diff --git a/demo_baseLoad.ipynb b/demo_baseLoad.ipynb index 35d5c00..8471c63 100644 --- a/demo_baseLoad.ipynb +++ b/demo_baseLoad.ipynb @@ -2,398 +2,88 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ - "# imports\n", - "import polars as pl\n", - "import json\n", "import altair as alt\n", + "import polars as pl\n", "\n", "%load_ext autoreload\n", - "%autoreload 2\n", - "# %autoreload?" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# First some speedtests" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## test 1 reading in a newline delimited json to check efficiency\n" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "7.42 μs ± 671 ns per loop (mean ± std. dev. of 7 runs, 100,000 loops each)\n" - ] - } - ], - "source": [ - "%%timeit\n", - "energy_use_df = pl.scan_ndjson(\n", - " \"data/PP/energy_use_test1.ndjson\",\n", - " schema={\"timestamp\": pl.Datetime(time_zone=\"Europe/Brussels\"), \"total\": pl.Float64},\n", - ")" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "shape: (5, 2)
timestamptotal
datetime[μs, Europe/Brussels]f64
2023-01-01 00:00:00 CET0.025
2023-01-01 00:15:00 CET0.017
2023-01-01 00:30:00 CET0.023
2023-01-01 00:45:00 CET0.024
2023-01-01 01:00:00 CET0.023
" - ], - "text/plain": [ - "shape: (5, 2)\n", - "┌───────────────────────────────┬───────┐\n", - "│ timestamp ┆ total │\n", - "│ --- ┆ --- │\n", - "│ datetime[μs, Europe/Brussels] ┆ f64 │\n", - "╞═══════════════════════════════╪═══════╡\n", - "│ 2023-01-01 00:00:00 CET ┆ 0.025 │\n", - "│ 2023-01-01 00:15:00 CET ┆ 0.017 │\n", - "│ 2023-01-01 00:30:00 CET ┆ 0.023 │\n", - "│ 2023-01-01 00:45:00 CET ┆ 0.024 │\n", - "│ 2023-01-01 01:00:00 CET ┆ 0.023 │\n", - "└───────────────────────────────┴───────┘" - ] - }, - "execution_count": 3, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "energy_use_lf_1 = pl.scan_ndjson(\n", - " \"data/PP/energy_use_test1.ndjson\",\n", - " schema={\"timestamp\": pl.Datetime(time_zone=\"Europe/Brussels\"), \"total\": pl.Float64},\n", - ")\n", - "energy_use_lf_1.collect().head()" + "%autoreload 2" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "## Test 2, reading in the \"smaller version of the json\" and tranforming it into polars." - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "39.9 ms ± 5.04 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n" - ] - } - ], - "source": [ - "%%timeit\n", - "# Read the JSON file\n", - "with open(\"data/PP/energy_use.json\", \"r\") as file:\n", - " data = json.load(file)\n", + "# Base Load analysis\n", + "\n", + "Demo of a base load analysis for a dossier, we define some KPIs we want to measure.\n", "\n", - "# Convert the data into a list of dictionaries\n", - "data_list = [{\"timestamp\": int(k), \"value\": v} for k, v in data.items()]\n", "\n", - "# Create a DataFrame from the list\n", - "df = pl.DataFrame(\n", - " data_list, schema={\"timestamp\": pl.Datetime(time_zone=\"Europe/Brussels\"), \"value\": pl.Float64}\n", - ")" + "\n", + "## loading in the data" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "# Base Load analysis\n", + "# Base Load Analysis Demo\n", "\n", - "## loading in the data" + "This notebook demonstrates how to analyze base load (standby power consumption) in energy usage data. Base load represents the minimum continuous power draw in a system, typically from devices that are always on or in standby mode.\n", + "\n", + "## Key Metrics\n", + "\n", + "We analyze three core metrics:\n", + "1. Base load value in WATTS - Shows the consistent minimum power draw\n", + "2. Energy consumption in kWh - Quantifies power used over time\n", + "3. Base load percentage - Shows what portion of total consumption is baseline\n", + "\n", + "## Data Format Requirements\n", + "\n", + "The analysis expects data in the following format:\n", + "- Timestamp (datetime with timezone 'Europe/Brussels')\n", + "- Total power (float, in kW)\n", + "\n", + "Example input data structure:\n", + "```json\n", + "{\n", + " \"timestamp\": \"2024-01-01T00:00:00+01:00\",\n", + " \"total\": 0.5\n", + "}" ] }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "shape: (12, 6)
timestamptotal_usagebase_load_kwhperiod_startbase_percentagebase_load_watts
datetime[μs]f64f64datetime[μs]f64f64
2023-12-01 00:00:00181.1254347.02023-12-31 23:00:002400.0181125.0
2024-01-01 00:00:00148349.2503042074.82024-01-01 00:00:001.39859186450.0
2024-02-01 00:00:00128940.8753541923.62024-02-01 00:00:001.49184780150.0
2024-03-01 00:00:00128139.3753941898.42024-03-01 00:00:001.48151279100.0
2024-04-01 00:00:00116175.5002481705.22024-04-01 00:00:001.46777971050.0
2024-07-01 00:00:00113613.5001881789.22024-07-01 00:00:001.57481374550.0
2024-08-01 00:00:00107086.8752861680.02024-08-01 00:00:001.5688270000.0
2024-09-01 00:00:00114579.5002481730.42024-09-01 00:00:001.51021872100.0
2024-10-01 00:00:00126714.8752341814.42024-10-01 00:00:001.43187675600.0
2024-11-01 00:00:0013360.3750282108.42024-11-01 00:00:0015.78099487850.0
" - ], - "text/plain": [ - "shape: (12, 6)\n", - "┌────────────────┬───────────────┬───────────────┬────────────────┬────────────────┬───────────────┐\n", - "│ timestamp ┆ total_usage ┆ base_load_kwh ┆ period_start ┆ base_percentag ┆ base_load_wat │\n", - "│ --- ┆ --- ┆ --- ┆ --- ┆ e ┆ ts │\n", - "│ datetime[μs] ┆ f64 ┆ f64 ┆ datetime[μs] ┆ --- ┆ --- │\n", - "│ ┆ ┆ ┆ ┆ f64 ┆ f64 │\n", - "╞════════════════╪═══════════════╪═══════════════╪════════════════╪════════════════╪═══════════════╡\n", - "│ 2023-12-01 ┆ 181.125 ┆ 4347.0 ┆ 2023-12-31 ┆ 2400.0 ┆ 181125.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 23:00:00 ┆ ┆ │\n", - "│ 2024-01-01 ┆ 148349.250304 ┆ 2074.8 ┆ 2024-01-01 ┆ 1.398591 ┆ 86450.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-02-01 ┆ 128940.875354 ┆ 1923.6 ┆ 2024-02-01 ┆ 1.491847 ┆ 80150.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-03-01 ┆ 128139.375394 ┆ 1898.4 ┆ 2024-03-01 ┆ 1.481512 ┆ 79100.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-04-01 ┆ 116175.500248 ┆ 1705.2 ┆ 2024-04-01 ┆ 1.467779 ┆ 71050.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ … ┆ … ┆ … ┆ … ┆ … ┆ … │\n", - "│ 2024-07-01 ┆ 113613.500188 ┆ 1789.2 ┆ 2024-07-01 ┆ 1.574813 ┆ 74550.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-08-01 ┆ 107086.875286 ┆ 1680.0 ┆ 2024-08-01 ┆ 1.56882 ┆ 70000.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-09-01 ┆ 114579.500248 ┆ 1730.4 ┆ 2024-09-01 ┆ 1.510218 ┆ 72100.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-10-01 ┆ 126714.875234 ┆ 1814.4 ┆ 2024-10-01 ┆ 1.431876 ┆ 75600.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-11-01 ┆ 13360.375028 ┆ 2108.4 ┆ 2024-11-01 ┆ 15.780994 ┆ 87850.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "└────────────────┴───────────────┴───────────────┴────────────────┴────────────────┴───────────────┘" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "
\n", - "shape: (310, 6)
timestamptotal_usagebase_load_kwhperiod_startbase_percentagebase_load_watts
datetime[μs]f64f64datetime[μs]f64f64
2023-12-31 00:00:00181.1254347.02023-12-31 23:00:002400.0181125.0
2024-01-01 00:00:004403.8750582822.4001152024-01-01 00:00:0064.089014117600.0048
2024-01-02 00:00:004963.0000182570.4000582024-01-02 00:00:0051.791256107100.0024
2024-01-03 00:00:004891.2500182578.8000582024-01-03 00:00:0052.72272107450.0024
2024-01-04 00:00:004745.1250122419.22024-01-04 00:00:0050.982851100800.0
2024-10-31 00:00:004312.0000162158.82024-10-31 00:00:0050.06493589950.0
2024-11-01 00:00:002502.5000122175.62024-11-01 00:00:0086.93706390650.0
2024-11-02 00:00:002762.3752184.02024-11-02 00:00:0079.06240191000.0
2024-11-03 00:00:002585.6250222175.62024-11-03 00:00:0084.14213190650.0
2024-11-04 00:00:005509.8749942167.22024-11-04 00:00:0039.33301690300.0
" - ], - "text/plain": [ - "shape: (310, 6)\n", - "┌─────────────────┬─────────────┬───────────────┬────────────────┬────────────────┬────────────────┐\n", - "│ timestamp ┆ total_usage ┆ base_load_kwh ┆ period_start ┆ base_percentag ┆ base_load_watt │\n", - "│ --- ┆ --- ┆ --- ┆ --- ┆ e ┆ s │\n", - "│ datetime[μs] ┆ f64 ┆ f64 ┆ datetime[μs] ┆ --- ┆ --- │\n", - "│ ┆ ┆ ┆ ┆ f64 ┆ f64 │\n", - "╞═════════════════╪═════════════╪═══════════════╪════════════════╪════════════════╪════════════════╡\n", - "│ 2023-12-31 ┆ 181.125 ┆ 4347.0 ┆ 2023-12-31 ┆ 2400.0 ┆ 181125.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 23:00:00 ┆ ┆ │\n", - "│ 2024-01-01 ┆ 4403.875058 ┆ 2822.400115 ┆ 2024-01-01 ┆ 64.089014 ┆ 117600.0048 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-01-02 ┆ 4963.000018 ┆ 2570.400058 ┆ 2024-01-02 ┆ 51.791256 ┆ 107100.0024 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-01-03 ┆ 4891.250018 ┆ 2578.800058 ┆ 2024-01-03 ┆ 52.72272 ┆ 107450.0024 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-01-04 ┆ 4745.125012 ┆ 2419.2 ┆ 2024-01-04 ┆ 50.982851 ┆ 100800.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ … ┆ … ┆ … ┆ … ┆ … ┆ … │\n", - "│ 2024-10-31 ┆ 4312.000016 ┆ 2158.8 ┆ 2024-10-31 ┆ 50.064935 ┆ 89950.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-11-01 ┆ 2502.500012 ┆ 2175.6 ┆ 2024-11-01 ┆ 86.937063 ┆ 90650.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-11-02 ┆ 2762.375 ┆ 2184.0 ┆ 2024-11-02 ┆ 79.062401 ┆ 91000.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-11-03 ┆ 2585.625022 ┆ 2175.6 ┆ 2024-11-03 ┆ 84.142131 ┆ 90650.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-11-04 ┆ 5509.874994 ┆ 2167.2 ┆ 2024-11-04 ┆ 39.333016 ┆ 90300.0 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "└─────────────────┴─────────────┴───────────────┴────────────────┴────────────────┴────────────────┘" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "
\n", - "shape: (7_416, 6)
timestamptotal_usagebase_load_kwhperiod_startbase_percentagebase_load_watts
datetime[μs]f64f64datetime[μs]f64f64
2023-12-31 23:00:00181.1254347.02023-12-31 23:00:002400.0181125.0
2024-01-01 00:00:00204.7500084914.0001922024-01-01 00:00:002400.0204750.008
2024-01-01 01:00:00182.04368.02024-01-01 01:00:002400.0182000.0
2024-01-01 02:00:00169.754074.02024-01-01 02:00:002400.0169750.0
2024-01-01 03:00:00162.753906.02024-01-01 03:00:002400.0162750.0
2024-11-04 18:00:00243.2499965837.9999042024-11-04 18:00:002400.0243249.996
2024-11-04 19:00:00208.254998.02024-11-04 19:00:002400.0208250.0
2024-11-04 20:00:00199.54788.02024-11-04 20:00:002400.0199500.0
2024-11-04 21:00:00170.6254095.02024-11-04 21:00:002400.0170625.0
2024-11-04 22:00:00124.2500022982.0000482024-11-04 22:00:002400.0124250.002
" - ], - "text/plain": [ - "shape: (7_416, 6)\n", - "┌─────────────────┬─────────────┬───────────────┬────────────────┬────────────────┬────────────────┐\n", - "│ timestamp ┆ total_usage ┆ base_load_kwh ┆ period_start ┆ base_percentag ┆ base_load_watt │\n", - "│ --- ┆ --- ┆ --- ┆ --- ┆ e ┆ s │\n", - "│ datetime[μs] ┆ f64 ┆ f64 ┆ datetime[μs] ┆ --- ┆ --- │\n", - "│ ┆ ┆ ┆ ┆ f64 ┆ f64 │\n", - "╞═════════════════╪═════════════╪═══════════════╪════════════════╪════════════════╪════════════════╡\n", - "│ 2023-12-31 ┆ 181.125 ┆ 4347.0 ┆ 2023-12-31 ┆ 2400.0 ┆ 181125.0 │\n", - "│ 23:00:00 ┆ ┆ ┆ 23:00:00 ┆ ┆ │\n", - "│ 2024-01-01 ┆ 204.750008 ┆ 4914.000192 ┆ 2024-01-01 ┆ 2400.0 ┆ 204750.008 │\n", - "│ 00:00:00 ┆ ┆ ┆ 00:00:00 ┆ ┆ │\n", - "│ 2024-01-01 ┆ 182.0 ┆ 4368.0 ┆ 2024-01-01 ┆ 2400.0 ┆ 182000.0 │\n", - "│ 01:00:00 ┆ ┆ ┆ 01:00:00 ┆ ┆ │\n", - "│ 2024-01-01 ┆ 169.75 ┆ 4074.0 ┆ 2024-01-01 ┆ 2400.0 ┆ 169750.0 │\n", - "│ 02:00:00 ┆ ┆ ┆ 02:00:00 ┆ ┆ │\n", - "│ 2024-01-01 ┆ 162.75 ┆ 3906.0 ┆ 2024-01-01 ┆ 2400.0 ┆ 162750.0 │\n", - "│ 03:00:00 ┆ ┆ ┆ 03:00:00 ┆ ┆ │\n", - "│ … ┆ … ┆ … ┆ … ┆ … ┆ … │\n", - "│ 2024-11-04 ┆ 243.249996 ┆ 5837.999904 ┆ 2024-11-04 ┆ 2400.0 ┆ 243249.996 │\n", - "│ 18:00:00 ┆ ┆ ┆ 18:00:00 ┆ ┆ │\n", - "│ 2024-11-04 ┆ 208.25 ┆ 4998.0 ┆ 2024-11-04 ┆ 2400.0 ┆ 208250.0 │\n", - "│ 19:00:00 ┆ ┆ ┆ 19:00:00 ┆ ┆ │\n", - "│ 2024-11-04 ┆ 199.5 ┆ 4788.0 ┆ 2024-11-04 ┆ 2400.0 ┆ 199500.0 │\n", - "│ 20:00:00 ┆ ┆ ┆ 20:00:00 ┆ ┆ │\n", - "│ 2024-11-04 ┆ 170.625 ┆ 4095.0 ┆ 2024-11-04 ┆ 2400.0 ┆ 170625.0 │\n", - "│ 21:00:00 ┆ ┆ ┆ 21:00:00 ┆ ┆ │\n", - "│ 2024-11-04 ┆ 124.250002 ┆ 2982.000048 ┆ 2024-11-04 ┆ 2400.0 ┆ 124250.002 │\n", - "│ 22:00:00 ┆ ┆ ┆ 22:00:00 ┆ ┆ │\n", - "└─────────────────┴─────────────┴───────────────┴────────────────┴────────────────┴────────────────┘" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ - "from openenergyid.baseload.main import main, TimeFrame\n", + "from openenergyid.baseload.main import main\n", + "from openenergyid.enums import Granularity\n", + "\n", "\n", "# Monthly analysis\n", - "monthly_metrics = main(\"data/PP/energy_use_big.ndjson\", TimeFrame.MONTHLY)\n", + "monthly_metrics = main(\"data/PP/energy_use_big.ndjson\", Granularity.P1M)\n", "\n", "# Daily analysis\n", - "daily_metrics = main(\"data/PP/energy_use_big.ndjson\", TimeFrame.DAILY)\n", + "daily_metrics = main(\"data/PP/energy_use_big.ndjson\", Granularity.P1D)\n", "\n", "# Hourly analysis\n", - "hourly_metrics = main(\"data/PP/energy_use_big.ndjson\", TimeFrame.HOURLY)\n", - "# print the metrics\n", + "hourly_metrics = main(\"data/PP/energy_use_big.ndjson\", Granularity.PT1H)\n", + "\n", "display(monthly_metrics)\n", "display(daily_metrics)\n", - "display(hourly_metrics)\n", - "\n", - "\n", - "# metrics = main(\"data/PP/energy_use_big.ndjson\")\n", - "# display(metrics)\n", - "# print(f\"Base Load: {metrics.base_load_watts:.1f}W\")\n", - "# print(f\"Daily Usage: {metrics.daily_usage_kwh:.1f} kWh\")\n", - "# print(f\"Base Percentage: {metrics.base_percentage:.1f}%\")" + "display(hourly_metrics)" ] }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "\n", - "\n", - "
\n", - "" - ], - "text/plain": [ - "alt.VConcatChart(...)" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "def create_monthly_chart(df):\n", " \"\"\"Create bar chart for monthly data\"\"\"\n", @@ -483,76 +173,9 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "shape: (29_664, 2)
timestamptotal
datetime[μs, Europe/Brussels]f64
2024-01-11 09:15:00 CET119.874992
2024-01-11 09:45:00 CET119.000008
2024-01-11 10:30:00 CET117.25
2024-11-04 11:00:00 CET117.25
2024-01-11 10:15:00 CET116.375
2024-05-20 13:45:00 CEST15.749999
2024-06-09 13:00:00 CEST15.749999
2024-06-09 13:15:00 CEST15.749999
2024-06-09 14:15:00 CEST15.749999
2024-06-23 11:00:00 CEST15.749999
" - ], - "text/plain": [ - "shape: (29_664, 2)\n", - "┌───────────────────────────────┬────────────┐\n", - "│ timestamp ┆ total │\n", - "│ --- ┆ --- │\n", - "│ datetime[μs, Europe/Brussels] ┆ f64 │\n", - "╞═══════════════════════════════╪════════════╡\n", - "│ 2024-01-11 09:15:00 CET ┆ 119.874992 │\n", - "│ 2024-01-11 09:45:00 CET ┆ 119.000008 │\n", - "│ 2024-01-11 10:30:00 CET ┆ 117.25 │\n", - "│ 2024-11-04 11:00:00 CET ┆ 117.25 │\n", - "│ 2024-01-11 10:15:00 CET ┆ 116.375 │\n", - "│ … ┆ … │\n", - "│ 2024-05-20 13:45:00 CEST ┆ 15.749999 │\n", - "│ 2024-06-09 13:00:00 CEST ┆ 15.749999 │\n", - "│ 2024-06-09 13:15:00 CEST ┆ 15.749999 │\n", - "│ 2024-06-09 14:15:00 CEST ┆ 15.749999 │\n", - "│ 2024-06-23 11:00:00 CEST ┆ 15.749999 │\n", - "└───────────────────────────────┴────────────┘" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "
\n", - "shape: (5, 2)
timestamptotal
datetime[μs, Europe/Brussels]f64
2024-01-01 00:00:00 CET51.625
2024-01-01 00:15:00 CET50.75
2024-01-01 00:30:00 CET38.5
2024-01-01 00:45:00 CET40.25
2024-01-01 01:00:00 CET59.500004
" - ], - "text/plain": [ - "shape: (5, 2)\n", - "┌───────────────────────────────┬───────────┐\n", - "│ timestamp ┆ total │\n", - "│ --- ┆ --- │\n", - "│ datetime[μs, Europe/Brussels] ┆ f64 │\n", - "╞═══════════════════════════════╪═══════════╡\n", - "│ 2024-01-01 00:00:00 CET ┆ 51.625 │\n", - "│ 2024-01-01 00:15:00 CET ┆ 50.75 │\n", - "│ 2024-01-01 00:30:00 CET ┆ 38.5 │\n", - "│ 2024-01-01 00:45:00 CET ┆ 40.25 │\n", - "│ 2024-01-01 01:00:00 CET ┆ 59.500004 │\n", - "└───────────────────────────────┴───────────┘" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "energy_use_lf_1 = pl.scan_ndjson(\n", " \"data/PP/energy_use_big.ndjson\",\n", @@ -569,95 +192,9 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/tmp/ipykernel_13152/3491075188.py:2: DeprecationWarning: `GroupBy.count` is deprecated. It has been renamed to `len`.\n", - " value_counts = tf.group_by(\"total\").count().sort(\"total\")\n" - ] - }, - { - "data": { - "text/html": [ - "\n", - "\n", - "
\n", - "" - ], - "text/plain": [ - "alt.Chart(...)" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# Compute the value counts using Polars\n", "value_counts = tf.group_by(\"total\").count().sort(\"total\")\n", @@ -689,46 +226,9 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "shape: (5, 5)
timestamptotal_daily_usagelowest_recordedmin_power_usage_per_daymax_power_usage_per_day
datetime[μs, Europe/Brussels]f64f64f64f64
2024-01-01 00:00:00 CET4462.50005428.0000022688.0001926468.0
2024-01-02 00:00:00 CET4943.75002224.52352.08400.0
2024-01-03 00:00:00 CET4912.25001625.3752436.08484.0
2024-01-04 00:00:00 CET4757.37501421.8752100.08736.0
2024-01-05 00:00:00 CET4779.2500122.752184.08316.0
