAkT0LdvX7z66qvIzMzE1KlTw+4/depUHDx4EJ9//jmOOuooFBcX49hjj8WgQYOaeeSEEEIIIeRw4rjjjsMtt9yC22+/HS1atEBhYSFef/111NTUYMKECcjJyUH37t3x3XffBR33888/Y8SIEXA6nSgqKsLdd98Nv98PAHjttdfQrl07iKIYdMzZZ5+Na665BkBoqp6a5vb000+jqKgILVu2xE033QSfz6fts2fPHpx++unIyMhAly5d8MEHH6C4uBjPP/98xOennvexxx5DYWEh8vPz8dBDD8Hv9+Pvf/87CgoK0KFDB7z11ltBx+3YsQMXXXQR8vPzUVBQgLPPPhtbt27VtgcCAUyaNAn5+flo2bIl/vGPf0CSpJDX1piq9+6772LYsGHIyclB27Ztcemll2Lv3r3a9jlz5sBisWDWrFkYNmwYMjMzMXr0aKxbty7i80sESRNOXq8XS5YswdixY/XBCALGjh2LBQsWhD3myy+/xKhRo3DTTTehsLAQ/fv3x2OPPVZv12mPx4PKysqgf+nI6t2VuOLNhfhje1myh0IIIYQQEjuSBNTUNP8/0+Q9Ft5++220atUKixYtwi233IIbbrgBF154IUaPHo2lS5fi5JNPxhVXXKE19921axdOO+00DB8+HMuXL8crr7yCN998E4888ggA4MILL8SBAwcwe/Zs7RoHDx7EzJkzcdlll0Ucx+zZs7Fp0ybMnj0bb7/9NqZNm4Zp06Zp26+88krs3r0bc+bMwYwZM/Daa68FCY9I/PTTT9i9ezd++eUXPPvss3jggQdwxhlnoEWLFli4cCGuv/56/PWvf8XOnTsBAD6fD+PGjUNOTg5+/fVXzJs3D9nZ2TjllFPg9XoBAM888wymTZuGqVOnYu7cuTh48CA+++yzesfh8/nw8MMPY/ny5fj888+xdetWXH311SH73XvvvXjmmWewePFi2Gw2TWw2GVKS2LVrlwRAmj9/ftD6v//979KIESPCHtOrVy/J6XRK11xzjbR48WLpww8/lAoKCqQHH3ww4nUeeOABCUDIv4qKioQ+n2Rz1ktzpc53fS0d/9TsZA+FEEIIISQsdXV10urVq6W6ujp9ZXW1JMkypnn/VVfHNfZjjz1WOvroo7XHfr9fysrKkq644gpt3Z49eyQA0oIFCyRJkqR77rlH6tWrlySKorbPlClTpOzsbCkQCEiSJElnn322dM0112jb//Of/0jt2rXTtj/wwAPSoEGDtO1XXXWV1LlzZ8nv92vrLrzwQmn8+PGSJEnSmjVrJADS77//rm3fsGGDBEB67rnnIj4/9bzqdSVJnnuPGTMm5Dn/97//lSRJkt59992Q5+fxeKSMjAzp+++/lyRJkoqKiqR//etf2nafzyd16NBBOvvss4Ne29tuuy3i2H7//XcJgFRVVSVJkiTNnj1bAiD9+OOP2j7ffPONBCD4vaUQ9n2nUFFREbM2SLo5RDyIoog2bdrgtddew9ChQzF+/Hjce++9ePXVVyMeM3nyZFRUVGj/duzY0Ywjbj6W7ygHAGzeX5PcgRBCCCGEpCkDBw7Ulq1WK1q2bIkBAwZo6woLCwFAi+6sWbMGo0aNCuojdNRRR6G6ulqL2lx22WWYMWMGPB4PAOD999/HxRdfXG+vq379+gU1ci0qKtKuuW7dOthsNhxxxBHa9u7du6NFixZRn1+/fv2CrltYWBj0/NTnrF5r+fLl2LhxI3JycrRarIKCArjdbmzatAkVFRXYs2cPRo4cqZ3DZrNh2LBh9Y5jyZIlOPPMM9GpUyfk5OTg2GOPBQBs3749aD/j36OoqAgAYoqsNZSkmUO0atUKVqsVpaWlQetLS0vRtm3bsMcUFRXBbrcHvVH69OmDkpISeL1eOByOkGOcTiecTmdiB08IIYQQQhJDZiZQXZ2c68aJ3W4PemyxWILWqQLJXLNUH2eeeSYkScI333yD4cOH49dff8Vzzz0X9zjiuWY8563vWtXV1Rg6dCjef//9kHO1bt26QWOoqanBuHHjMG7cOLz//vto3bo1tm/fjnHjxmnpf+HG25DXPl6SJpwcDgeGDh2KWbNmaT7uoihi1qxZuPnmm8Mec9RRR+GDDz6AKIqaGl6/fj2KiorCiiZCCCGEEJLiWCxAVlayR9Ek9OnTBzNmzIAkSdrEft68ecjJyUGHDh0AAC6XC+eddx7ef/99bNy4Eb169QqKFsVLr1694Pf78ccff2Do0KEAgI0bN6KsLPF18EcccQSmT5+ONm3aIDc3N+w+RUVFWLhwIY455hgAgN/vx5IlSyI+x7Vr1+LAgQN44okn0LFjRwDA4sWLEz72hpDUVL1Jkybh9ddfx9tvv401a9bghhtu0JxJALmwbfLkydr+N9xwAw4ePIjbbrsN69evxzfffIPHHnsMN910U7KeAiGEEEIIIWG58cYbsWPHDtxyyy1Yu3YtvvjiCzzwwAOYNGlSUErcZZddhm+++QZTp06t1xQiFnr37o2xY8fiL3/5CxYtWoQ//vgDf/nLX5CRkRGUMpgILrvsMrRq1Qpnn302fv31V2zZsgVz5szBrbfeqqUi3nbbbXjiiSfw+eefY+3atbjxxhtRXl4e8ZydOnWCw+HAiy++iM2bN+PLL79MmR5PSRVO48ePx9NPP437778fgwcPxrJlyzBz5kwtP3T79u3Ys2ePtn/Hjh3x/fff4/fff8fAgQNx66234rbbbsPdd9+drKdACCGEEEJIWNq3b49vv/0WixYtwqBBg3D99dfj2muvxX333Re03wknnICCggKsW7cOl156aaOv+84776CwsBDHHHMMzj33XEycOBE5OTlwuVyNPreRzMxM/PLLL+jUqRPOO+889OnTB9deey3cbrcWgbrzzjtxxRVX4KqrrsKoUaOQk5ODc889N+I5W7dujWnTpuHjjz9G37598cQTT+Dpp59O6LgbikWSGuDFeAhTWVmJvLw8VFRURAwpHooU3/2Ntrz1idOTOBJCCCGEkPC43W5s2bIFXbp0SfgknkRm586d6NixI3788UeceOKJyR5Os1Pf+y4ebZC0GidCCCGEEEJI4vnpp59QXV2NAQMGYM+ePfjHP/6B4uJirc6INAwKJ0IIIYQQQtIIn8+He+65B5s3b0ZOTg5Gjx6N999/P8Qhj8QHhRMhhBBCCCFphGrnTRLLIdUAlxBCCCGEEEKSAYUTIYQQQgghhESBwokQQgghhDQrh5mpM0kyiXq/UTgRQgghhJBmQTUnqK2tTfJIyOGE1+sFAFit1kadh+YQhBBCCCGkWbBarcjPz8fevXsByA1ULRZLkkdF0hlRFLFv3z5kZmbCZmuc9KFwIoQQQgghzUbbtm0BQBNPhDQ1giCgU6dOjRbpFE6EEEIIIaTZsFgsKCoqQps2beDz+ZI9HHIY4HA4IAiNr1CicCKEEEIIIc2O1WptdM0JIc0JzSEIIYQQQgghJAoUToQQQgghhBASBQonQgghhBBCCIkChRMhhBBCCCGERIHCiRBCCCGEEEKiQOFECCGEEEIIIVGgcCKEEEIIIYSQKFA4EUIIIYQQQkgUKJwIIYQQQgghJAoUToQQQgghhBASBQonQgghhBBCCIkChRMhhBBCCCGERIHCiRBCCCGEEEKiQOFECCGEEEIIIVGgcCKEEEIIIYSQKFA4EUIIIYQQQkgUKJwIIYQQQgghJAoUToQQQgghhBASBQonQgghhBBCCIkChRMhhBBCCCGERIHCiRBCCCGEEEKiQOFECCGEEEIIIVGgcCKEEEIIIYSQKFA4EUIIIYQQQkgUKJwIIYQQQgghJAoUToQQQgghhBASBQonQgghhBBCCIkChRMhhBBCCCGERIHCiRBCCCGEEEKiQOFECCGEEEIIIVGgcCKEEEIIIYSQKFA4EUIIIYQQQkgUKJwIIYQQQgghJAoUToQQQgghhBASBQonQgghhBBCCIkChRMhhBBCCCGERCElhNOUKVNQXFwMl8uFkSNHYtGiRRH3nTZtGiwWS9A/l8vVjKMlhBBCCCGEHG4kXThNnz4dkyZNwgMPPIClS5di0KBBGDduHPbu3RvxmNzcXOzZs0f7t23btmYcMSGEEEIIIeRwI+nC6dlnn8XEiRMxYcIE9O3bF6+++ioyMzMxderUiMdYLBa0bdtW+1dYWNiMIyaEEEIIIYQcbiRVOHm9XixZsgRjx47V1gmCgLFjx2LBggURj6uurkbnzp3RsWNHnH322Vi1alVzDJcQQgghhBBymJJU4bR//34EAoGQiFFhYSFKSkrCHtOrVy9MnToVX3zxBd577z2IoojRo0dj586dYff3eDyorKwM+kcIIYQQQggh8ZD0VL14GTVqFK688koMHjwYxx57LD799FO0bt0a//nPf8Lu//jjjyMvL0/717Fjx2YeMSGEEEIIIeRQJ6nCqVWrVrBarSgtLQ1aX1pairZt28Z0DrvdjiFDhmDjxo1ht0+ePBkVFRXavx07djR63IQQQgghhJDDi6QKJ4fDgaFDh2LWrFnaOlEUMWvWLIwaNSqmcwQCAaxcuRJFRUVhtzudTuTm5gb9I4QQQgghhJB4sCV7AJMmTcJVV12FYcOGYcSIEXj++edRU1ODCRMmAACuvPJKtG/fHo8//jgA4KGHHsKRRx6J7t27o7y8HE899RS2bduG6667LplPgxBCCCGEEJLGJF04jR8/Hvv27cP999+PkpISDB48GDNnztQMI7Zv3w5B0ANjZWVlmDhxIkpKStCiRQsMHToU8+fPR9++fZP1FAghhBBCCCFpjkWSJCnZg2hOKisrkZeXh4qKirRK2yu++xtteesTpydxJIQQQgghhBwaxKMNDjlXPUIIIYQQQghpbiicCCGEEEIIISQKFE6EEEIIIYQQEgUKJ0IIIYQQQgiJAoUTIYQQQgghhESBwokQQgghhBBCokDhRAghhBBCCCFRoHAihBBCCCGEkChQOBFCCCGEEEJIFCicCCGEEEIIISQKFE6EEEIIIYQQEgUKJ0IIIYQQQgiJAoUTIYQQQgghhESBwokQQgghhBBCokDhRAghhBBCCCFRoHAihBBCCCGEkChQOBFCCCGEEEJIFCicCCGEEEIIISQKFE6EEEIIIYQQEgUKJ0IIIYQQQgiJAoUTIYQQQgghhESBwokQQgghhBBCokDhRAghhBBCCCFRoHAihBBCCCGEkChQOBFCCCGEEEJIFCicCCGEEEIIISQKFE6EEEIIIYQQEgUKJ0IIIYQQQgiJAoUTIYQQQgghhESBwokQQgghhBBCokDhRAghhBBCCCFRoHAihBBCCCGEkChQOBFCCCGEEEJIFCicCCGEEEIIISQKFE6EEEIIIYQQEgUKJ0IIIYQQQgiJAoUTIYQQQgghhESBwokQQgghhBBCokDhRAghhBBCCCFRoHAihBBCSFrj9YvJHgIhJA2gcCKEEEJI2vLCrA3oc/9MLN9RnuyhEEIOcSicCCGEEJK2PPvDegRECQ9/vTrZQyGEHOJQOBFCCCGEEEJIFCicCCGEEJL2+EQp2UMghBziUDgRQgghJO3xB2gQQQhpHBROhBBCCEk4N32wFBe8Mh+BJEZ6/theBgDodmAHLn3rMdRcegXwr38BUuLHNG3eFhz95E/YfqA24ecmhKQGFE6EEEIISSiiKOGbFXuweFsZVu+uTNo45m3cDwC4/rcZuGzZTGT99z3grruAtWsTfq0Hv1qNnWV1ePy7NQk/NyEkNaBwIoQQQkhCqfMFtGUJyYs4qf2bcj3VwRsqm07MJTPCRghpWlJCOE2ZMgXFxcVwuVwYOXIkFi1aFNNxH374ISwWC84555ymHSAhhBBCYqbWqwunZOoIj1LX5Aj4gjf4fGH2Tgwuu7XJzk0ISS5JF07Tp0/HpEmT8MADD2Dp0qUYNGgQxo0bh71799Z73NatW/G3v/0NY8aMaaaREkIIISQW6gzCybjc3KgRJ6ffJJS83ia7psOW9KkVIaSJSPqn+9lnn8XEiRMxYcIE9O3bF6+++ioyMzMxderUiMcEAgFcdtll+L//+z907dq1GUdLCCGEkGjsr/EAAPLrKhFYswbYuLFJDBmi4WvCiFOV2wcpzHOicCIkfUnqp9vr9WLJkiUYO3astk4QBIwdOxYLFiyIeNxDDz2ENm3a4Nprr416DY/Hg8rKyqB/hBBCCGkaajx+nPfyfPTctxW/v3QFjj5zDNCjB3D99c0+FjXiFCKcGhlx2ri3GgMe/B9ufH8pAKDa49e2uX3Ji7CRQ486bwAz/9yDKnfTpY+SxJFU4bR//34EAgEUFhYGrS8sLERJSUnYY+bOnYs333wTr7/+ekzXePzxx5GXl6f969ixY6PHTQghhJDw7C6vAwD02rcNdtEgIv74o9nHoqfqmYRSI4XTOwu2AgC++1Oeq9w9Y4W27dOluxp1bnJ4cf8Xf+L695bi5g+a//NB4ueQiidXVVXhiiuuwOuvv45WrVrFdMzkyZNRUVGh/duxY0cTj5IQQgg5fAko6WuCZGo46/eH2btp8Sqpes6AfG2/zS5vaGSqntk57+sVexp1PnL48vGSnQCAn9fvS/JISCzYknnxVq1awWq1orS0NGh9aWkp2rZtG7L/pk2bsHXrVpx55pnaOlGUvxRtNhvWrVuHbt26BR3jdDrhdDqbYPSEEEIIMaOKCqsinPwWATZJBALNn8KmRpxcATnC5M3Igq2qvNERJzEJ9VqEkOST1IiTw+HA0KFDMWvWLG2dKIqYNWsWRo0aFbJ/7969sXLlSixbtkz7d9ZZZ+H444/HsmXLmIZHCCGEJBnlfiYcSv8mrxrlSUrESR6DGnHyZGTJGxoZcRLF6PsQQtKPpEacAGDSpEm46qqrMGzYMIwYMQLPP/88ampqMGHCBADAlVdeifbt2+Pxxx+Hy+VC//79g47Pz88HgJD1hBBCCGl+/IqqsCvCySfYAHiSI5z8cpRLNYdwuzKVDY2LOC3dXqYtq859hJD0J+nCafz48di3bx/uv/9+lJSUYPDgwZg5c6ZmGLF9+3YIwiFVikUIIYQctqhpbHbIgsJnVaYaSUhv01z1FHMITTg1IuK0Ymc5Nuyt1h4//u1aXDC0Az5RalUIIelL0oUTANx88824+eabw26bM2dOvcdOmzYt8QMihBBCSINQAzB2izHihOTUOAVEQJJgVxrg1jkbH3Hasr8m6PHUeVtw8/HdtcfDi1s0+NyEkNSGoRxCCCGEJAzVHMKuRJj8asQpCYVBXr8Iu6inCNY5XPJCIyJOtd5QARgwRNPUuipCSPpB4UQIIYSQhKGn6qkRJ6uyofmFky8gwWroJeW2Ky67jYg41XhCa7WM9uQ+P2ueCElXUiJVjyQWSZJgsViSPQxCCCGHIX4xuMbJLyQ34mQ1XNdtcygbGi6cqhXh1LG8BO9O/yda1paj4vOeePuMB+CxOWgWQUgaw4hTGsL2EoQQQpKFqAgnmxpxsiavxsnjF7V+UgBQa1dS9TyeBp/zy+W7AQA3LvgIxeV7kOOtQ4d1y3HU1mUAgLJaH6b/vh1lNY1z7iOEpB4UTmkIdRMhhJBkERDNrnrJS9Xz+gOwGVL1NOHkdjfofFv312DzPtkc4oTNi4O2nb5uLgBgf7UHd81Yib++u6RB1yCEpC4UToQQQghJGKpRghpxSmqqXkDUapwCFgG1aqpeXV2Dzrf9YK28IEnIdcsCandBEQBAMD2/RVsPNugahJDUhcIpDZGYq0cIISRJiJqrnlrjlGxzCHUcAmqtjRNOKjneWmT45XS/6SPPBgBk+hoWxSKEHDrQHCINoWwihBCSLMwRJ6/Vrmxo/hqngCjBJsnXFS1W1ArKWBqYqqfSpkqOJlU6s1BizwYAZPhkIdWitgIvf/EE/izsBuD0Rl2HEJJaUDilIQw4EUIISRZqjZMtyREnNftCTdXzCwJqVOHUwIiTR7EaL6w+AAAozS5AuSBHsVThdPKG3zBq+0qM2r4SqKwEcnMb/BwIIakFU/UIIYQQkjBU4aS62SWrAa7aWklN1QsIVl04NTDiVOuVrciP2L0WgCyc6pTeUMN3rcbAPevx5MwX9QPWrGnQdQghqQmFUxpgrmmSmKxHCCEkSZiFU7Ia4Grj0CJOVlQraYPbdu7H9e8uibsm2O2Tz9WmugwAYBcDqHZmats/f+fO4AM++aRBYyeHB8b3n8PKKfmhAP9KaYD5e5+peoQQQpKFKJlT9ZLTx0kfh1rjJKBaSaurK6/CzFUluktejHiVVD2XIJ97VZuu2FTQQdsumG9cLg62LCfEiHG+lpdpT95ASMxQOKUB1EmEEEJShYASWBLUiFOSUvUkU6qeX7DCrYg4uxKF8gXiG5Na49QpS46iedsUotqZCREWbZ9auxN3nD5JfrBpU4PHT9If0aCceNP70IDCiRBCCCEJI6AIFVuSU/VEkzlEQLAiYLEGrRPjnKx6FaHlEOVaJzgcCAhWbClop+2zLb8Ia9p0kR/s2JEUG3ZyaGB8+7GVzKEBXfXSgJAaJ372CCGEJAm9tijZ5hDB4whYBAQE+X6xWn8lxvmDqabqOfw+AIDkkI0hLh//CIbvXA0AWNixHw5m5ukHbdwI9OzZwGdB0hnj2y/e9yJJDhROaYD5o0ZzCEIIIckioKbIme3IJUn+Z7FEODKxqNEktcYpIFi1sagRp3jnqqpwsgfUiJNcl7IntzW+7Hts0L57s1qgTU2ZXOdE4UTCYBRL/gDnbocCTNVLA2gOQQghJFUQTa56WgNceWOzjUMyRZz8ggBRiTjZtFS9hkWc7AE54gSnK2j76QOKtOVyV468UFER38DJYUmVx699dkjqQuGUBjDCRAghJFUIKGJEMNiAazSjcDLbkQcEK/xKjZNqXBF3xEmpcbIpqXqC0xG0/doxXbTlJe17ywsHDsR3EXLYYH7/HajxJmcgJGYonNKAkIhTcoZBCCGEhPZxshqqAppROGmpemp0SbAioIg4W2NT9RThBJczaHuuS3+u5Rm58sL+/fFdhBw2mCOezZTFShoBhVMaQmcWQgghycJsDuETkiOcJFMfp4Bg1c0hGpmqFy7iJFiATIf+XA+qwokRJxIB87uPBhGpD4VTGsCIEyGEkFRBFU4hfZyAZm2Cq0ac7MqvojHi1FBXPY+WqienVAkuvcbJJgjIdOhpiWWZjDiR+jHf6A6wxinloXBKA1jjRAghJFUw24D7kxRxErWIk2JHbtVrnDRXvTjPqUacrH7ZVU9w6ql6VsECl90gnDIUcwhGnEgEzDqJwin1oXBKQxjpJYQQkixCI07JMYdQhZNdUmuc9D5ONmUc8bqYacLJJ0ecLK5g4eS0CShumQkAKGONE4kGhdMhB4VTGhAilPi5I4QQkiRCXfWSVeMk/69GnEJS9Rpwl1EXTnKNk9UUcbJYLPj2tjEAgCqHLKBQWdmg8ZP0x5wxROGU+lA4pQFsgEsIISRVCASCXfWC7MibtcYpTKqeYSw2MRB/qp5S4yT41BonXTjZBNkSzW6Vp1aqSGvO50wOLZiqd+iRMOG0Zs0adO3aNVGnI3FAFz1CCCGpgh5x0oWTpPosJ6GPk2Y9brFCtOjTHkGS4k7V89UjnKyKcLIqz1VNC6RwIpEIMYfgfC7lSZhw8nq92LZtW6JOR+IgJOLEzx0haUtppRs7y2rhDzTfBJSQeFDFiCqcAoIAqCKiGYRTRZ0PkiTprnqGiJNoaJRjkcSQO/7RUFP1VOFkDXLVk88tCBYIFiBgoXAi9WN++/kDnMClOrbou8hMmjSp3u379u1r9GBIw6AdOSGHB+/9tg33ff4nAGB4cQt8fP3oJI+IkFC0iJNqymARIAkCLIFAkwun2ev2YsJbv+P2sT1w+oAiAHrKoCQIQcJJkKS4Mza8frk2SlBrnAzCyWrVz20VLHqqnuLAR4gZsx0++zilPjELp3//+98YPHgwcnNzw26vrq5O2KBInJiFEz94hKQlqmgCgN+3liVxJIRERg2GahEniwCpmaIvf/toOQDg+R834NT+snDKCMjRIZ/NoY8DsqCKN+Lk8YtwBHQhJGQYa5wM5xYsjDiR6Jjef37WOKU8MQun7t2744477sDll18edvuyZcswdOjQhA2MxI7ZDIIfO0IIIcnCnKonCgJgbZ5UPZ8hhVW9e+9UmtV6HU5TxEmMvwGuPwB7wKc9thlqnAT91LAJQrA5hCQBhmsTAoTO1+KtuSPNT8w1TsOGDcOSJUsibrdYLIx0JAm+7IQQQlIFvyac5EhLwGLVIz1NLJwsBnGiiiKXIpx8dqceBQJgkaT4hZNPhMMgnOwZxhonU8TJ8Lg5TTHIoYP5/ceIU+oTc8TpmWeegcfjibh90KBBEPnFkBJQSBFCCEkWoslVLyDINU7yxqYWTvqy+luoCSeH0+SqJ8b9e+n2B9BCTdWzWuFw2rVtVkPIyW61wGu4Fvx+wNgImBCEztcYcUp9YhZObdu2bcpxkEbAPk6EEEJSBdUG3KKm6lkEoJnqfYzJcCt2VgAAXD41Vc8VpKyscabqBUQJvoAEpxpxcjrhMIghm8kcIln9q8ihQ4irHoVTysMGuGlASIokP3eEpCXt8zOSPYSYEUUJr/+yGYu3Hkz2UEgzo/dxUlP1BEjNVOMkGITRPZ+tBAA4/XK2jN8h1yOJSvTLYrAsjwWPX34+mT63vCIrCw5bcHqeik0QgtICKZxIOMwRJvZxSn1ijjh16dIlKHc4HBaLBZs2bWr0oEh88GNGyOFB6xwndpXXAUj9OvPv/izBo9+uAQBsfeL0JI+GNCfh+jg1X41T6Do94iQLJ0mwAqIYtzmE2yePPdMbXjjZjMLJarAjB2hJTmIiwD5OKU/Mwun222+PuG3r1q34z3/+U28NFGk6GHAi5PCgzivfte65byuG7VoD6bVdsJx6