" - ], - "text/plain": [ - "shape: (5, 5)\n", - "┌────────────────────┬───────────────────┬─────────────────┬───────────────────┬───────────────────┐\n", - "│ timestamp ┆ total_daily_usage ┆ lowest_recorded ┆ min_power_usage_p ┆ max_power_usage_p │\n", - "│ --- ┆ --- ┆ --- ┆ er_day ┆ er_day │\n", - "│ datetime[μs, ┆ f64 ┆ f64 ┆ --- ┆ --- │\n", - "│ Europe/Brussels] ┆ ┆ ┆ f64 ┆ f64 │\n", - "╞════════════════════╪═══════════════════╪═════════════════╪═══════════════════╪═══════════════════╡\n", - "│ 2024-01-01 ┆ 4462.500054 ┆ 28.000002 ┆ 2688.000192 ┆ 6468.0 │\n", - "│ 00:00:00 CET ┆ ┆ ┆ ┆ │\n", - "│ 2024-01-02 ┆ 4943.750022 ┆ 24.5 ┆ 2352.0 ┆ 8400.0 │\n", - "│ 00:00:00 CET ┆ ┆ ┆ ┆ │\n", - "│ 2024-01-03 ┆ 4912.250016 ┆ 25.375 ┆ 2436.0 ┆ 8484.0 │\n", - "│ 00:00:00 CET ┆ ┆ ┆ ┆ │\n", - "│ 2024-01-04 ┆ 4757.375014 ┆ 21.875 ┆ 2100.0 ┆ 8736.0 │\n", - "│ 00:00:00 CET ┆ ┆ ┆ ┆ │\n", - "│ 2024-01-05 ┆ 4779.25001 ┆ 22.75 ┆ 2184.0 ┆ 8316.0 │\n", - "│ 00:00:00 CET ┆ ┆ ┆ ┆ │\n", - "└────────────────────┴───────────────────┴─────────────────┴───────────────────┴───────────────────┘" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "lf = (\n", " energy_use_lf_1.filter(pl.col(\"total\") >= 0)\n", @@ -755,19 +255,9 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Average Basislast: 90671.5W\n", - "Average Daily Usage: 2176.1 kWh\n", - "Average Percentage: 58.3%\n" - ] - } - ], + "outputs": [], "source": [ "lf = (\n", " energy_use_lf_1.filter(pl.col(\"total\") >= 0)\n", @@ -807,87 +297,9 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "\n", - "\n", - "
\n", - "" - ], - "text/plain": [ - "alt.LayerChart(...)" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "total_new = (\n", " alt.Chart(df)\n", @@ -924,87 +336,9 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "\n", - "\n", - "
\n", - "" - ], - "text/plain": [ - "alt.LayerChart(...)" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "month_filter = \"month(datum.timestamp) == 2\" # Altair datetime function syntax\n", "\n", @@ -1042,88 +376,9 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "\n", - "\n", - "
\n", - "" - ], - "text/plain": [ - "alt.LayerChart(...)" - ] - }, - "execution_count": 13, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "# Resample to monthly totals\n", "monthly_lf = (\n", @@ -1171,46 +426,9 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "shape: (11, 3)
timestamptotal_monthly_usagebasislast_monthly_kwh
datetime[μs, Europe/Brussels]f64f64
2024-01-01 00:00:00 CET148429.75030462244.0
2024-02-01 00:00:00 CET128935.62535257708.0
2024-03-01 00:00:00 CET128010.75039856952.0
2024-04-01 00:00:00 CEST116233.25024651156.0
2024-05-01 00:00:00 CEST118999.12546547879.999136
2024-07-01 00:00:00 CEST113646.7501953676.0
2024-08-01 00:00:00 CEST107087.75028650400.0
2024-09-01 00:00:00 CEST114583.00024852164.0
2024-10-01 00:00:00 CEST126777.87523454180.0
2024-11-01 00:00:00 CET13460.12502863252.0
" - ], - "text/plain": [ - "shape: (11, 3)\n", - "┌───────────────────────────────┬─────────────────────┬───────────────────────┐\n", - "│ timestamp ┆ total_monthly_usage ┆ basislast_monthly_kwh │\n", - "│ --- ┆ --- ┆ --- │\n", - "│ datetime[μs, Europe/Brussels] ┆ f64 ┆ f64 │\n", - "╞═══════════════════════════════╪═════════════════════╪═══════════════════════╡\n", - "│ 2024-01-01 00:00:00 CET ┆ 148429.750304 ┆ 62244.0 │\n", - "│ 2024-02-01 00:00:00 CET ┆ 128935.625352 ┆ 57708.0 │\n", - "│ 2024-03-01 00:00:00 CET ┆ 128010.750398 ┆ 56952.0 │\n", - "│ 2024-04-01 00:00:00 CEST ┆ 116233.250246 ┆ 51156.0 │\n", - "│ 2024-05-01 00:00:00 CEST ┆ 118999.125465 ┆ 47879.999136 │\n", - "│ … ┆ … ┆ … │\n", - "│ 2024-07-01 00:00:00 CEST ┆ 113646.75019 ┆ 53676.0 │\n", - "│ 2024-08-01 00:00:00 CEST ┆ 107087.750286 ┆ 50400.0 │\n", - "│ 2024-09-01 00:00:00 CEST ┆ 114583.000248 ┆ 52164.0 │\n", - "│ 2024-10-01 00:00:00 CEST ┆ 126777.875234 ┆ 54180.0 │\n", - "│ 2024-11-01 00:00:00 CET ┆ 13460.125028 ┆ 63252.0 │\n", - "└───────────────────────────────┴─────────────────────┴───────────────────────┘" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "display(monthly_df)" ] @@ -1239,87 +457,9 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "\n", - "\n", - "
\n", - "" - ], - "text/plain": [ - "alt.LayerChart(...)" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "alt.data_transformers.enable(\"vegafusion\")\n", "\n", @@ -1345,88 +485,9 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "\n", - "\n", - "
\n", - "" - ], - "text/plain": [ - "alt.Chart(...)" - ] - }, - "execution_count": 16, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "alt.data_transformers.enable(\"vegafusion\")\n", "alt.Chart(tf).transform_density(\n", @@ -1440,88 +501,9 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "\n", - "\n", - "
\n", - "" - ], - "text/plain": [ - "alt.LayerChart(...)" - ] - }, - "execution_count": 17, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "max = (\n", " alt.Chart(df_extended)\n", @@ -1555,88 +537,9 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "\n", - "\n", - "
\n", - "" - ], - "text/plain": [ - "alt.LayerChart(...)" - ] - }, - "execution_count": 18, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "# comparing the options\n", "max + lowest + lowest_new" @@ -1644,35 +547,9 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "ename": "ValueError", - "evalue": "DataFusion error: This feature is not implemented: Unsupported TRY_CAST from Float64 to Null\n Context[0]: Failed to get node value\n", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", - "File \u001b[0;32m~/.cache/pypoetry/virtualenvs/openenergyid-Nm3FK_LY-py3.11/lib/python3.11/site-packages/IPython/core/formatters.py:977\u001b[0m, in \u001b[0;36mMimeBundleFormatter.__call__\u001b[0;34m(self, obj, include, exclude)\u001b[0m\n\u001b[1;32m 974\u001b[0m method \u001b[38;5;241m=\u001b[39m get_real_method(obj, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprint_method)\n\u001b[1;32m 976\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m method \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 977\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mmethod\u001b[49m\u001b[43m(\u001b[49m\u001b[43minclude\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mexclude\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexclude\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 978\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 979\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n", - "File \u001b[0;32m~/.cache/pypoetry/virtualenvs/openenergyid-Nm3FK_LY-py3.11/lib/python3.11/site-packages/altair/vegalite/v5/api.py:3417\u001b[0m, in \u001b[0;36mTopLevelMixin._repr_mimebundle_\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m 3415\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 3416\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m renderer \u001b[38;5;241m:=\u001b[39m renderers\u001b[38;5;241m.\u001b[39mget():\n\u001b[0;32m-> 3417\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mrenderer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdct\u001b[49m\u001b[43m)\u001b[49m\n", - "File \u001b[0;32m~/.cache/pypoetry/virtualenvs/openenergyid-Nm3FK_LY-py3.11/lib/python3.11/site-packages/altair/utils/display.py:225\u001b[0m, in \u001b[0;36mHTMLRenderer.__call__\u001b[0;34m(self, spec, **metadata)\u001b[0m\n\u001b[1;32m 223\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkwargs\u001b[38;5;241m.\u001b[39mcopy()\n\u001b[1;32m 224\u001b[0m kwargs\u001b[38;5;241m.\u001b[39mupdate(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmetadata, output_div\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_div)\n\u001b[0;32m--> 225\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mspec_to_mimebundle\u001b[49m\u001b[43m(\u001b[49m\u001b[43mspec\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mformat\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mhtml\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", - "File \u001b[0;32m~/.cache/pypoetry/virtualenvs/openenergyid-Nm3FK_LY-py3.11/lib/python3.11/site-packages/altair/utils/mimebundle.py:122\u001b[0m, in \u001b[0;36mspec_to_mimebundle\u001b[0;34m(spec, format, mode, vega_version, vegaembed_version, vegalite_version, embed_options, engine, **kwargs)\u001b[0m\n\u001b[1;32m 120\u001b[0m internal_mode: Literal[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mvega-lite\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mvega\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m mode\n\u001b[1;32m 121\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m using_vegafusion():\n\u001b[0;32m--> 122\u001b[0m spec \u001b[38;5;241m=\u001b[39m \u001b[43mcompile_with_vegafusion\u001b[49m\u001b[43m(\u001b[49m\u001b[43mspec\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 123\u001b[0m internal_mode \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mvega\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 125\u001b[0m \u001b[38;5;66;03m# Default to the embed options set by alt.renderers.set_embed_options\u001b[39;00m\n", - "File \u001b[0;32m~/.cache/pypoetry/virtualenvs/openenergyid-Nm3FK_LY-py3.11/lib/python3.11/site-packages/altair/utils/_vegafusion_data.py:250\u001b[0m, in \u001b[0;36mcompile_with_vegafusion\u001b[0;34m(vegalite_spec)\u001b[0m\n\u001b[1;32m 248\u001b[0m \u001b[38;5;66;03m# Pre-evaluate transforms in vega spec with vegafusion\u001b[39;00m\n\u001b[1;32m 249\u001b[0m row_limit \u001b[38;5;241m=\u001b[39m data_transformers\u001b[38;5;241m.\u001b[39moptions\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmax_rows\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[0;32m--> 250\u001b[0m transformed_vega_spec, warnings \u001b[38;5;241m=\u001b[39m \u001b[43mvf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mruntime\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpre_transform_spec\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 251\u001b[0m \u001b[43m \u001b[49m\u001b[43mvega_spec\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 252\u001b[0m \u001b[43m \u001b[49m\u001b[43mvf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_local_tz\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 253\u001b[0m \u001b[43m \u001b[49m\u001b[43minline_datasets\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minline_tables\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 254\u001b[0m \u001b[43m \u001b[49m\u001b[43mrow_limit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrow_limit\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 255\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 257\u001b[0m \u001b[38;5;66;03m# Check from row limit warning and convert to MaxRowsError\u001b[39;00m\n\u001b[1;32m 258\u001b[0m handle_row_limit_exceeded(row_limit, warnings)\n", - "File \u001b[0;32m~/.cache/pypoetry/virtualenvs/openenergyid-Nm3FK_LY-py3.11/lib/python3.11/site-packages/vegafusion/runtime.py:371\u001b[0m, in \u001b[0;36mVegaFusionRuntime.pre_transform_spec\u001b[0;34m(self, spec, local_tz, default_input_tz, row_limit, preserve_interactivity, inline_datasets, keep_signals, keep_datasets, data_encoding_threshold, data_encoding_format)\u001b[0m\n\u001b[1;32m 369\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 370\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m data_encoding_threshold \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 371\u001b[0m new_spec, warnings \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43membedded_runtime\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpre_transform_spec\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 372\u001b[0m \u001b[43m \u001b[49m\u001b[43mspec\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 373\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_tz\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_tz\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 374\u001b[0m \u001b[43m \u001b[49m\u001b[43mdefault_input_tz\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdefault_input_tz\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 375\u001b[0m \u001b[43m \u001b[49m\u001b[43mrow_limit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrow_limit\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 376\u001b[0m \u001b[43m \u001b[49m\u001b[43mpreserve_interactivity\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpreserve_interactivity\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 377\u001b[0m \u001b[43m \u001b[49m\u001b[43minline_datasets\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mimported_inline_dataset\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 378\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeep_signals\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkeep_signals\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 379\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeep_datasets\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkeep_datasets\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 380\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 381\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 382\u001b[0m \u001b[38;5;66;03m# Use pre_transform_extract to extract large datasets\u001b[39;00m\n\u001b[1;32m 383\u001b[0m new_spec, datasets, warnings \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39membedded_runtime\u001b[38;5;241m.\u001b[39mpre_transform_extract(\n\u001b[1;32m 384\u001b[0m spec,\n\u001b[1;32m 385\u001b[0m local_tz\u001b[38;5;241m=\u001b[39mlocal_tz,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 392\u001b[0m keep_datasets\u001b[38;5;241m=\u001b[39mkeep_datasets,\n\u001b[1;32m 393\u001b[0m )\n", - "\u001b[0;31mValueError\u001b[0m: DataFusion error: This feature is not implemented: Unsupported TRY_CAST from Float64 to Null\n Context[0]: Failed to get node value\n" - ] - }, - { - "data": { - "text/plain": [ - "alt.HConcatChart(...)" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# Assuming df is your DataFrame from the previous analysis\n", "\n", @@ -1749,87 +626,9 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "\n", - "\n", - "
\n", - "" - ], - "text/plain": [ - "alt.Chart(...)" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# Create a KDE plot for the 'total' column\n", "kde_chart = (\n", @@ -1846,639 +645,6 @@ "# Display the KDE chart\n", "kde_chart.display()" ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Test 2, testing the old pandas way" - ] - }, - { - "cell_type": "code", - "execution_count": 21, - "metadata": {}, - "outputs": [ - { - "ename": "SystemExit", - "evalue": "Stopping the notebook execution here.", - "output_type": "error", - "traceback": [ - "An exception has occurred, use %tb to see the full traceback.\n", - "\u001b[0;31mSystemExit\u001b[0m\u001b[0;31m:\u001b[0m Stopping the notebook execution here.\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/root/.cache/pypoetry/virtualenvs/openenergyid-Nm3FK_LY-py3.11/lib/python3.11/site-packages/IPython/core/interactiveshell.py:3585: UserWarning: To exit: use 'exit', 'quit', or Ctrl-D.\n", - " warn(\"To exit: use 'exit', 'quit', or Ctrl-D.\", stacklevel=1)\n" - ] - } - ], - "source": [ - "raise SystemExit(\"Stopping the notebook execution here.\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "" - ] - }, - "execution_count": 4, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "# show each unique value with how many times it occurs in that column\n", - "energy_use_lf_1[\"energy_use\"].value_counts()\n", - "# now plot that in a simple histogram but only the 100 most common values\n", - "# round the values to max 3 after the comma\n", - "energy_use_lf_1[\"energy_use\"].round(3).value_counts().head(40).plot(kind=\"bar\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "C:\\Users\\oscar\\AppData\\Local\\Temp\\ipykernel_3400\\3503598125.py:6: FutureWarning: 'H' is deprecated and will be removed in a future version, please use 'h' instead.\n", - " energy_use_hourly = energy_use_series.resample('H').sum()\n" - ] - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "import seaborn as sns\n", - "import pandas as pd\n", - "import matplotlib.pyplot as plt\n", - "\n", - "# Resample the data to hourly intervals\n", - "energy_use_hourly = energy_use_series.resample(\"H\").sum() # noqa: F821\n", - "\n", - "# Reshape the data to a matrix with days as rows and hours as columns\n", - "energy_use_matrix = energy_use_hourly.values.reshape(-1, 24)\n", - "\n", - "# Create a dataframe with the reshaped data\n", - "energy_use_df_heatmap = pd.DataFrame(energy_use_matrix, columns=range(24))\n", - "\n", - "# Create a figure and axes for the heatmap\n", - "fig, ax = plt.subplots(figsize=(10, 6))\n", - "\n", - "# Create the heatmap using seaborn\n", - "sns.heatmap(energy_use_df_heatmap, cmap=\"YlGnBu\", ax=ax)\n", - "\n", - "# Set the labels and title\n", - "ax.set_xlabel(\"Hour of Day\")\n", - "ax.set_ylabel(\"Day of Month\")\n", - "ax.set_title(\"Energy Use Heatmap\")\n", - "\n", - "\n", - "# Set the y-axis limits to show only 1 month\n", - "ax.set_ylim(0, 30)\n", - "\n", - "# Show the heatmap\n", - "plt.show()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "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", - "
energy_use
2022-12-31 23:00:000.025
2022-12-31 23:15:000.017
2022-12-31 23:30:000.023
2022-12-31 23:45:000.024
2023-01-01 00:00:000.023
......
2023-12-31 21:45:000.024
2023-12-31 22:00:000.022
2023-12-31 22:15:000.046
2023-12-31 22:30:000.035
2023-12-31 22:45:000.027
\n", - "

35040 rows × 1 columns

\n", - "
" - ], - "text/plain": [ - " energy_use\n", - "2022-12-31 23:00:00 0.025\n", - "2022-12-31 23:15:00 0.017\n", - "2022-12-31 23:30:00 0.023\n", - "2022-12-31 23:45:00 0.024\n", - "2023-01-01 00:00:00 0.023\n", - "... ...\n", - "2023-12-31 21:45:00 0.024\n", - "2023-12-31 22:00:00 0.022\n", - "2023-12-31 22:15:00 0.046\n", - "2023-12-31 22:30:00 0.035\n", - "2023-12-31 22:45:00 0.027\n", - "\n", - "[35040 rows x 1 columns]" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "C:\\Users\\oscar\\AppData\\Local\\Temp\\ipykernel_3400\\784061356.py:16: FutureWarning: \n", - "\n", - "`shade` is now deprecated in favor of `fill`; setting `fill=True`.\n", - "This will become an error in seaborn v0.14.0; please update your code.\n", - "\n", - " sns.kdeplot(energy_use_series, shade=True)\n" - ] - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "import pandas as pd\n", - "import seaborn as sns\n", - "import matplotlib.pyplot as plt\n", - "\n", - "# Read in pandas series from a json file\n", - "energy_use_lf_1 = pd.read_json(\"data/PP/energy_use.json\", orient=\"index\")\n", - "energy_use_lf_1.columns = [\"energy_use\"]\n", - "energy_use_lf_1.Name = \"energy_use\"\n", - "display(energy_use_lf_1)\n", - "\n", - "# Convert DataFrame to Series\n", - "energy_use_series = energy_use_lf_1.squeeze()\n", - "\n", - "# Plot KDE to identify the most common usage levels\n", - "plt.figure(figsize=(10, 6))\n", - "sns.kdeplot(energy_use_series, shade=True)\n", - "plt.title(\"Kernel Density Estimation of Energy Usage\")\n", - "plt.xlabel(\"Energy Use\")\n", - "plt.ylabel(\"Density\")\n", - "plt.show()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "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", - "
energy_use
2022-12-31 23:00:000.025
2022-12-31 23:15:000.017
2022-12-31 23:30:000.023
2022-12-31 23:45:000.024
2023-01-01 00:00:000.023
......
2023-12-31 21:45:000.024
2023-12-31 22:00:000.022
2023-12-31 22:15:000.046
2023-12-31 22:30:000.035
2023-12-31 22:45:000.027
\n", - "

35040 rows × 1 columns

\n", - "
" - ], - "text/plain": [ - " energy_use\n", - "2022-12-31 23:00:00 0.025\n", - "2022-12-31 23:15:00 0.017\n", - "2022-12-31 23:30:00 0.023\n", - "2022-12-31 23:45:00 0.024\n", - "2023-01-01 00:00:00 0.023\n", - "... ...\n", - "2023-12-31 21:45:00 0.024\n", - "2023-12-31 22:00:00 0.022\n", - "2023-12-31 22:15:00 0.046\n", - "2023-12-31 22:30:00 0.035\n", - "2023-12-31 22:45:00 0.027\n", - "\n", - "[35040 rows x 1 columns]" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "C:\\Users\\oscar\\AppData\\Local\\Temp\\ipykernel_3400\\1600994407.py:21: FutureWarning: \n", - "\n", - "`shade` is now deprecated in favor of `fill`; setting `fill=True`.\n", - "This will become an error in seaborn v0.14.0; please update your code.\n", - "\n", - " sns.kdeplot(energy_use_series, shade=True)\n" - ] - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "import pandas as pd\n", - "import seaborn as sns\n", - "import matplotlib.pyplot as plt\n", - "import numpy as np\n", - "\n", - "# Read in pandas series from a json file\n", - "energy_use_lf_1 = pd.read_json(\"data/PP/energy_use.json\", orient=\"index\")\n", - "energy_use_lf_1.columns = [\"energy_use\"]\n", - "energy_use_lf_1.Name = \"energy_use\"\n", - "display(energy_use_lf_1)\n", - "\n", - "# Convert DataFrame to Series\n", - "energy_use_series = energy_use_lf_1.squeeze()\n", - "\n", - "# Calculate percentiles\n", - "percentiles = [1, 5, 10]\n", - "percentile_values = np.percentile(energy_use_series, percentiles)\n", - "\n", - "# Plot KDE to identify the most common usage levels\n", - "plt.figure(figsize=(10, 6))\n", - "sns.kdeplot(energy_use_series, shade=True)\n", - "\n", - "# Plot vertical lines for percentiles\n", - "for p, value in zip(percentiles, percentile_values):\n", - " plt.axvline(value, linestyle=\"--\", label=f\"{p}th Percentile: {value:.3f}\")\n", - "\n", - "plt.title(\"Kernel Density Estimation of Energy Usage with Percentiles\")\n", - "plt.xlabel(\"Energy Use\")\n", - "plt.ylabel(\"Density\")\n", - "plt.legend()\n", - "plt.show()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "import pandas as pd\n", - "import numpy as np\n", - "import matplotlib.pyplot as plt\n", - "from scipy import stats\n", - "from scipy.fft import fft\n", - "from ruptures import Pelt\n", - "\n", - "# from ruptures.costs import GaussianChangesCost\n", - "from statsmodels.tsa.seasonal import STL\n", - "\n", - "# Load and preprocess the data\n", - "\n", - "data = pd.read_json(\"data/PP/energy_use.json\", orient=\"index\")\n", - "data.columns = [\"usage\"]\n", - "data.index.name = \"timestamp\"\n", - "data.index = pd.to_datetime(data.index)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAA+QAAAIjCAYAAACKx9GpAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/TGe4hAAAACXBIWXMAAA9hAAAPYQGoP6dpAACYAElEQVR4nOzdd5hTZdrH8V+SmWR6ZQaGXi10RRBBbIgoiiK7YlsF+66476prxYJlFbGy7iqW3QVddcXK2hFRBLuCWBZEUDoDQ5tek5z3j5NkJjOZnkxmku/nuuZKcvKc89zznKBz52kWwzAMAQAAAACANmUNdwAAAAAAAEQjEnIAAAAAAMKAhBwAAAAAgDAgIQcAAAAAIAxIyAEAAAAACAMScgAAAAAAwoCEHAAAAACAMCAhBwAAAAAgDEjIAQAAAAAIAxJyAADCwGKx6I477gh5PcuXL5fFYtHy5ct9x4477jgNHjw45HVL0ubNm2WxWLRw4cI2qS8YmnNvLBaLrrrqqtAGFIHuuOMOWSwWv2O9e/fWjBkzwhMQAIQJCTkAhNjChQtlsVjq/fniiy/CHWLIeJOxBx98MOD7Dz74oCwWizZv3ty2gQVZ7969fffTarUqLS1NQ4YM0eWXX64vv/wyaPW88MILmjdvXtCuF0ztObbW+uyzz3THHXcoPz8/qNf1/vvw/thsNvXs2VNnnnmm1qxZE9S6wqG0tFR33HGH35dBAAB/MeEOAACixV133aU+ffrUOd6/f/8wRINgGz58uP785z9LkoqKirRu3Tq9/PLLevrpp3XNNdfo4Ycf9itfVlammJjm/W/4hRde0I8//qirr766yeccc8wxKisrk91ub1ZdzVVfbL169VJZWZliY2NDWn8w1b43n332me68807NmDFDaWlpQa/v3HPP1aRJk+RyubRu3TrNnz9f7777rr744gsNHz486PW1ldLSUt15552SzFEZNd1666266aabwhAVALQvJOQA0EZOOeUUHXHEEeEOQyUlJUpMTAx3GBGnW7du+t3vfud3bO7cuTrvvPP0yCOPaMCAAfrDH/7gey8uLi6k8ZSXl8tut8tqtYa8roZYLJaw1t8SbR3v4Ycf7vfZGTt2rE4//XTNnz9fTz75ZKuu3V7/vcfExDT7CykAiEQMWQeAdqLm8O6nnnpK/fr1k8Ph0MiRI/X111/XKf/TTz/pt7/9rTIyMhQXF6cjjjhCb7zxhl8Z73D5jz/+WFdeeaWys7PVvXt33/uPPfaY+vbtq/j4eI0aNUorV67Ucccd5+vNKi4uVmJiov70pz/VqX/79u2y2WyaM2dOUNvhm2++0cSJE9WpUyfFx8erT58+uvjii/3KPPjggxozZowyMzMVHx+vESNG6JVXXqlzrbKyMv3f//2fOnXqpOTkZJ1++unasWNHwDnCO3bs0MUXX6zOnTvL4XBo0KBB+te//tWq3yU+Pl7//ve/lZGRoXvuuUeGYfjeqx1DUVGRrr76avXu3VsOh0PZ2dmaMGGCVq9eLcnsYXz77be1ZcsW3xDn3r17S6qeJ/7iiy/q1ltvVbdu3ZSQkKDCwsKAc8i9Vq1apTFjxvja+YknnvB73/v5qT2loPY1G4qtvjnkH374ocaNG6fExESlpaXpjDPO0Lp16/zKeOcZb9y40dc7nZqaqosuukilpaUNtv2jjz4qm83mN8z8oYceksVi0bXXXus75nK5lJycrBtvvNF3rOa9ueOOO3T99ddLkvr06eP7/Wq3yeLFizV48GDfZ+e9995rML6GnHDCCZKkTZs2+Y59+eWXOvnkk5WamqqEhAQde+yx+vTTT/3O87bX2rVrdd555yk9PV1HH3207/3nnntOo0aNUkJCgtLT03XMMcfo/fff97vGu+++67svycnJOvXUU/W///3Pr8yMGTOUlJSkHTt2aMqUKUpKSlJWVpauu+46uVwuSeZ9z8rKkiTdeeedvnar2a6155AHkp+fr6uvvlo9evSQw+FQ//79NXfuXLndbr9yL774okaMGKHk5GSlpKRoyJAh+utf/9ro9QEg3PhqEgDaSEFBgfbu3et3zGKxKDMz0+/YCy+8oKKiIl1xxRWyWCy6//77NXXqVP3666++Yb//+9//NHbsWHXr1k033XSTEhMT9dJLL2nKlCl69dVXdeaZZ/pd88orr1RWVpZuv/12lZSUSJLmz5+vq666SuPGjdM111yjzZs3a8qUKUpPT/cl7UlJSTrzzDO1aNEiPfzww7LZbL5r/uc//5FhGDr//POD1kZ5eXk66aSTlJWVpZtuuklpaWnavHmzXnvtNb9yf/3rX3X66afr/PPPV2VlpV588UWdddZZeuutt3Tqqaf6ys2YMUMvvfSSLrjgAo0ePVoff/yx3/teu3fv1ujRo30LdGVlZendd9/VJZdcosLCwmYNEa/N24b//Oc/tXbtWg0aNChgud///vd65ZVXdNVVV2ngwIHat2+fPvnkE61bt06HH364brnlFhUUFGj79u165JFHfNeu6e6775bdbtd1112nioqKBoepHzhwQJMmTdK0adN07rnn6qWXXtIf/vAH2e32Ol+ANKYpsdX0wQcf6JRTTlHfvn11xx13qKysTH/72980duxYrV692pfMe02bNk19+vTRnDlztHr1av3jH/9Qdna25s6dW28d48aNk9vt1ieffKLTTjtNkrRy5UpZrVatXLnSV+7bb79VcXGxjjnmmIDXmTp1qn7++Wf95z//0SOPPKJOnTpJki/ZlKRPPvlEr732mq688kolJyfr0Ucf1W9+8xtt3bq1zr/vpvjll18kyXfuhx9+qFNOOUUjRozQ7NmzZbVatWDBAp1wwglauXKlRo0a5Xf+WWedpQEDBujee+/1fQl055136o477tCYMWN01113yW6368svv9SHH36ok046SZL073//W9OnT9fEiRM1d+5clZaWav78+Tr66KP17bff+t0Xl8uliRMn6sgjj9SDDz6oDz74QA899JD69eunP/zhD8rKytL8+fP1hz/8QWeeeaamTp0qSRo6dGiT26G0tFTHHnusduzYoSuuuEI9e/bUZ599pptvvlm5ubm+NQuWLl2qc889V+PHj/d9JtatW6dPP/004JeJANCuGACAkFqwYIEhKeCPw+Hwldu0aZMhycjMzDT279/vO/7f//7XkGS8+eabvmPjx483hgwZYpSXl/uOud1uY8yYMcaAAQPq1H300UcbTqfTd7yiosLIzMw0Ro4caVRVVfmOL1y40JBkHHvssb5jS5YsMSQZ7777rt/vNXToUL9ygXh/pwceeCDg+w888IAhydi0aZNhGIbx+uuvG5KMr7/+usHrlpaW+r2urKw0Bg8ebJxwwgm+Y6tWrTIkGVdffbVf2RkzZhiSjNmzZ/uOXXLJJUZOTo6xd+9ev7LnnHOOkZqaWqe+2nr16mWceuqp9b7/yCOPGJKM//73v75jtWNITU01Zs6c2WA9p556qtGrV686xz/66CNDktG3b986sXrf++ijj3zHjj32WEOS8dBDD/mOVVRUGMOHDzeys7ONyspKwzCqPz/e+9PQNeuLzfsZWLBgge+Yt559+/b5jn333XeG1Wo1LrzwQt+x2bNnG5KMiy++2O+aZ555ppGZmVmnrppcLpeRkpJi3HDDDYZhmP8+MjMzjbPOOsuw2WxGUVGRYRiG8fDDDxtWq9U4cOCA79za96b257QmSYbdbjc2btzo97tIMv72t781GKO3be68805jz549xq5du4zly5cbhx12mCHJePXVVw23220MGDDAmDhxouF2u33nlpaWGn369DEmTJhQp73OPfdcv3o2bNhgWK1W48wzzzRcLpffe95rFhUVGWlpacZll13m9/6uXbuM1NRUv+PTp083JBl33XWXX9nDDjvMGDFihO/1nj176rRl7Vhr6tWrlzF9+nTf67vvvttITEw0fv75Z79yN910k2Gz2YytW7cahmEYf/rTn4yUlBS//8YBQEfBkHUAaCOPPfaYli5d6vfz7rvv1il39tlnKz093fd63LhxkqRff/1VkrR//359+OGHmjZtmoqKirR3717t3btX+/bt08SJE7Vhwwbt2LHD75qXXXaZX+/2N998o3379umyyy7zm8d5/vnn+9UtSSeeeKK6du2q559/3nfsxx9/1Pfff19nznRreRfMeuutt1RVVVVvufj4eN/zAwcOqKCgQOPGjfMN75bkGzJ85ZVX+p37xz/+0e+1YRh69dVXNXnyZBmG4WvPvXv3auLEiSooKPC7bkt4e4uLiorqLZOWlqYvv/xSO3fubHE906dP92ubhsTExOiKK67wvbbb7briiiuUl5enVatWtTiGxuTm5mrNmjWaMWOGMjIyfMeHDh2qCRMm6J133qlzzu9//3u/1+PGjdO+fftUWFhYbz1Wq1VjxozRihUrJJk9pvv27dNNN90kwzD0+eefSzJ7zQcPHtyqxdpOPPFE9evXz+93SUlJ8f2bbczs2bOVlZWlLl266LjjjtMvv/yiuXPnaurUqVqzZo02bNig8847T/v27fN9NktKSjR+/HitWLGizvDt2u21ePFiud1u3X777bJa/f/08w4bX7p0qfLz83Xuuef6/Ruw2Ww68sgj9dFHH9WJO9B9aerv3BQvv/yyxo0bp/T0dL+YTjzxRLlcLt+9TUtLU0lJiZYuXRq0ugGgrTBkHQDayKhRo5q0qFvPnj39XnsT5AMHDkiSNm7cKMMwdNttt+m2224LeI28vDx169bN97r26u5btmyRVHeF95iYmDrDha1Wq84//3zNnz9fpaWlSkhI0PPPP6+4uDidddZZjf4+TeFNCo499lj95je/0Z133qlHHnlExx13nKZMmaLzzjtPDofDV/6tt97SX/7yF61Zs0YVFRV1ruP9Ha1Wa53fvfbvvGfPHuXn5+upp57SU089FTC+vLy8Vv1+xcXFkqTk5OR6y9x///2aPn26evTooREjRmjSpEm68MIL1bdv3ybXE2gV//p07dq1zmJfBx10kCRz/u/o0aObfK3m8H72Dj744DrvHXrooVqyZEmdhcga+jeRkpJSb13jxo3zDYlfuXKlcnJydPjhh2vYsGFauXKlJkyYoE8++UTTpk1r1e9UOz5vjN5/s425/PLLddZZZ/m2zBs0aJDv875hwwZJ5pct9SkoKPD7Iq325+CXX36R1WrVwIED672Gtx7v/PXaardzXFyc37B9qXm/c1Ns2LBB33//fZ16vLz/Lq+88kq99NJLOuWUU9StWzeddNJJmjZtmk4++eSgxQIAoUJCDgDtTM2e7JoMz1xQb2/Yddddp4kTJwYsWzvpbGqvaX0uvPBCPfDAA1q8eLHOPfdcvfDCCzrttNOUmpra4Hne1arLysoCvu9dmMtbzmKx6JVXXtEXX3yhN998U0uWLNHFF1+shx56SF988YWSkpK0cuVKnX766TrmmGP0+OOPKycnR7GxsVqwYIFeeOGFZv9u3vb83e9+V2/S05x5r4H8+OOPkhre4m7atGkaN26cXn/9db3//vt64IEHNHfuXL322ms65ZRTmlRPa+9zbfUtuuVduKutNPZvoj5HH320qqqq9Pnnn2vlypW+0Sbjxo3TypUr9dNPP2nPnj2+420dn9eAAQN04oknBnzP+/l84IEH6t0CrfZ8/ZZ8Drz1/Pvf/1aXLl3qvF97RfT6fudgcrvdmjBhgm644YaA73u/QMrOztaaNWu0ZMkSvfvuu3r33Xe1YMECXXjhhXrmmWdCHicAtAYJOQB0MN4e09jY2Hr/iG9Mr169JJm97ccff7zvuNPp1ObNm+skoIMHD9Zhhx2m559/Xt27d9fWrVv1t7/9rdF6srKylJCQoPXr1wd8f/369UpISPAtlOU1evRojR49Wvfcc49eeOEFnX/++XrxxRd16aWX6tVXX1VcXJyWLFni12u+YMGCOr+j2+3Wpk2bNGDAAN/xjRs31okxOTlZLperxe3ZkOLiYr3++uvq0aOHDj300AbL5uTk6Morr9SVV16pvLw8HX744brnnnt8CXlTVqVuqp07d9bpif75558lyTdKwtvrWnOlcqm6l7umpsbm/ewF+kz89NNP6tSpU9C26Ro1apTsdrtWrlyplStX+lZLP+aYY/T0009r2bJlvtcNCWa7N5d3KHxKSkqLP5/9+vWT2+3W2rVr603qvfVkZ2cH7d9Ba9utX79+Ki4ublI8drtdkydP1uTJk+V2u3XllVfqySef1G233dbgF2EAEG7MIQeADiY7O1vHHXecnnzySeXm5tZ5f8+ePY1e44gjjlBmZqaefvppOZ1O3/Hnn3++3iGnF1xwgd5//33NmzdPmZmZTeq1tdlsOumkk/Tmm29q69atfu9t3bpVb775pk466SRfb9uBAwfq9Cp6Ewjv0HSbzSaLxeLXS7t582YtXrzY7zzv6IHHH3/c73jtLxJsNpt+85vf6NVXX/X1ZNfUlPasT1lZmS644ALt379ft9xyS4M9zgUFBX7HsrOz1bVrV78h+YmJiXXKtZTT6fTb47qyslJPPvmksrKyNGLECEnVSZp3rq431kBD+5saW05OjoYPH65nnnnGL9H/8ccf9f7772vSpEkt/ZXqiIuL08iRI/Wf//xHW7du9eshLysr06OPPqp+/fopJyenwet4vyCo/cVEWxgxYoT69eunBx980Df1oaamfD6nTJkiq9Wqu+66q858c++/t4kTJyolJUX33ntvwPUbWvLvICEhQVLL223atGn6/PPPtWTJkjrv5efn+/7btW/fPr/3rFar70vFmv9+AKA9ooccANrIu+++q59++qnO8TFjxjRrnrBkLhB39NFHa8iQIbrsssvUt29f7d69W59//rm2b9+u7777rsHz7Xa77rjjDv3xj3/UCSecoGnTpmnz5s1auHCh+vXrFzBxPO+883TDDTfo9ddf1x/+8AffFmyNuffeezV69Ggdfvjhuvzyy9W7d29t3rxZTz31lCwWi+69915f2WeeeUaPP/64zjzzTPXr109FRUV6+umnlZKS4kvUTj31VD388MM6+eSTdd555ykvL0+PPfaY+vfvr++//953rREjRug3v/mN5s2bp3379vm2PfP2Atf8He+77z599NFHOvLII3XZZZdp4MCB2r9/v1avXq0PPvhA+/fvb/T33LFjh5577jlJZq/42rVr9fLLL2vXrl3685//7LeAWm1FRUXq3r27fvvb32rYsGFKSkrSBx98oK+//loPPfSQ3++0aNEiXXvttRo5cqSSkpI0efLkJt2H2rp27aq5c+dq8+bNOuigg7Ro0SKtWbNGTz31lO/eDho0SKNHj9bNN9+s/fv3KyMjQy+++KLflzgtie2BBx7QKaecoqOOOkqXXHKJb9uz1NTUOvvDt9a4ceN03333KTU1VUOGDJFkftlx8MEHa/369ZoxY0aj1/B+QXHLLbfonHPOUWxsrCZPnhy0nvyGWK1W/eMf/9App5yiQYMG6aKLLlK3bt20Y8cOffTRR0pJSdGbb77Z4DX69++vW265RXfffbfGjRunqVOnyuFw6Ouvv1bXrl01Z84cpaSkaP78+brgggt0+OGH65xzzlFWVpa2bt2qt99+W2PHjtXf//73ZsUeHx+vgQMHatGiRTrooIOUkZGhwYMHa/DgwU06//rrr9cbb7yh0047TTNmzNCIESNUUlKiH374Qa+88oo2b96sTp066dJLL9X+/ft1wgknqHv37tqyZYv+9re/afjw4Y2OSgGAsAvb+u4AECUa2vZMNbaDamiLMAXYOuiXX34xLrzwQqNLly5GbGys0a1bN+O0004zXnnllTp117eN2KOPPmr06tXLcDgcxqhRo4xPP/3UGDFihHHyyScHLD9p0iRDkvHZZ581qw3WrVtnnH322UZ2drYRExNjZGdnG+ecc46xbt06v3KrV682zj33XKNnz56Gw+EwsrOzjdNOO8345ptv/Mr985//NAYMGGA4HA7jkEMOMRYsWBBwG6WSkhJj5syZRkZGhpGUlGRMmTLFWL9+vSHJuO+++/zK7t6925g5c6bRo0cPIzY21ujSpYsxfvx446mnnmr09+vVq5fvflosFiMlJcUYNGiQcdlllxlffvllwHNq3tOKigrj+uuvN4YNG2YkJycbiYmJxrBhw4zHH3/c75zi4mLjvPPOM9LS0gxJvm3GvNuQvfzyy3XqqW/bs0GDBhnffPONcdRRRxlxcXFGr169jL///e91zv/ll1+ME0880XA4HEbnzp2NWbNmGUuXLq1zzfpiC7TtmWEYxgcffGCMHTvWiI+PN1JSUozJkycba9eu9Svjvad79uzxO17fdmyBvP3224Yk45RTTvE7fumllxqSjH/+8591zgn07+3uu+82unXrZlitVr+6JQXcrq72Fl6BNLYtYE3ffvutMXXqVCMzM9NwOBxGr169jGnTphnLli3zlamvvbz+9a9/GYcddpjhcDiM9PR049hjjzWWLl3qV+ajjz4yJk6caKSmphpxcXFGv379jBkzZvj9G5w+fbqRmJhY5/qB/g1+9tlnxogRIwy73e7Xrk3Z9swwzO3Ybr75ZqN///6G3W43OnXqZIwZM8Z48MEHfdvzvfLKK8ZJJ51kZGdnG3a73ejZs6dxxRVXGLm5uQ03KgC0AxbDaOKKIwCAiOd2u5WVlaWpU6fq6aefrvP+mWeeqR9++KHOPOyOZM2aNTrssMP03HPP6fzzzw93OAAAIIoxhxwAolR5eXmd+drPPvus9u/fr+OOO65O+dzcXL399tu64IIL2ijC1gu0uvu8efNktVobXcgLAAAg1JhDDgBR6osvvtA111yjs846S5mZmVq9erX++c9/avDgwX77i2/atEmffvqp/vGPfyg2NrbBudDtzf33369Vq1bp+OOPV0xMjG9LpMsvv1w9evQId3gAACDKkZADQJTq3bu3evTooUcffdS3YNeFF16o++67T3a73Vfu448/1kUXXaSePXvqmWeeCbhHcXs1ZswYLV26VHfffbeKi4vVs2dP3XHHHbrlllvCHRoAAICYQw4AAAAAQBgwhxwAAAAAgDAgIQcAAAAAIAwifg652+3Wzp07lZycLIvFEu5wAAAAAAARzjAMFRUVqWvXrrJa6+8Hj/iEfOfOnaykCwAAAABoc9u2bVP37t3rfT/iE/Lk5GRJZkOkpKSEOZoOxOWSvv1WcrvN11ardNhh5vNvvzUfDztMstkaPr+xcqES7vrBPQg22hMAAKDDKCwsVI8ePXz5aH0iPiH3DlNPSUkhIW+OykppxQozCZDMP/6PPtp8vmKF+Xj00VKNrZECnt9YuVAJd/3gHgQb7QkAANDhNDZtOuITcrSNZcuWadmyZcrLy5Pb7TZ71r/7TpL0r1mzwhwd2guXy6WFCxf6f1Zq+PDDD8MUWcdEewIAAHRsJORospKSEt33wAP64Nln9cuBAyp98EG5XC45nU45nU4lJyfL4XDo6KOPNhPy8vKA16mTvNfwr3/9K+S/R7jrj2Z/+tOftHDhQp166qkaPHgwCy22Eu0JAADQsZGQo8ku/f3v9fHKlepiGCqoqNDAwYOVkpqqL774QocccohOPvlkSdIjjzxiDq+9994617jzzjt111136YgjjlBOTk6bJxDhrj/avfjii3rppZc0adKkcIcSEWhPAACAjo2EHE327pIlenvxYp0xaZJeP/tsTVqwQLLblZmZqbfeekv9+vVr9BpPPPGEFi5cqAsuuKANIm5/9Uc7u92u/v37hzuMiEF7AgCAYDEMQ06nUy7vGlJokM1mU0xMTKs7+EjI0WTpaWnKSE+X3WZT/4wM3/FLL71UL7zwgm677bZGr1FZWakxY8aEMsx2XX+0+/Of/6y//vWv+vvf/87ohCCgPQEAQDBUVlYqNzdXpaWl4Q6lQ0lISFBOTo7srVhsl4QcTXb3HXfo9rvu0h+PPFLTXn5Zx1utsthscrvdeuqpp/TBBx9o6NChio2NNVdn/+orSdLDNRZ1a07yHgrhrj8aTV20SFqzxtw6T+ZCY++++64GDRpkflZqeO2118IQYcdCewIAgGByu93atGmTbDabunbtKrvdzhf9jTAMQ5WVldqzZ482bdqkAQMGyOr526y5LIZhGEGOr10pLCxUamqqCgoK2PasOdxuaeNGHTZliiySft2+XbJaVVJSIsMw5HK5ZLFY/D546enpkqTBgwebBzzfsB02Zozk+Uftdrv1zDPPaOjQodXJew0PP/xwUOOXpGvnz2/7+uG7BxfdfLOUnOy7Bw1ZsGBBGwTWQdGeAAAgBMrLy7Vp0yb16tVLCQkJ4Q6nQyktLdWWLVvUp08fxcXF+b3X1DyUHnIEZrVKBx2kKWefLUlavHhxo6cMHz5cUt0k4Pjjjw9Y7scff2x1mPXyxC9J365Z0/b1w3cPFrz6argjiQy0JwAACKGW9vBGs2C0GT3kaLWLL75Yf/3rX5WcnOx3vKSkRH/84x/ZSgw+J5xwgl577TWlpaX5HS8sLNSUKVPYN7uZaE8AANBa3h7yQL28aFhDbdfUPJSvQRCYy2XOU121yvxZs0Z9+/bVvrw8nTBqlPJXrjTLSHrmmWc0ePBgFRYW6oQTTvCdX/bVV3r22Wd95SQzeS8qKqpTXUlJiS6++OLgx79mTXjqR8B7sHz5clVWVtYpWl5erpUrV7ZtfB0N7QkAABBxGLKOwFwuafHi6mTWZtPmzZvlqqzU8q+/VuUbb6jw0ENlxMbKMAzt3LlTe/bs0YoVK1RYWChXWZneefRRZcfHm9ew2SSZyft9991Xpze9rKxMzz77bPB6073xS9LAgW1fP/zuwfcul+SZr7927Vrt2rWrRjGX3nvvPXXr1i0cUXYctCcAAEDEISFHo974+WfJapVhGHrak7A+vWqVbsvO9pVxOp0aMGCADMPwLe5mMQzdedxxkswhG4ZhyDAMFRUV+Q3pcLlceuedd5Rd43rBFu76o93wkSNlsVhksViqR1HUEB8fr7/97W9hiKxjoj0BAACkGTNmKD8/32+9q1deeUW/+93vdM899+iHH37QM888I0mKiYlRRkaGhg4dqnPPPVczZszwmwPeu3dvbdmypU4dc+bM0U033RSy34GEHI2a8tJLvue3zp5tPn70UZ1ydrtdf/rTnzRp0iTZLRb1+u9/1dXTE52WluZLIA7yLLZWk8Vi0Z133hmi3yD89Ue7TevXy4iNVd++ffXVV18pKyvL957dbld2drZsnlEMaBztCQAAUNc//vEPzZw5U0888YQuuugizZgxQyeffLIWLFggl8ul3bt367333tOf/vQnvfLKK3rjjTcUE1OdEt9111267LLL/K5Ze2RtsJGQo1HuW2+VbDb1+Mc/9N9XX9URo0frq8suU9b110t2u7Zv364+ffqoc+fO1UlAZaVUY0Gpjz76SIZh6IQTTtCrr76qjIwM33t2u129evVS165dQ/Y7hLv+aNerVy/Jbpfb7Q53KBGB9gQAAKFkGIbKqlyNFwyB+Fhbi/ZBv//++zV79my9+OKLOvPMM33HHQ6HunTpIknq1q2bDj/8cI0ePVrjx4/XwoULdemll/rKJicn+8q2FRJyNNm2X3+VJBXdfLNe+t//tPGf/1TXHj10zjnnKDMzU5K0adMmbdy4UTmdOmlwjXOPPfZY3/s9e/Zs0T+y1gh3/ZAqKyu1ePFiff755745z126dNGYMWN0xhlnyG63hznCjsswDC1fvtz8t5eTo4kTJyrWM8ccAACgucqqXBp4+5Kw1L32rolKsDcvTb3xxhv1+OOP66233tL48eMbLX/CCSdo2LBheu211/wS8nAgIUejBj7xhD65+GJlSPrll180et48FVZWyrJkidxut66//nrdc889WrlypW/+hsVi0bE9e+qNc89VUo1r7d69W4sXL/ZLyI466iiNGjWqTX6XXr16+Z77vjzIydHgwYMbOAuttXHjRk2cPFk7d+7UkUceqc6dO0uSvv32Wz3xxBPq3r273n33XfXv3z/MkXYMk04/Xf9ZtEipqanav3+/Jk2apK+++kqdOnXSvn37dNBBB2nFihV+Q9kBAAAi0bvvvqv//ve/WrZsWcC1depzyCGH6Pvvv/c7duONN+rWW2+tc/1x48YFJdZASMjRqJ/27pXT7dbGjRt12JFHqrS8XEd1765Pt23TcSdO1JpvvtSf//xn2Ww2Pfvss5o6daq+/eorTZ86VfesWKE5kvLy8jR16lR99tln6tmzpy8h2717t6655hqNHTtWr776asgWVrvyyit1//33KykpSWVlZbrgggv02muvSfJ8eXDssXrjjTeUlJTUyJXQEn/44x81ZMgQffvtt3X2YSwsLNSFF16omTNnasmS8HwT29G89/77qqiokCTdeuutKioq0i+//KI+ffpo+/btmjJlim6//XbNnz8/zJECAICOKD7WprV3TQxb3c0xdOhQ7d27V7Nnz9aoUaOa/Pe8YRh1Rs1ef/31mjFjht+xUO9cwz7kCCwmRjrrLGnaNMlikSZP1h/+7//kdrv16rx5mnbdXyVZtG3IdP3zhVdls9k0bNgw/fvf/1ZCQoLGHnOMHr7rLr22Y4cUE6Mrr7xSbrdb69at0+bNm/Xll1/qyy+/1ObNm7Vu3Tq53W7NnDkz+PGfdZYUE6Mnn3xSpaWlkqS7775bX375pZYtW6bi4mKtWLFCW7du1T333BO8+uF3Dz79/HP95S9/qZOMS1JKSoruvvtu9s1uTM3PdA0ffvih5syZoz59+kiSunfvrrlz5/LlBgAAaDGLxaIEe0xYfpo7tbRbt25avny5duzYoZNPPllFRUVNOm/dunW+v5+8OnXqpP79+/v9xMfHNyue5iIhR2BWqzRokDRkiCTJcuih+vSzz5SYmKikEUfp4Z3mfN8Kp6FXfyqV0+nULbfcUp1UWa0aNnmytu3eLVmtWrJkiR577DEdfPDBdao6+OCD9eijj+q9994LfvyDBvm2bPN68803df/99+v44483vzwYO1YPP/ywr8ccQVLjHqSlpWnz5s31Ft28ebPS0tLaLLQOqeZnWvL9z+rAgQPq16+fX9H+/ftr586dbR4iAABAOPTq1Usff/yxdu3a1aSk/MMPP9QPP/yg3/zmN20UYf0Yso4mGT9+vKqqqlRUVKTnlnwhqa9kkfJX/lv/XVosq9WqH374wS+p2rdvnxITEyWZqxsWFhbWe/2ioiI5HI6Q/g7eBGbXrl0aOnSo33vDhg3Ttm3bQlp/NLv00kt14YUX6rbbbtP48eP9piwsW7ZMf/nLX/THP/4xzFF2LDNmzJDD4VBVVZU2bdqkQZ5EXTI/43zBAQAAokmPHj20fPlyHX/88Zo4caKvs6+iokK7du3y2/Zszpw5Ou2003ThhRf6XaOoqMi31pVXQkJCwFGewUJCjsDcbmndOsnt1uzf/16yWPRherq++uorff3Wa+rSa4wcgw/TrgPbVLx3h+xx8Zo7d66uv/563/nvLFyoQb17S263zj77bE2fPl2PPPKIxo8f7/tQFxYWatmyZbr22mt17rnnBj9+STr0UEnSbbfdpoSEBFmtVu3cudMvgan55QGCpMY9uOuOO5SYmKgHHnhAf/7zn31fjhiGoS5duujGG2/UDTfcEM5o278a7Tn9wgvNqSSSzjjjDN90DK9XX31Vw4cPb+sIAQAAwqp79+5+SXlOTo7ee+895eTkKCYmRunp6Ro2bJgeffRRTZ8+XVar/4Dx22+/XbfffrvfsSuuuEJPPPFEyGImIUdgTqf08suSy6XZmZmSzabZS5fq3rn3a+5f7lXRt8tlsVplSDLchmLSO+m2m66rTqqcTp1nsWjGuHGS06mHH35Ybrdb55xzjpxOp2+Lq8rKSsXExOiSSy7Rgw8+GPz4JWnWLB1zzDFav369JGngwIHasmWLX/F33nnHL0FHENS6BzfeeKNuvPFGbdq0yW+V/dpzd1CPGu254KmnpAa2iZs9e7ZstuYtiAIAANDRLFy4sM6xbt266eeff272tRqaXhlKJORolsnnX66EJWtV7CzTCXOv1hfbCvXQJ3kaeuhBuuFP/tsB9E1P9z13OByaP3++5s6dq1WrVvklZCNGjAjpMBBJWr58eYPvn3feeXVWVERw5ebmav78+frkk0+Um5srq9Wqvn37asqUKZoxYwYJZDPRngAAAB0fi7qhWb7fUSBJGtS5k8YcdZQmHz9GruJ9Wvu/tfp18xZdfPHFvrLlTqee/e47v/NTUlJ0/PHH6/TTT1d5ebk++OAD/fvf/9a+fftCGvcf//jHBlfx7tu3r7p37x7SGKLZN6tW6dBDD9U777yjqqoqbdiwQSNGjFBiYqKuu+46HXPMMU1eERO0JwAAQKQgIUez/JRr/pGfnezQzz//rAljR2j38zdp6z+u1OlnTPEbNlJQXq6L/vtfSeYw8f3790uStm3bpsGDB+uaa67R0qVLdfvtt2vgwIHatGlTyOJ+7LHHdNxxx+mggw7S3Llz6yzWgNC6+rrrdM011+ibb77RypUrtXDhQv3888968cUX9euvv6q0tFS33npruMPsMGhPAACAyEBCjiZ748039clHS/Tjvu36ds82XXjJJcrKytKI6bcqY8IfVFhcIsMwtHXr1jrn/vTTT3I6nZKkm2++WV27dtWWLVv01VdfacuWLRo6dKhuueWWkMb//vvva9KkSXrwwQfVs2dPnXHGGXrrrbfkdrtDWi+k1d9+qwsuuMD3+rzzztPq1au1e/dupaen6/7779crr7wSxgg7FtoTAAAgMjCHHE025ayzZMiijw239JPk29l71SrJkPZ7jowbN04fLVmi+tYs//zzz/XEE08oNTVVkpSUlKQ777xT55xzTkjjHzJkiMaPH68HHnhAr7/+uv71r39pypQp6ty5s2bMmKGLLrpI/fv3D2kM0So7O1u5ubnq27evJHO7M6fT6Vs7YMCAAb4RFGgc7QkAAILNMIzGC8FPMNqMHnI0WU6XLso54wY9PPZcFd10i5KTk7V27Vot/ORX9brxTU296zlZrVZNnjxZx06YoJ9rzQv3bnVVXl6unJwcv/e6deumPXv2tMnvERsbq2nTpum9997Tr7/+qssuu0zPP/+8Dj744DapPxpNmTxZv//97/Xee+/po48+0vnnn69jjz1W8fHxkqT169erW7duYY6y46A9AQBAsMTGxkpSnW1U0Thvm3nbsCXoIUdgNps0ZYrkcvleH/LZl1q9+1etHHyM/jRtjA75YIm++eYb9Ro1UZKUW1AhwzD097//XTIMnf7vf5t7JXtWex4/frxiYmJUWFio9evXa/Dgwb7qtmzZoszMzODH731ej549e+qOO+7Q7Nmz9cEHHwSvfvjdg7/06aPcyy/X5MmT5XK5dNRRR+m5557zFbVYLJozZ06YAu0gaE8AABACNptNaWlpysvLkyQlJCT4OtIQmGEYKi0tVV5entLS0lq1uw0JOQKz2aThw/0OnXbB7/Xjm9+pfPBQWQ47TGdOnar//Oc/euyUqZKkvbZ0ffjhh5Kkvz/2mNyGoSeeeMLcw3z2bL9rJSUl+b1+8803NW6c/7ZpwYy/V69eDf5DsVgsmjBhQvDqh989SJK0aNEilZeXy+l01rn/J510UtvH19HQngAAIES6dOkiSb6kHE2Tlpbma7uWshgRPlmgsLBQqampKigoCPle15FuwaebdOeba3XK4C6a/7sRvuOVTrcOvf09udyGvpw1Xp1T4sIYJQAAAICWcLlcqqqqCncYHUJsbGyDHX5NzUPpIUdgbre0caP5KElWq3YdqJLFcGtg8S7p55+l/v0lq1X2GKu6psVp2/4ybdlXaibk3vMlX7mwxB+u+sE9CDbaEwAAhJjNZmvV8Gs0H3/RITCnU3rhBen5582fF17QnvwSxbhdGvPlEvM9zzZmktQ701xTffO+Ev/za5Vr8/jDVT+4B8FGewIAAEQcEnI0WW5BuSQp0VF3YEWPjARJ0vb9rM4IAAAAAE1BQo4myys0E/JkR91l/bummvPGd3qSdgAAAABAw0jI0SSGYWiXJyFPCtBD3jXN3P84t6CsTeMCAAAAgI6KhBxNUl7lVqXTXOAt0VF3oYecVE9Cnk8POQAAAAA0BQk5mqS4wlxEKj3Brhhb3Y9NN08P+Y78MkX4TnoAAAAAEBQk5GiSEk9Cnp3sCPh+51TzeIXTrQOl7F0IAAAAAI1hH3IEZrNJkyZJLpck6def98r1P0MZqfHSMZOqy3g4YmzqlOTQ3uIK7cwvU0aXJPP8WuXajDf+cNUP7kGw0Z4AAAARh4Qcgdls0qhRvpcbq36Re91PykxJkEYND3hK17Q47S2uUG5BuQZ3S/U7v83Vih9hwD0ILtoTAAAg4jBkHU2yt7hSkpSZaK+3THayufVZXhELuwEAAABAY+ghR2But7R1q/koyfXrJlkMtzITYqXNm80yPXtK1urvdLI888v3FFVUnx+gXJsId/3gHgQb7QkAABBxSMgRmNMpLVzom0M++PtdijnoVGXFW83jkjRrlmSv7jH3S8i95wco1ybCXT+4B8FGewIAAEQculjQJKWV5irrnRIDr7IuVa/AnldU0SYxAQAAAEBHRkKOJimrNHvKOyXVn5D79ZADAAAAABpEQo5GGYahUk9CnpFU/zBZEnIAAAAAaDoScjSqwumW2zAkSZkNJOTZNRJyw1MeAAAAABAYCTkaVV5l9o4n2m1yxNjqLecdzl7pcquwzNkmsQEAAABAR0VCjkZVVJlbn6XGN7yqc1ysTSlx5sL9e4rZixwAAAAAGsK2ZwjMZpMmTJBcLu3clq+V+9crOdFRfdxbppasZIcKy53KK3GqfwPlQq6RONEGuAfBRXsCAABEnLD2kK9YsUKTJ09W165dZbFYtHjxYr/3DcPQ7bffrpycHMXHx+vEE0/Uhg0bwhNstLHZpLFjpWOO0dZBI7Sq+0ClJMVVHx87NmBSkJ0cJ0naU+ZssFzINRIn2gD3ILhoTwAAgIgT1oS8pKREw4YN02OPPRbw/fvvv1+PPvqonnjiCX355ZdKTEzUxIkTVV7OcOi2VFhWJUlKjY9ttCwrrQMAAABA04R1yPopp5yiU045JeB7hmFo3rx5uvXWW3XGGWdIkp599ll17txZixcv1jnnnNOWoUYft1vKzZXcblVt3qrORXuVHtet+rgk5eRIVv/vdLwJeV5BmbRjR73lQq6RONEGuAfBRXsCAABEnHb7F92mTZu0a9cunXjiib5jqampOvLII/X555/Xe15FRYUKCwv9ftACTqf09NPSU0+p/+IXdO53S5Rmt1Yff/pp83kt3q3P9heUNlgu5BqJE22AexBctCcAAEDEabcJ+a5duyRJnTt39jveuXNn33uBzJkzR6mpqb6fHj16hDTOaFDh9K6yzpB1AAAAAAiWdpuQt9TNN9+sgoIC38+2bdvCHVKH592HPC2hOQk58/wBAAAAoCHtNiHv0qWLJGn37t1+x3fv3u17LxCHw6GUlBS/H7ROhdNMyOkhBwAAAIDgabcJeZ8+fdSlSxctW7bMd6ywsFBffvmljjrqqDBGFn3Kq5oxZD3JTMjzy6rkchshjQsAAAAAOrKwrrJeXFysjRs3+l5v2rRJa9asUUZGhnr27Kmrr75af/nLXzRgwAD16dNHt912m7p27aopU6aEL+go5B2y3pSEPC3BLoul+rxER1g/YgAAAADQboU1W/rmm290/PHH+15fe+21kqTp06dr4cKFuuGGG1RSUqLLL79c+fn5Ovroo/Xee+8pLi4uXCFHHcMwPIu6WZSaYG+0vM1qUXqCXUWFVSojIQcAAACAeoU1WzruuONkGPUPa7ZYLLrrrrt01113tWFUkCTZbNJxx6myvFKfbIyXYbXqsqQ433FfmQAyEu3KLyrTruGj1albar3lQqoJcSLEuAfBRXsCAABEHLovEZjnj//9BWX6fHmVYqwWJcTbJYulOimoR0aiXRutNm0afJgGD+vaNvHWVjN5QXhwD4KL9gQAAIg47XZRN7QP+aVVkswtzyzeyeGNyEw0h7bvL6kMWVwAAAAA0NGRkCMww5Dy8lSydYcyiw+ol7PYPOY5rrw883kAGYl2yTBUuj23wXIh1YQ4EWLcg+CiPQEAACIOQ9YRWFWV9PjjSsst0PQfctU5PVGqOtV87/HHzcdZsyR73YXeMhLtinU7dfBrz0prO9dbLqQ88TcUJ0KMexBctCcAAEDEoYccDarwbHkWF9v0j0qGZ8h6WaUrJDEBAAAAQCQgIUeDKpyehDym6as6+xLyKhJyAAAAAKgPCTkaVF7lliQ5mtFDnpnokEQPOQAAAAA0hIQcDSr3DVmnhxwAAAAAgomEHA0qd5o95HExzeghT/Im5G4ZrAYNAAAAAAGRkKNBvjnkzeghT08wE3LDMHxD3gEAAAAA/tj2DIHZbNKYMVqzK0mb4kt0zKhDzGOSNGZMdZkA7DFWJcTbtarbodo/fKi61VMupDzx+56j7XEPgov2BAAAiDgk5AjMZpNOOkkffxerzWml+uP4o6qTgJNOavT09OR4rexzuHaOOip8CXkT4kQIcQ+Ci/YEAACIOAxZR4OKK5ySpOS45n13413YbV9xZdBjAgAAAIBIQEKOwAxDys+XDhxQSlmRksuLzWPe4/n55vN6ZCTYlVJerKJdexosFzJNjBMhxD0ILtoTAAAg4pCQI7CqKrkefkQXfv6qLv16sTKfni9VVZk/8+aZP1VV9Z6e5bDo4m/+q17/fqrBciHTxDgRQtyD4KI9AQAAIg4JOepV6axeId3ejG3PJCndM2S9tJK9yAEAAAAgEBJy1MubkMfaLLJaLM06NzPRuxc5CTkAAAAABEJCjnp59yC325r/MfH2kJfRQw4AAAAAAZGQo16VLrOHvLnD1SUpPSFWklRe5W6kJAAAAABEJxJy1Ms7ZN0e0/x9