KtCxY5JHFsrmfWxRcbji11L1gvs4yQ+auhY6VDmZI06Soq7i7eOkRpyyRVmIISsLDquhZspi7uPEiBOpH/PbjxGn1Cdm4XTbbbeFrDt48CAefvhhvPLKKxg5ciSefPLJhA6OxEaIHTk/d4SkJXU+2db4v/+9By3rKoHvARx3HDB7drKHFgK/hg5fwkecFFHR1DVOYSJOqh253yk74KkiLt4+TmrEKS9gEE4RUvXsxigbwIgTCYs54hlgjVPKE7NwMlJXV4dnn30WTz/9NDp37oxPP/0Up512WqLHRmIlJOLEDx4h6UitN4BcT40smlR27UregOqBN3AOX9S75sERJyVtralT9cKs0/o42dWIk7HGKf6IU66oZNdkZsIZQTipy6LNBsHvZ8SJhMX87qNwSn3iMocIBAJ49dVX0bVrV7zxxht44YUX8Mcff1A0JRl+zAg5PKjz+pHnNqXANeBO9k9rS7F0exkAYOXOCny/qiRo+46DtfhkyU7sLKvF9N+3w+2TJ32SJOHzP3bhp7Wl9Z5fkiR8tHiH9vjhr1fjzblbmL53mGB21Qs0Y6qeECbk5PTJQidgijgJDYw45USIOBmvbVcc9jTByIgTCYM5VZTCKfWJOeL00Ucf4b777kN5eTnuvfde3HDDDXA4HE05NhIjITVO/NwRknZIkoQ6XwAZqqOXSpx3snccrMU10xYDkE0bznxpLgDgspGd8Oi5AwAAxz41O2hCed/nf2LDo6dh1e5K3D59GQDgzauG4cQ+hWGvce7L8zUTCwB4c+4WAMCMJbn49rYxcY2XHHqIZlc9waqn6iXBHMKpmEP4HaZUPVGMr8bJZ6pxysxEpkM3gDhQo9d5qxEnSbUrZ8SJhMGskyicUp+YhdPFF1+MjIwMXHLJJdi2bRvuvvvusPs9++yzCRscaRj82BGSfngD8t1xp98XvCHOCdnOMl3QGK1w31+4XRNO5t9uX0DCzrJa7KnQRdu1by8O65ZXUuHGsh3l2mNBDGDYrjVoUVeJ1eVdAVA4pTvh+jhpEadm7OOkokac/E4XIOrmEPGm6nkD8vNxKoIQLhdyXHoD3LIa/bNpV0wjKJxI/TDidKgRs3A65phjotqNR7MrJ01DqDkEP3iEpBturzJpU9OEVBoxIav1xX6sxy+iyu2Lul+d6ZwXrfgBT3z/kr7iqYuAnJyYr0sOPTThFFAjTs1pRx46D3FowskJ1CkNeaGk6sUxHJ8inFySknZnyrqp8erpeGoKnyYYmapHwkBXvUOPmIXTnDlzmnAYpDHwc0ZI+uNWCtPViFPAIsAqiXFPyIw3WspqgkWYKEoQhPA3wERRQrUn+rXMRweJJgBYuBAYOzamsZJDk4DJjrw5a5zCp+oZapzqDHbkiDPi5Jf3dagRJ5NwqvXoNw1Um3LRqkyzGHEiYTAHmPyMOKU8cZlDVFZWQgzzpSeKIiorK8McQZoD88eMQoqQ9EPt4ZQD+f9axSEs3gmZ2xAR2l8d3HvPeMc85Pq+AKrc0YWTelceALI9taE7LF0awyjJoYzawzNsql4SzCEcSo2Tag4hKoYNco1T7Of2aal64SNOXsN7X03VExlxIvVgzhgSKZxSnpgjTp999hnuuusuLFu2DJmZmUHb6urqMHz4cDz99NM488wzEz5IUj9MzSPk0GTbgRq8+vMmlNf60K11Niad1DNixEeNOOVa5AlYnd2FHG8dpEAA9362Eh8s3I6zBrXD4B8/wzVTH8bmrv1Q3b4Teq77Ax4IWP/DPFz4wSqMsxzEU9+8A2fAiwMzrXjBqwupNXNegCBY8ILB2EFl65dAD7uAF3z65LBq/TTkDBkI3Hcf/txdiRdmbdDc+i5Y+SPunvOWtu+yoh4YvGcDcNddqFywCLkD+gL/93/hQwRpxLYDNbjhvaVYvacSI7oU4MguBTiyW0tc+vpCvDVhOI7v1aZJrz/zzxJs3FuFm47v3mzp9GKYVD0xSX2cBDEAh2JH7nNmAHAbapzEuCJO0YSTETVVL1rEae6G/fhxTSnuGNsTeZn2sPuQ9MX89mPEKfWJWTi98sor+Mc//hEimgAgKysLd911F1566SUKpyRAVz1CDk0ue2NhkFnD2L6FGNwxP+y+asQpS6mvqLXLd88DPj8+WLgdAPDzb+vwwtSHAQBdN68CNq8CALgArJ5wM3DSDbjz9fvQ88D2xDyBNQA++wSBvn1xxu8ubXV+XSWe/vZ57fHytj3wzJgr8O5H9wMAcj+fAXw+Azj9dPiHDcdVby1Cr8Jc3H9m38SMK4V49of1WL1HzsgY/e6LuGLpN1jbphi2Cx/ChLd+D2uwkUiuf28JAGBo5wKM6taySa+lEtaOvJlqnMwRJ5dfT0cNuFwA3IYaJykuO3KvX60zVGr9FOF00bAO+GjxTowf1lHbVzOHsNQfcZowbRF8AQnT5m9t8vcCST3Mwp0Rp9QnZuH0559/4uWXX464/ZhjjsF9992XkEERQsjhgFE0AcFpdGY8yqQtS5QnbXVKqp4loE/Ihuxepy3P7TwIP3YfiQdnvQYA6F+yCZAkTTTN7zQQs3uPwuhuLbGr3I3CXCdyXHbM/FPv6TSkUz7Kan3Yur9GWzeuXyG+XyX3cVLPvffjL4Di8do+p6+dqy3PvuUB/DzoWPy6oRbjL3kcffZuwQ0rv0Xh3p3Ajh1Y2LIb5m08gHkbD6SlcDL+jS9e/j1a1lXiqG0r0HfvZqwo6tls4yitdEffKUFowkkRC6LQjDVOpsdBwsmhNMBVorpCAyNOdlPE6d7T+2JUt5Y4oZduz69FnKK4CfoCnCgfzjDidOgRs3AqKyuDv54cXZ/Ph7KysgYNYsqUKXjqqadQUlKCQYMG4cUXX8SIESPC7vvpp5/isccew8aNG+Hz+dCjRw/ceeeduOKKKxp07XQgJOJEQ3JCDknqm8Tpjl5qjZMS4THUVfQrlV1PlxX1xOUXP6rt96+ZL6B1TRmO3LFS2/e2M/+G7gN74N6/HBl0ndsfm4USZZL9oHIHfMy/fsKOg3Xaukvu/gYA0LZqP65f9CkyV/8ZJJzGrV8gL5x4Io5/4UH0q3Rj2mOzsLDTACzsNADjDm6QhdPu3fAOaNqJdLLRMi8lCS3q9Frg/qWbsKJtjya9tvHudXNmRKrOYEZzCLHZXPWCH2coxhBwuWBRrMFFi1LjJMXXx8mriBxHIFg45WXYce6QDkH7OpQGuAHakZM4iEfIk+QQszlEcXExFi9eHHH74sWL0blz57gHMH36dEyaNAkPPPAAli5dikGDBmHcuHHYu3dv2P0LCgpw7733YsGCBVixYgUmTJiACRMm4Pvvv4/72ulCqB15kgZCCGkU9X121TShDMWOXBVOapNRABi+czUAoNyl231vbCWnD3WqKMWZa37R1u/LLoDdFvoTYDR3iMbaNl0AAHkr/wh6EsdsVR4feywA/e67Skl2gbywZ0/a12iqjVBzvLVwGqKDj30/BV+9fTvg9UY4svGodXHNTWiNk1WL8jR7qp4qnDIztb+FGNTHKfZzaxGnQBw1TvWk6pl79sTz2SPpgVko+RmBTHliFk7nnXce7r33XpSWloZsKykpwX333Yfzzz8/7gE8++yzmDhxIiZMmIC+ffvi1VdfRWZmJqZOnRp2/+OOOw7nnnsu+vTpg27duuG2227DwIEDMXfu3LD7Hw6ERpwIIYcisUScMpT6CreaqidJsEjytuKy3QCA9a06aceta6Xf0Dp2s1zv8kN3OaIfzocinjue8zsN1JZVB70CQ1QFl18OIIxwysyXF3bvDvr+SkcRpU7W21eE3gwcULoJWLGiya5dazD+aM472QHDexIw1Tg1szmEy68Ip4wMbZsqnOJO1fPHLpzUGqeAEDniZLb3r4nB7p+kF+zjdOgRs3C6++67kZOTgx49euDGG2/Ev//9b/z73//GDTfcgJ49eyI7Oxt33313XBf3er1YsmQJxhp6egiCgLFjx2LBggVRj5ckCbNmzcK6detwzDHHhN3H4/GgsrIy6B8hhCSbH1bLN6GO2roMX7x9B76bejOGnHEscMMNYUNPP6/fBwA4bc4nAIAqp27U06qmHP/972QUl+8BAPzWaYC2rcaZiUqHvG+HSvkc3/U6CgAwvLgg5Don9pHrNDoWZER9DntzWsJtkyePfz5/Eb6bejOWvngZAKXZaBc5IqX2tFHZYMuVF955BwWzZmrrP1q8A5e+/hvmbdwf9dqHChal6ubOX98Nv8Pw4cAn8t905p8lmPDWIhww2cSrfLNiD65+a5FmI//Gr5tx/ivz8eeuirD7H6hWolmSBP+VE7CmTRdsKuqGNW26YFuH7nAPPgKYOTPssY1BlCRYDZGlgGDVLMCbO+KU4TdEnJRtUgPNIfSIU7A5RDhChJMp4rS2pBLHPz0HANCitgJXLvkK+z75MvbBRGH+xv244s2F2LyvOmHnJIljQ2kVrpy6SHMhVaE5ROoTs3DKycnBvHnzcPnll2P69Om44447cMcdd2D69Om4/PLLMXfuXOTE2Q1+//79CAQCKCwsDFpfWFiIkpKSCEcBFRUVyM7OhsPhwOmnn44XX3wRJ510Uth9H3/8ceTl5Wn/OnbsGHa/Q5nQPk784BGS6kx8R059vuKPbzCoZAP67NuK7PVrgFdfBXbvDtq3os6H/y7aAQBw1clGDQcy87Ttd8z9AKO26/VLR117HqZNGK49XlnUPeh8tz13B/7vrH64bkyXkHE9eFY/PHBmX3z011HaupuPl48/a1A7AMCPk47Vti3q0E9b7rNvq7bsHjtOW7ZZBbx9zQg8P34wAGBVYTdtW/87/6ot3zVjJeZvOoCbP0ifXk9qimW/0s0AgF87D9YifhovyU2Cr39vCWav24en/7c+7Llu+mAp5qzbhzd+3QIAeOSbNViyrQwvz9kYdv8dB+UoYLeDO3Hhnz+iz76t6FayGX32bUXnXZvgWv4H8OKLjX6OZkRRrh/SHlsEzQK82YWTIVVP3RYQVOEUX42TpwGpen5VOPl8Qdsvf2MRDioNqG+b91889ON/0OOqC4E9e2IeT33c+MFS/LphP574bm1CzkcSy3XvLMYv6/fh/75aHbSeEafUJ2ZzCADIy8vDyy+/jClTpmD//v2QJAmtW7cO2xti3rx5GDZsGJxOZ8IGq5KTk4Nly5ahuroas2bNwqRJk9C1a1ccd9xxIftOnjwZkyZN0h5XVlamnXgyf/HzY0fIoUNh1UEAwDNHX4Y7574vrzTVvXyvON1leWq1mo3XRpyPib9/DkC2/waASmcWTr5mChacMjDIzW3CBf+HaX0CyHdY0OvY4ejcqSOuiuBLkO20YcJRwYLqomEdMbRzCxS3zAIAdG+TjaX/PAnDHvkB115wP4bsXqdNJv92ck+0bJWPTqcdH3SOY3u2BgB8u3IP/rcauOmsuzDlyydh93rkCJvhd6SsNniSeSjjUeqM8pX+W08cPwGrCrtBEAO4Z977uG7+R4AnOMJ0sCZ8xEllt6nPljoBN6M2ZG1TLb/Hdua2wV2n3goAGFiyAXf9/HaISE8EkiRBEINT9cTmEk6m28Gaq15GhrYt2I48nlQ9eV9bDBEnNcrqVyKy5r+xsfl014O79A07dwJFRTGPKRLlymdo1W5m2aQiu8pCe+UBNIc4FIhLOKlYLBa0bt263n1OPfVULFu2DF27do24T6tWrWC1WkPqpkpLS9G2bduIxwmCgO7d5TuggwcPxpo1a/D444+HFU5Op7NJxFsqERpxSsowCCENQJ3U/tLlCNy6/CvYqypD7k6rTXFVVzaPzYEKV7Z+jho53ePR469BSW4rWCwWOO36DNJrs2P0tec0eIwWiwXd2wRnFBRkOXD5kZ3xzoJtWNSxv7b+/Wvq70XTMlv+Pv6hh+7m17GiFDvyI3/nH8qoNvJOZQJf6ZTFpyhYsbhTP1w3HyF/b7u1/mQQl10IumFmNhlQUXt/FSrvsW0t2mJe8WAAQFlGbpMJJ1EyRZyE5qtxihhxysjQtkkw1jjFfm41Vc/mjz3i5FMb4NZjAhJUF9hAd+JIGL8HSOogvxdD33xM1Ut9muwTFUv42+FwYOjQoZg1a5a2ThRFzJo1C6NGjarnyGBEUYTHU/8dunSGQomQQxOLJKJNjTyp3ZtdAMkavh7CpUx+8jxyml5VZo6WbgQAw3atAQCUZ+jixmmzNtm4VTId8d97CygRB6/Nrq0buGcDAMDh9+Hlzx7D+x/eA2zblphBJhk1Vc+iTJy9Vv01qxOU18D0+2WuCTPjtFk1QQbUI5yUvmCqOC/N1hvglqrOhnv3hgi3xiJKEgSTOYTYXH2cTMJp8mzFaMognNTol1VsWB+nWCJOqvjV3uf1zFFy3YY6pHHjgJqaiPvGS7T3EkkOkdoD0Fgx9Un6J2rSpEl4/fXX8fbbb2PNmjW44YYbUFNTgwkTJgAArrzySkyePFnb//HHH8cPP/yAzZs3Y82aNXjmmWfw7rvv4nLFvenwJCTmlJRREELio0VdFeyKnfi+rBaQ1Em1SThl2GURlKMIp5qMbAQsoV/f+zJbaMvOMFbjiUYdV0NRJ+8DS2ThdPHymTht/XwctW0FcOedjR5fKuDxi7CKAQjK39Rj0yfbNTYlG8I0UQ4XcTKKI6dNgMcXXTipDZXViNNeVSwBOJiZi4D6fgvjltsYRAmwGmzyA0Lz9XEyOkVmeN0oqj4gPygu1hwO1ZsOFkhx3Xj0ahGnGFL1lM+f16oIp3oiTrkek1Ay3ExuLM3xPUDixxrO0hRM1TsUSPonavz48Xj66adx//33Y/DgwVi2bBlmzpypGUZs374dewzFkjU1NbjxxhvRr18/HHXUUZgxYwbee+89XHfddcl6CkknxI6cnztCUpoKpf7ghE2/y4+z8+G32sIKp29W7MG1by8GJAlvffx/AGThBIsFHmtwxGdDa92GvDnuNB/do2XQ437tcqMec1JfPSXv1+IhAIC/LvoUG/91Fh768T/6jjNmYF2vIRjx0ExNGOwsq8Xox2fhvs9XBp1zx8FaLS0t1fD4RTj8ekTHY9Un29Xq8pYtGHnT29p6m9I89f2F29Dv/pl4cdaGIOe8N+ZuweCH/xd0DSNnT5mH4ru/wSPfyJHIaxd/AQDYm6ULJ8kioCpf+fsluJ2HJElBqXpSkswhglLgnntOtyOHIeIUR2qUGj20xpCqZ1f+hlqEMULEySoGkO82Od998EHYfQ9Ue4Jqo2KhOSLPJH7MKaUqFE6pT9KFEwDcfPPN2LZtGzweDxYuXIiRI0dq2+bMmYNp06Zpjx955BFs2LABdXV1OHjwIObPn4/x48eHOevhA+NNhBxarN9bBQDoUCHf6c+pkSfFoi00Ve+NubIbW8vaCs1aeW7bPgCA//XQU5qlUaNx/VlHaI53gmDBT3cei4fP6Y/f79VbPiSSoZ0L0EqpWfrPFUPx378cGeUIYGyfNmiXJzfv/XiAPi6bFDqh7rV+GZy7d+E/v2yS91+8E7sr3Hjvt+3aPmtLKjHmX7Nx8vM/N+q5NBUefwCOgC6cJKcDk0/tDQDYlq+bABy1bbm23DJLnpA/87/1qPEG8MwP60OK/I3zqxpvcIRy+Y5ybTlL6a8FAOs69MQ5g9tpj/MPKJGmffvifFb1IxrMIVQb8voawSYSq2FCqpqmlLdoDTgcuqueImasYqBBNU7WWCJOVlPEKYJw6lSuOwj/otxICJc66QuIGPrIjxj2yI+agIuEsVRi0daD9e5LUotI0WOSOjSZcArntEeaBt6gIOTQosotT4w6OOQP77djLwYAiGEiTmokpX+pLB6QkYF5E/8OALjl7Lsw8LYPgd27YZn7K246vju6t9FNI7q2zsYVR3ZG65ymM8j5/d4Tsf6RUzGuX1vkuuxR97dYLLhqdDEAYGGnAeh7x8cYftM7GHPbe9i/bjP63vExet35KeqUNLY21Qfx9vytAIBKd+iEcqbiOLjjYHiXqmTjC4iaMQSsVix/+DRcOlKODNY5XJjRT3YfPHXdPBy1dRnemf5PtNq8DoBsQ69SZXrumd46LR2uxhM52jZm6x/a8tQ3bsfzFw/B38f1AgAsPupUZZCJrnHSzSFERUCI9TSCTSTGqYcayanJkiOhanqUahFuEwNx1jjJ+8YknNRUPfV5R0jV66gIp40FHfBp/xPklVVVIfvV914w4zUVyqRTX7R0IdIMmbop9UmqOQRpGvjSE5LaVLllYZQnKoYBTrnZrGQLX+MEAO0r98oLBQXIdOjpN5WubNm+2OzD3ExYLBZtkhgrNkMaYa0jA/uyC+BpXYiWPYpR68iAx+bAyrZyr6fC6oPaHXa3L/ROe6pPNLx+EU414uRywWmzwmb4W1W4ZEOPMVuX4f3p9+GYrX9g3FNyM3ljGYT6ngGAaxd9htXPXYifXv8rnD4Pqj2RozhFVcqkuagITrv8/spxyf/7hOiObw1BNKTqSYpw0MxMmlE4ZXllMe11ZQZt82nCyR/XXEWNOAm+2M0h3FEiTqoj5q68NqhxKE2nK0IbGsfzu25O3VxfGirESJIxKaccTw3+9e3zuPKRm4ArrgDq6WVKkkujf2m9Xi+qq0M7U1dVVdVrRU4Sh2RKzjM/JoSkFpXKJDhbSb1ThZMYxlVPnTAVVSoT4BNOQIbj0K5bCFewnuW0BWUqqPU4hdUHUKNE3Ty+0El3Kt+kC4gSREm3IodLTlE0Fob/0ENOTdf6DQEo3CzXJlkMsytjtO38VT8BADqXl6BL2W54/aI2qTe/Hv1LlOa4p+s28eqkXjOqcLsb9gQjIEnQUvUkc6peEwsn49N3aZ8v5XW3mCNO8dmR6zVOyt8qhoiTxxIqTo1/o2wllbLKmYVqVTiFmVMZU7iiNUk1p/Ix/Sv1OX7T77ho5Y/o88evwHvvAR99lOwhkQjE5SX71ltvYenSpTjyyCNx2WWXYfLkyXj22Wfh9/txwgkn4MMPP0TLli2jn4gkFJpDEHJoUa0IJ/2OuCKcBD3i5PYFsK/Kg60HapDjqcFfFn0qb+vbNyjidCgSzlHKvEp1gOuxfzs6lG6HtHYtLOV6j5vNq7bAWVUO/5rt6HpAvju7b/EK+AMi2vbvgSqrA25fAPkZDvgCIiTI6U4+vwjBXYeMkt2wChY48nPhLSxCQVbwJLi81ov91V647AJ8O3ahjeTGgfI6WCUR/owMZNstqPMGYAHgFyVkOmwQIMHr9cMLC2yCBa7OcrN1TTgpPQVthidr7IFlZN/P89Fx7zbszmmNoqr92LHgILoekCfZuW7dhe3pb5/H7K7DcGBuAbwOJ5wuJ5w+D9pX7kNAENDt4M6gawO6cKpSzClq9pchK+woZGo8fjhtAmxWAZVuH3KcNlR5/BFTM4MjTs2bqmf8+VN7OPmUz5egCSf5c2YT/XGl6nkbEHGqE0LNIfwGIaN+B1Q7MvSIUxjh5DOk3/kD9Y/ZHHFKhOHA7vI6tM5xRu0xRhpGptd08yLMe4CkBjELp0cffRSPPvoojjrqKHzwwQeYO3cuPv/8czz00EMQBAEvvPAC7rvvPrzyyitNOV4SBgolQg4tlm6XBcDA3+XIgV9JJVL7OAW8PvT+50wAQIfyEsz9j8E1tKjokHfKOr5Xm5B11x4dnKFQmiMLp0uXf49Ll38PvAE8brVh4XWvoqCuEp0HnAWrJOIuAHepB72hHz/69o9Q7cwMuc6IHX/iow/uDlp338k3YvBjk5HlsOL43m3w7co9mPSRbNbw95/fxk2/fQwA9YqLSLzXeZAeTcqSzyAYhFNAsOLlIy/Ajb99EnRc6+OOQiym1P1LN8n1b8dN19atC7ejoUG86vi2WfGNyJryAi4ZeAnOO6I9ehTm4Pkf1+PcIe1x9uD2qHT7MOShH9C9dTb+Pq4XrntnsXaeiWO6IMtpw60n9Ah6TkZzCO093UwRJ6NyyvTJk1GfQ444qUP0K2LO1kBzCEsMwkmNqh70KRedPh147jkAwcImWxFONY4M1NgV4RSmxslYtxQtgmR0YEwEL8zagGd/WA8A2PpE/Q2uSWyYbx3ZRNPnoi41azZJHMJp2rRpePPNN3HJJZdg8eLFGDlyJD766COcf/75AID+/fvj+uuvb7KBksiEpOpRSBGS0rTIlO/UH2xVhIL9e+DOlA0d1FS9muo6APIk6vR1ulV0oH9/WM8/H+JsvTlsriv+JrTJpm2eCwsmnwB/QMKDX67C/hovLhkhR2f++OdJOGvKXCzsdxS2LP8eLerkSWS2pxaOgB/9Sjejx4HtWkSj3JUddG7VEOCiFT9g6vCzg7ZleWpDRBMAnLNqNi74+DQAwJWjOuOdBfLr6/K5NdEUDuO1BVFErrc2ZJ+jDW556Nw57HleGjUel/3xHUSLgBbu8PUoFc4s3dIbgCBJ8AlWtFSd41zZobbWCtVFHZB9wgnaYzVqsLpNF21d0Zcf4e+bT9Qez1m3D0M6tsDGfVUIiBLWlVbh/i/+DDrv679uAQC0zXXh4hG6Fb5sDiFPBPWIU/MIJ2N0RY04qTVOqrjzaRGnQHw1Tn4JkCQIvuipellO5XOp3uQoLta2GVPp9IhTJmoVgRct4uSL0iX1r+8uCXrc2DmBKppI02EXTXWKCU6fJYkj5l/c7du34+ijjwYADBs2DDabDf376ykGAwcODOq3RJqPkFQ91jgRktKohf7qHfH97ToD5bpNst/rgyqctLSs446DdfbskHOdM6R9k4+3KSjKk5/fm1cPD1rfIsuBX/9xAoATgJeuQ/Hd3wAAXp/xEE7auAgFdZU4Zf0CAMC/R1+M58YENz//5L2/Y9iuNbj/p9dx3e+f4fiJ/0GG34NMnxuPfj9F22/iefchw+fBC189hWG71uC6RZ/ijRHn4aPFO7R9jtyu94u65OJH0aFiL7xWG07