xNMSzB7ycoasAwAAAEBAJOSoV3VC3vyPCQk5AAAAADQsJtwBoJ2yWrVzwGB9tzdJMT3TpJEHS1ZPYj5ypK9MfdKTHPou5yBJUqVbsoc43Dqs1ibFiRDiHgQX7QkAABBxSMgRWEyMfjriGC3b21kZI7pLpw6rfu/UUxs9PSUpXh/3Hym3IeVXuZUdF8JYA4mJaVKcCCHuQXDRngAAABGHbhbUq7jcKUlKimv+9zZWq0Wp8ebCbvmlVUGNCwAAAAAiAQk5AjMMlecXKr6iTOlGpVRSIhmG+VNSUv26gfNzYlyKryzXgeKKtou7Rv1NihOhwz0ILtoTAAAg4jBkHYFVVWnUK/9S2s4DOnpflrS6kzRrlvneAw+Yj7NmSfZ6ZodXVWn6py8rt6Bc+ReMbJuYa9XfpDgROtyD4KI9AQAAIg495KhXa1ZZl6S4WHO7tILSyqDFBAAAAACRgoQc9apwmluWtTYh309CDgAAAAB1kJCjXpUuTw+5rWUfk3hPQs6ibgAAAABQFwk56uUdsu5oZQ85CTkAAAAA1EVCjnq1dg65t4f8AAk5AAAAANRBQo56tX5RN/M8FnUDAAAAgLrY9gwBVbgN/ZDVR1a3W7bDh0nxDsnqScyHDzcfrQ0k6larXMOGa+3ueO0rc4Y83kD1NylOhA73ILhoTwAAgIhjMQzDCHcQoVRYWKjU1FQVFBQoJSUl3OF0GHuLK3TEXz6QJP167yRZrZZmX+OnXYU6ed5KZSbateq2CcEOEQAAAADapabmoXSzIKDicrNXO8kR06JkXJLSE+ySpPyyKkX49z4AAAAA0Gwk5AiouLxKsa4qpVndUkWFVFkpGYb5U1lZ/bo+hqG0GEOxriq5XG4VlrfxsPWmxonQ4R4EF+0JAAAQcZhDjoCKiko18/OX1CneJv3lM8lmk2bNMt+8917zcdYsyW4PfIGqKjnun6urv9qoeaN+q/zSSqXGx7ZN8J76mxQnQod7EFy0JwAAQMShhxwBFVeYPdotXWHdK46tzwAAAAAgIBJyBORNyGNtrU3IzfMPlLD1GQAAAADUREKOgLyLujlibK26Tryvh5yEHAAAAABqIiFHQNVD1lu2wroXQ9YBAAAAIDAScgRU4h2ybg3OHPJ8esgBAAAAwA8JOQIqq3RLkuytnEPOkHUAAAAACIxtzxBQidOlXZk9NbB/Z2lgF3PbM29v+cCB5mNDvedWqzRwoMqteXIXW9t+yLqnft9ztD3uQXDRngAAABGHhBwBFbksevvQcRp1yiBpTG//N6dNa/wCMTHStGkq+HaHXIvWtP2QdU/9CCPuQXDRngAAABGHbhYEVOqZQ55gb90q62kJsZKkAyUs6gYAAAAANZGQI6CSSpckKdHRukEU6Ql2SSzqBgAAAAC1MWQdAVWWlunqT57XoQXLpE6J5hzyWbPMN++913ycNUuy2+u5QKV0773qXVqlWGOkDpS2rqe92Tz1S2o4ToQO9yC4aE8AAICIQw85AiqtMHvIW7vKepzdPL+syqXyKler4wIAAACASEFCjoBKKj37kNssrbqO3WZVjNW8BlufAQAAAEA1EnIEVOrpzY6Nad1HxGKxKDWehd0AAAAAoDYSctRhGIbKKoMzZF2S0ljYDQAAAADqICFHHRVOt1xuQ5IUG4SEPN279VkpPeQAAAAA4EVCjjpKK6sXX4tp5RxySUr19JAzhxwAAAAAqrHtGeooqXDKbbFqe6fush50kHnQZpOsnu9vBgwwH60NfJ9jtfrKpcWEYch6jfobjBOhwz0ILtoTAAAg4pCQo47SSpdcVps+GjFBunBC3QLnn9/4RWJifOVS310nqY2HrNeoH2HCPQgu2hMAACDi0M2COrxbniU4bEG5XjpD1gEAAACgDhJy1FFaYc4hT7QHZwCFd1G3fBZ1AwAAAAAfhqyjjtJKp2JdVbrgw+ekgo8ki8WcQ3799WaBBx4wH6+/XrLbA1+kstJXLv3UCyS1cQ95jfobjBOhwz0ILtoTAAAg4pCQow7vKuvxcktOc/i63O7qAlVN7On2lEuP9wxZL2njIetNjROhwz0ILtoTAAAgojBkHXV455AHYw9ySUpjH3IAAAAAqIOEHHV455Dbg5aQmz3kheVVcrmNoFwTAAAAADo6EnLU4e0hj7FZgnI9bw+5YUgFZfSSAwAAAIBEQo4AvHPI7THB+XjE2qxKdpjLFbD1GQAAAACYSMhRR0lFcOeQS1JaonfrMxJyAAAAAJBYZR0BlFa6ZMii8m49pF4Z1dueWTxD2Hv3Nh8tDQxpt1j8yqUn2LVtf5kOlLTRkPVa9SMMuAfBRXsCAABEnHadkLtcLt1xxx167rnntGvXLnXt2lUzZszQrbfeKgt/kIZMaaVTTluMdkw5WzqyV90CM2Y0fpHYWL9y3oXd2mzIeq36EQbcg+CiPQEAACJOu07I586dq/nz5+uZZ57RoEGD9M033+iiiy5Samqq/u///i/c4UUs7xzyRHvwPh4ZCd4h6yzqBgAAAABSO0/IP/vsM51xxhk69dRTJUm9e/fWf/7zH3311VdhjiyyeeeQJ9htQbtmm/eQAwAAAEA7164T8jFjxuipp57Szz//rIMOOkjfffedPvnkEz388MP1nlNRUaGKigrf68LCwrYINaKUVroU66rSgGfmS2kO82BMjHT11ebzefPMx6uvluz2wBeprPQrl97WCXmt+uuNE6HDPQgu2hMAACDitOuE/KabblJhYaEOOeQQ2Ww2uVwu3XPPPTr//PPrPWfOnDm688472zDKyOPdhzyuqlwqc5sHbTV6y0tLm3ahGuXSPaust9mibrXqR5hwD4KL9gQAAIgo7Xrbs5deeknPP/+8XnjhBa1evVrPPPOMHnzwQT3zzDP1nnPzzTeroKDA97Nt27Y2jDgylFaYc8iDuu0ZQ9YBAAAAwE+77iG//vrrddNNN+mcc86RJA0ZMkRbtmzRnDlzNH369IDnOBwOORyOtgwz4nh7yIOZkKezqBsAAAAA+GnXPeSlpaWyWv1DtNlscrvdYYoo8rnchsqrzPa1BzUhp4ccAAAAAGpq1z3kkydP1j333KOePXtq0KBB+vbbb/Xwww/r4osvDndoEausyuV7HmuzSDKCct30RDMhzy+tkmEY7CMPAAAAIOq164T8b3/7m2677TZdeeWVysvLU9euXXXFFVfo9ttvD3doEavUs+WZzWqRzWqR3MFJyDM8PeSVLrdKKl1KcrTrjx4AAAAAhFy7zoqSk5M1b948zfNu9YOQK6k0e8jj7TGydOsmuTw95jab5O3V7trVfGyol9ti8SsXH2uTI8aqCqdbB0oqQ5+Q16ofYcA9CC7aEwAAIOK064Qcba/E00Nuj3dIl18euFB9x2uKja1TLiPRrtyCch0orVSPjITWhtrs+tHGuAfBRXsCAABEnHa9qBvaXqmnhzzRHvzvarwLu+0vYWE3AAAAACAhhx/vlmcJDlvQr52RyErrAAAAAODFkHX4Ka0we8iTbZLmzfOfQz5zpvn8scfMx5kzzWG0gVRV1SnnXWl9f0kb7EUeoH60Me5BcNGeAAAAEYeEHH68PeSJsVYpL98/ITc8K67n55uPRgMrsBtGnXLpCWYCcaAthqwHqB9tjHsQXLQnAABAxGHIOvyUeeaQJ4RgFXTvHHKGrAMAAAAACTlqqe4hZw45AAAAAIQSCTn8eOeQJ4RilfVEVlkHAAAAAC8Scvjx9pDH24P/0cjwDllvi0XdAAAAAKCdIyGHH28PeWIo5pAnmou67WfIOgAAAACwyjr8+XrIHTFSVpb/KusWi/k8K8t89L4OxGKpU867qFt+aaUMw5ClofNbK0D9aGPcg+CiPQEAACIOCTn8lHpXWU+Ir953vLb6jtcUG1unnDchr3IZKq5wKjkuhPsoB6gfbYx7EFy0JwAAQMRhyDr8lHp6yBMcwV9lPd5uU7xn9XbmkQMAAACIdiTk8OPtIU8MwSrrUvXWZ8wjBwAAABDtGLIOPyUVnh5yi1t67DH/OeSXX24+f+op8/Hyy81htIFUVQUsl54Yqx35ZaHfi7ye+tGGuAfBRXsCAABEHBJy+PH1kMfapD17/BNywzCf79ljPnpfB2IYAcul+7Y+C3FCXk/9aEPcg+CiPQEAACIOQ9bhx9tDHh+COeRSdUK+P9QJOQAAAAC0cyTk8DEMo83mkId8yDoAAAAAtHMk5PCpdLnldJtDYUOxyrpUs4ecVdYBAAAARDcScviUVrh8zxNiQ5OQZySaC1Hl00MOAAAAIMqRkMOntMpMyB0xVsXYQvPRSGMOOQAAAABIYpV11FDqWdAt0REjWSxSWpr/KusWi/k8Lc189L4OxHt+rXJtNoe8nvrRhrgHwUV7AgAARBwScviUeBZ0i4+1mXscX3114IL1Ha+pnvPbbA55Q/GjbXAPgov2BAAAiDgMWYdPdQ95aOaPS9U95PmllTLYSxkAAABAFCMhh4+3hzwhRFueSVJagrmom9NtqMjzBQAAAAAARCOGrMOntLJGD3lVlbRggf8c8osuMp8vWGA+XnSROYw2EO/5tcrFxdqUYLeptNKlAyWVSomr5/zWqqd+tCHuQXDRngAAABGHhBw+JRU1esgNQ9q50z8h9w4x37nTfGxoyLn3/ADl0hPsKq0s0/6SSvXKTAzmr9Ck+tFGuAfBRXsCAABEHIasw8fXQ24P3RxyqQ1XWgcAAACAdoyEHD6l3jnkjtAOnEj3JuShXmkdAAAAANoxEnL4lHh6yBNiQ9xD7lnYbX8JPeQAAAAAohcJOXxKK9qmhzwj0SFJ2kdCDgAAACCKkZDDp6SN5pBnJplD1vcVV4S0HgAAAABoz1hlHT51esgTEiSnZ6/wmBoflYSEpl2wnnKdPAl5yIesNzVOhA73ILhoTwAAgIhCQg4fvx5yu1264YbABes7XlMD53uHrO8NZULeUPxoG9yD4KI9AQAAIg5D1uHjW2XdHtrvaRiyDgAAAAAk5KihpMLTQ+4I7RzyTt5F3YpZ1A0AAABA9GLIOnzKqmr0kFdVSc8/b84ht1gkm006/3yz4PPPm4/nny/Fxga+mPf8AOW8PeRlVS6VVjpD0yPfQP1oI9yD4KI9AQAAIg4JOXxKvIu62W2SYUibN0su85hsnmOSeVyqfh2I9/wA5RLsNsXFWlVe5da+4kolZITgY9hA/Wgj3IPgoj0BAAAiDkPW4VPqW9QttN/TWCwWZbIXOQAAAIAoR0IOSZLbbVQv6hbiOeQSC7sBAAAAAAk5JFXPH5dC30MuSZmJ3oScHnIAAAAA0YmEHJKq9yC3WKS42NB/LDKTvHuR00MOAAAAIDqRkEOSVOpZ0C3RHiOLxRLy+qqHrNNDDgAAACA6sco6JFX3kCfYa8wfj401u8y9257VPN4UDZSrHrIewh5ytoUKP+5BcNGeAAAAEYWEHJKkssoaW55Jkt0u3XJL4ML1Ha+pofOl0K+y3kj9aAPcg+CiPQEAACIOQ9YhSSrxJeRt8x0NQ9YBAAAARDsSckiSSis8e5C3wZZnktQpydtDzqJuAAAAAKITQ9YhKUAPudMpLVokuTzbodls0tlnm88XLTIfzz5biqnnI+Q9v55yNXvIDcMI/kJyjdSPNsA9CC7aEwAAIOLwFx0kSaWVtXrI3W5pwwb/hNztNp9v2FBdpj7e8+spl+FZ1M3pNlRY5lRqQpAXq2qkfrQB7kFw0Z4AAAARhyHrkCSVVLTtHHJHjE3JDrMu9iIHAAAAEI1IyCGpRg+5vW3mkEvVw9b3h2qldQAAAABox0jIIam6hzy+jXrIJSnTu7BbKPciBwAAAIB2ioQckqSyqjD0kHvmke9l6zMAAAAAUYiEHJJqzCF3hKOHnIQcAAAAQPQhIYekMM0h9/SQsxc5AAAAgGjEtmeQFKCH3G6X7rgjcOH6jtfU0PkeNfciD7om1I8Q4x4EF+0JAAAQceghh6RwrbLuGbJODzkAAACAKERCDklSSWXb7kMuSZ0SQ9hDDgAAAADtHEPWIUkqrfD0kDs8PeROp/Taa5LLTNRls0lTp5rPX3vNfJw6VYqp5yPkPb+BctU95CFIyJtQP0KMexBctCcAAEDEoYcckqTSKm8PuSchd7ultWv9f9xu/+Nud/0XbEI57xzyA6WVcroauFZLNDVOhA73ILhoTwAAgIhDQg5JUmlF2w9Zz0iwy2a1yDBC1EsOAAAAAO0YCTlU6XSr0tNDndiGCbnValEnTy95XiELuwEAAACILiTkUJlnQTdJim/DVdYlKSvZnEeeV1TepvUCAAAAQLiRkEMlni3P7Dar7DFt+5HITo6TJO0pooccAAAAQHQhIYdvD/IER9v2jktStq+HnIQcAAAAQHRp9wn5jh079Lvf/U6ZmZmKj4/XkCFD9M0334Q7rIhS4lnQrS3nj3sxZB0AAABAtGpRBvbrr7+qb9++wY6ljgMHDmjs2LE6/vjj9e677yorK0sbNmxQenp6yOuOJt4h637zx2NjpVmzJMMwX1ss5jHJPO4tUx/v+Y2U8/WQB3tRtybWjxDiHgQX7QkAABBxWpSQ9+/fX8cee6wuueQS/fa3v1VcXFyw45IkzZ07Vz169NCCBQt8x/r06ROSuqKZd1G3xJoJucUi2e2BT6jveE0NnV9DlncOeXGQE/Im1o8Q4h4EF+0JAAAQcVo0ZH316tUaOnSorr32WnXp0kVXXHGFvvrqq2DHpjfeeENHHHGEzjrrLGVnZ+uwww7T008/3eA5FRUVKiws9PtBw0oq234Pcq+sUPWQAwAAAEA716KEfPjw4frrX/+qnTt36l//+pdyc3N19NFHa/DgwXr44Ye1Z8+eoAT366+/av78+RowYICWLFmiP/zhD/q///s/PfPMM/WeM2fOHKWmpvp+evToEZRYIllphTlkPbHmom5Op7R4sfTqq+bP4sXmMe9x7+v6NLGcd8j6nqIKGd7h8cHQ1DgROtyD4KI9AQAAIk6rFnWLiYnR1KlT9fLLL2vu3LnauHGjrrvuOvXo0UMXXnihcnNzWxWc2+3W4YcfrnvvvVeHHXaYLr/8cl122WV64okn6j3n5ptvVkFBge9n27ZtrYohGgTsIXe7pTVr/H/cbv/jbnf9F21iOW8PeaXLrYKyqlb9Hi2pHyHEPQgu2hMAACDitCoh/+abb3TllVcqJydHDz/8sK677jr98ssvWrp0qXbu3KkzzjijVcHl5ORo4MCBfscOPfRQbd26td5zHA6HUlJS/H7QsIA95G0kLtam1HhzgSr2IgcAAAAQTVo0afjhhx/WggULtH79ek2aNEnPPvusJk2aJKvVzO/79OmjhQsXqnfv3q0KbuzYsVq/fr3fsZ9//lm9evVq1XXhL5xzyCWzl7ygrEp5RRUa0Dk5LDEAAAAAQFtrUQY2f/58XXzxxZoxY4ZycnIClsnOztY///nPVgV3zTXXaMyYMbr33ns1bdo0ffXVV3rqqaf01FNPteq68Ffq2fbMb5X1NpSd7NDGvGL2IgcAAAAQVVqUkC9dulQ9e/b09Yh7GYahbdu2qWfPnrLb7Zo+fXqrghs5cqRef/113XzzzbrrrrvUp08fzZs3T+eff36rrgt/JRVmD3l8mHrIay7sBgAAAADRokUZWL9+/ZSbm6vs7Gy/4/v371efPn3kcrmCEpwknXbaaTrttNOCdj3UVVYVvjnkElufAQAAAIhOLVrUrb7tqYqLixUXF9eqgND2vD3k4ZpDnp1sfmby6CEHAAAAEEWalYFde+21kiSLxaLbb79dCQkJvvdcLpe+/PJLDR8+PKgBIvQCziGPjZWuv17yfvlisZjHJPO4t0x9vOc3Vk5SdoqnhzyYc8ibUT9ChHsQXLQnAABAxGlWQv7tt99KMnvIf/jhB9ntdt97drtdw4YN03XXXRfcCBFyvh5yR42Pg8UiJSYGPqG+4zU1dH4tWaGYQ96M+hEi3IPgoj0BAAAiTrMS8o8++kiSdNFFF+mvf/0re3xHiPawyrrEkHUAAAAA0aVFk4YXLFgQ7DgQRgH3IXc6pSVLJO8CfTabNHGi+XzJEvNx4kQppp6PkPf8xspJyvLMIS8qd6q8yqW42CB8MdCM+hEi3IPgoj0BAAAiTpP/ops6daoWLlyolJQUTZ06tcGyr732WqsDQ9sprTB7yBNq9pC73dLXX/sn5BMmmM+//tp89L4OxHt+Y+UkpcTFyBFjVYXTrbzCCvXMTGiwfJM0o36ECPcguGhPAACAiNPkhDw1NVUWi8X3HJHBMAyVVnnnkIdnyLrFYlFWskPbD5RpT3F5cBJyAAAAAGjnmpyQ1xymzpD1yFFe5fYtpJ4Ypm3PJHMe+fYDZexFDgAAACBqtGgf8rKyMpWWlvpeb9myRfPmzdP7778ftMDQNko8C7pJUnww5m63EHuRAwAAAIg2LUrIzzjjDD377LOSpPz8fI0aNUoPPfSQzjjjDM2fPz+oASK0Sr1bntltslotYYsjJHuRAwAAAEA71qKEfPXq1Ro3bpwk6ZVXXlGXLl20ZcsWPfvss3r00UeDGiBCy9tDnhDG4eqS1DnF7CHfVUAPOQAAAIDo0KKEvLS0VMnJyZKk999/X1OnTpXVatXo0aO1ZcuWoAaI0PLtQR6mBd28clI9CXlhWVjjAAAAAIC20qJu0f79+2vx4sU688wztWTJEl1zzTWSpLy8PKWkpAQ1QIRWSUWAPcglKTZWuvpq+VZ8s1jMY5J53FumPt7zGyvn0cWTkOcWBGnIejPrRwhwD4KL9gQAAIg4LUrIb7/9dp133nm65pprNH78eB111FGSzN7yww47LKgBIrRKKwPsQS6ZCXhaWuCT6jve1PMD6JoaL0nKzS+XYRi+LfZarJn1IwS4B8FFewIAAEScFiXkv/3tb3X00UcrNzdXw4YN8x0fP368zjzzzKAFh9ArqbGoWzh5e8jLqlwqLHMqNYEeQAAAAACRrcUreXXp0kVdunTxOzZq1KhWB4S2VW8PucslLVtmPkqSzSaNH28+X7bMfBw/3jweiPf8xsp5xMXalJ4QqwOlVcotLGt9Qt7M+hEC3IPgoj0BAAAiTosS8pKSEt13331atmyZ8vLy5Ha7/d7/9ddfgxIcQq+k0ky4Ex21Pgoul/TZZ/4J+XHHmc8/+8x8PO64hhPyppSrISc13kzIC8p1SJdWrkXQgvoRZNyD4KI9AQAAIk6LEvJLL71UH3/8sS644ALl5OS0fr4vwqa0wuwhT6qdkIdBTmqc1uYWKjefvcgBAAAARL4WZWHvvvuu3n77bY0dOzbY8aCNFde3ynoYeOeR7ypg6zMAAAAAka9F+5Cnp6crIyMj2LEgDLxzyJPCvA+5VL0XedC2PgMAAACAdqxFCfndd9+t22+/XaWlpcGOB23MO4e8PfSQ53i2PttVSEIOAAAAIPK1KAt76KGH9Msvv6hz587q3bu3YmP9V8RevXp1UIJD6JV45pAntqMe8p35DFkHAAAAEPlalJBPmTIlyGEgXKoT8vD3kHepMWTdMAwWCwQAAAAQ0VqUhc2ePTvYcSBMSjxzyBNrD1mPjZWuvFIyDPO1xWIek8zj3jL18Z7fWLkavEPWSytdKqpwKiWuFXuRt6B+BBn3ILhoTwAAgIjT4m7R/Px8vfLKK/rll190/fXXKyMjQ6tXr1bnzp3VrVu3YMaIECr1rbJea8i6xSJlZwc+qb7jTT2/HvF2m9ISYpVfWqVdBeWtS8hbUD+CjHsQXLQnAABAxGlRQv7999/rxBNPVGpqqjZv3qzLLrtMGRkZeu2117R161Y9++yzwY4TIeLrIW8HQ9YlqUtKnPJLq7Qzv0wHdU4OdzgAAAAAEDItWmX92muv1YwZM7RhwwbFxcX5jk+aNEkrVqwIWnAIvRJPD3mdhNzlkpYvl5YtM3+WLzePeY97X9enqeVq6ZrmWWm9tVuftbB+BBH3ILhoTwAAgIjTom7Rr7/+Wk8++WSd4926ddOuXbtaHRTahmEYNeaQ1xqy7v3j3/uHv80mjRljPl++3HwcM8Y8Hoj3/MbK1dIlWHuRt7B+BBH3ILhoTwAAgIjToh5yh8OhwsLCOsd//vlnZWVltTootI3yKrdvzbb2MmQ9J8VMyFvdQw4AAAAA7VyLEvLTTz9dd911l6qqqiRJFotFW7du1Y033qjf/OY3QQ0QoVPs2fJMkuJj20dvm7eHfGcBe5EDAAAAiGwtSsgfeughFRcXKysrS2VlZTr22GPVv39/JScn65577gl2jAiRUs9w9QS7TVZr+9jzO2hzyAEAAACgnWvROOXU1FQtXbpUn376qb777jsVFxfr8MMP14knnhjs+BBC9S7oFkbeHnIScgAAAACRrtmZmNvt1sKFC/Xaa69p8+bNslgs6tOnj7p06SLDMGSxtI+eVjSu3gXdwijHk5AXVThVVF6l5NbsRQ4AAAAA7VizhqwbhqHTTz9dl156qXbs2KEhQ4Zo0KBB2rJli2bMmKEzzzwzVHEiBEoq2tce5JKUYI9ReoKZhO/IZx45AAAAgMjVrExs4cKFWrFihZYtW6bjjz/e770PP/xQU6ZM0bPPPqsLL7wwqEEiNHxD1u0BPgYxMdJll0lut/naajWPSeZxb5n6eM9vrFwA3dMTdKC0QNv2l+mQLinNOjcY9SNIuAfBRXsCAABEnGb9Vfef//xHs2bNqpOMS9IJJ5ygm266Sc8//zwJeQfhHbKe4AgwZN1qlbp1C3xifceben4jemTE64cdBdp+oLRF57e2fgQJ9yC4aE8AAICI06wh699//71OPvnket8/5ZRT9N1337U6KLSN0nY4ZF0ye8glafsBhqwDAAAAiFzNysT279+vzp071/t+586ddeDAgVYHhbZRUukdsh6gh9zlkr74wnyUJJtNGj3afP7FF+bj6NHm8UC85zdWLoDu6ebWZ63qIW9F/QgS7kFw0Z4AAAARp1kJucvlUkwDcxdtNpucTmerg0Lb8C7qlhBoDrnLJS1d6p+QjxxpPl+61HwcObLhhLwp5QLwJuTb9reih7wV9SNIuAfBRXsCAABEnGYl5IZhaMaMGXI4HAHfr6ioCEpQaBulnh7ypHY7ZL0VPeQAAAAA0M41KxObPn16o2VY0K3jKK5oYFG3MPL2kBeWO1VQVqXUePYiBwAAABB5mpWQL1iwIFRxIAxKPausB9z2LIwS7DHKTLRrX0mldhwoIyEHAAAAEJGatco6IotvH/J2NmRdqjGPnGHrAAAAACIUCXkU8y7qFnCV9TBj6zMAAAAAkY6EPIr5tj1rxz3kLOwGAAAAIFK1v0wMbcbXQx5oUbeYGGnGDMntNl9breYxyTzuLVMf7/mNlatH94xW9pC3sn4EAfcguGhPAACAiMNfdVHMu6hbwH3IrVapd+/AJ9Z3vKnnN0H1XuQt7CFvZf0IAu5BcNGeAAAAEYch61HMu6hbe9uHXJJ6eBLyHQfKZBhGmKMBAAAAgOBrf5kY2oTLbaisykzIEwIt6uZySatWmY+SZLNJI0aYz1etMh9HjDCPB6zA1bRy9eiWZg5ZL6pwqrDMqdSEZm591sr6EQTcg+CiPQEAACIOCXmU8g5Xl+pZ1M3lkt55xz8hHz7cfP7OO+bj8OENJ+RNKVePeLtNnZIc2ltcoW0HSpWakNqs81tbP4KAexBctCcAAEDEYch6lCr1rLBus1rkiGmfHwNWWgcAAAAQydpnJoaQK67wLuhmk8ViCXM0gVUn5OxFDgAAACDykJBHqVLPgm6JgVZYbye6p5vzyFu80joAAAAAtGMk5FGqpLKBPcjbiZ6evci3kJADAAAAiEAk5FGqpMKbkLffHvLenTwJ+T4ScgAAAACRh4Q8SpVUtv8h670zEyWZQ9adLneYowEAAACA4Gq/2RhCqrqHvJ4h6zEx0nnnSW5PImy1msck87i3TH285zdWrgFdUuLkiLGqwunWjvwy9fIk6E0ShPrRStyD4KI9AQAAIg5/1UWpEt8q6/V8BKxW6aCDAr9X3/Gmnt9EVqtFvTIT9PPuYm3eV9q8hDwI9aOVuAfBRXsCAABEHIasRynvPuTteQ65VD1sffPekjBHAgAAAADB1b6zMYSMb8i6vZ4h6y6X9MMP5qMk2WzSkCHm8x9+MB+HDDGPN3R+Y+Ua0buTJyHf18yEPEj1oxW4B8FFewIAAEQcEvIo5d32LKG+HnKXS1q82D8hHzjQfL54sfk4cGDDCXlTyjWixT3kQaofrcA9CC7aEwAAIOIwZD1KlVaYiXZSO96HXJJ6Z7L1GQAAAIDIREIepYobW9StnejlGbK+la3PAAAAAEQYEvIoVb2oW/vuIc9JiZM9xiqn29DO/PJwhwMAAAAAQUNCHqW8c8gT23kPudVqUa8Mc9j6puYu7AYAAAAA7RgJeZTyrbLezrc9k6pXWt9CQg4AAAAggnSohPy+++6TxWLR1VdfHe5QOrySio6xD7lUvbDb5r0s7AYAAAAgcrT/bMzj66+/1pNPPqmhQ4eGO5SI4Nv2rL59yGNipLPOktyehdSsVvOYZB73lqmP9/zGyjVBi/YiD2L9aCHuQXDRngAAABGnQ/xVV1xcrPPPP19PP/20/vKXv4Q7nA7PMAzfkPWk+nrIrVZp0KDA79V3vKnnN5NvL/LmJORBrB8txD0ILtoTAAAg4nSIIeszZ87UqaeeqhNPPLHRshUVFSosLPT7gb8Kp1tVLkOSlBTX/r+T8faQb2PrMwAAAAARpN1nYy+++KJWr16tr7/+uknl58yZozvvvDPEUXVs3j3IpQZWWXe7pXXr/IesH3qo+XzdOvPx0EPN4w2d31i5JvBufVbpdGtnfrl6euaUNyiI9aOFuAfBRXsCAABEnHb9F922bdv0pz/9Sc8//7zi4uKadM7NN9+sgoIC38+2bdtCHGXHU1zu3fLMJpvVEriQ0ym9/LL00kvmz8svm8e8x72v69PUck1gtVrUxzNs/Zc9xU07KYj1o4W4B8FFewIAAEScdp2Qr1q1Snl5eTr88MMVExOjmJgYffzxx3r00UcVExMjl8tV5xyHw6GUlBS/H/jz9pB3hOHqXv2zkyRJG/OamJADAAAAQDvXrjOy8ePH64cffvA7dtFFF+mQQw7RjTfeKJutnhXC0aCi8kYWdGuH+pGQAwAAAIgw7TojS05O1uDBg/2OJSYmKjMzs85xNF11D3lsmCNpOl8PeVOHrAMAAABAO9euh6wjNIorqiRJyR2oh7x/VnUPuWEYYY4GAAAAAFqv42RkHsuXLw93CB1ecQccst43K1EWi1RQVqV9JZXqlOQId0gAAAAA0Cr0kEeh4gpzMbyOtKhbXKxN3dPjJTGPHAAAAEBk6DgZGYLGO2S9wR5ym02aMkXyrmRvs5k/knnce6yx8xsr1wz9s5K0bX+ZNuYVa3TfzIYLh6B+NBP3ILhoTwAAgIhDQh6FvEPWkxvqIbfZpOHDA79X3/Gmnt9C/bOT9NH6PU3rIQ9B/Wgm7kFw0Z4AAAARhyHrUaioouPNIZeqV1r/hZXWAQAAAESAjpWRISh8i7o11EPudksbN5qPkmS1Sv37m883bjQf+/c3jzd0fmPlmqF/c/YiD0H9aCbuQXDRngAAABGHv+iiUHFTesidTumFF6Tnnzd/XnjBPOY97n3d2PmNlWuGfp6tz3ILyn2/Q1vWj2biHgQX7QkAABBxSMijkDeZbXAOeTuUlmBXpyS7JOlXhq0DAAAA6OBIyKNQ9T7ksWGOpPm8veRsfQYAAACgoyMhj0IddVE3qZnzyAEAAACgHSMhj0JN2vasnfIm5BtIyAEAAAB0cCTkUcbpcqusyiWpY/aQH9w5WZL08+6iMEcCAAAAAK1DQh5lSipcvueJHTEh72Im5Fv2laqksZXWAQAAAKAd63gZGVqlqKJKkuSIscoe08D3MTabNGmS5HJVv7bZzOeTJlUfa+z8xso1U2aSQ9nJDuUVVWj97iId3jO9TetHM3APgov2BAAAiDgk5FGmyVue2WzSqFGB36vveFPPb6WDuySbCfmuRhLyENWPJuIeBBftCQAAEHEYsh5lqrc867jfxRyakyJJ+im3MMyRAAAAAEDLddysDC3i2/KssR5yt1vautV8lCSrVerZ03y+dav52LOnebyh8xsr1wKHeOaRr9vVwMJuIawfTcQ9CC7aEwAAIOKQkEeZJveQO53SwoX+c8hnzTKfL1xoPs6aJdntDZ/fWLkW8C7stn5XkQzDkMViadP60UTcg+CiPQEAACIOXSxRxjuHPMkRG+ZIWq5/dpJsVosKyqq0q7A83OEAAAAAQIuQkEcZbw95o4u6tWOOGJv6ZSVKkn7KZT9yAAAAAB0TCXmU8c0h78CLuknSwV08C7s1NI8cAAAAANoxEvIo45tD3oF7yKXqhd1+2sVK6wAAAAA6JhLyKFNcUSWp4/eQH5rjScgZsg4AAACggyIhjzJFnh7ylA7fQ24OWf9lT7Eqne4wRwMAAAAAzdexszI0W2G52UOeEt/IKus2mzRhgv+2Zzab+XzChOpjjZ3fWLkWykmNU3JcjIrKndqYV6yBXVPatH40AfcguGhPAACAiENCHmUKy7w95E1IyMeODfxefceben4QWCwWDcxJ0Zeb9uvHnQWBE/IQ1o8m4B4EF+0JAAAQcRiyHmWqe8g7/ncxQ7qlSpJ+3FEQ5kgAAAAAoPk6flaGZiks8yTkjfWQu91Sbq75KElWq5STYz7PzTUfc3LM4w2d31i5VhjS3UzIfwiUkLdB/WgE9yC4aE8AAICIQ0IeRQzDUKF3UbfG5pA7ndLTT/vPIZ81y3z+9NPm46xZkt3e8PmNlWuFwZ4e8nW5hXK63Iqx1UhQ2qB+NIJ7EFy0JwAAQMShiyWKlFa65HIbkprQQ94B9MlMVJIjRuVVbm3cUxzucAAAAACgWUjIo4h3/niszaK42I5/661Wi28xtx+2M48cAAAAQMfS8bMyNFnNFdYtFkuYowkOFnYDAAAA0FGRkEeRJu9B3oEMbWhhNwAAAABox0jIo0j1CuuRs5afd2G3tZ6F3QAAAACgoyAhjyKR2ENec2G3X/aUhDscAAAAAGiyyOkqRaNqziFvlM0mHXec/7ZnNpv5/Ljjqo81dn5j5VrJu7DbV5v26/vt+Tq4S3Kb1o8GcA+Ci/YEAACIOCTkUcQ3ZD2+Cbe95h//tdV3vKnnB9mQbqn6atN+/bijQGcd0aPN60c9uAfBRXsCAABEHIasRxHfkPUI2IO8Ju9K69+zsBsAAACADoQe8ijiG7LelDnkhiHt2WM+SpLFImVlmc/37DEfs7LM4w2d31i5IDisZ5ok6X87ClXhdMkRY2vT+lEP7kFw0Z4AAAARh4Q8ilT3kDfhtldVSY8/7j+HfNYs8/njj5uPs2ZJdnvD5zdWLgh6ZiQoM9GufSWV+nFHoUb0Sm/T+lEP7kFw0Z4AAAARhyHrUSQSV1mXJIvFosN6pkuSVm85EOZoAAAAAKBpSMijSLNWWe9gRvTyJORbScgBAAAAdAwk5FGkuoc88mYqHO6ZR75qywEZ3nnvAAAAANCOkZBHEd+2ZxHYQz60e5pirBblFVVoR35ZuMMBAAAAgEaRkEcJwzBUWN6MVdY7mHi7TQO7pkiSVm/ND28wAAAAANAEJORRoqTSJZfbHModiT3kknQ4C7sBAAAA6EAibzIxAvIOV4+1WRQX24TvYWw2acwY/23PbDbz+Zgx1ccaO7+xckF0eK90Lfxss7mwWxjqRy3cg+CiPQEAACIOCXmUqN6DPFYWi6XxE2w26aSTAr9X3/Gmnh8i3oXd1u4sVJlLim/j+lFLGD4DEY32BAAAiDgMWY8Svi3PInD+uFe3tHh1TnHI6Tb03fb8cIcDAAAAAA0iIY8S1SusN3