e8BveOeIMLOw0IOja7Sv2Ittbi3Wti5FXV4XlL1wS/KQ/+yzsa1HryMCg26cHretcthsTFn+JlrUV+KrPMfhfT9l6/t8XD8a3K/fg+1Xhm9Zet+hTDNu1Bi+OGg9BkuCx2fH4/ZdiaIHeHFlNFVTrqwDgzl/ew6f9Tww61+b91XBY9eimOQVM5ftVJUHCSQpjDtFcwsn46+dShJPfqUaclFQ9izHiFJ85hFUSYVGPqUc4FWTK2xa37SmvMDQ59vj11yBbEdtBqXo+n1wTZTi/z2+ocYqzZoklTqmH2XnaZv5c/PZbM46GxEPMwsnn88FpyJF2OByw2/X8ZpvNhkBTh+BJTDDiREhqowonm0e+2+zPyATK9ToQr1svJO+zV76rj+OPD3uuw6VhYlmGbCndoq5SsyrXeuQYeGbM5fjvh/cCANpV7ce6Z88P2Wd9y074oceRyKvTozv3zZ6KN0acFzTJPHPtr9rygs6DtOUv+oX/W+zK01MQKzJy8LfTbsfT3z4vrzjrLCBbj1BZBUu9E+BtLdrhwZNCszhsgqDZYofjjRHnGTMWAeipeSrqpE0UrLjm/PsxdcZDaF8V2stJgt6MFwCqIrj3md0ORaM5hJqqJ4QanzQFxghSYbXcw8jnDDblUF31rGIAUcqFgvAGRNgNPbnqE07ZSiS41q5EkYzCyRcmVc9pEE4AUF4OtNHfT96giFN8n/loESrS/Jg79oREnIqKQFKTuKr8Vq9ejRUrVmDFihWQJAlr167VHq9ataqpxkiicJjMmwhJG6rcPlgkETYlHSPgCnbV83l04ZSvpm5lB6ekqRwucyKjcCpQ0tOWdOgTst+CzoPwyPHX1HuuCy7/FwBZ3Jx+9b+19QW1FfAbXtDjNsn1PNOOOKNBY/5kwFgcccv7GHXDWyHRJlecFu4qNqsl7omw2YzDKLZXtu2hLRub5QKyCYHxWpEar9aaGvCGM4dorhonVYt2KC/B+JU/AAD8yudLnaz6LQ3t4yTCETA813qEk1WwIMthRZ0qnGr119YogrK0iFMmAoJVS9tFmW6Eol5bpT7BHW6bMcJFUhO1xklzVjzIxsWpSlzJ8SeeeGLQ3ZwzzpB/TCwWCyRJYtPbJMHUPEIaz/5qDw5Ue9GrbU6TXkcUJSzfWYFWtXoBdyAjE4Bbuyu/54AsljqX7cYRu5VS/y5dzKcCEHrnMl3RhVMV8hXhpK4z88aI8/C/HqPwy2sTg9ZXOjJx+5l/k3tfKawq7KYtL33xMvz1nHsAyHeA1fqhL/se2+BxH8zMkxdMfbZcdqtmsx4v0VzVzJid0Iy/4/uy9RS+Vc9fpD1/ANj91nq0Ovm4oGP7lm6G12rDxlZ6al5FnQ+Ltx7EoI75sAkWSBJgNUWc1FQ9ye/Hyp3lKG6VFVPD5HhRn1nvfXod4Pqhx2As9FS9OuipevHcePT6RdiNwsle//hzXHbU2pVMHUMpgzHiZHTVA4C6rFy4aqvrFU5+MbJwNu5nD/gwatsKFLu2A0d31MxJSOrRc/92AMC+rHw5CjkrFmsYkgxiFk5btmxpynGQBMIIFCHxM+yRHwEAs/92HLq0aroJxjcr5QnUgz++pq0TlVQiD+RJ5icLtyG7d0f8/Npf9AMHDtQWC3Nd2vItJ3RvsrGmAlePLsa0+VtRliEL2vy6Sq0upCqMa57K9hZF+Pupt+Kp714AAHT/2+fwW8P/5H3bczROWz8fAPCfzx8L2b68qGejnkM4Aw+XvWHOiMf2bI0fVuv1TWcOaoevlu+u9xhzxEkzLghDyPN/Grjl719AFKwYtW25lgZ57fn/xKzuco3U1gO1uODVBRjSKR8zrh8NAFodkGQJjjht21eFs16ah66tsvDT346L8mwbgHJd1QL+t479saeHXI+tRpc8qnAK+OOqF/IFJGSrwsnhiHrXItNhRZXD8B7dsAHo0SMoApTj0V31AMCtGFlgwwbgyCMN1zYKp8hjNkazJi76DP/45R35QekKoIGuxy67ELb5NGk4xndOlqcWZyhpwfuyWqBL2R6gbdvkDIxEJWbh1DmCGxBJPjSHICRxLNtR1qTCaet+udahVY1yR3n4cFiVSfSmcjd6ALBJAQzbuVo7xn/bbbAZGopfPboY60qqMLZPoWaykK7cPraHIpzk6FLrmnI4lcnrycO7YsDAbji2V2sMe+RHDOmUj4JMB2at3QsA+PXos9Ct/4nypN1iwZgerbCnwo1urbNQ5fZj/qYDAIAbz5mMR/73MnoZohRWARjSuQDSVVfjicFD8PdPVmBMj1Zol5eBR8/tD8FiwdqSKrw0ewPOG9IBHyzaji37a3By30JcO6YLRjyq3zG+bkxoM3hjAOqbW4/G6S/MDdnHyOkDi/DSJUNgsVgw+dTecPsCuHh4JxzROV8TTrkuG0Z2baml1P28Xq5bspmE0+hurYIen3nlc/jqnTuwpUUR9mfKEah8dxV6HJCNMn56/Xr83PUIXLX0G+2Yy/74Di1rKlBQV4nveo3Gtvwi/LG9XBMnqqseTHbkG3ZXAL2Azfv1mp9Eov76OQOycPLYHJpwVCN1amTXJsWXqucNiHotSj1pesb9jRE9bNkC9OhhctXTzSEAIKd8f/hzGcwh6os4+gznNr6fsb7hznjFLbOwtiS82yNpGMYMrdY1enTx5SMvxIhP/g+orEzGsEgMxCycVqxYEdN+Aw13RUnzYP4KZcSJkIZjdBFrCtQC+05q0Oj++2H1q25fetH6yB2K9XOPHrA9/3zQOVx2K54bP7hJx5kqZDrkn6kKJb2usPqAtu3BS0YCLvmFbEx/mfJaLwabogcPn90PR4wqhgXAhQAuHNYx5Li+7XLx8mVDAQBj+xYGbdv6xOmaI2BGmOiSYLhev3Z5Ycf16uVDcf17srW0TbBok62W2U68dOkRIfuf1LctnrlINrH4esVuXTiZUvXMEagNnXoBkoTj7/4maP3WJ+V0/OLyPSheGrzthM2LccJmuQbs7p+n4YNB43DPKbdoNUZ6jZN8rYCiFAVzv5oEI2oRJ9nEwWNzaIGhdvmyOFFFnCCKMTvOSZKk1DhF7+GkclLfQrw1byt29RmM9muWaQYRwTVOcsTp6nED8PflddjcczAGLpkT0scn9lQ9ozmG/llBRcN7O8Xr4kfiI0txVy3JLsCydr3klbW1srtilHRQ0vzELJwGDx4cdR+LxUJnvSQQTx8KQkgoxkmJy96wov1YqXLLEy+n2ik+KwvWSnVyqReta256EWqbDhccNgEOq6C5kxXUKndiLRbA4PTa2GuYyUlg/U2491QspWlOw7iEGIrZjO55NkNIyxxxMuOwhn/PX3jpE/g4TN+rcFy6/Hvsz8yH138yAD1VD4IacZL/F+qZ9CcC9bJqqp7b5tBeO/VpGj9nsf5+BkQJkgS9xikG4aS+h+ocwc56asRJEAPIUYSTmJcHoA5+9caNzxd0LqN4qTfiZPgua1NtMBgoL4863kgcLs6dzYnxE5mpvAdq7S5UG1M7q6qAgoLmHRiJSszCafny5cjNDV+IS5JLSMQpKaMg5NClzqff8HHamjbiVKlYkTuU2gZkZsJaLc/o/Mpk1yoGdDe9UaOadDyHAplOK+qUInuHmiqVlZUwZ4xwwiGcmGoo4d5TsQgho3CK5ZkarcODRVQU4RThuf7esX/Q45dGXYSnj7lSi0SZuXXBdOxbeAuAUHMILeLU1H2clB9AlyKcPFYH1KevvubqWKySGLMoUKNEcQknpZbM7KynRoVUK3IAkHLzAJRozXnNwsk4zvrS8Y3RrDaGFDDs2BFm79hgwKlpyVT6jdXZXfBbbaizOZHh98hRQgqnlCNm4TRo0CCMGDEC1157LS6++GLk5DSt8xSJnZAaJ94dIiQuaj36ZM7c8ybRzFm7V77TXLJLXpGVFXIn/Jgtf2DwHqUmYcSIJh3PoUCWw6ZPPrWViatDM6eyJZqwZgwxvM2MgiYvM3oEzBhlMuoym1D/86tPxJ18zUu4aunXWNquD2YqTXh7TZqBB2a9hveGnI421Qdx+7wPtPdr6+OOxs1jLkeXMsWwwmQOUWfoUSZJEpZsK0O1x4/jerVBIhBN5hAem90QcbIEjcUaR6qe2oA2voiT/HffL8qf65XzlqP4Sh9+3SCnUKpRZb8rA4JLvjHgUw1MvN6gcxnHWV/QTo1mZXtqg4QZvF55Ip4XPi20PoJEGx2Uw7J8Rzn2VnlwkillNxLGl9Dll4WT2ya/p6qdGbJw2rfvsM84SEVi/rX4+eef0bdvX9x5550oKirCVVddhV9//TX6gaQZkOp5RAiJxoqd5dpyU35+6rwB1HgDOGrbcn1lQQGsysRWTdM4Zusf+nYKJ2Q6rKh0Zem9gACgZcuEXuP6Y7uhIEufDKv1MI3h7+N64cTebXByv9DJ1Mgu8p1kNRrSXrmeMfqVm2HHUxcMxJFdC3DbiT1CzmGmT5F+Q9NiUGa2MDcDju6uG0Qc2VV+Le8YG+oeuL51Me4ddzNmDDgRNYqLocfuxD2n3ILVhV0xp9swnHPls5jR/wTtmL/9+h7O//MnAIA/S65NU1P1fF49krJsRzkueHUBrn7rdxTf/Q3OemkuxASFN4zmEOpE36pFnJRawjjMIdRIjkOMvcZJUP64B73yNUrmL8aLP23Eh7/vACQJ0/87GQDgK2ip3bBRm/OGRJwMr0t9Y1ZT+gbuCWMG8dtvUcdc3zkB1lBH4uwp8zDxncXYvK86xiP0z6TDUI8HAFp8etGixA2QJIyYI05jxozBmDFj8OKLL+Kjjz7CtGnTcOyxx6J79+649tprcdVVV6Et7ROTAr/ICGkcNYYGnk2Zz19WK0/m2lQbUmjatYNtpZyW9+bwcyBZLMjye3HqgLbIO30c0KpVuFMdVmQ6bahyZuHvp92GYTvX4ILhHeG4/LKEXuPuU3vj7lN7Y/bavdh6oAaDO+Y3+pw3HR/ZKv6e0/qgbW4GTh9YBACY/tcj8cmSnbh0ZCdMX7QDGQ4rerTJRs/CnLDGFEY+vXE0ftt8ABcMNexn0EpmMwgAeOzcAXjy+7XIdthwz2lyI+FbT+yOgCjio8U7UVLp1va9/4y+OKJzC1z82oIgW+q/HNMVv6zfh7UlVXhg7PUozS5Afp0+cRx/ZDFWHX068CcQUESLy6B9tx8Mbri7YmcF/re6FKf0b/hcQq9xUiejdj1VL0zEKdaPuyqcMhTTi1iEk9qnamduG+16/10k9+sxRoM2XXerFhX0CpEiTrEJJxXNxAJAWccuaLFjS4gYixXj5URJghBT4ujhyZ4KN7q2Dt+sPBJqU2VXtnxjQnC5gBpojpQktYirAS4AZGVlYcKECZgwYQI2btyIt956C1OmTME///lPnHLKKfjyyy+bYpykHuiqR0jjqHbrwqkpPz9VynVaWpQJzPnnA9AndLvy2uDjyyZh5u3HNN0gDkGyHPIE4tP+J+LT/ifi3IdOARxNM6k4vndiUsaikeOy47axehSpQ4tM3K5EfG6JIbpk5IhOLXBEpxZB64xT23A1Tp1aZmKKyZnPYrFg0sm9cMHQjjjmqdkAgD/+eRJaKJG4tQ+fir9/vBwfL9kJQBZ/p/Zvi3Nfno9qZyY23n4vPv1jl3a+ix49FVWrSoA//9DEit8wed9b6QkZl3pzoaGo9T/OoBqn4IiTKBhT9WL7wLuVOshMi5LWG4Nwctjk6/3RrjcAoLD6oPYdoDreVTizsP2Cy2FX/kQRI05S+GUz6vNpnSFP75YV9UCb3By0QMOFU3B9FTFjjAaam03HghodzW8hC65tvQYif34J4PfXdxhJEo1K7O7evTvuuece3HfffcjJycE333wT/SDSDPCrjZB4qHQ3T8RJddTLl5TJYaZ8h9E4sc0J0yz1cEe1JFcJF0EhwRjrUOJ9vYyfgXBpfsH76svm965gsYQYMsBgDrG3yg0zjf3LiqaIk9uuCxytn5Pq8CcFYq5x8iiRtizELpxUSnPktEyjy526XJrdEgFR0tJ1YzGHqO87St2k2sGLFgGiNfw5YyUQY5rg4YrRkCNWUxljjZOaqhdQ3qsB9e9F4ZSSNPgX+pdffsHUqVMxY8YMCIKAiy66CNdee20ix0ZiJNQcIjnjIORQpSpIODX9dfJERTgpBgfWIOHEvh1mzLXo0VziSLAAibeY3zg5jnYH3bhvpskEw2IxONkpESeLYZJZGibi1FjfAdUcSatxsjpgUT7UamRXbICrntuvRJxU4RRDfx21zqw0W64ha11bDlvAD7/VhkJNOBVAlCRNoMaWqhf5mup+gvK/aBG0mi400NEw2ByiQadIa9y+xpkLqWmVoiqcIkQdSWoQl3DavXs3pk2bhmnTpmHjxo0YPXo0XnjhBVx00UXISqDDEYkPuugREh81Hj+e+n4dPli4HXed2huv/rwJZ63+GUduXwHHKY8DPVsn/JoBUcI/v/gTue5qXDZzmrwyrHBixMmM2TBAoHCKSn4MLnyRMEb4zMKpuFXwb31+hn4dq0H1WCyyYFP/VD41yqNM3gfvXofjvn4GY80Ncb8EjAn/gy8Yh04P3RPz2NV3imZHbnPApog1q0nE2UQx6u/n1Llb8NDXqwEAhVX7cd/0J+QNGdHNQ9QUx7KMHHgFGxyiHxufPgdf9R6DM9fK5lp7cwpglQC7WuNkiW4OUd+Y1S1WyM85YBEQUGtlGhjBoDlE/Xj8+s2AWNoMmOl2QE59FZUopigw4pTKxPwLfeqpp+LHH39Eq1atcOWVV+Kaa65Br169mnJsJEbYx4mQ+Ji1di+mzd8KAHj469WAJOGFr54CAOyY2gk47rWEX/OntXuxs6wOF6+dq69s3x5AcI0Ve6aE0rsoB7PW7k32MA4pBrTPw60ndEenlvHf1Gyb58Jdp/RGttMakuZ37dFdUFrpxtg+slNgj8IcTDqpJ9rkOLG7XDc8MFuAi2rESRFKk+e8hZE7/ow+mId/wfNbanDN6w9qZgsz/9yD53/cgBcuGYKehcGtUcwNcD02O5xaxEnepvWUEgP1WntLkqSJJgB4+IdXYVOFXrt2UYc+qINs/S1ZBKxr3RkDSjcBgCaaAGBzi/Y4o20OKupkoeSNqcZJf7DjYC3+8u4SXHt0F1wwtIMmqtQ+WqIgaK99QyfixmvX10PqcMVjMEwJxPgFbhS/qshXbyoErI37e5GmJWbhZLfb8cknn+CMM86AlU4fKQVT9QiJD6NQAfQ+GgBgP3gg4dfbVV6Hie8sBgAU1FXKK2024K9/la9puKt/fK/ER7sOdW44rjumzN6U7GEcUqhGDw3lhuO6hV3vslvx0NnBjXFvVcwsnvtBt8A2N531K/8LivBoX1EKAPi877FYVhR+nA/Okm9gHPPTDEybd7V2nevfWwoAuGP6Mnxz65igY7RUPYM5hF80RZw0O/L6U/WMDoKAweK7QwfgscciHqdisVgw967jcfSTs3HWVc/hgpWz8NR3/9a2l994K0ZPvB19inKxZJucuqcJp/pS9QzDevDLVVizpxJ/+3i5IpygPTfAFHFqaKpeUI1Tg06R1qhpnAAw+dOV+OqWo6MeY3wdC2orAAAHe/YFAGw46MZoAH9s3o8hCR0pSQQxCye65aUu5jtATN0jpH48/uAJhNFCud5b0A3kx9Wl2nI3p3LtW27RzCGcdl04tcx2Jvz6hzrZThvOHtwOXyzbneyhkHoQglL1FKGkWYDLk3eL8vlyKnUdr468AGvbhG/yeTAzDy989RQ6lpei1hs66a9yh96RV3/9nIbeOP6AEoUx2ZELUv0NcFUzF5XWNeXywjvvAK1ju8HRoYX8GZcsAj4eeBKuWvo1+iuRp/x/TsZRShsXzY7cEp85RHld8H7qFpvRHKLRESeaQ9SHMeK0cldFTMcYX0e13q2sSw+gBPArqXoL1u2hcEpBmrZdOmke+D1GSFx4/cHi6NlvntWWrdWVCb+e8WZGjrtGXsjL09YZm542pLj4cECdWJLUxZjVp0ec5P/ViJOaqqc6iXmtkWuxVraV+2C1ri1Hmw2rQraHS4sSzeYQNjv8ZnOIoD5OkX9AjW6bWZ5aLYqDgQMjHhONGoehNqqFbiGvmkO4Y0jVk4KWg8evRoe0iJNgMIdIRKpe4u8rHfKYb8TFgjGKl6X09PJnyWmnfjUi2gQ38Ujj4S9RGsAaJ0Liw1jMC0nCoD16ipG9ojzh1zNOPLJU4ZSbq1/TIJYsbC4ZFgrK1Mdo2mHunaRFeUwRJ68tsnDanq83wh369fsh2/1hJpbmBrhum0MTWOpY1ImpTQzUG0ExRpz67d2sbygoiHhMNPZmGfptOfXosnpjQDXRiLUBrlk7auYQhlQ9fyJd9TjDCMEXiP81Mb7tsnyqcJL7OKk1eDazcQpJCSic0gDWOBESH8aIU+uaMmT59H4y+SuWApdf3iQpewAwZOU8ecEQcereRi9wb5vnapLrHupE6ydEko8lKOKkRJhUsQK1xkkEJEmLOHmskfshBQQrnjvqUgBA35+/RUWtD8V36/0iBy+ejdWFXbGmTResadMFezr3xP+9/xCsYgBOpW7RY3NoESctVU+InqrnC4jYekC+yTF052p89MHdAIA/O/RulGf6qyPPx8IO/fDHzZOD1mvugxF6Lhl/12OzI1fNIawJTtVr0CnSmoaURwTZ+Hvl359ApmzkovYZs1I4pST0vU0DQmqceEeIkHoxplZ0LNfrj9w2h+xw9P77wH33Ab17J+R6xk9kmT0Lme5aIEcXS6O6tcQFQzsgL8OOLq3Y2iEcTNVLfQSTHTlgrCtS7MhFP2xiAILyqfDUE3ECgEUd+8kLoojB/zcTsOjvgymfP6HV8qgUYQNO6jbaVOMkBo1PFRJHb1uOt9x1MOP2BTDi0R+1VL3nv35G27b/zPPqHW80VrXtjvGXPYnHzh0QVL+ivl6RzCEiNaEN+bVXVtgSGHEKxGiFfrjSkFdEfUntAR8covw+k4XTQS210i7SVS8V4S8RIeSwwxhxalMjF+auaV2ME697Vd+pKaxgJQmtasvk5REjgjY9feEg/POMvom/ZprQkP4opHkRwkSctEiKoKfqqQ0/AaBvcStt+Ztbj8amx07DD3ccg69ulp3JFnWUHfzsfh/aV+iW9E6fRxMHk8fdjMvGP6JtG7txEfItskjwWO1aKpUq4jw2Pcp1xnfvhDyP37ceDKpvciozpV33P4YxLz0Ssn9D6No6+AaJGpnzCdHNIaQIy/J+8v9qSmRj+zhJkmSyQo/7FGlPQwwz1GOyPbXaOr8ScVKjjrYGCl3StFA4pQEhn1l+sRFSL96ALpxUR6NNBR2wK68N3C0Vt6wE/mipk5t8dxWcAWXy0rZtPUcQM1b+WqU8RnGrmUMIqh25LpxUq3AAyMnTBUS/dnmwChb0KMyBS3GaDAhWVDpkZ7rBSi2iPeDDumfP147776BxmFc8GB8NGAsA6FhRCqtPT9ULqHbkyntobufB2rGt9oU6NZpNJ1pWyi0K2l9xYUhfq4ZibnRttm03pwobh1RfryA148SqpeoJWn1ZQ4ST+VqMOIXSkJdEPSbPLTu61jgzYbHL7wmvIpyMNxhI6sCfojSAuomQ+DDaxxZWy5OivdlywbekpoQlsMbJ7Qso15JFGlq2DCoMJ9GxMlUv5QkWTpag/wMIE3GyWiEJ4SsGLIZzbW9RBEDvd3PGml/NOwMAfi2Wk99yPDUQvKqrnl7jpI6lzuHCPeNuAgC4VLMWA0ZxlOF1w6re7GjZMvwTbwBqM1/tKSj/i+q0zHTjRopQZ2SetGsRJ2WDaLHAL4Q/Zyz4xfARLaLTmIhTrkd+/1VlZGvGQG6b/Nvg8nvDH0ySCn+J0gDzHSDeECKkfjxKxCnLU4urlnwNACjNUYRTI5tFhr2ekhrYRhVO7dol7NyHC4w4pT5BqXpCsKueGkmxSgE4VCFSz80D42R0UQe5zqld5T4AwIkbF2nbbjvjTm15h+LC13fvFm2dnKqnRpz0AVYrtuAZYYST0dmyQ4VeA4n8/IjjjZdsZ/iIk4jwEadINU7mFD51PhDkqoeGR5xChRMnGGYaVuMkH6VGnCqd2drnp9YhGwSpNuUkteBPURrArzFC4uN/q0oAADPfukVz1CvJlu8mS2ohdQIjTvur5bShC1f+KK8oKkrYuQ8XxvSQUygTlSpFEo/xb2PVXPXkx+rkXZBEzVEPLhfOGCh/FtrnG/obIfgGoGpLfv2iT7HxX2fhjHVzAQCvDT8XX/Q7XttvZ16bkDG57U5NdBgjYmo/JZdbrzGRJAnzN+1HSaX8nZBfV4kfpsqRKQwZ0mA3vRxnaFQt25Sqp546oCys3FGG2z/8Q9tujjIt2nIQ3e/5Fqt2633ndpbVaa+bVZJv/IgWq25x3pBUPZPVNucboTTMVU/+/57ZUwEABx2Z2ntAfW9mGtxeSepA4ZQOhPRx4FcbIfXRuaVcV1Gk3MHeWNABa4YdCwCQtBlM4iJOrbPlO+tabQeLfuPmyK4t8fH1o7Bg8gnJHgqJgDG9ThVRVlONk1UU4VKa08LpxNmD2+G/E4/EN7ceHXQuo3nCgs4D4VYMHYwueu8PORUA8OT5AwAA+7NaYE3rYm37nt6DEBCsuPf0vkFjAfTJaYZBOL3400Zc+vpC/O3j5QCAYzcv0Qd06qkxvQbhePic/iGC324KoeoCU16QRBGfL9PrryRTlOnp/60LiQat2VNpqHGS/w8IAnyWxqTqmWqtmKsXQry6yfi3bFEnC9+SnJba56daqeljxCk1oR15GhBiR87vNULqJSBKgCRpk7CLLnsSgzu3xfq1e/UapwR+kNxKql7XHOUr94orEnbuw4nhxQ1vPEqanqCIkxBc46Sm6tnEgB5xcjphsVgwqlto7ZDdKmDDo6fC7Qtg1e5KDMlri2yvLnIqnVnw2J3o0CID44d3Qvc22Tj/lQU4dcKLaF1Thg//ciS69e+G9SLgsAkh46tSJqfGiNOzP+iNsAGg+4Gd8sKAAcCjjzboNQGAc4a0x7h+bXHKv3/BtgO1YffRasFUEw3l+8frF+GwCSG9lA7W6PUvYzcsxE0LPkKbP/th7WMvANB7AIkWQRNjiTGHiPsUaU+8WtK4v1rj9PSYK3C78h5QRX02hVNKQuGUBoQ0wE3OMAg5ZPCLolYDAAB+warll0uWxJtD1HnlSYxW7Otik1uSfljDuOqpgRU1XUyQDOYQUQxS7FYBdquATgWZqHO4UOcI/dzorQWUC1os2JddALGwLSAIcBgCO+FS9TI84YUMALSvVOzPE9DPLcNhhT8Q+ddZ7zGlCE7l+6nOG4DDJsBgBApRkuAwRKwmz3kL3Q7uBL5Zh51XTFSOT1TEiTVO0Yj3NVH3twd8yFTcHytd2VplXa1d/lwwVS81YapeGsDvMULiwx+QYDN0ZRctgpYmIakzviZw1bNTOJE0RjBEdNRl9XOlRj2sYuzCScVs3W3E4w//OQ1XjhScqqdEnDx1EX9Ex6omFEOHxjTOaPgCkb9TtAxh5XWyKGOq9clRIrMJhBpFAyCLJgVbmewSqtY4BSwCvFLi7MgpnEKJ9yVRX8Mcg2ivdmRATXaos8u/DxmKqCKpBYVTGsI+C4TUj1+UtAaRAOAXBIMjWOKFU50mnPSieELSDWPZjhp90l31DOYQqnByOBALWY7IwkmNOJk9QyxhlJMxIqa66gmSBNSEOuvluqu1NCoccURM44xGfd4SZuFkjDgBoXbkqnBymiyru7z+ony88v0lWgR4G9HHyRxx4uwilHjnXOruavPbGrsLomDV3BzVPk52sQmasJNGQ+GUBrCPEyHxERAl2CQ94nRMnyLtR6tJapyUvlE2r3IHkT2cSBoi1GMO4VMjTpKoGzzYYqsWEEyq6PaxPZDlkFP/ehRmAwB6FuYE7RNOoxhbgdXZnXpj2KoqrNxZoW1rX7EXK/59sb7zUUfFNM5o3HNaHwDAVaM6h45N63elR+YAoFYRTkb9IkoSnIpwGrHjz6DzFCxdiA7lJdrxAUGAtxGGNwHTDSTemA0l3ldEjTipWQ9+xclV/TP5rHKPL3vAn9AbeCQxsMYpDQj5IuP3GiH14g+IWvE0ALxy9UjcMn0ZAIOrXhOk6tl8TNUj6YtROKkRH1X0qHbkVlGEXf2RUnumxcDEMV3w2+aDeOjsfhjSqQUGdsjDY9+uxQNnyo55WU4bRnVtiQWbDwRd30iQs53Fghq7C7neWqCqCqsrfNqmIbvXasvSjTfCkpkZ8zjr4+zB7XFk15ZokxN640RrgKvauCuvkSqcAqaIkyqcOpeXhJyrf+mmoD5Ovkak6rEBbnTir3GS/1d/gwKacFJuMlgNU3OfjzfaUgwKpzSA32OExIdflJBpEE5Wm1WvcWoCcwiv2oBTjThROJE0JNhVT/7fZoo4CcaIUxzCSbUUVzmhdyFO6F0YtK5Nrj7BDNfuSzCJqWpnpiycKipQ57Vr68duXAgAWDDqVIyaMiXmMcZCYW74z75uDqGnNAJAjUcWO5Kpxklrql0lC8V3h5yGNtUHMW7Dbxi2czXsWfL0zmu1w4tGmEMEWOMUjYbWOGniVgmFqu9Zr1V/L8LjoXBKMZiqlwaEBpz4xUZIfQTVOCnpQuaJS0KFk1qH4dX71xCSbghBrnrmVD35c2UTAw2KOMWCUbhZwiTrmXsp7c/KlxdKSrSWAQBwzuqfAQD+jMREmmJBfekkzVVPfo2qFeEkmlz1VOFUWH0QAFCaXaCZDYgWAZ13bQQA1DgzdOGUiIgTM8dCiFdMavcNDFFBQP/MeI0RJ29wDRtJPhROaQH7LBASD0E1TppwUjY2QaqeT4s4KfayjDiRNMQoTNRJoBpx8gt6JMWG+CNOsWAzCqdwrnqmlaXZSv+oXbs0Ewaj2cKSY89I6PjqwxIScZJ/yNWIk7mPk3ozpk2NLJz2ZhVgbvFgAECLuirkVpfL+0KAp1F9nEw1Trwx22jUv6V68y6gWPWr707JIsCnpO9ROKUeFE5pQEjEid9rhEREkiQEREkrnjZHnJrCjnzV7krYAn5Y65SGhhROJA0xBnTUZbXGSZ0cWkURtiaLONU/pTGbTOzJaSUvTJsGj1tOo+1+YIe2fXvPQQkdX71jU7921BonJRqhRpyCapzE0IjT3uwClGXkAgAu/PNHLXK1uWV7eNUp+Z49cY/LnKrH+UUoDe3jpEacROV9a6zL0+qcPLQkTzVY45QG8HuMkNhR+5JofZyswY5GWo1TgmYIG0qrAABXLflKX5mTE2FvQg5dhKAap+CIkzo5tDawxikWbGH6SNXHnlxFOC1ciH7ffATkH4lb5n8IANhU0KF+//AEo06aA6aI009r98JisUAUjREnCR6//P3VuroMgCycRMN486rk9btzW6ONsg8WLIh7XOzjFJ34a5zk//WIkyqc9H18gg2AhxGnFIQRpzSApnqExE7AlCYRWuOU2IjT1gNy3UGHyr3yCrsdyM5OyLkJSSWs9dQ4BQymBzapqSJOBuEWQfTMuGEURndrifb5Gfi873Ha+tzd2wEArZW6/E0tOyR0bNEQTDdu1GjE/E0H8PDXq/Hz+n3avsZUvVyv/P1S6crCPCVVDwByqmV79XJXDra2KJJXFgabacQCXfWiE+9rohp92C1mcwj9Peu1KW9ERpxSjpQQTlOmTEFxcTFcLhdGjhyJRYsWRdz39ddfx5gxY9CiRQu0aNECY8eOrXf/wxH2WSAkMppeMtU4GfPLg3ZsJFVu2ea4S4ay4sEHE3JeQlKN8DVO8udJiziJIuzNUOMUKWtvaOcCfDDxSEy57AjsyW2Nd4+7BAAgKY5zRQ55bF/2OSZ8M6gmwnzjRnXVUymr1e3SA6IEX0CEIAa0mqxauwsBwYpKR7ChRYUrG3uzC+QHDYheMOIUnXjnXOpLqkZe1bo249vNY6VwSlWSLpymT5+OSZMm4YEHHsDSpUsxaNAgjBs3Dnv37g27/5w5c3DJJZdg9uzZWLBgATp27IiTTz4Zu3btauaRpw7mYk1+rRESGTXipKXqhdQ4JVo4yTUKWX7lBzArKyHnJSTVCNcAV9UyesQpoEVTmjLiZLYeN2Mel2qc4HDLdYi1dldSfkz1GqfIF5eFkwSXwciiziY7dVa69O8XyWZDncOlpH2hQcLJHHGibgqloXbkduVzoDbANYp9L4VTypJ04fTss89i4sSJmDBhAvr27YtXX30VmZmZmDp1atj933//fdx4440YPHgwevfujTfeeAOiKGLWrFnNPPLUQf3QDtizARMXfgrJH3+vBkIOF7TCXFONk/qjpf0GJjjilOVTfgAT1EyTkFTD1F9W+d8Cq2DRBIqtCc0hhBhS9fSxKm5/JuFkU4RTnb15WwaE9nGKPBv3+kX4/CIyfW5tndvuAABUOXXhZGnRAg6bVTca8PkQLyGuelROIcTrNKj+BhkjTuP6FQaZQ3hs8t8TbnfI8SS5JNUcwuv1YsmSJZg8ebK2ThAEjB07FgtiLGKsra2Fz+dDQUFBUw0z5VE/sl+9cwcAYNWMnsCgu5I3IEJSjNd+2YTN+2rw4Fn9tCJrzVXPGty1PdHmEFv2yzUIHbesllcw4kTSFGsYcwh1OaDcVQ8yh7AldgpilErRIk7qZvVuf2W1fGMjf8sGAECd3YW8THvYY5sCvcZJT9Ubt34+rl7yFQqrDqAkpxXmdx4Ij9UBT5dLUOXxo427Wj4mM1P73tqfma+fND8fDqsAv9Bw4cQap+iYX5OPft+BQR3z0atteBMgyZSq16FVNp4bPxiLthzU9vGwxillSapw2r9/PwKBAApNBYuFhYVYu3ZtTOe466670K5dO4wdOzbsdo/HA4/hjVdZWdnwAaco5jtAOevXJGkkhKQeG0qr8Ni38vdJ19ZZOP8IuehbkMzmEPLDRNuRl9XK6TGZFYqzlb35JmOENCeRIj42waIVwAOAXVT6CSU64mQ0p4iST6NHnOQx+L1e2AO6sOjavQi3ndgjoeOrD3Mfp3x3Nf7z2WP6eMp2Y/T2FQCALz378c4xf8GR21fKGw1zgL3ZLfSTtmgBh02AT32dJQkIBOJ63VnjFB3zS/KPGStQlOfCgsknht1ftyOX/8/LdgEOW7A5hJqqx4hTypH0VL3G8MQTT+DDDz/EZ599BleEviiPP/448vLytH8dO3Zs5lEmAbb2JkRj8/4abfnXDfu1u4NWtUDd5GgkJtgcQr3z7ncq31H9+yfkvISkGkaxZEw7slos+ucKgKOJhJMxyBS9xklx+1M+ny6LhAyffpP12bvPR36mI6Hjq3888v9imHF7rDZMH3AS5naW+0q1KpF7TTlUoWfIuPmt0wD9wJ49YbcKeo0TEHedky9A4RSNcK/JnorIgkczh4A560Hfx2Nlql6qktSIU6tWrWC1WlFaWhq0vrS0FG3btq332KeffhpPPPEEfvzxRwwcODDifpMnT8akSZO0x5WVlWknnkI+sxROhITFJlj0u33qSpNwUlNlElrjJEmwe5Tmt3l5CTkvIalGsDmEvt5qtcBnFE6B4PrCRGEJY04RCXWzGnGyBAKwB/z6Ds0cGTZHnFTWt+yEk697GQAweusyHL1tOVpVHgAAdFOcOi2nnKLt//GAk7C1RTsc18qKmx75KxyvLIbfapjq+XxARgZixVzjRPepUOJ9ScwNcLU626AaJ0acUpWkRpwcDgeGDh0aZOygGj2MGjUq4nH/+te/8PDDD2PmzJkYNmxYvddwOp3Izc0N+pduhBQm8o4QIRrm6VPIj5bWtV1+KCHRwskPR8APQZ0sssaJpCnG9Dih3lQ9JVKSaOFkXI5iJa4KFZ8inISAXxdODkezNr/Vx2S4caPgNphUlGa3BAC0rZaFk+bUaewLZ7Hg9479sWLYcUBODuxWC3yC4XWOs86JNU7RidcwQzKZQ2gRJ8M+dNVLXZIacQKASZMm4aqrrsKwYcMwYsQIPP/886ipqcGECRMAAFdeeSXat2+Pxx9/HADw5JNP4v7778cHH3yA4uJilJSUAACys7ORfZg2lTR/Zi2MOBESloCkf14iRpyExJpDVLn9yDC4X1E4kXQlyA7cZA4hWvTJu9PfNMJJMKUH1r+v/L/mqhcI6LVXjuZL0Qsek+4+qOJ26mUIe3PklLxcTw0yvG7kKOYQyMoCTGa6FmUa7rBZIQpWSIIgzw3iTNVjjVN04rcjl/+3m4UTXfUOCZIunMaPH499+/bh/vvvR0lJCQYPHoyZM2dqhhHbt2+HYLhT9corr8Dr9eKCCy4IOs8DDzyAB9lYEgDtQgkxYvzdtxtS9QTJXOOk7J/gVL1qj1+3DXY4Eu4kRkiqYBQrwREnoVnMIRpS46T10BEDcKiCLmnCCSjNLsDCDv0wZM96OJx2rDzyJG17lSMTfosAmyRizXOGOVB2NlBhOpfycjusSgqgzQ6r1wPU1WHFznJ8vWIPbj2xB7Kd9X8f+VnjFJV4XxPNjlz9jVHSQo3ZpRROqUtK/ILffPPNuPnmm8NumzNnTtDjrVu3Nv2ADjEYcSIkMt6A/nno0CLDEHFSFkJqnBJrDlHt8SNfLTqPo7aAkEONYFc9fb3DJgRFUrSUuIRHnMKPJfy+qqueYv8dCMAhJlc4WWCBKFgx/rIn0T4/A/PuPgFH7q4AXpir7GDR07tUXC7g6KOBbypDzgUAZbXyc7J6le+gdetw1s9K49WAhPvP7FvvmPwhfZwa8szSm3hfk1/X7wcA+KuViKHS288SrsaJqXopxyHtqkdkzJ9Zi98fdj9CDkc8Pj2HxZivbxZOenF24iJOkiTB6xd19ytn8zbVJKQ5CbYD15cdVgGwWCAqn7WmEk6WOOqStD5OSgqhTTSYQyTpcxoUMVNmZ62zg8eysrCbtlzmygEOHgTGjMHcu45HvrHvlHKuzi3lSbk7N19eYUjVW1sSvT2LucYp3mavhwPxRpwe/VZuGeMyNUU3an2txqmurtHjI4mFwikNMKfmWfzxN7kjJF0xRpwComRI1TNHnOSHiTSH8Pjlc1A4kcOBSKl6Dpv8GVMd45pKOMWDKuxUtz+rUTglscbJvKy+dipVTr1Gcna3YVoUu0OLTJzctzDk+I4F8qR8X9fe8oYavT1DLATMqXpMaEkYGX6TcDIoJ7dN+a1gql7KkRKpeqRxhEScAow4EaLi8em/9H5R0tIqQoWTyY48ATkpFE7kcMLoqmcUUXa1zkawAgG/3mi2CWucomG2I7dKhshwslL1DOO3RhBO1c5Mbbm0RXDbFqPwUpccii+8x6mkCdfUAMgLuV4kQl31GHEyY35NCqv2I9sbPVKUYYo4GT8zbrXGqbY2MYMkCYPCKR0wfY8JTNUjRMMccVI/LjaEtyNPZANcryqc/BROJP0JdtXT16uT/4BixGD3KeliCbcjj1056TVOesTJmQKueirqosNqijg59DrJPzoHN9M2Riy0423hhJOyTwyvV6irXtRDDjuMusnp9+J/b96EPE8N8I8TgR49Ih4XIpwMfz9NIFdVJXy8pHFQOKUB5pzj3JV/JGkkhDSc5TvKcfaUeQCA4cUt8PdxvTGiS0GDznWwxoujn/wJtV65vun4Tb/jHz+/jQMDh0I8/i0Aoa56FnPEKSGpevL1s1SvYAonksZEStWzK5P/CmcmMjy16LB7i3JA8iJO6r5qqp5NDCBD/ZwmzRxCR339bFYBVsGiCRhjqt6unFZBxweZY6jHKytXlvvRDwB+/hnoJU/mY6lX8oWYQ1A5mTGKyXaV+2TRBACbNtUrnFymVD2bwVGl2iGvk+bMieN2AGkOWOOUBpi/xzzZeckZCCGN4PxX5mvLv28tw98/Wd7gcz31/TpNNAHA3XPeQp99W3H0rBmw7twJwNDHSevaLj9UC9gTGXHKpHAihwGWCMKppEKu0yioKZf/Pyj3X2zKBrjRUMenNoe1iiIypOR+TiPZqRujThtbdQIAVDoyccH5RwcdHy5Vb+n2MgAGC3jDhCGWrzhzjRNlUyhGAaqlewIQa+pPszNHnGxGV0pReS927JigUZJEQeGUBoTUOJntSgk5BDDn0m870PDc7j0VwfnlvfZv15atJbsBhOvjpESc1B0TaA6RmeQJGSHNgTVMqhgAnNpfrsWZ03UYAEN9YTLNIZQBqjbpVklEZrJT9SK8fsY6p/cHn4JzrngG9z42HVef2Cf4eONByqL6HTSz52h5xfffa7sEYogeqd/LghjA0J2rUbDgZzmSQjSML6PDYM4ViFKfFGIOYfj77cprI5/bE1/DYtL0MFUvDTB/97HGiRzu+Ax1TU5/8A+PtaQEQD6EkD5O8sNE9nHSIk5Scm2OCWkOjKl6xt+lDIc81TiYkWs6ILHCKZ76G80cQos4BeCUUi9VDwgWTpJFwLJ2vXDSEb1C7NeDdZP8wK58v+3ObR1yPTGGF0xNEbx1/oe4fd5/gfchf2du2wZ06BD1+MMBY/qi3WDOFX/ESf87a32c6KqXcjDilIYItCMnhzk+v/5D1rG8JGibtVR+bDW56ml9nNTpSwJd9SicyOGA0RAiKH1JmfhrTmEqCRZO8fQY0j7vgl7j5JJSxxzC+Fo6baFTtXDrgmvMlHXKws5cOYIBt1tzNYzFIU+NOBWX7dZXiiKwY0fUYw8XjPrTGUeqnrmPk9VQ4+SxKu9BNsBNORhxSgPMPxYUTuRQJttTi//74RW0rK0EcpYB994b9zmMBc0dKkqDtllL9gAZvSPakSeyAa5qDuESKZxI+mNM1TPePXcoE8ImF06NjDi5kl7jZKhxiRBxUgknnMKl+qn/V7qyELAIsEoiWteUYXduGwRieL38AZMzqApNIjSML4XdKJziTNUz/s29asTJw4hTqkHhlAYwVY/EwuZ91TjrpXmo9vhx7pD2eG78YG3bpOnLsGl/DT65fpTmgJVIpv++HZM/XYniVlmwCRZkO234+PrR+t3QMvkHxuH34c/nL9IPvG8JUFwMXHZZzNfyB0T8sb1cO9+0T/4vaHvWnFnAqcdHTNVrCjvyDAonchgQKb1MizjZTe//BAunI7u2jHlfvcZJHoNNDOg3OFKgj5MlgjmEitMe+tqFS9U7e3A7zN90AJJFgMdmR6bPg1PXzsObI87F8h3lUcekpuoZTQ8AsBOuAWPkzmFI1ZPq6u/lVJ8duccqCycLU/VSDqbqpQHm+z5WHyNOJJg6bwAnPPMzqj3yl/pnf+wKysv+9I9dWL6jHIu3ljXJ9T//YzdECdi8rwbrS6uxdHs5Nu6t1ra/9stmAEDP/dtCD/7tt7iuta5U73vx2Pcvacseq3yfKJCXDwCwIoI5REIjTvI5XCL7OJH0J9iCXF92KZN8t61phdPQzi0w44ZRWHTviVH31fo4KREnQRKTLpz2VelpWUZr8V3l+gTcbrUg12XDcb1Ca5bCpfpdOFR3ZVNf/4K6SgBAi0x71DH5NeFkuiHLiJOG8ZUwCkzJ0DMrHC0symsaxlXPo0ZnKZxSDgqndMD0BSaYv+DIYY/ZZQ4A3D55Um80UmiqHh3hcumNd9cOVMsGDm2qDwIAtuW3xVunT5Q3RvnxMeM35J/0K5Xdn8pcObjp7MkAAKFSnjQIornGSRlrAoWT+tq6RLrqkfTH+Jk2Rq5V4RRiDtEy9ghRrAztXIA2Oa6o+6kfc7Upr00MwCEm1xyiZ2G2tmwUQacPKNKW37/uSCy6d2zY52gUW6rVhCBY8OZVspvhu0NOAwDkeGpDrhEJNeLkNEecKJw0gs0hDMKptv6Ik1CnpPJlyM2Jg2qcFOFk8XoZ3UsxmKqXBoREnFjjREyE+4mrcvuQ4bAG9TtqKsIJJ2NHer/yw1CoCKf1rTqhyqqIjDiFk1EIqucbf+njyHPLES5rZYX8f0iqXtOZQ2iTjiRNyAhpDsI1YAV04fR1nzFoXVOGUfnA0aP7Auec07wDNKCl6imff6sowpnklNqgiJFhOcupT9WsgkV7Pc0Ya2SMmihbOb5SaZ6b65G/C2P5hlO/m0NqnDiZ1wiyIw8STlFqnLxKNClL/rsY/35qqh4AwOsFXNFvBpDmgcIpDeCNHxKNcO+RSrcfbXLlND4VXzx+vnGg1voYMQocVUQVVh8AAOzLKkCl6ioUp3CqUZ6P0+/VUlJKs1tqVr/WinIAaBY7cvU5asKJESeSxhjrcox92TKUiX6tIwNTRo9H1ajOOPrs/s0+PiOaOYShxsmRQjc4jMLHKJyEeoJExtffuJt6fKVLEU5u+TvV+B0cCTWCH1LjxImHRqQaJ9RT42SRRL3GSRVO4VL1AKC2lsIphWCqXhrQVOlVJH0wRncgSehcthvuTVuwu7wOtV79i74uQdGnnWW12o9ytcePTfvkH+p2lXvxxHcvYO4rE1A44VJsm78U1btLsWX7PnQ9sBPdDuwEAJRmF+CApNxxq6xEpTv2KGqtUsfVWok2eax2VLiytTQh28EDKKrcF+qqJyTeVc+nCEYHa5zIYUbA8PnJMEVIYkkRa2pCIk6SIeKUCnbkhuVspzXs+tiPl4VTWUYeAN1avMrtR1lN/Q1W/ZHMITjv0IhU42SpJ+IU1F9QEU7GGie/1abV5aK6GiR1YMQpDQj79eX1psRdM5IaGCM+j/zvZVy+7DvgNeCfJ12P7445T9tW54u/Pq6kwo2VuyowqltLPPHdGrz323Zt2+/3jsXwR38EANz5y7u4ZcF0/cAfvpX/AZhlOufe7AJUCcr799dfMfDB/2Hq1cNwQu/CqONRI043/vaJdi5YLDiQmaftc+u8/2J3197yA3Mfp4TWOMmfTi0lQykCJiTdcRiMHzIcwfdorfWFTZoJ9WNutCN3JFs4GV4m42uU6TBGnOoTTvpyuIhVaXYBAKBr2W4UH9yFrQXtMfzRH/HlzUejbztT/ZkCXfWiExxxMrxO7sgRp0yfoT9TGFc9AKhxZMJZVwlUVYGkDow4pSuFhcDmzckeBUkRvIaUjOE7VxmWV2N/tX7ny+OL/8fwmKdmY+I7i9H/ge+DRBMAXP3WIm157MaFQdsqHaEioiozB1Lv3vi56xHaj3yNXU5RuP+LVSH7h6NGiTjlKjVNPmcG+hTlQhSsWNRzOAAgx1sX2gBXOV5CAoWTcg6bn3bk5PDg7lN7o3/7XFx9VLG2rrhlVtA+qSGcLLBYghvg2gPJ/ZxaDAl24WqUgGBxZSaoj5NhfatsWQiubVOsreuzdwsAOaK0vjTyxNzHPk7RCerjpN98jBRxctkFPU3P5Qq5eadS45BNIxhxSi0onNIASULol1h5ObB0aTKGQ1KQcIYJgO5iF26/WAlXv6Syanelttxn31YAwCUXP4biu77GwDs+wn9G6NGuaUecgZyaSljWrIHUsRNKcloBALJ8bkCSEGt2T42SethN0WVdH/8nHj9vAABgTr+jAchpElEb4CZgYhBQIk42tbGmjUF+kt5cf2w3fH3LGORl6MXtNquAk/rq0eJwfYmSgWCxaDVO1hSocYpkrhFc4xRbqp7FtHxC7zbwWe34qavssJftrcOwnavw+4uX45QTBwE//xz2nH6Tq56opo9ROGkERZwMAlOIUJ9rgQWCpPxu1vObUK0Kp8rKiPuQ5ic1vr1Io5Ag52er7G1XrGzgFxuRUcWN0+9Fvlu/e9W5bA8shveON5ZW8g0g26PfeVvdpou2/OGgcXDbHKhyZODlIy/U1ue4bKg1NMt0+Q1pDVGo9cgixWUovFVzx32K8YMgic3SADegfAYFMfqPJCHpTI5Lf+83RZPthiBYDHbkkqhPepOV5h5Uo6Svzoq5xinsqZRzyK+/GsXI9tZi3PoFaF1bDlfZAeCrr8KeU4s4KcIp4FC+l5mqpxHkqifqESdrhEiRKEm6cKrn73kwU0mf3Lu30WMkiSM1vr1Io5AkCVbDl5jXpdyl4BcbUVB//FqbIkxF1Qfw9kcPhOyXaHop0SbJYkFFRo62fktBewy9+T2MuOld7M3Re7rkuOyoMwinDF/swkmNOLkMdUVqapDX4KCliZlIEadECCflbq1V7Q+T4IafhBwq5BiiJnZb8lP1ADkSo9Y4AYBDLdhPsYhTdoyuekERJwTvmOWQn6fqrJfjqUVR1QF9h7Lwzc/Vm26qW5xfFU68Math9F4Kijh5wtc4SQAs6utXj3Dal9VCXtizp7FDJAmEtz/TBEHS3dACqv8/hVPas+1ADbx+EbXeAAZ2yAvJkQZkYf3b5gNw+r24eMX/AAAHMnLRUrHqPmbrH9q+9aXdGfEHRCzfWYEB7XXDha4HdqLH/u1h9//rohnyWHJyQrbVOENrnXJcNoiCFT6HE3avB6esX4DyXblY/8oO7CyrxcDubVFx5NHYUi2iR2E2dpe7MbJLAep8AczbuB8A0GbLWvlkhoiTX20KKYp6lLYJG+BqwimGtAxC0pkcl566lzqpenrECQAc6s2WJAkn47e3JUKqXrjveH1b+GUAyFCFk1NusjugZAM6l5XoO6xdG/acG/dWwyKJesTJSeFkRkJ4cwiL2x1+f0kKSRUPx94suc6Xwim14K94GiBJgM0wyfOrd7UpnNKavZVuHPvUHO3xbSf2wB0n9QzZb/6mA3j91y24e+77uH6hLGA2teyAljtXa/sM2bUWL375JHZtPgs48Y2o137qf+vwn583Y0wPuQ4p21OLr9++LdgpKAzi8BE4Y2ARvl4R+kNw3dF6Cl++Uh9RYXOhldeDx79/Sd7wKaA+wz+6j8TE8/+pHfPsRYMwZ90+rC+tRl5dFaw+5QcsN1crmvYqQXabFNBT9ZTPS0gD3AQKJ0EtGKZwIocp+Zm6cIrUwLW5ESwWBCz6xNXhUSa6KdEAV1+faxCddmtk4WSNYA4BAPkZshgsz5CF00kbFwXvMH9+yPmq3D74RQlH7F6nrfNmycdzfqEjRTCHECIKJ8CC6BGnvdmMOKUi/BVPAyQY8mVhuIPGO0JpzW0fLgt6/O9ZG8IKpx0H5fqi9hV6nvTLR16IEZ/8n/b44R9eQYfKfejw8ZsAogun//wsOzb+ukGO7nQqL0GmzwOP1YYVbeUx5LhskCCn/3l8IrJa5qHvy1PwUs+eOO+IUry7YBuO6t4Kc9btw8UjOuKMge20818xqhj7qj2YcfZfMGrBd0Fuf8N3yYJvyO7gO6S/by3Dl8vl/iRqnxJ5xyGwlcs/YFqNkyjqd/yUHy71xp8mnBLw+fGbI05M1SOHKacPLMJvmw/AYrHg5L7R2wo0B7XeAByGiFNmVbm8kBvemrupMc6hjSKodY4Tfz22K+q8AXQqiNzSIEh4mXL6zh/aHs/9uB5f9TkGw3esQp7SBNcu+jB4z4awrRJUx9VCQ0qfz6Xsx/mFhhTBjtzqcSsqKfhvIUqSnqpXX8RJcZZFSUnEfUjzQ+GUBkiSoYYCQEB1veEdobRm0daD0XeCbkXeLlOeINx78o2Y02047jv5Rjzyv5cBAN0P7DAcEH8PMNWdb2PLTkF255E4oXeh1pPpujFdQ7YP7dwC7193JHDdkQD+BQAovvsb+XlU7sX8V65Bq9oKnLNqNv5o1wvbWrQLah7YpkbJ1x8xArBa9RonRRTZREPESRVOyv9SIs0hVOEUoKseObwpysvAG1cNT/YwQvAbJq6ZFcp3akFBUsZiCYo4BU+2J5/aJ+rxQeYQpm0dWmTi1P5t8d2fwHUX6HWtLWor8MeLlwG1tUAgEHRzx+2Tv7da2eTvsV+Kh6AXlO9FCicNtcYpr64K566eE7zR7QYyMoJWscbp0CY1Eo1Jo5Cgp+qJsCDAVL3DgoAY2w+XGq1xKHVwPkGevL835DT80H0EAMBl7GIew90tc4Fyrkd2D1LTQJqS3TmtteXnv34Gb338YMiY8lTnQGUCZFMmRz4o1sOSqE8sTD00Ak1Q4ySIFE6EpCKiMVWvVrGPbtEiKWMJrnFqwPGWepQTwvfPqjbWmJpsr1XhlCXKURSPzQEpgd+P6YJa43TXz2+HbqwLNYiQJIS4uoZDq3GKUH9GkgOFU5qgmkMEBCGhDTzJoY8acVJtUv2GO4ql2S1DD9i9O3SdCYct+KsjV0n7UAuPmxSLBVvzi7SHXct2Y/7LV+PmG05HUeW+oPEgPx+APmHwKZ8NqxgIsYPV7cgTKJzMduRM1SMktbBYUOkMbtCbrIiTUE/EKd7jza56AIKi8io+qx0+1YnX5KznVm66ZYvyjTW3zaFH5Blx0lDvYbZWMh2MdXMw1TmpaX2xRJz25LbSH2zd2uhxksRA4ZQGSJJeQxEQrPqHNhCo5yhyKLO7XL+LleuuxrW/f46T1y/An7sq8I3JeMGj3DW0B4IjTgBQmh1mgrByZb3Xrvb4tR9UAMjwunHLgukAEDoBaSKWFwXXcrWr2o/We7bjn7Nex83zP8QJm5TCZ0U4aa56gm5HblF/902pehV1ssCsnf1Lo8epNsBlxImQ1KUsw+T2qXxvNDfGOXR9tuORMJoVhjveFsHNsC4nX17Yty9ovccvf29lSvJ3osfm0P3jKJw0tHIlZR529yk3681rTTciRW3f6BGnWkcGPGrpxezZCRsvaRwUTmmABAltK+XiTZffq5tDUDilLbf+V7cQf/K7F/DPn97Aa589Cu+o0Zj09gKs2FmubfcoESe7UrTqs+qT9515YYq0f/1VW3T7Arjzo+VBYuyfn/8ZtPv4Ff9DoVLj5GxfhKbinMG6ecRrI84NaqSrctr6+fjbr+/h6G3L5RVt2gAArIoTlfrZECQxxNVInWgcUGp7M1etwOQZyxs1Zj3iROFESKoSdAOpdeukfU4bG3EypuqFOzxcxClo5y1bglarN8gyld8ON1P1wqJGkdR+mpJFQIWaffH552H3jcVVDwAOZigtP/bvT8xgSaOhcEoD5IiTwRxCFU4+X4QjyKHO4m16SsWxW5Zoy0fsWI1R21dgbUmVtk6tcVINRKZcNVLb9l2v0fizsBtqDc1mUVurLb732zbMWLoTN32wVFv32R+7gsYycocupMb8+8EGPqPoPHXhIExSXANXte2O0ya8iDOueh7vDjkNn/c9Fh8OPBkfDDpF++e57Q7ghhsA6BOGgHJ3zyaKIeYQ6qTjkwEnatf8YU790bdohJhDMFWPkJTjkROuw7tDTsOW8y4Dpk1L2jiC+zAlPlXPWOOU6dC/i+xqbZfJFEiLOAWYqlcf5ohTwCJgU8sO8sqqqqB91YhTLK56ADCn61B5oaYmIWMljYe3P9MENVVvQ8uOeid0v7+eI0g6MHTn6pDeSS3qgr+o1Ronm9LR3OpyApB/EN12F864+t8AgHHr5uM/nz8WlFpQWhm+D4WRU9cr/T9eew0te4ZGgRKF3Srg1hN74Nkf1mvr/mzbHX+27R52/4sfO00LI6kTBr9FjTgFQs0hlIelOa1Qml2AwuqDGL1tOYDLGzxm1Y7cwhonQlKWFUU9saKoJ166dAi6GNoiNDdGsdSQHsFBrnpRIk6jurZEx4JMTJu/FQc6d0eHVUtCokjqTTenVh9rY8QpDKIacTLUmv/WaYDcXN4knFQjiUg1Tp1bZmLbAf3mZaVLiVxROKUMjDilAZIkacXnAYugR5wonNKe/qWbtOVveh0FAMj11AT1lfD6FeGkNuaz680UjewL02zPGuVumNMo2saMiXnczYGxj4nqqqdGnOyBQGgfJ8MPmOq5d/bqn4Ney3gRNVc9NsAlJNWxN0StJBCj8Gm0OUSY443f54JgMbRgCN+7zqfMK2yKBblfsFI4hUF91dRUPdEioE7N4jC56pmjU+aIk/mv5rYp56FwShkonNIAozmEKAi6axqFU9rTt1RuRPvmsLNR4ZILnPPc1aj26KmbHkU4WVXhFKFHk9Zsb/du7dvdaav/K6LvXkNOfM/Q5rupgjoh8Vll0WgX/aE1Toan+rOSHnHc5iXa69cQ1GifwD5OhKQ8jqQLp/qFT9TjDcor3NE2qyGiZbFowY5IwilgauAdsFgj7ns4o0acjKl6dargMaS+A/rLpv0lovydax0UTqkGf8XTAAl6/YpfsDJVL81Zs0futXHU1mUYv/IHAMDu3NaaFeqkue/jx5t3o2Ld7/is3/HYMPBkPLHkK2TuL5VPECHipPWM8HrlqFO7dkG24yMe/RFXYQ+e/fot2JT3m9pRfm2bLugdJTqVTCwWC2yCBR5FODn8vog1TgAwfeDJuHjF/2CVREhDBgP/vA8YP17bvv1ALV6esxGCYIHbF8Cori2xclcFrjmqC4pb6c6Cah+UnF3b5RVM1SMkZTCnRZnbLDQ3wRGnxh0fLVXParUYWjCEb/qtCie1T2RAECLue1ij/JRoESfBEHEyCSezyIpW4xRJgJHkQeGUBgRFnCwCdlcrphAUTgnj7hkrsK/Kg9evHBZ0V685+XNXBf728XLN+OH96fdp29a2Lg6y1B27XLYuvXrJV7hwxQ/I8hlqlQoLARwIOb/XZkelKxu57mrg9tuBjz5ClqGAeG+VBzc9eWXYsdUOHxl2fVMwtk8b/LhmLwDgmqO6YOq8LSH7DO0c2sDSL0qao6Aj4NPtyJUfLuPd3mXt9OiZbdWfssnE+PGocvtw+RsLsXxnRdC5P10qG2Zs2V+Dd68diXcXbMU/v1gVOninM3QdISQpvHPNCBz71Bztcavs5H4+jTdvmrqPkxxxsqg7y0SKOImGVD11ok/XXg29xkmPzLkjCCfJvBDl76yl6oVppEuSA4VTmmA11jhZGHFKJJIk4cPfdwAA1pRUol+7vKSM46/vLsEupX+TyyCElj/wNOa5e0MQAwhYBLSoq8IJm36XC1MBTTSJl1wC4aqrgC5dAKwOe42NhV1wxLaVQHk5gOAf8myP/gMw5/TLkde7O2q8AdTCiqPuvj6RT7VeXrr0CHy7cg96Fuagf/s83H9mX8zftB8Hqr3Iy7Cj1hvAoI7h/0ZeNeIUCI04GfWw1WrF8JvewbmrZuOeOW/Jr4ck4Z0F20JEk5FfN8iWsUbRlGc06+jSdOYZhJD46NwyC/3b5+LPXXIUv1fbnChHNC2JjDiFO95Y42QV9FS9aBEnNaNFtDDiFA7tHpykR+a8FmV6HSnihAg1TiYh5bYrqfUUTikDhVMaIEEK+sCqd9UltztsnjOJD9UZDUCj6l0aS2Wdbi+v9k2CzYYOd94EPDoLomDFF/2OBwBMG3YWbpv7Ae6Y94F2jHDppcC4cfVeY/qIM2ThpFjZ+wL68x22UxcDx339bqOfT0Nx2a0474gOQetGd2sVYe9gvDa1ximgp0qEMYe4/MjOmLsxC+/bT5WFkyQBbjdqPPHfjOhQUao/yM2N+3hCSNPh86dOrU6ja5yi9XEy1jgZzSHUmYIp4uQ31Tj5BYHmEGEQzal6lsipelqNUwRXPbMZkU8VTu7oDrekeUjdogQSM5IU/IGtcmYCAALlke+Mk9gxigd/IHk/ssbvV004dekChz183UxQU0cAGDIk6jXc6l0yr9y3w2t47meulRvjHsg4dCf/asQJAOyKPbte46Tv57AJyHHZ9B8/AKipCeqDEis9DsjRSgwaFPexhJCmxfgdl2yMwqch3zXRXfVMqXrKciQxJIZEnKwQmaoXgl81ATKaQ9hd8sYQ4aTWOMXWx6nOyohTqkHhlAZIMOTWCgIqFN//wIGDSRxV+mC8I+lP4o+ssbZKNWVAu3Zw2sILp5KcltqyV7ABRUVRr+ExCSf1ubeuPojz//wJALC4Q9+4x54quG26o2BmneJSFCbi5LAKyHbaIApWBJy6q1E4u+JjNi/BPT+9iVPXzg17zRyPch1TPw9CSPIJiKkTcTJqnQal6hm+nqKZQ8RiR26OONEcIjy+QHAtWECIxVUvfMSpXX5G0GPtN4vCKWWgcEoHJEOqnsWqCSfnF5/ho49+SebI0gLjHUlPkoSTKEoor5UjJLaAHy9+9ZS8oX172K3hf2FLcvT0tf1Z+UG/qh0LMsIcAXjUH0WfD16/CK9yV/GvC2do+0wfcmpDn0bS8Vtt2JMtC8pu29bIK8OYQzhtAnJdcnSqQpB/AH875yrsKgv+8Rqx40+88/ED+Mvvn+GVL57AV9NuA/bu1ba3qK3Awz+8Kj84++wmeU6EkIZzXK/WAIBW2eHbNDQnxu+ghphDGKNM4cwhgiJOAqLakWumBwG1sasVEoVTCH6135XaKFgwmEMcPKilvgP6a2qJEHF66sJBOLF3G7xy2REAAJ+g3Mw0nIMkF9Y4pQESoNlDBwQB61t11ratf/Vt4KJjkjSy9MCYqufxJSc9YfG2Mm15yO61+obBg2GxWNCpIBPbDwbf2VrfqpO2vKrfSLQzbPv4r6Px7co9CIgSHv12DRxWAd6AiDrFWMRd60a/+2dqd2MvWvkjAGBDy4645L7rEvzsmpdMxSyjoEI2cghnDuGwCchQHAV35bZGQV0ljlz2M5784gegfW8AsoD96IO7g849oHQTVr7xIYBuAIBb53+obxw+vAmeDSGkMdx9am90aZWFk/oWJnsoJjvxpqhx0ifpNkHQrhEpVU+NOBlT0LRUPQonDTWFP0uQ//cLtuBU+aVLgZGy86xmphehxql9fgbevHo4KpSaZq29DIVTysCIUxogSYBgcNVb26YL5naW6yny3Gya1li8BkMIb5JqnMpqvdry0F2KcMrOBiZNAgB8efNR+OGOY/DTncdq+4mCFUNvfg/nXf4Uxsz+NOh8bfNcuOboLrhuTBf8OOkYzJ98AgDAK8hRlvLy6qAUFjWK+cyYy9G+ZXbin2AzsqhjfwBAhilVzzhRcdgEXDdGdsC75JLHtfW3zv+vtty2ar+2fMfpk1CmNCCe8ZNuopGrpOmJHTsBF1+cyKdBCEkAmQ4bJhzVBR1aZCZ7KKaIU/zHW4MiTqEEpepZjH2cIkScTDVOfmOqHmucNNSbq7lW+fUa3bst/FYb6nKVthgGYwctiofwEScVNTroV8y+3HXesPuR5ofCKQ2QIOl9nJS7E0vbyXfFtfoK0mCMrnq+JLnqGcWbNmE/6SStoWp+pgM9CnPQtXU2ivJc2r4HsvKxtH0fuFzh01AsFgu6t8mBU2n8qDoy2kxW9m2q5Zqqda2Lke08tAPV+7LyASCMq56+j9Nm1Z5ntTMTbw6T0+yO37xE26eFYjO+J7slPut/Ar7vOQoAkOXV0/la1sgGLeJ990bt10EIObxpfB8n43IMqXowuepFijhp5lNWXWQx4qShvU6K4ZDNJf8G17aU00CDokVRapxU1D+VGnGqqqGrXqpA4ZQGGBvgBpS7QZWuLAD6HW/ScPyGHwhfkmqcjMKpdY2Stte/f9h9c1zxCxvV9MCvCDFbQP+id/o8cAZkIVWWkYMsZ3gzikOFaofpznIL+a6gYIo4ZTr01/HDgSdry8dt+h0A0O3gTgBAudJ4uNoh140Zb1YcrfTSsrVunajhE0LSlMb2cbJES9ULEk6Cdg2tbilSA1zJEHFiql4ImquecsNRssuZGwFraH2Seh/WFsVVT/09UoWTXWRfzlSBwikNkAAIao2TKpyccjpVn71bkjWstMFoQZ4s61q3X0+LOGnDQnkhgr14QyJC6g+qmqpnC+hf0h0qdLODclcOHLZD+2tDvamgMXEigFA78gyDzfsGQ73Y098+DwDotW8bAMDpl1Mo1HRG480KdR3atEnI2Akh6UtQql6D7Mjr3x7RHEJdGaEBrhDQG+BKTNULQXXVUyNOsMu/weGEk6S82tqfOkLESUvVU4STmi5Jks+hnXND8Povm/HKnE347/r5AKDdDVLvgvfZtxV47z3g8suTNcRDHmOqnreeVL0ajx9ltd4myZW/97M/4fR78dm7d8Kh3nnq0iXsvlkm4XTO4HZh9zOifkmrqXrZNZXY+uQZAHQxvqZ1MWCxRLQ/P1SodBqEU04OkJcHINRVz2UP9va976Qb8MgPr6BVbYX22gDA/3ocKZ9XEUmXLv8ely7/Hn6LAJuaDtivXxM9G0JIumAMPjQoVU8wRpxCj7cZLmC1WLR91BR/sxgKSMGpen5BT9Xz+fywgwB6VorFJ/82WxwOAJ56I07WKBEnqxZxks9hp3BKGQ7tW8cEj34rWyqb04Tmd9abbUozZoQeSGImYLgL567HVe/Yp2bj6CdnY8v+xKZHqg3zuh3Yib5KBLEmtwUwYEDY/Y/qLtuQd22VhXeuGYEnzh8Y9RoWiwU2wYKSnFbYkRfsLqWlgZ5yCj7666hDNuKk2g4vbd8HHrUR7imnaHf8OrfMRKtsB7IcVvQtyoXFYkF7Q0+N6YNOxsEwzX8/7S8ba6h1hSqqaNrUYxCQn5/op0MISTOCa5ziP94otmxhTmCzmlP1VOEUPooU0PoTBbT99tXK4uDd+cxmUfEHJECSYFEiTqKaqmcLE3FS7cij1ThpESf5b8OIU+rAiFOaoDZe+6b3GAByQfv150zGq58/Duzek8yhHfL4DKl6dfUIp/3VcsrWL+v3oUurrIj7xYtHiXJlKDbaUmYmsg7s1YwhzFx/bDeMH9YROS5bkP1sNGxWC9w2O46f+B+cvfpnXLv4c6w4+hSc/ew9yMh0ov8hXqfz9IWDMOyRH/Fn2+4YcusHOLlzFp6/9RRte47Ljnl3nwBRhGZF/us/jofbH4AkyZFH7z9Lcd3L/8PynbLpw3cPnQPhnT+AkiqsLOoRdD1p40bUWh3o2jF6xI8QQhpvR64vW8MJpwipepGc8vSIk1rjZEW5W14uq2RDVhWfKMIqiZrFuEURTmK4VD014qSuqOfvLFiCI05iQIQQx286aRqS/heYMmUKiouL4XK5MHLkSCxatCjivqtWrcL555+P4uJiWCwWPP/888030BTHZvhiU9mjNkDdszsZQ0objLbcdd7oNU6JNk9ThZPaf8jSvTtgq/+eR4ssR1yiCdDT2/1WG2YMOBGnTXgRCy/6CzI6dwAOcdEEAC5DzVKtIwPV+a1C/lhOm1UTTYB81y/TYUOW04a8DDta57pQ16oN9mUXYF92AVq2yA6qp37uqEsBACUdusLSrRuyijvCEkHgEkKIkcY2wI0WcTKKKUHQ7cgDESJOohgsnAIWQUvVE0xGEocz/oAUVBcsOWTh5K9HOAlR7MgB+e9lnNMF/DSISAWSKpymT5+OSZMm4YEHHsDSpUsxaNAgjBs3Dnv37g27f21tLbp27YonnngCbdu2bebRpjaq64125whAaXZLeWHPHjrgNAJjjZPRpCESDblTWB9q091Mv0dekZW4aJaRZBlfNBeukBTDhv2djB8li8WiFfsCwJRRF2H8JY/j5QfebNC5CSGHL43t4xTNXCKkxgn11ziZ7cgDglUTWRROOr6AFFSDZLHV56pn6uNUb8TJotUdA0DA7UnUkEkjSKpwevbZZzFx4kRMmDABffv2xauvvorMzExMnTo17P7Dhw/HU089hYsvvhhOp7OZR5t6+A0TXauheFNlf1Y+RFhg8fuB/ftDjiexYXydSyvcqPH4ERAlVHv8KKsJbUpX3++dLyCi2hP7XaNqjx/bDtYCALpXlMgrM5PfqPFQxByB88QggsMhmiYMxod+qw0LOw2Qa9AIISQOGhtxMh4SLeJkFSx6qp4ihrweX9DvnZaqp0RT5IiTvK/WFoPAL4qwGezCZXMIvb1HsKuesk8UcwhA/ht5bHoPxkBNbWIGTBpF0mqcvF4vlixZgsmTJ2vrBEHA2LFjsWDBgoRdx+PxwOPRVXplZWXCzp1sajz6xM+q3RHSP4R+qw0HM3PRqrYC+Oor4Nprm32M6YAx4jRr7V70e+D7oO2vXj4Uo7u3jOlcl77+G9aVVOHXf5yAvMzInkQlFW48+u0afLVcTrO8YunX+PssJYrRRBGncBzqPZvqY/O+hpl4tMoOvmmTHaZvVjq/boSQpiGoj1MDQk5mYWQm2BzCot30EZXbfS/+sBZzWszHV7ccDUA3h7CoDXAFXThdunwmSmf+hMJTToh7nOmGPyAhQ03Vs1hgqceOPN6IU0CwwidY5RqnOtaVpQJJizjt378fgUAAhYXBDl6FhYUoKSlJ2HUef/xx5OXlaf86duyYsHMnm0q3/mFUa5zuPK0fOhXoEYksr9Jtet++Zh1bOmHs4wQA7Sr3YsSOP7VQwyPfrMaecr2rd6RJsyRJ+H1rGSrdfizaerDeax75+CxNNAHAKYrdPADgkkvifQoxcesJ3VGQ5UCfIt057rYTezbJtZLFdUfrFu4HahqW9nDT8d3RtVUW/nlGXwDArSf0QFGeS9veMsuBW07oEelwQggJi1EsNTZVL7o5RGjEySqJWLmrQttHjzjpNdQ/dh+pba+YtzD+QaYhvoCoN6i12/WG8kLkGiftL1FPxEn9c7mVqJNUy4hTKpD2rnqTJ0/GpEmTtMeVlZVpI56q3HpoWK1x6tkuHz9fexy6TP4WAPDhoJMxYclXQBpF2v6/vfsOj6rM/gD+nT7pvRMSWigBQkeQKggooqggoougLsoqKj8Ul1UUdHdF18aK2NZVdG3YwIKi0hFC7wSBACEJ6b1PfX9/3DL3Tk1PJjmf5/Exc+fOnTtzmZl77nnPeVubWVrUwhi++d8yxFQVY8GsldjZYzjKakyybnsms/Ox3wbJHFC6BrT01lhMuPbKSe7Ghg3AHXc07AXU09IpvbF0Su8W2XZ7seKmfnj/d66Nrn1AXF/9YgOx/YkJ4u2JfSKR+rdJzbF7hJBOTJp8aFxzCNvfKiePl9U4STNO/BB/pasJcK22GurUhGRsGHA95pz6jc4reGYrg1qoD9NooOEzeyalk6F6YsaJf6/dHGch+K1T6xBgrIW1hjJO7UGbZZzCw8OhUqmQn58vW56fn9+sjR90Oh0CAwNl/3UUlU4yTlCrZc0JqrR89om+4BpNeoIdaKhGTFUxAGDqeW5IKWNMNr+TwUWTBWmGUNOAjneDcs7ZbkyZUu/HEfcsVNxMCGlHmtocQuEh4yQbyqdQOLQjF+bsE7rpCYGTwq6GupqfN5LOK7j3ymJltoyTViv+vhudddXj/1+fjJNwvIQ6JytlnNqFNguctFothg4dim3btonLrFYrtm3bhlGjRrXVbnkVacZJvFJk16a6XM/Xw5RSIWdjSduRR1UWi3+H13BDGkxWJss4Gc3OAyfp8ZJu05OJlw4DADKCY2gi1WZEcRMhpD1p6jxO0sBIWs/kbJlSqRCfw2IXOAkdVsWMk6Q5BACU6/259cvLGryPHY2JP/fSWByH6hmFidaNtiZSYo0Tq1+NE2ALnFhNnct1Setp06F6S5cuxfz58zFs2DCMGDECa9asQXV1Ne69914AwD333IO4uDisXr0aANdQIi0tTfz76tWrOH78OPz9/dGzZ882ex1tpdLgPOMkVebDZdhMJ04hu6i6WSdm7ehKq404lFGCwiquFqZ/XjrmH/lRvD+hNBdTz3G1R4FbC6E3+aFOo0d6QSWySmoQz9eaMcaw5XQejmeViY81WizIr6hDZkkNwvy08NGqEBPk47APGosJD+3/GgBwKronElvotRJCCGlbTZ/Hyfm2BLLASqmAib9ZzE9q62fkhoIZTFboNSqHjJOFzziV+gQAAPwvXWjwPnY0wogU8RxMo4GWD5wMQuAkaerQsBonYaiekHFqXEMj0rzaNHCaM2cOCgsL8eyzzyIvLw+DBg3Cli1bxIYRmZmZUEr+UeXk5GDw4MHi7VdeeQWvvPIKxo8fj507d7b27re5Kic1TvaBU4WOC5Q0Z05h4is7ceLZKW67uRGbe9cfEoOdHkVZ+PGjJbL7k4oz8e6mF7gbm4DlQ27CqusX4fODWfj8YBbC/LRYMDoRof5aPL3xtOyxRrMVt7+9D9mlti/U9+8Zhsn95M1SFvFBEwDgzjub66URQghpZxTNOI+T2skJubS2tspgFtcpreUuwo7I4n6nuKkaNLbAyS7jVMmfV0SdONTwnexghMBJmnHSabj3qVbFtxKvs2WKhIyTsh5d9Ww1Tvx2ainj1B60eXOIxYsXY/HixU7vsw+GEhMTxcI6AlRIAie1MFSPnzfgrbuH4KFPjyItkusiZoUCYAxZpTUI8g1q9X31Jis2nQJjkGWIehddka1Tp9biVBSX5YyqK0fX4qvoWibvBllcbcSrv52Xb5wxxFQWwVJSKguaAODPHx9GxovTZcu6ldo66814ZlFjXxIhhJB2rqntyGXNJZwkMuKCbaMaSqqNiA7kuoHWabgpFgr9uPnnhEZGQh2owiLPOJ2LSAQAGPW+sM0y1DkJQ/XUkhonvYZ7n2qFrnqSwEmcvkkInNxlnPi76jT8UL06ag7RHrR54EQaz12N040DYhAf6oNSAzdUTwkGndno7uIGAVBeY8In+zMdlkdWyduHD1iyASY+DX/npX148asX4GvyfDVo+a71WHTgG1je16LHPf/GxXB5h0erlUGpVMBXq0KN0YLAuirujv/8x+0XLCGEEO/W9KF6tsc469wqzWhZrUw8HzgVzV0EDDBwzQeEycHN9jVO/G9Qvn8oAEBbVwNYrZ36t0nIOOn4+jBoNGLgVK3kR/c4CZzESUvcZZzEoXpcYMuoq1670Hn/tXcAsq56wlA9lW0OIbVSiVqNbbJOvdkIBShycsdVp7UgIYAB8ODMp8SgCQBKFdzfPibbvEAjM09h5dZ3oTPJ5wq69/B3AACVyYhBuXbZKNiuXgm7EWjgxzRTUwhCCOnQ5DVKDX+8tIbJU+dWC2NiICUM6Q/gf2+EjJNVrHHizi+EjFONxjZvHTr5pKwmPhunZ7ahej584FSjcJJx4jNNSiHQcptxsh+q17nf6/aCAicvJss4MflQPYD7ErUoVbDwaV4fk0EcX0ucc/VbJQQwb4+chV96j5bdV6HkglMx48QYNnz+N9x75Ac8cPBb2brihHgArsk85fA8wtUrYWy5cAUQQTS8khBCOjJFEzNO0od4DJystueo4LvkCRcIhcBJyDgp+AyUUOMkDB0DAHTyFtnCeyTNOAmBU5WTjJPVvjlEPbrqUeDUvtBQPS8mzTgpnLS2FGYJN2r18DEZ4WuqE9uMepJTVov/7b+CMD8t5o1KgE6t8vygDsDVd9ik9IMAgAq9Y1fCGj6rF1lVgsX7vsCCIz+I9z3++6dg/EbVVgv8JMP5ehVfweJ9XyAzOAZ5AWFIyTkPc85AsMQu4nHqW5jBrRwQ0NSXRnh6jRJ1JqvTeU4IIaStSIOlxgyrlz5e62GS9QC9Wjx5L/HhLsyF1FZi8b4vkHP5J0Q/fI9jxokPnJhCiTq1FnqzkQIn/rdaB37Uj1YLHy0/pNHIv8NHj4rrC3X69ck4qezakaO2FhYrw6ZjVzE8MRRdw3yb62UAAOpMFnxzNBujuoehe4R/s267I6HAyYtVGaQZJ8dCQ2HOhnKFGj4A+hZcdjnH0Ku/noNeo8LDE7mxzsu+PoG96dycRWqlAguu7dYCr6D9i6gqxVubViOxLBcAUOSksUYJvyzIUI0n9nzicL+zZQAwKPcCBuXK27nW/lMNy7tvAwDiygskOxLRqP0njjY8MAp//zENT03v29a7QgghIk/txD0RamsAwF/n/PTu77ckY8uZPCwYnYhf07iGRiW+gTCoNNBZTOLv1R/bN8O8fD3AGBQW+VA9AKhV6yhwAmByUuMU6MNlmoSaMBTb5n+0is0heG6Ocx2f6RNqnFBbi88OZuKZTVz3Q/tmUk310b4MrP75D/SK9MdvS8c367Y7EgqcvJh0qJ7CSeCk4v+O5hsb+BtrZBO1CvLK67B2ezoAYOHY7tCqlWLQBAA/nsztNIGT/UjG+w9txPCraeJt0623o081cE33MEzpF4W73j+ArOBoPDv5QfQptHXeCzRUo1zvB4Xd9npE+uH9gL4YkHsB4TXluOvEFtn9isuXxC/i8GrJpMU9ejTPCyRIiQ/G138Z7XlFQghpRU1tDuGvU+PV2SmoM1sQFah3us68UYmYNypR9hwWpQpLbnocYzOOQ2cx4vbT29Gn6ApCSwtxmdnqpC2S84tajQ4hdZWdPnAyWx1rnCIDuPf+QlhXbpmvNDNk147cTcapjj9fq9Zy3RAV1VXYf7HY5fpNtZff9oWCKg9rdm4UOHkxpzVOkg+hhr98tbHfBNyathP+hhrUGR0DpxqjbTtmqxVau9I3ZzOQd1T2NWD3Hf5e/Luoaw+sWThOvF0nCUI/HjrD47ZnD+2Cu2anYM7yzfit1zUAgJDaCtxwfp+4jjIvF7V86t9XaCzRlzIjhBDS0UljJQ8lSi7dPrRLox73c58x+LnPGCiYFbef3g4AmHLoZxwfeLO4jizjJDSe6uSBk3ChU8tsE+ACgK9WJQY80tqkhmSc+scGIb+iADVaLhBjlVVi/XNLoNHr9UPNIbxYhYcaJ6GGo0rHXe0IMNaIqV8p6cfQ2VA+T0WmHYn0OynAUA0tPzeDQaXB1seel61r/774at3XgQXoHScefmXcPOxOHIz/DrsFAKDKzRHHTOvNfODk27zjmAkhhLQ/8hqnlj+LdZbVYgoldnUbAgAIqK6Aymo7ZxBqnADJ8LFOHjiJNU7MVuMEcDVmRjX/m282c23bIZnHqR41TkKdWhUfgLHKSrEZRUtoTJazM+o8Z8QdjNXKZDVOCidpXyFTVKXlTrz9DTWoNToGRlbJB7HO1LkDJyYJI4dnnRH/7v34t8gfOFy2rn1zgUAngZGUXuP4Pl4Mi8c9c/6ON0bfyW2ztBSmau7qlI+Q+tfpHB5HCCGkY5H+prTGSayrp9iXMBAAFziprbZzAmlXWDHjVFnZYvvnDcSuelZbjRPAnTcZJdOWwGgEYBvVIg7Vc3OchcCpRsMP1auqatHOyBQ21Q8N1fNSNSaLrB7HWXMIocapks84+RtrUS0ZXsYYw6rvz+CjVFttjsFsEbu+CNSdKH8rfemv//gqAOBAfH9AofA4ZDHIR4O8CteT4HYJcZ05Ktf7i12KzIMHY01IAmam7eLu1LgPyAghhHg/6U9ta/zqugrOyvRcF9eAGnnGySytcRIyTrNnA998A9x2W8vtaDsmzOOkldQ4AYBWpUS5NHAyGAC9XpJx4pe7yTgJF62FjJOyqqpFM06tkeXsCDpPKqGDkbYiBySBk+QfvlDjJHzo/A01srqc3ReKZEETwM3fYLAbrteZapyEt9HPUIMgfu6mg12SXa4/NCFE/Ds+1Ef8+9XZKZjcN0q8rVEpcMcwbuz52rmDHTekUKDEJxAA0CU3wxY0AdRRjxBCOgGFk6H2LcnVU4iBU20lNFbbyBarZKje3sRBtgf8+mtL7J5XMLuocdKoFDCqJLkJAzf0njUi4yTUSqmqqxwubDcnTSc612sKyjh5KWljCMD5UD3hi7eSnxX8pnO/47/n0gC+5XhumeNkanUmi8NcT51pzlwhDa43G8Vla8bcBcB5/dc/ZvbHDf/eAwAY2S0Ms4bGA2CYmhztskh3Rkos4kJ88On+TIxLCofJwvDEVydw+59exuT0AxiZeRo3nfudWzkgAHjjjWZ8hYQQQtojWVe9VhnpYXuO6EA9pvWPxvp9GSj34SfEra0UM05WtVp2kv/ONbMQozJj/vZPOvXErEJXPa1VXuOkUSkBhQJWjQZKk8kWOPGPczZKyJ6WzzgJzSHUNdUt2hxCWpbBGKMMlAsUOHkp+4yTwkmhoZApuhDeVVyW9OsmYNHNcMVgtopXUASmek6a2xEIgZOvkEdXq8VOQs4mDw7Q2z5CWrUS0/pH1+t5hnQNwZCutmzVE1+dQG5gBP435CbUavS2wCknB/CniegIIaSjk8/j1LrPd+uQOIT6cif9QsYpsLZSrHFiasch4wXCvIaduEGE0FVPY5VnnNR8EGLVaGWBk3COoahHxkln1xxCU9OyQ/Wko4uMFit0avcNrzorGqrnpSrsMk7Ohuqp+SDqdHRPfD5wCgDAtzDf7XYNJqtDoGS0dJ6Uk/A2qoW0u9oWGDnLODnrlNdU++P7AwCKAsIAP79m3z4hhJD2R5pxUrVKcwjbc+jUSuj5zrClPlzgFFxTAY2Fu0jLVLaT6CB+gtcqoc6purrF97W9EjNOdkP1tHwQYtXy75E4VI+7WZ95nIQMUDXf4EtTWyNr5tXcNJJ9qXPSSIxwKHDyUlX2Q/WcpH2lTR32JaQAAAKK8txut85kcQiczJ0o4yS8jRohgycJnJxl3qSzs9c5mVy4MbKDo3Hjgjfw6OK1bq9GEUII6TikX/et047c9rdeo4Kez3AIGSc1syK4jpsMlUl+C4XAqVJJgZM4jxMfYDpknPihe/YZp4bUOAkZJ7XRAKvJ5HL9ppLuSm0znc90RDRUz0vZZz+cZZykxaV5AWEAgKQ/juJ8eAL+Ne1B9Lj7VgDAkKtn8cy297l5gz4AKgH8LNm2r1YFfBYPbNgAREa2yOtpjPV7L+NQRinW3Dmo2VqmC19q4nhlWeDkeKVH+h47a+XeWGlR3dEnMqDZtkcIIaR9U7Z6cwjbc+jVSvjwGSeDRodatQ4+ZgPuOMk1fnAWOJUq+aBg926YUg9AM2pki+yn0WzFkg3H8NMp+YXfyX2jsPVsPrRqJXpF+mNS3yjsPl+I41llGJ8UgbV3DUZhpQF/++YUhiWGYMnkJGjVSpy+Wo6b1v6OgV2C8P3iMbJt/nwqF18ezsKrdwxCqJ/W474JpQ1qhxon7r21aOSBU4NqnNTyGicASL+UB+gbN3x/3Y50bP+jAM/dnIz+cUEO90vPcZ797jTqzFbcMawLbhoY26jn66gocPJS0gJBpdViu3ohaV2dW25rjZ0eFi/+nVSciUe2rceshEEAgFmntmJw7jn3T3j1IvDSS8CrrzZ955vJqh/SAABT+0fj5pTm+WAL76paMl75+n5R+C0tH7NcNHvoHxeI01crMKZXWKOf945hXfDl4WzZss7UzZAQQjo76Tl0K/eGgE6jQrdw29BwH34C9snpBwHIA6fyWi7rcTnE9rtbuvYdRLZA4PTUxlP45ki2Q7dfANh6lis9MJqtOJNTgTM5FeJ9u84XYu+FIpzILsfBjBIczCjB27su4r5ru2H3+UIAwMnscqz87jSeu6W/+Li/fHoUAPDKr+fwwq0DPO6fQ3MIyTxOAFfjBMChq5741rvJOAnbMKk0MKjU0FnM8DfWoKKRgdPLv3DneR/uzcCrd6Q43G+RzNn1axr33u4+X0iBkx0KnLyUtEBQY5EM25NMlpocF4jf04sAAKW+QXhkxjKs3PYewmvKEV5dJl5dCLNyH+iPB0/HL0mjHJ5r/deruOeocz1HUVtqriFygC3jpJYM1Vs7dzCultWiR4TzL6vPF16DvPI69IpqfIZo9W0DsXBsd2z7owAv/vwHAFtHHUIIIR1fa3fVk2WcNEokxwbhw3uH494PD2HFlIfwj1/fsnWYlbTWHtsrHJ8eyERGaBzeG34rHji0EYrcnBbZx88OZDos+9OxnzD46llAoUCV1gefDboB5yISHdarqDOh2mA7P2IM+O/vl2XrfJR6RRY4CQoqDPXaP5N9xskucDI7BE7cTaVwjlGPoXoAV+ekq62An6FxHQylpQZ1ZufnTC3ZeKIjocDJS0mvDGgl8ywIaWIA8NPKD+8P/cbjXEQCfv1gMeIqC9E/Lx2no3uim577sJyJ6i6fm4H3v6n34r6f/tNuA6fmDDDEGifYAie9RuUyaAK4BhFNbRKhUirQKyoAxdW2NujNNfyQEEJI+yeta3I1OW2zPp/kb6GDWp9o7gKgMK+g3sSf8EsyTmH+OvhqVagxWnCga388cGgj1Pm5Lb6/ABBRVYp//PqWbNmYjBOYtPAdh3Ur68yN7gpc37dfqAHX2NU4iUP1hG6EYo0Td1P8dXczVE8nOQeo0egRWlsBP1PjzsOkU9ioXQTlLdnqvCOhMzMvJb0yoDVLigUlQ/V8NI6tJK8Ex4h/33BuLwBAb+Q+iDUavcP6AFCr5oOxdjRXg7TGqzkDDCGNrnZS49QapM0mpFebCCGEdGzS89nW6Kpnn3GSPq+Zn4ZDuDArDZwC9WpxKo58f26Iuq6woMX3FwCuT9/vsKxHSTYiqkrF24klV3Hr6e2oqqpt8SYHQmCmtjiZxwmARTgnM3IXRcWheg3MOAkNIvyMjTsPk05h4yqYdFbHTRzRmZmXsjgZqmdRa2QfQqG1KAAE8CfkBo0O74y4DQAw4dIRqC1mdD1xAIC8AFGqVsV/8NtR4FRrtH0ZNuds18LbqrE6dtVrDb6SY0YZJ0II6TykgUxrNFSVddXjM05CUwqTyu63T/JbGKBXi6Ms8v1DuceXFAKWlu/EtmL7+06Xf/zlM+Lf72x8Aa9vfg23/PU+6LMdh/o1J9tQPT6j42GoXkMyTtJzgGo+cPI3Nm7OLGnGSXr+JCUdyaS0WrBy67t48MDXjXq+joyG6nkpWY0T/4G1arSQ5pj0kqsVIX5aVPJjfbODuUlakwsuIf2VmeI6lTrncwbVqrgP/s4TWViwfLO4/IfFYzCgi2NnltZQUdcyLTkZhBqnts84uUqnE0II6XhkGadW+P6X5hd0fMZJmP/RpHQXOGnEjFOxbxAsCiVUViuYVgvFoEFAaqqsbKA+1u1IF5sXPLH7Yyw8+C3OTJ8DXa/b8fvb9yGktsJWewzgHxPvg4/JgMWpG6CzmNG3MAOXXpoBq0Ihrtft1EG8tGwm/qlQwqjWwNdkgFmhRFZwFGbOew3l/HxViZLzGsFvafnILq1BlxBuDqVDGSVY/NlRPD29n6wZldAcwn4CXOGC7rlSI+IA1P60BT533w3hXXfWCdmeNOMkzK317sYXAABvjroDwHT3b6pEdqkt4LLvAPzDiRys/uksqo0WqKwWfPnpXzE05w/x/kceHgKMGYO1cwfX+/k6Mrqk7aUsTobqWTTyOhsfSfYiRNJW88c+8vabAIBhw/Dgk3fLFq2+jesoU6Xktqs3y4sl914sasSeNw9p4NScBY1ioqmNAqcwfx16RXL1VMMTQ1v1uQkhhLSd1q5xKqqy/ab3jOBOzFX8Cb9ZZTfUX/JbGOqnxaju3BA9q1KFvfw8kQqrFTh6FLhwocH78vpv57k/GMPi1C+hs5gx5PtPcV36QUTUlMmCJgD4eMgMrL12LoY88pm4TAnmsB7ANXvy5Wu11MyKbqW5GCIJDHyNtYiq5M5ngmsr8FDqlxiYex5jXtqBi4XcPFYrNp5GfoUBT3x5QrZtoR25yiLPOAnzOAUYuIAlo5QribDaN4dwk3EShvUBcGjctTj1S5ePc0Y6DM9++OIjnx9DTnkdymtNiK0olAVNABCddhw/nGiZ5h/eiDJOXkr4sCoUgI4vShTbXvKE1DvAzQqeEOaLK8U1KPMJRNLjGzH1/D5orGbMXPUQxg3riUkAziVzNVCM2brKVCq4fyZidx2e/VxSrUk6AXBjiz+dccg4aZrW9KGhVEoFfn5sLCrrzLJglxBCSMcmn8ep5Z9PejId5Mv91gk1TvYZJyb5LewW7odruofh/jHdoNeosKh7KB4/mY6dX/0VfgW5jZoQV7gAOiAvXba8d9EVAECtWodxD/4HO5ZNhCY2GkcsDEazFX46NUqfq4GisABmixX+eg2sjGFDhgH/2JyG0JpyPLT/K9x75AfZdqMqi7Hk90+xZO/n4rL/m74U/QouYeGhTbjv8HcY9sin2HmuED0i/HEuvxIAYLQ73xDeQ7E5BJ9pE5pWfd9vHIZfTYOqkmuV7tBVzz5AlYgIsHVJ/mrgFLz88xvyFRir95hO6VA9aSfigkp5swmhGUipPgDbew7H7ae3I7K6BADXCENNJQQUOHkrMT2sUoozVlvsUuMaSZpXp1ZCJ7ltVGvwQ7/xAIC7I0Il69k+xHott36FgvvC1LWjwEn6JWBuxoJG4UtNbWmbGieAu1JFQRMhhHQu0tF5ilbIOJmdXHR0VePEJIGUHz+kPMyfO7GPCfXFHv9QGHx84Qc0KnASxJfny24n518EAGxMnoBC/1D4J3DzKeok1zT1Gh8gMEH2uOCSbFiUKhT6h8rmmxLEVBbjsX2fy5ZNSj+IbqVcZiW8phyAPOvjjJGv61JZnA/Vq+BLIDRVXOAkTHkiDtVzEzjZN4h6YcK9eGrnh7YFFRVAUP3KJVw1hyiplp/XCfN31Wj0OMu3eI/kG28YKXACQEP1vJZwdUYrCZzsM07SpglaldJlswFXrbSFrnxCjZMwVG90xnEc//edeOiOUcB+xw43raHSIB2q13wBnPClpm2joXqEEEI6J+ncTa0xVM/ZMHehttZsl3GySE7wfe069grnEAa+gUFDAydpcBJdWSy773p+At5yfcPmSZSe7+QFhDvcbx80AUBywUWE1ZSJt0dknfZYCmAy86NUXAzVEyar1VVxGSthayqhJspN4CS9kA0A7w+fienz16BGw2ei8vLc7ptUpWyUjuvXJIwsqtNoUcB3TIyq4o6JwdR2F8vbEwqcvJRQ46RVK201TvYZJ8kXh0aldHmlQNqQQErPfznW8e3IffgU7upf3kRwXRV8K0qB559vwqtovPp+CTSU8B3ZVjVOhBBCOifZUL02yjgJwZvRLuNklZzg20/OK5xDVCj5c5ArV8T7KupMHrM20mYFyQUXna5zNTDC7TbsSc9/jsckoULrC7NCiR97O6nx5nUrzUV0VYl4+/5Dm+B3OR25B09AaeUaJ3QruYr8QydQce4iwBhq+GFvPhV8O3S7duRlfMAXm34GrK4OJn6kjlIIodzN42SXcbIqVTgT3RO5QiDoJnAyWayoMdrOk6QZJ2fHXSAM1TOotSjwDwEARFTbMk4AYLUyh0xVZ0JnhV5KGJ6mUSncZJxsHzqtWilrNSkldMexp1EpoVYqUKfmrm7ozUb0LMpEQpnkw2pqme52nvx8yrYPzTlpm1Wcx6nthuoRQgjpfKSjRFqjHfnkflFY9UMaukfIO+qqlQqHoXp+/lw2KcDJhdZAHy7LctWkRG8AWLwYGDwYx+P7Yea6vQjy0WD/3ybJGlYJiqsM+HBvBgBgyvlU3H56u8M6Oyfehq8HTGrQa5MOcysICMOIxR9DazEjqegKbjr3u2zdb5Mn4rYzOxy2MfXCfuDeaQCAL+P6YtjVs9wd/+H+lzluCn4Y9SjCqssQnHWZW+jLdeHT8scyP8BWCpGf1B+Pz10DKBTodYFvMuE24+Q8qCryC0GPkqtArutJhye9ugtXy2pxatUU+GrVOHDZFhAaJRebFZD/QxMzTmotCvy4fe9RchWALeP02Ibj2HwyB5/++RqM6hHmch86Kso4eSmL0xonnWwdaTtrjUqJ01crnG7LT+s6OPDRqGDQCEP1jOifb3c1qLTUyaNanr8k2GvW5hB84KShjBMhhJBWpJVc7GyNduRdQnxxZMVkbHlsnGy5SqlAVlAUfk9IQYVPABAZCc3cO3Hi2Sk4tGKyw3bGJ3HZoO/5umkAQGoq3tzOddcrrzVh5fenne7DrW/tw5s7uIYQM87uFpc/fPNfUegXjMNJw9Dry/VIjI/Ai3yn3/rwsRtOGBYRggq9Pw7H9cPz1y3Eiuv/gokL38Xr196Fp6c8jLl3/hNGpRplen8cj+mFC2HxKNP7izVKYtAk0XX3r1ApFehZnGVbOHw4ANtQvZyACOzqNgQAEJ11EYEGbhhjloYfeujm4rN9jZOgwI/LBLnKODHGkFlSA4uV4Wwud94XGWibp9NdeUNy/iUAQJ1aJ87RBQCBdVViPdcPJ3JgZcCnB6443UZHR2eFXkoYd6txW+MkzzhJLRzbDf/Zw10hsU+7S+k0KnGont5sRFAd15oz1z8MMVXFQEmJy8e2pMoWakcu9oSgjBMhhJBWZD+8vjUIDR6k1EoFDEoV/nTnP9Ez0h9bl3IBkas2BD0j/ZEU5Y9NmIh++ZfwwKGNQE4OICkt+vJwNv41K8XhsZkltvmFhMldj9/3GDZHjMXmvmOxdel4xIX7Y8uScQ6PdUcvCZwiA3TYu/w67LtYhLv+cwAfDL8FybGB2PHoWCQujwMApCakIGnZJgDAmJ7hSIoKwAd7L0NvqsMfr80St3U0tjc+HnIT1vz4KgAgvLwQPia+M92QIYA/V9MkHj+FAvPveB7H/j0XIXWViKksQoXeH1HCkMBxrl+XfY2ToFAInDIynN5vkDTuEvZD1hxCcr99ZtPCDx0MqylDtc5XXB5TWeQw/1NzXrT2JpRx8lIWq3SonjABrrzJg7w5hPzTUd9YQ6OyDdUDbGNds4KjuAVtFjhJu+o1f3MIqnEihBDSmqRZJm0bdi9T2o1WqQ+hjEnMUrgZRubKoBxuLqfqfrbMUqCLUgJPpBknoRxBWjfm56K2G+COg/CYOo0epZLGFJnB0diUPFG8PTw7DX7CHJd+tiGPGrtzrrwAbkib0PwispI/d4p17PgncJVxKuRrj/C//zm9v8ZoazcuTGgsqwuXnADaXzcPruWaWGzvMQIAxM560ZXFDq3Ym/GatVehwMlLOc042Q3Vc3f1qr51QRqVUsw4AUB4dRkAIEco1KystH1jtqKWaw4h1Di1zTxOhBBCiEbdCkVOLqiVri+6elIgBE45DZ8wVaivMQcEistcdf31RBo4+TvZhv1QPimFQl77LTRJAIA9idywu70JAwEA9xz9ESGMz+bIAif5OVc+36Huo69Wom/BJYRVeQ6cXA3XvBTCZcmgdT5tiXSCW+GcxlU7cvtTQWEoYTnfDVDY78iqYhjNVtmFak9NPzoqupzupSySwEnjIuOklnzhaeyuXNhfDXFFrVLArFLDpFRBY7WgT2EGAEl7T6sV2LMHGDcO1QYzLhRUIaVLkDgHhclixcnscug1SkQF6hHuZFhAQWUdymtMqDVZ0C3cz+GL8vTVcsSH+iLIR4OcslqUVBuRWVIDH2MdRmeeQJwiHVBkAhMm1CtDlF9RhyqDGTUGC8IDtIgJ8hHvyyvnUu4h/LwFlHEihBDS2toy46RSuh7m74kQOFWfPQ/Vpk2YKrkvc9l+ZPYeiJqR1yIq2Bcp8cEAAAWzYkzGcXEOofLEnsAlLvDSaxr3Pkgf5yxr5W67CgCBkvOQd0bOwuubXwMAlPpw2aecgEgAwIjsNOTEduNWdBM4pUV1w4TLRwAAP3/4KP9ECiAqqp6vyOZA1/7cH3l5yDt0Asd9IrnheQcOwHglC1adDjpzFAxqLcxWBsYY8isM0FhMWL3lTQQYqmE9+x8oJ0/GhXG3AwB6FGWhZ3EWehRnAwAq9NxrETJlo6+cRMmGb1G9cDb33Iwh+PghHCs9iZggPaKDfIBRo4CYmAa/Hm9DZ4VeSjaPE9+O3Kq2H6onyTjZXbl4YFwPbDqeg9sGx7l9nuIq7gpQjUaPIEM1BuVyqfR8/1AYlWporWZg/HggLQ1ztxXjZHY51s4djBkp3FWUv/+Yho9TbQWEGS9Od3iOEf/cJv4tHU8NQByTHBukx97l12H6G3tQWsO93me2/wd3nfiFW/FFAOvWAQ895Pb1AMDIF2zPFxGgw6GnbcWuS7/kOt1M3/0tt8BNq1BCCCGkufhKus61RnOI+lDX8zdwSNcQXCioEk+0/Qpy8e6mFxzW6wrgrWtmIc9Qi4Ih/YCwcbjh3D689d2L3Ap+fvDrEgOAC5waOxGwr2QontAuXTo8Lz6Eq9/pGxOIs7kVCPfXoog/3+kS4osgX9v51KEu/VCqD4BJpcaJmCQAwNrRczD79FYAwMyDm7kVA2xD+uwvTq+59m6E1FRg7slfbQujohp1cbZMMnRQP2EcFj3yGSZePIQPv35OXD6H///RO9Nx95Y/AAAPp36JWaf5858LAL77DqsX+SJI64uf1j8KncWWlRKGJwoZp1vTdgJP7UTJj58AY5/ENVmn8MrnT8l3rG9fIC2twa/H21Dg5KWErnpatRIaK59xskvbSosjFQoFNjxwDea8tx9/u6EPIgJ0OPjUJI9fSuW13Afp1bF/woKsA/DXqXFV6Yufel8LldWCFTs+4FY8cwYns7nMzVdHssXASRo01Ud6QZXs9pbTXNeYnPI6GMxWMWgCIGa/6nQ+0BtqgYvO539wp7DSAIPZ4lCEaVTxX5pjxzZ4m4QQQkhDdY/wx4PjuiPUT9vogKE5lNbY5ui5Z1RCvR7zf9cn4bez+bjCYvDB0JsxIC9ddv+QnD+gYtx5y0P7v+YWHtuM5Plx6M3/lgMAXnoJE/pEYc6weAyMd9WOwjN/nRqPTuqFwxkluH8MlxFKjg1E93A/XCqqxqOTewEAXp41EOt2pOPxKUlY9MlRpBdU4fEpSbILz9nB0Rj6yCcAuLmUACAzJAZf3HAvBp0/gshAHULDgoC//EV8jH3GyajW4OmpD6NOo0P/vItgCmDEqqUeX8c/b+2Pk1nlyCypQeolfnJghQIvjl+A5bvWI7CGK5cYfPUPp48vfuXf2NeFy/t159uKS8VUFCJQ6wudxQSDSo2T0UkIT0rEHr4T4NcDJmFA3gVcd+kw99QX0oGxQNdS7tysTO+PjJAYDMq90KhzMG9EgZOXMknmcdIJGSe7wMl+DO/I7mGyjE9Dvpg/HjoDz//2DgAgEkD+8s14f8RtGJxzDtPP7eXHM/fgtutmO4wx2fNaG1BdWG0wy25H8mOET/cYiGFpB+o1W7mzMblVdWbo/FWysbvCOF9MmVLv/SOEEEKa4m839m3rXcD4pAhs/6MAADCtf3S9HhMdpMfRZ64HAPR6Wum09nj5zg+x6MA3smXXZJ7CQCX/e/uPfwAPPwwVgJdmDWz8C+AtvT5JdluhUGD7ExNky/rHBeHtPw0FANloFwBIivLH+XzuYu6lf93s5BkcR9AIpIHT1OQoHLlShqIqA56b/KC4PON+148X3D0yAXeP5P4+lFGC2e+kAgDWD70Jy3ethxIMfsZahNRxTR029RuPmWm7xMf32f4DcA8XOPVTcO/z4pufxPOnNiH08nloLGYEGrjXmBUUjdl/+hf2PDkRVf/i5rXKCo7GfbNXIa68AHvfuQ8BJQVQMCtiNNz50oEeQ/DXSYtw/I27AKMRsFjczk3VEdA4JC8l1DipZe3I5fVDrZHqb2ghaLWk2wsgL2L0+FiDZF3GEMnXIWUIhZL1CJycNcUQGk0ILTzVFjP8hPaiwcH13j9CCCGkI2lM5stVQ4ev+jvOAdWv4BLCK/hMiptGCd5GWmMeoNegOUrWlJJjUafWwcxnvwIMNZh48RAA4ERMEr7pf524Xnxuhvi3XzUXXJXpA2DhSzu0FjMC67hzp0p+ziq1kxr4vIAwWBRKqC1m9C68gkArV49m0PnAoJJctDcYmvoy2z0KnLyUtMZJIwZOzd8BztV3phCTCeNf6xs4STu7APK2mZ5USTJOIbUVXH0VgMuBfHFlTY2zh8k4m/NJ2K6RD5z8jLW2O4MaP1SAEEII6Wz0LhpKXAyPx4+9x8iWhdZWILS8iLvRgQInaXMPf5263rVi7siuhSsUqOEbOAQYqsVpaSp1fnh8+lLcNH+NbV1+pI1PTSW/ji9MfBdmvdkgzp9Vyc/b5Oyiu0WpgoEPtialH0SAhRvOadLqYZTW19fVNe1FegEaquelhBon2TxOLlpTAkBjm0YqXDw22FeLkmqjOGdDybbdWNyDX3MfcCpnKKrm3C2u36fgMialH4Txub04NfF6PHpOgVlDu6Ck2oiUnHMYm3FMXLfquWNY6TcQN04fKXvO/ZeKkZyXjiE5f+APfm6BIt8g5Cn4GbG3b3f7Wo5mlmJrWr54O7qiCLec3YmDx7+Ff99I6LslAKwLwmvKuBX0euqqRwghpFNpyTbTK69fhD3dBqNvwWUsOPojJl46YruzAwVO0qF6gXo1KuwuGjeGfUBTpvFBICqw4OgPCK0pBwDs49ukn4uw1abFVhZCyRiCC7m5tSr0/rhiUCAWwIisM2LAVKXl6tQ1LoK8rT1H4uazu3HdxUPw9+XON416H1iUKljVaijNZgqcSPtlttjakQtD9ZjWsdW3oGekf6OeR6lQiPMASE3sHYlvjmbjahDXkjM05wqeyJE0gtjzCeaeqQESuJnC1/zwCvoUXQH2AJfWf4TLD7yHl385h/DqUhz+3+Pyje8BJvYZi/uL/ooFoxPFxc//mIbDX61EOP8FAXAzaAsfdpSVuR1fe8c7qbKM0ycbVqBnCdd6E3xzvuF3vShOwudqjgRCCCGkoxrdIxw7zhWiW7if55WduKZHGL496tiIAACK/YKxIWUqEkpzsODoj/I7u3dv1PO1lOGJoTifXyWb16q+pMPddBqVbO7JxlLaDQEq8gtG1/J83H18CwCgWqNHLj9VjEllywKt2/QSBueeE2+X+ASiQsHdP//oj9jRnavxEhpfqFxMV7Oz+1DcfHY3hubYGlFU+3Ojcqw6HQVOpH0T53FSS2ucHIfqfbVoFI5cKcVNAxrXW5/7oDoGTqtu7odvjmbjUJd++Ne4e9ClvEC8b0zGMXQtz0diaS5SE1KgMxm4oInXtSwPSqsFVqUKM87uFpd/OWAywqvLcN2lw4gv4zq2CHVHAKC0WmRBkyA1QVJEWlMjawkqMFmsDsP0gviCyMwgbqhf1/J89C24jJC6Cm6FdvYlTgghhLS0eaMSUGuy4Lo+kY16/MoZycgrr0O4vw6rbxuANVvP42BGKfrFBKCw0gjGGPZeVOLt+U/jmvzz6BMXDJ9//l02D1J7sPyGPogM0GP6wIafP0mH6l3bMxwv/3LOzdr1Y59x+vt1C3Hbme3wVQEhflqkpVyLF25Pwd++PQUAOBndEwPz0mVB06/XzkC5TwDeHz4TUy/sh4pZoeZHMGUGc+dCGqUS3/xlFH5Ny0dGUTV2nCuE0WzFT72vRWJJDkYHWtEr0h9B0eHYGTIWKAesWh1XZ06BE2mvZPM4iUP1HDNOwxNDMTwxtNHP46rGSSj+ZAol3hp1h+y+f/7yJu4+vgVRVVzB55ofX5Xdr2ZWhNVUoNA/BKOvcPMm7eg+FE/euAQDcrm2lyl5F9C1NBeFlbYv7jAnQdOOSbNQofMDUyigYMxl4FRlf7WHMQTXcuN9Z9/9Ehanfol5x37C8Ow01ApNNmbPdvGuEEIIIR2TXqPCo5N6NfrxQT4afLbwGvH209P7uVjzhkY/R2sI0Gvw2OTGvQ/SICc2SN8s+2OfcToW1wfH4vogKcofv/7feFwH4IcTtnrzcp3jSKMPbnoQKAMOdUlGnVoLvdmIvoWXAQBnIrnOyBqVAkMTQjE0gTt33HwyFw9/dhR1Gj1eGzcPj0q6Mxve2QeUl9qak3WCwImaQ3gpMeOkUtgyTi0wtMz+g1ofQsMIYZ6lG87vE+8r4ifHE4KqgfxcD+fCufG4Bf4h4rovbXkDBZW2Di1RfPtxqbrwSEChgEXPD9dz0VnPPk0+JOcPaKxcY4oyn0Awvom6WamytSIPCQEhhBBCSENIO/hKJ+NtCled+bSSZhzS+TsDjI4Ns0rV/LmSQiGWOQjnVq6aQzjrsmf/3Gbh/JMCJ9Jema22GqcpF/YDAFiLBE4Nf4zQMGLa+VTcfewncXmefyhy/bhgJI4f2hdWXQYAOMnPxl3sGyyuPyrzFIpKbYGQEGxJWUO55zLp3AdO9oWZc07YZu82qLU4Fd0TANcaNUAInKijHiGEEEIaSBY4aZpnXiNXF7J1atv2pfN3HojvL1uvtEcfGCWn/eV6eUaqig+c7FvQa930Uhee26LtPBknGqrnpYSuesFlheKy2ui4Zn+exmScKnS2ccrLdn8s/j3hgfew9vuXMQDpeHfTC/it5wio+ZnET8Zw6XCzSv5P8q23H0FmMDe+OL4sH/Yqu/cGzpajXKmBD4BTd/4ZxqAQxAb7wJR9FfuGXIeLs+/BMH64YvfibCw68DXuOLUVAPDqGK7zX4lvIACgd1EmehdlchunwIkQQgghDRSgt53LKJtpTk1Xc3NKAxu9xvZ3keRC9O7Ewch992NYj9rOGQ/H9UOPElsTj+xA5zVt0g6BPnZBoE7MOFHgRNo5IePkZ7DNOZSVMtLV6o3n5vOuUIjTA8gc6DpA/Du4jmvAcDYiEXUaPXICw8X7rk8/KP6dzTdoALhJ8maf5gKbQbkXMCj3gtPnN0VFI6xLFHC2HJm+oYguycOAtIOydbqeOoSUoEE4nZwIALj3yPdi0AQAquuuAwzA0dg+jk8wZIiLV04IIYQQ4lz3CH88fn0Swvy5gGL20C746kh2k7bp6kK2vyRIiwq01VPtTRwEADCoNHj7mllYFB+Fmy0arN3OlUhkB9kCpZ8Xr0SBX5jT7XeLsF0M3/TwtU7XuVRpQRiAsr0HEXzjjfV6Pd6KAicvJaSB9SYucMr1D0N8aPN3pHGXcfr9r9chLacCccE+OJJZCgWAa7qH4kxOBf4x4RgGHd4BXUkhkqIDUTB0DLC3HC9MuA+nonthZJgaZ3K47nU3LJ2Ht+N7wFenxvwPDmLZ9CU4ef9jCNn5KyqquBqnGSmxMFutYHofVMd0QY+iLCTOvgn3JXVDdKAeX4f9Ez/+ugVKxqBkDM9u/4+4n9FVxbhSHAEACOIDufSxU+H/lwdwz803QbX/Co5kluKHt7+G5cBBTOwTiaCJY4GYxnUiJIQQQkjn9oikwca/Zg3E9f2i8MD/jrh5hHvSzFVimC8yirkapqdu7Csujw/1xUf3jUBWSQ1WbAJ6PbERPUJ98OhNAzG2ZzhGdQ9Dz0h/PPbFcbx9zWxkB0XhydnDcSwiBdh9yenzxgX74IsHrkGwrwa9o+XNt7ae5UYChdZy53Npuw5jdKNfoXdoF4HTunXr8PLLLyMvLw8pKSlYu3YtRowY4XL9r776Cs888wwyMjLQq1cvvPTSS7ixg0e49oR5nPRGLrCo1egQ5OPYjryp3GWY44J9EBfM1Rb1iw0Ul/eMDMAtg+KA2waJyxIATC45hK1nC/D1gMm479GxWPbGHgDAjORk3JAQgqwSWyHj9TeORPaogXhjI9dW8+aHRmNkV8dmDf4A7hgejyqDGc8X216/NHCKqixGDt8corsvv4/3zALm3gZA+uU2Alh0u9v3gxBCCCGkIRQKBaYkR0OrVsIomWalIVSSC9nX9YnCB3u5bnhdQ31l641P4i4Ur9h0GiaVBuNSuuJGfkoarVKBWwbFYdnXJ2GEGhv7X4dnZ10P7Lro9rmv6e48GyWMOvqp97V4JHUDYrKcjxDqSNq8OcSGDRuwdOlSrFy5EkePHkVKSgqmTp2KgoICp+vv27cPc+fOxf33349jx45h5syZmDlzJk6fPt3Ke962zHyNk87EBU51Gp1sTG1zaUyNU334alUOf/tIlvloVbLXI13fGXevPbK6FJUGLnDy5QNN+Pq6XJ8QQgghpLk1pdyJSebU1Eg63bmqfXK2rkAv6cSnVinAnNVd1INw3nY2shsAoFvmeec1HB1ImwdOr732GhYuXIh7770X/fr1wzvvvANfX1988MEHTtf/97//jWnTpmHZsmXo27cv/v73v2PIkCF48803W3nP25YwVE9bxw3Vq1XrZONcm4t9d5Xm4ixwki5TKuTjdn017l+bMK+UM5GSNubC0Mb2NtEeIYQQQjq2plyMljTq8xgsSSmcFKtL25Zr3HTN88Sfb7WeKqltR7FjB+SOpE2H6hmNRhw5cgR/+9vfxGVKpRKTJ09Gamqq08ekpqZi6dKlsmVTp07Fpk2bnK5vMBhgMNjmAqqoqGj6jjeT/Y+sQNQ3nzfqsZ+YrWAA4hXca6vR6Fsk49RCcRP0siCJexK9pKUmY0CAZO4DnyZknO4/tAkzzu4GAESW53ILKXAihBBCSCtSNSVwkkRODQmc+sYEOiyTnlNpVMpGXyQP1GuQW16HUt8gVGp9EGCsBSIicDmme723EZy6ByEJsY16/rbQpoFTUVERLBYLoqKiZMujoqLwxx9/OH1MXl6e0/Xz8vKcrr969Wo899xzzbPDzYzl5aFbrvNivIYqiO4q6+XfXB69riee+e4MZg5q+j/qu69JwNazBRjZLRR+Wts/vYgAruuMtPCxV2QAjBYrlAoum+SpfqtbOBcIaVQK9Ijwx4JZq7D+61UAgLDaCoTVSgJmhQLo2bPJr4cQQgghpL4em9wL/9h8FrOGdmnwY4VzJQC4aWAs1m5PR2yQ3uX6mx8dg+NZZbhxQLTDfUO7huBKcQ1igvRQKRWYPiAG7+2+JJ5L1dcD47rj8a9OAAAOxvfHpIuHAKBB57ZFJmODnrOtKVhjBzY2g5ycHMTFxWHfvn0YNWqUuPzJJ5/Erl27cODAAYfHaLVafPTRR5g7d6647K233sJzzz2H/HzHeX6cZZzi4+NRXl6OwEDHKLw1ZR04gbKz6Y1+fEywHuH+OhTUWaEZcy1Cgps/i8IYw8XCKnQL92/QFQ5XLhZWoUuID3RqFYqrDLAwhsgA2we/rMaIOpMV0fyXQVZJDXQapWwdV64UV0OtUiLIR4MTWWXQqhTQnToBXUUZjGaGAL0aCWG+UHTrRoETIYQQQlpVU8+pCirroFIoEOavQ2ZxDcL8tfDTNTwHYjBbcPRKGfpEByDETwuAO4eKCtTLhvF5whhD6qVipBdUIUDJ0OPiaSiMDQuEkmbfAJ1f29adV1RUICgoqF6xQZtmnMLDw6FSqRwCnvz8fERHO0bIABAdHd2g9XU6HXQ6ndP72lr8yBTEj0xp8nacT1nWPBQKBXpGBnhesZ56RNhmqhbmN5AK9tXKbseH1v/DlBBmCxyv7cnPF9XtugbuISGEEEJI82vqOZX0InLXsMYHGzq1CqN6yDvlSc+h6kuhUGB0j3CM7sGfc43s1uh98hZt2hxCq9Vi6NCh2LZtm7jMarVi27ZtsgyU1KhRo2TrA8Bvv/3mcn1CCCGEEEIIaao2n8dp6dKlmD9/PoYNG4YRI0ZgzZo1qK6uxr333gsAuOeeexAXF4fVq1cDAB577DGMHz8er776KqZPn44vvvgChw8fxnvvvdeWL4MQQgghhBDSgbV54DRnzhwUFhbi2WefRV5eHgYNGoQtW7aIDSAyMzOhVNoSY6NHj8Znn32GFStW4KmnnkKvXr2wadMm9O/fv61eAiGEEEIIIaSDa9PmEG2hIQVghBBCCCGEkI6rIbFBm0+ASwghhBBCCCHtHQVOhBBCCCGEEOIBBU6EEEIIIYQQ4gEFToQQQgghhBDiAQVOhBBCCCGEEOIBBU6EEEIIIYQQ4gEFToQQQgghhBDiAQVOhBBCCCGEEOIBBU6EEEIIIYQQ4gEFToQQQgghhBDigbqtd6C1McYAABUVFW28J4QQQgghhJC2JMQEQozgTqcLnCorKwEA8fHxbbwnhBBCCCGEkPagsrISQUFBbtdRsPqEVx2I1WpFTk4OAgICoFAo2np32kRFRQXi4+ORlZWFwMDAtt4d0gB07LwXHTvvRMfNe9Gx81507LyXNx47xhgqKysRGxsLpdJ9FVOnyzgplUp06dKlrXejXQgMDPSaf9REjo6d96Jj553ouHkvOnbei46d9/K2Y+cp0ySg5hCEEEIIIYQQ4gEFToQQQgghhBDiAQVOnZBOp8PKlSuh0+naeldIA9Gx81507LwTHTfvRcfOe9Gx814d/dh1uuYQhBBCCCGEENJQlHEihBBCCCGEEA8ocCKEEEIIIYQQDyhwIoQQQgghhBAPKHAihBBCCCGEEA8ocGpju3fvxowZMxAbGwuFQoFNmzY5rLNgwQIoFArZf9OmTWvydqUWLVoEhUKBNWvWuF3v999/x7XXXouwsDD4+PigT58+eP311x3WW7duHRITE6HX6zFy5EgcPHjQ7Xa9kbcdO6m9e/dCrVZj0KBBsuWrVq1y2N8+ffrUe7veoi2PXWO2CwA7d+7EkCFDoNPp0LNnT6xfv95hnY7+ufO245abm4u77roLSUlJUCqVWLJkicM669evd9iuXq93u11v5G3Hjn7rbLzt2EnRb13bnqecPXsWN998M4KCguDn54fhw4cjMzPT7bZPnjyJsWPHQq/XIz4+Hv/6178c1vnqq6/Qp08f6PV6DBgwAD/99JPbbTYnCpzaWHV1NVJSUrBu3Tq3602bNg25ubnif59//nmzbBcANm7ciP379yM2Ntbjun5+fli8eDF2796Ns2fPYsWKFVixYgXee+89cZ0NGzZg6dKlWLlyJY4ePYqUlBRMnToVBQUFHrfvTbzt2AnKyspwzz33YNKkSU7vT05Olu3v77//Xu9te4u2PnYN3e7ly5cxffp0TJw4EcePH8eSJUvw5z//Gb/88ou4Tmf43HnbcTMYDIiIiMCKFSuQkpLicr3AwEDZdq9cueJ2u97I244d/dbZeNuxE9BvXdseu4sXL2LMmDHo06cPdu7ciZMnT+KZZ55xe2GooqICU6ZMQUJCAo4cOYKXX34Zq1atkn3u9u3bh7lz5+L+++/HsWPHMHPmTMycOROnT592u8/NhpF2AwDbuHGjw/L58+ezW265pdm3yxhj2dnZLC4ujp0+fZolJCSw119/vcHbv/XWW9mf/vQn8faIESPYww8/LN62WCwsNjaWrV69usHb9hbedOzmzJnDVqxYwVauXMlSUlJk9zlb1tG19rFrzHaffPJJlpycLFs2Z84cNnXqVPF2Z/vcecNxkxo/fjx77LHHHJZ/+OGHLCgoqNHb9UbeduwE9FvnXceOfuvkWvvYzZkzR/Z5qY+33nqLhYSEMIPBIC7761//ynr37i3evuOOO9j06dNljxs5ciR78MEHG7bjjUQZJy+xc+dOREZGonfv3vjLX/6C4uLiJm/TarVi3rx5WLZsGZKTk52uM2HCBCxYsMDlNo4dO4Z9+/Zh/PjxAACj0YgjR45g8uTJ4jpKpRKTJ09Gampqk/fZG7WnY/fhhx/i0qVLWLlypcttX7hwAbGxsejevTvuvvtuj2n1jqwljl19tmt/7FJTU2WfKQCYOnWq+Jmiz51cezlu9VVVVYWEhATEx8fjlltuwZkzZ5plf71Rez129FvnWXs6dvRb1zDNfeysVis2b96MpKQkTJ06FZGRkRg5cqTDkL4FCxZgwoQJ4u3U1FSMGzcOWq1WXDZ16lScO3cOpaWl4jrufg9bGgVOXmDatGn4+OOPsW3bNrz00kvYtWsXbrjhBlgsliZt96WXXoJarcajjz7qcp2uXbsiJibGYXmXLl2g0+kwbNgwPPzww/jzn/8MACgqKoLFYkFUVJRs/aioKOTl5TVpf71Rezp2Fy5cwPLly/HJJ59ArVY7fczIkSOxfv16bNmyBW+//TYuX76MsWPHorKyskn7641a6tjVZ7v2xy4vL8/pZ6qiogK1tbX0uZNoT8etPnr37o0PPvgA3333HT755BNYrVaMHj0a2dnZTdpfb9Qejx391tVPezp29FvXMC1x7AoKClBVVYUXX3wR06ZNw6+//opbb70Vt912G3bt2iWuFxMTg65du4q3Xf3WCfe5W6fVPnetktci9QI3w7KkLl68yACwrVu3Nnq7hw8fZlFRUezq1avisoYM97p06RI7efIke++991hoaCj77LPPGGOMXb16lQFg+/btk62/bNkyNmLEiHpt2xu192NnNpvZsGHD2Ntvvy0uq89QhdLSUhYYGMjef//9eu2vN2rNY9fY7fbq1Yu98MILsmWbN29mAFhNTU2n/Nx5w3GTcjVUz57RaGQ9evRgK1asqNd2vZE3HTv6rZNr78eOfutca81jJ3w+5s6dK1s+Y8YMduedd7rc1vXXX88eeOAB2bIzZ84wACwtLY0xxphGoxE/h4J169axyMjIeu1vU1HGyQt1794d4eHhSE9Pb/Q29uzZg4KCAnTt2hVqtRpqtRpXrlzB448/jsTERI+P79atGwYMGICFCxfi//7v/7Bq1SoAQHh4OFQqFfLz82Xr5+fnIzo6utH721G01bGrrKzE4cOHsXjxYvExzz//PE6cOAG1Wo3t27c7fVxwcDCSkpKatL8dRXMcu8ZuNzo62ulnKjAwED4+PvS5c6Mtj1tjaDQaDB48mD5zaB/Hjn7rGqetjh391jVdcxy78PBwqNVq9OvXT7a8b9++bodEuvqtE+5zt05rfe4ocPJC2dnZKC4ubvCQEKl58+bh5MmTOH78uPhfbGwsli1bJuvUVR9WqxUGgwEAoNVqMXToUGzbtk12/7Zt2zBq1KhG729H0VbHLjAwEKdOnZI9ZtGiRejduzeOHz+OkSNHOn1cVVUVLl682KT97Sia49g1drujRo2SfaYA4LfffhM/U/S5c60tj1tjWCwWnDp1ij5zaH/Hjn7r6q+tjh391jVdcxw7rVaL4cOH49y5c7Ll58+fR0JCgsvHjRo1Crt374bJZBKX/fbbb+jduzdCQkLEddz9Hra4VslrEZcqKyvZsWPH2LFjxxgA9tprr7Fjx46xK1euiPc/8cQTLDU1lV2+fJlt3bqVDRkyhPXq1YvV1dU1ervOOBvuNW/ePLZ8+XLx9ptvvsm+//57dv78eXb+/Hn2/vvvs4CAAPb000+L63zxxRdMp9Ox9evXs7S0NPbAAw+w4OBglpeX18h3qX3ytmNnz9nwhccff5zt3LmTXb58me3du5dNnjyZhYeHs4KCAs9viBdpq2NX3+3aH7tLly4xX19ftmzZMnb27Fm2bt06plKp2JYtW8R1OsPnztuOG2NM3O7QoUPZXXfdxY4dO8bOnDkj3v/cc8+xX375hV28eJEdOXKE3XnnnUyv18vW6Qi87djRb52Ntx07e/Rb1zbnKd9++y3TaDTsvffeYxcuXGBr165lKpWK7dmzR1xn+fLlbN68eeLtsrIyFhUVxebNm8dOnz7NvvjiC+br68veffddcZ29e/cytVrNXnnlFXb27Fm2cuVKptFo2KlTp5rzrXOJAqc2tmPHDgbA4b/58+czxhirqalhU6ZMYREREUyj0bCEhAS2cOFCj1/MnrbrjLOT7/Hjx8se88Ybb7Dk5GTm6+vLAgMD2eDBg9lbb73FLBaL7HFr165lXbt2ZVqtlo0YMYLt37+/IW+LV/C2Y2fP2Y/JnDlzWExMDNNqtSwuLo7NmTOHpaenu91fb9RWx66+23V27Hbs2MEGDRrEtFot6969O/vwww8dnr+jf+688bg5225CQoJ4/5IlS8RjFhUVxW688UZ29OjRpr5V7Y63HTv6rbPxtmNnj37r2u485b///S/r2bMn0+v1LCUlhW3atEl2//z589n48eNly06cOMHGjBnDdDodi4uLYy+++KLD83/55ZcsKSmJabValpyczDZv3tzg96axFIwxVu/0FCGEEEIIIYR0QlTjRAghhBBCCCEeUOBECCGEEEIIIR5Q4EQIIYQQQgghHlDgRAghhBBCCCEeUOBECCGEEEIIIR5Q4EQIIYQQQgghHlDgRAghhBBCCCEeUOBECCGEEEIIIR5Q4EQIIaTTmTBhApYsWdLWu0EIIcSLUOBECCGEEEIIIR4oGGOsrXeCEEIIaS0LFizARx99JFt2+fJlJCYmts0OEUII8QoUOBFCCOlUysvLccMNN6B///54/vnnAQARERFQqVRtvGeEEELaM3Vb7wAhhBDSmoKCgqDVauHr64vo6Oi23h1CCCFegmqcCCGEEEIIIcQDCpwIIYQQQgghxAMKnAghhHQ6Wq0WFoulrXeDEEKIF6HAiRBCSKeTmJiIAwcOICMjA0VFRbBarW29S4QQQto5CpwIIYR0Ok888QRUKhX69euHiIgIZGZmtvUuEUIIaeeoHTkhhBBCCCGEeEAZJ0IIIYQQQgjxgAInQgghhBBCCPGAAidCCCGEEEII8YACJ0IIIYQQQgjxgAInQgghhBBCCPGAAidCCCGEEEII8YACJ0IIIYQQQgjxgAInQgghhBBCCPGAAidCCCGEEEII8YACJ0IIIYQQQgjxgAInQgghhBBCCPGAAidCCCGEEEII8eD/ATw0CLsdlADcAAAAAElFTkSuQmCC", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# The Median can be less sensitive to outliers\n", "var_smoothed_median = df2[var].rolling(window=\"30s\").median()\n", "plt.figure(figsize=(10,5))\n", "plt.plot(df2.index, df2[var])\n", "plt.plot(df2.index, var_smoothed_median, \"r-\", label=\"moving median\")\n", "plt.xlabel(\"t\")\n", "plt.ylabel(var)\n", "plt.legend();\n" ] }, { "cell_type": "markdown", "id": "86f44119-354b-4ab3-bf7c-d4d9d5c27317", "metadata": { "tags": [] }, "source": [ "### 6.3 Subsampling\n", "\n", "A DF with time-based index can be subsampled at a given frequency using method `asfreq` (http://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.PeriodIndex.asfreq.html)." ] }, { "cell_type": "code", "execution_count": 31, "id": "80d0316f-307d-4311-a066-666bbec5764a", "metadata": {}, "outputs": [], "source": [ "df3 = df2.asfreq('1s')\n" ] }, { "cell_type": "code", "execution_count": 32, "id": "054274da-fe38-42ad-87c6-7cd755af4326", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "DatetimeIndex(['2011-09-15 14:26:02.875000', '2011-09-15 14:26:03.125000',\n", " '2011-09-15 14:26:03.375000', '2011-09-15 14:26:03.625000',\n", " '2011-09-15 14:26:03.875000', '2011-09-15 14:26:04.125000',\n", " '2011-09-15 14:26:04.375000', '2011-09-15 14:26:04.625000',\n", " '2011-09-15 14:26:04.875000', '2011-09-15 14:26:05.125000',\n", " ...\n", " '2011-09-15 16:01:18.625000', '2011-09-15 16:01:18.875000',\n", " '2011-09-15 16:01:19.125000', '2011-09-15 16:01:19.375000',\n", " '2011-09-15 16:01:19.625000', '2011-09-15 16:01:19.875000',\n", " '2011-09-15 16:01:20.125000', '2011-09-15 16:01:20.375000',\n", " '2011-09-15 16:01:20.625000', '2011-09-15 16:01:20.875000'],\n", " dtype='datetime64[ns]', name='t', length=22825, freq=None)\n" ] } ], "source": [ "# This is before subsampling\n", "print(df2.index)\n" ] }, { "cell_type": "code", "execution_count": 33, "id": "6c02b486-1530-4f9a-9b6f-17b1f9ac11a7", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "DatetimeIndex(['2011-09-15 14:26:02.875000', '2011-09-15 14:26:03.875000',\n", " '2011-09-15 14:26:04.875000', '2011-09-15 14:26:05.875000',\n", " '2011-09-15 14:26:06.875000', '2011-09-15 14:26:07.875000',\n", " '2011-09-15 14:26:08.875000', '2011-09-15 14:26:09.875000',\n", " '2011-09-15 14:26:10.875000', '2011-09-15 14:26:11.875000',\n", " ...\n", " '2011-09-15 16:01:11.875000', '2011-09-15 16:01:12.875000',\n", " '2011-09-15 16:01:13.875000', '2011-09-15 16:01:14.875000',\n", " '2011-09-15 16:01:15.875000', '2011-09-15 16:01:16.875000',\n", " '2011-09-15 16:01:17.875000', '2011-09-15 16:01:18.875000',\n", " '2011-09-15 16:01:19.875000', '2011-09-15 16:01:20.875000'],\n", " dtype='datetime64[ns]', name='t', length=5719, freq='s')\n" ] } ], "source": [ "# This is after subsampling\n", "print(df3.index)\n" ] }, { "cell_type": "code", "execution_count": 34, "id": "97ca0415-c903-4e3a-9849-36838262a74a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(5719, 35)\n" ] } ], "source": [ "# What are now the dimensions of the DataFrame ?\n", "print(df3.shape)\n" ] }, { "cell_type": "markdown", "id": "bbc0d07b-5bd9-4774-8d60-db2d7415f7b8", "metadata": { "tags": [] }, "source": [ "## 7. Feature normalization and standardization\n", "\n", "### Motivation\n", "\n", "Different numerical variables naturally fall in different scales (e.g. N1 <0 to 100> and temperature <0 to 1000>). Many ML models are based on euclidean distance or weighted linear combination of variables and we don't want one variable to dominate the others just because they are on a different scale.\n", "\n", "Feature scaling removes the implicit dominance of variables with wider numerical ranges by transforming all numerical variables to the same range (typically from -1 to +1 or 0 to 1).\n", "\n", "Even for ML algorithms that are not based on euclidean distance or weighted linear combinations (like decision trees), scaling greatly helps convergence speed.\n", "\n", "### Scaling Strategies\n", "\n", "There are multiple strategies for feature scaling.\n", "\n", "* **Normalisation** Scaling: use when the variable is normally distributed. For example, Min-Max scaling:\n", "\n", "$$X' = \\frac{X-X_{min}}{X_{max}-X_{min}}$$\n", "\n", "* **Standardization** Scaling: use when data is not normally distributed. When in doubt use standardization scaling.\n", "\n", "$$X' = \\frac{X-\\mu}{\\sigma}$$\n", "\n", "### Fit the scaler on the training data only\n", "\n", "The scaler must be fit with the the training set only (i.e. the scaling parameters must be derived only from the training set). The test set and any prediction set must be transformed using the scaler fitted on the training set.\n", "\n", "This is the only way to guarantee that the test set and any predictions are subject to the same conditions and have been totally unobserved during the training process (**data leakage**).\n" ] }, { "cell_type": "code", "execution_count": 35, "id": "fbd2c0a9-7f81-4288-bb56-d82fa7f486d4", "metadata": {}, "outputs": [], "source": [ "\"\"\"\n", "EXERCISE - Data normalization and standardization\n", "\n", "1. Using the DataFrame `df`, apply min-max normalization (create a new DataFrame to store the result) on the \"VIB_CN1\" column\n", "2. Using the DataFrame `df`, apply standardization scaling (create a new DataFrame to store the result)\n", "\n", "Hint: Take a look at the documentation https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.html\n", "\"\"\"\n", "normalized = (df[\"VIB_CN1\"]-df[\"VIB_CN1\"].min())/(df[\"VIB_CN1\"].max() - df[\"VIB_CN1\"].min())\n", "standardized = (df[\"VIB_CN1\"]-df[\"VIB_CN1\"].mean())/df[\"VIB_CN1\"].std()\n" ] }, { "cell_type": "code", "execution_count": 36, "id": "9929fc79", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "\"\"\"\n", "EXERCISE - Plot normalized data\n", "\n", "1. Using the matplotlib library, create a plot of the normalized \"VIB_CN1\" with\n", " - A title\n", " - An X axis label (Time)\n", " - A Y axis label (Normalized VIB_CN1)\n", " - A plot title\n", " - \n", "\"\"\"\n", "plt.plot(df.index, standardized, label=\"VIB_CN1\")\n", "plt.xlabel(\"Time\")\n", "plt.ylabel(\"Normalized VIB_CN1\")\n", "plt.title(\"Normalized VIB_CN1 over the flight\")\n", "plt.legend()\n", "plt.show()\n" ] }, { "cell_type": "code", "execution_count": 37, "id": "d11aec8d-adb2-455d-bc1f-6adbabbd50e2", "metadata": {}, "outputs": [ { "ename": "NameError", "evalue": "name 'X_train' is not defined", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)", "Cell \u001b[1;32mIn[37], line 7\u001b[0m\n\u001b[0;32m 4\u001b[0m scaler \u001b[38;5;241m=\u001b[39m StandardScaler()\n\u001b[0;32m 6\u001b[0m \u001b[38;5;66;03m# IMPORTANT: the scaler must be fitted with the training data only.\u001b[39;00m\n\u001b[1;32m----> 7\u001b[0m X_train \u001b[38;5;241m=\u001b[39m scaler\u001b[38;5;241m.\u001b[39mfit_transform(\u001b[43mX_train\u001b[49m)\n\u001b[0;32m 8\u001b[0m X_test \u001b[38;5;241m=\u001b[39m scaler\u001b[38;5;241m.\u001b[39mtransform(X_test)\n", "\u001b[1;31mNameError\u001b[0m: name 'X_train' is not defined" ] } ], "source": [ "# Example: standardization in a training/testing set scenario (using scikit-learn)\n", "from sklearn.preprocessing import StandardScaler\n", "\n", "scaler = StandardScaler()\n", "\n", "# IMPORTANT: the scaler must be fitted with the training data only.\n", "X_train = scaler.fit_transform(X_train)\n", "X_test = scaler.transform(X_test)\n", "\n" ] } ], "metadata": { "kernelspec": { "display_name": "civil-332", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.7" } }, "nbformat": 4, "nbformat_minor": 5 }