FQhGFI+fnSgQPmT36+ecx73Pu6sfMbKxdEFotFR/TOkCR9+cu+Nq8ftYThMxDRaE8AAICIw5D1KJHvTcib2kNeVSXNm+c/h3zWLPP5vHnm46xZkt3e8PmNlQuyo/pm6u3vc/XVhl3Spy+0ef2oIUyfgYhFewIAAEQcesijRH5ppSQpPSGy/4gf3TdTkrRmW76cLneYowEAAACA+pGQR4kDnoQ8IzGyE/J+WYnKSnao0ulWbkF5uMMBAAAAgHqRkEeJA6XmkPW0hMhd1E0y55Ef5ekl336gNMzRAAAAAED9SMijRLQMWZeko/p5E/KyMEcCAAAAAPUjIY8SB0qio4dckq+HPLegXFXMIwcAAADQTpGQR4kDUdRD3iszQV1S4uQ2DOXmM48cAAAAQPvEtmdRIt8zh7zJCbnVKo0c6b/tmdXz/c3IkdVlGju/sXIhYLFYdGS/Tvou5yD1yOqinm1cPzzC+BmISLQnAABAxCEhjxLeHvImD1mPiZFOPTXwe/Udb+r5bWDUQZ11Q7+Ryu+Upt/E8DEPizB/BiIO7QkAABBx6GaJAmWVLlU4zbnU6RG+7ZnX0f07SZK+25bvW9AOAAAAANoTEvIo4O0dj7VZlGi3Ne0kw5BKSqTiYvOnpMQ85j3ufd3Y+Y2VC5GuqXEamhYjR0W5Vvy8p83rh8L+GYg4tCcAAEDEYSxvFKgerm6XxWJp2klVVdIDD/jPIZ81y3z+wAPm46xZkr2eHnfv+Y2VC5WqKl3/wxtateWAVo7oqdOHd2vb+hH+z0CkoT0BAAAiDj3kUcC75Vl6FGx5VlOfTomSpI9/3iO3mx5FAAAAAO0LCXkUqNlDHk1yUuNlt1l1oLRS3+8oCHc4AAAAAOCHhDwK5Pv2II+uHnKb1aJemQmSpI9+ygtzNAAAAADgj4Q8Chxo7h7kEaS3Z9j68vUk5AAAAADal3adkM+ZM0cjR45UcnKysrOzNWXKFK1fvz7cYXU40TpkXZJ6Z5oJ+XfbC7SnqCLM0QAAAABAtXadkH/88ceaOXOmvvjiCy1dulRVVVU66aSTVFJSEu7QOpT80uhc1E2SEh0xGpiTIkn6iF5yAAAAAO1Iu9727L333vN7vXDhQmVnZ2vVqlU65phjwhRVx3PAN4e8GT3kVqs0fLj/tmdWz/c3w4dXl2ns/MbKhUqN+k+I76Lv8jbp3R9yNe2IHm0fS7QK92cg0tCeAAAAEaddJ+S1FRSYK2VnZGTUW6aiokIVFdVDkwsLC0MeV3vnnUOe1pwe8pgYacqUwO/Vd7yp57eFGvVP2l2kRz7apE827lVBWZVS46NvpEBYhPszEGloTwAAgIjTYbpZ3G63rr76ao0dO1aDBw+ut9ycOXOUmprq++nRgx5R7yrrGYnRN4dckgZ0TtaA7CRVuQwtXbs73OEAAAAAgKQOlJDPnDlTP/74o1588cUGy918880qKCjw/Wzbtq2NImy/DpS0YFE3w5AqK6WKCvOnstI85j3ufd3Y+Y2VC5Va9U8akiNJeueH3LaPJVqF+zMQaWhPAACAiNMhhqxfddVVeuutt7RixQp17969wbIOh0MOh6ONImv/nC63Csudkpq5qFtVlXTvvf5zyGfNMp/fe6/5OGuWZK8nyfee31i5UKlV/6lDc/TXZRu0csMehq23lXB/BiIN7QkAABBx2nUPuWEYuuqqq/T666/rww8/VJ8+fcIdUoez39M7brVE57ZnXgfVGLb+AcPWAQAAALQD7Tohnzlzpp577jm98MILSk5O1q5du7Rr1y6VlZWFO7QOY0+xucBdRqJDNqslzNGEF8PWAQAAALQn7Tohnz9/vgoKCnTccccpJyfH97No0aJwh9Zh7C02e8g7JUVv77jXaUPNhHzFhj2+efUAAAAAEC7teg65wcJFrbanyOwhz0pmXv2Azska3C1FP+4o1Bvf7dT0Mb3DHRIAAACAKNaue8jRens9Q9azkkjIJek3h5uLAr6yanuYIwEAAAAQ7UjII9xeTw95J3rIJUlnDO+mWJtFP+wo0E+7CsMdDgAAAIAo1q6HrKP19rS0h9xqlQYO9N/2zOr5/mbgwOoyjZ3fWLlQqaf+jES7jj84W++v3a2Xv9mu204b2PaxRYtwfwYiDe0JAAAQcSxGhE/ULiwsVGpqqgoKCpSSkhLucNrc+f/4Qp9u3KdHzh6mMw9reA/3aLFs3W5d8sw3So2P1Zezxisu1hbukAAAAABEkKbmoXSzRLi9Rd5V1hmy7nXcwdnqlhavgrIqvfU9W6ABAAAACA8S8gjnHbJOQl7NZrXovCN7SpL+/cWWMEcDAAAAIFoxhzyCOV1uHSg1e8ibve1ZZaV0773+c8hnzTKf33uv+ThrlmSvZ39z7/mNlQuVRuo/e2QPzfvgZ323LV/fb8/X0O5pbRtfNAj3ZyDS0J4AAAARhx7yCLa/pFKGIVktUnoCf7zX1CnJodOGdpUkPb1yU5ijAQAAABCNSMgjWJ5ny7OMRIdsVkuYo2l/LhvXV5L0zg+52ra/NMzRAAAAAIg2JOQRbK93yzP2IA9oYNcUjRvQSS63oX9+Qi85AAAAgLZFQh7B9hZ7V1hnuHp9rjimnyRp0dfbfF9gAAAAAEBbICGPYHs8Q9azWGG9XmP7Z2pY91SVVbn05Me/hDscAAAAAFGEhDyCeXt8OzFkvV4Wi0XXTDhIkvTs51uUV1ge5ogAAAAARAu2PYtgvjnkLekht1qlAQP8tz2zer6/GTCgukxj5zdWLlSaUf+xB2Xp8J5pWr01X48v/0V3nD6oDQKMAuH+DEQa2hMAACDiWAzDMMIdRCgVFhYqNTVVBQUFSklJCXc4beqcpz7XF7/u17yzh2vKYd3CHU679unGvTr/H18qxmrRkmuOUb+spHCHBAAAAKCDamoeSjdLBMstMIdf56TGhTmS9m9s/0464ZBsOd2G5ryzLtzhAAAAAIgCJOQRyu02lJtvJuRd0+LDHE3HMGvSoYqxWvTBujyt3LAn3OEAAAAAiHDMIY9Q+0oqVelyy2KRurSkh7yyUnrgAcnplCwWcw759deb7z3wgPl4/fWSvZ4t1bznN1YuVFpQf//sJF1wVC8t+HSzbl38o5ZcfYziYm0hDjSChfszEGloTwAAgIhDD3mE2plfJknKTnYo1tbC21xVZSbkVVXmT83jNV83dH5TyoVKC+q/dsJB6pISpy37SvXosg0hCiyKhPszEGloTwAAgIhCQh6hcgvMhDwnleHqzZEcF6s7zzBXWX9qxa/6blt+eAMCAAAAELFIyCPUDs/88W7MH2+2iYO66NShOXK6DV2zaI1KK53hDgkAAABABCIhj1C5+d4eclZYb4l7pgxWl5Q4/bq3RHe88b9whwMAAAAgApGQR6idniHrrLDeMmkJdj189jBZLNJL32zXC19uDXdIAAAAACIMCXmE2smWZ602pl8nXT/xYEnS7Dd+1Deb94c5IgAAAACRhG3PIlSur4e8hUPWLRapd2//bc8sFvO93r2ryzR2fmPlQiVI9f/h2H76YXuB3v1xly555hu98vujNKBzcnBijHTh/gxEGtoTAAAg4lgMwzDCHUQoFRYWKjU1VQUFBUpJSQl3OG2i0unWwbe9K8OQvrn1RHVKcoQ7pA6trNKl8/7xhb7dmq+c1Dgtuvwo9cxMCHdYAAAAANqppuahDFmPQLsLy2UYkj3GqsxEe7jD6fDi7Tb9a/pI9c9OUm5BuaY9+bl+3VMc7rAAAAAAdHAk5BFop2eF9a6pcbIwtDUo0hPteuGyIzUgO0m7Csv12yc+Z045AAAAgFZhDnkEyi0wF3TLSW3Fgm6VldK8eeYcckmKiZGuvtp8Pm+e+Xj11ZK9nh547/mNlQuVENSfnRynFy8frRkLvtYPOwp03tNfavbpA3XeqJ588RFIuD8DkYb2BAAAiDj0kEegrftLJUnd0lu5wnppqVRWZv6Ulvofr/m6ofObUi5UQlB/ZpJDi64YrYmDOqvS5dYtr/+oy/+9SvuKK4JaT8QI92cg0tCeAAAAEYWEPAJt2Wf+wd6nU2KYI4lMCfYYzT9/hG499VDZbVYtXbtbJz2yQs99sUVOlzvc4QEAAADoIEjII9CWfSWSpJ4ZrAQeKlarRZeO66vFM8fqoM5J2ldSqVsX/6hTH/1E7/2YK5c7ojcvAAAAABAEJOQRaLOnh7x3Jj3koTawa4re/r9xumPyQKUlxGr97iL9/rnVOuGh5Vr46SYdKKkMd4gAAAAA2ikS8ghTUuHUXs98ZvbKbhuxNqtmjO2j5dcdp6uO76/U+Fht2VeqO95cq1H3fqDLn/1G7/2Yq/IqV7hDBQAAANCOsMp6hPHOH89ItCs1PjbM0USXtAS7rpt4sK48vp9e/ma7Fn29TWtzC/X+2t16f+1uxcVaNW5AliYc2lnHH5KtrGRHuEMGAAAAEEYk5BHm173FkqTere0dt1ikrl0ll6dX12Yzj0nmcW+Zxs5vrFyohLH+BHuMpo/preljeuunXYV6ffUOvfndTu0sKNfStbu1dO1uWSzSYT3SNP7Qzhp/aLYO7pwceVunhfszEGloTwAAgIhjMQwjolefKiwsVGpqqgoKCpSSkhLucEJu3gc/a94HGzTtiO66/7fDwh0OPAzD0NrcQn2wNk8frNutH3YU+L3fLS1e4w/N1gmHZGt030zFxdrCFCkAAACA1mpqHkoPeYTZmGf2kPfPTgpzJKjJYrFoUNdUDeqaqj+dOEC5BWVati5PH/6Up0837tWO/DI9+/kWPfv5FiXYbTq6fyeNPzRbxx+creyUuHCHDwAAACAESMgjDAl5x5CTGq/fje6l343upbJKlz7duFfLfsrThz/t1u7CCt+8c0ka1j1VJxxiDm0f1DUl8oa2AwAAAFGKhDyCuNyGft1r7kHePyu5dRerqpIee8x/DvnMmebzxx4zH2fOlGLrWTjOe35j5UIl3PU3Q7zdphMHdtaJAzvLMAbrfzsLPb3nu/Xd9gLfzyMf/KwuKXE6eXAXnTo0RyN6pstqbcfJeQe6Bx0C7QkAABBxSMgjyJZ9Jap0uhUXa1W39PjWXcwwpPx8/4Tcu9xAfn51mcbOb6xcqIS7/hayWCwa3C1Vg7uZQ9vzisr10U95WrYuT59s3KtdheVa+NlmLfxsszqnOHTK4BxNGpKjI3q1w+S8g96Ddov2BAAAiDgk5BFkXW6RJOngLimytbfkDC2SnRyns0f21Nkje6q8yhza/vb3uVq61hzaXjM5P/Ow7vrtiG7qn93K0REAAAAA2gQJeQRZm2uu3D0wh4QsEsXF2jzbpHVWhdOlTzbs1ds/VCfnT3z8i574+BcN75Gm347orslDuyo1gWHNAAAAQHtFQh5BvD3kA3Mif3u3aOeI8U/OP/ppj15ZtV0frc/Tmm35WrMtX3e9tVYnD+qic0b20Oi+me1vSDsAAAAQ5UjII8janYWSpENJyKOKI8amkwd30cmDu2hPUYX+u2aHXlm1XT/tKtIb3+3UG9/tVM+MBJ09sod+c3h3dUllGzUAAACgPSAhjxC7C8u1q7BcVgsJeTTLSnbo0nF9dcnRffTjjkK9+PVWvbFmp7buL9UDS9broffX6/iDs3X2yB46/pBsxdqs4Q4ZAAAAiFok5BFizbZ8SdJBnZOV6AjCbbVYpKws/1XWvftfZ2VVl2ns/MbKhUq46w8zi8WiId1TNaT7EN166kC980OuFn29TV9t3q9lP+Vp2U956pTk0G9HdNfZI3uoT6fEUAQR1fcg6GhPAACAiGMxjMjeP6ewsFCpqakqKChQSkrk9hzPfe8nzV/+i84Z2UP3/WZouMNBO/XLnmK99M02vbpqu/YWV/qOj+qToXNG9tApg3MUb7eFMUIAAACg42tqHkpCHiHOeepzffHrft03dYjOGdUz3OGgnatyufXhT3la9PU2LV+fJ7fnvwLJcTE6eVAXnTiws8YN6KQEO4NoAAAAgOZqah7KX9sRoMLp0rdb8yVJR/ROD28w6BBibVZNHNRFEwd1UW5BmV5dtV2LvtmmbfvL9PKq7Xp51XbZY6wa3TdTo/tm6Mg+GRrSLU32GOacAwAAAMFCQh4B1mzNV4XTrU5JDvXLSgrORauqpKee8p9Dfvnl5vOnnjIfL79ciq1nn2vv+Y2VC5Vw19+B5KTG66oTBujK4/rry0379f7aXVq2Lk9b95dqxc97tOLnPZKkuFirDs1J0cCcFA3qmqqBXVN0UOek+nvRuQfBRXsCAABEHBLyCPD5r/skSaP7ZsgSrMWeDEPas8c/IffObtizp7pMY+c3Vi5Uwl1/B2S1WnRUv0wd1S9Tt582UBvzivXJxr36atN+fbVpv/aVVOrbrfm+0RheOalx6puVqL6dkszHrCT1y0pU13ibrNyD4OEzDQAAEHFIyCOAtwdzTL9OYY4EkcJisWhA52QN6Jysi8b2kWEY+nVvif63s1D/21mgtTsLtS63UHuLK5VbUK7cgnJ9unGf3zWSrS7duHqLUuNj9eM7a9W9c5p6ZiaqV0aCuqbFM/wdAAAAUY+EvIPbV1yhbz1bnh1/SFZ4g0HEslgs6peVpH5ZSTp9WFff8QMllfp1b7F+2VOiX/eU6Nc9xfp1b4m27CtReaVbe4srtLe4Qv/6dLOqbNVDrK0WqWtavHpmJCgnNV5ZyQ5lJTuU7XnMSnYoM9GulLhYWa1s8QUAAIDIRELewX388x4ZhnRoTopyUuPDHQ6iTHqiXSMSMzSiV4bfcafLre27C2SUfaqCsioVH9Vbm4uc2rq/RFv3l6q8yq3tB8q0/UBZg9e3WS1KT4hVRqLd/yfBfExPtCsz0aH0xFjfoyOGbdsAAADQMZCQd3Bvf58rSZpwaHaYIwGqxdis6t0pUeqUKEkaftpAyW6XJBmGoT1FFdqyv1Rb95Vqd1G59hRVKK+oQnuKKrTX87y4wimX29De4kq/PdMbk+SIUXpirDISHcpI8Dwm1vdoV0pcTPDWXgAAAACagYS8AztQUqmPPfPHTx/etZHSQPtgsViUnRKn7JQ4jeydUW+58iqX8kurtK+kQgdKvI+V2l9Sqf2lnscaPwdKq+RyGyqucKq4wqlt+xvuffeKsVqUXqPX3ftj9r5XP2Ym2dU5OU5pCbEk8AAAAAgKEvIO7L9rdsjpNnRoTor6ZycH9+IWi5SW5r/KujcJSUurLtPY+Y2VC5Vw149W34O4WJu6pNrUJTWuSeXdbkOF5VV1EvX9pZXaX1ydxB8oqdQ+z2NJpUtOt9ljv6eookn12G1WZSU71DnFoc4pccpOdig7Jc73vHNKnDqnOJQaH+TEnc80AABAxLEYRmTvn1NYWKjU1FQVFBQoJSUl3OEEjWEYmvDICm3MK9ZdZwzShUf1DndIQIdTXuXSgdJK7Suu1AFPwu59vq9G8m4er9CB0qomX9tiMYfPp8TFKskRo6S4GCXHxcgRY1WMzapYq8V8tFkVa7PIavH+mFvQWSyqfm2xyFLjudUiz+ua76vW+RY5bFYlOGxKdMQo0R6jBLv3ufkYH2tj0TwAAIAQaGoeSg95B7X85z3amFesBLtNZx7WLdzhAB1SXKxNOanxTV4QsbzK5ZvvnldYrt2F5corqtDuwgrlFZUrr7BCu4vKlV9aJcOQisqdKip3hvi3aJ0Eu00J9hglOczHxBqPifYYJTqqE/nqhD7GTPRrlPO+JskHAABoOhLyDsgwDP31gw2SpPOP7KnkuNhGzgAQDHGxNvXISFCPjIQGy5VXuVRYXqWicqeKPUl5cUWVCsudqnC65XS55XQZqnKbj06XW25DchuG3Ib5b9z73G0YMnzv1Xjf3XB5l9tQpcutkgqnSiqdKq1w+T26PWOjSitdKq10aW9xcNrIYpESYm1Kjouts51d9bZ2cb7ncbGsig8AAKIXCXkH9MZ3O7VmW77iYq267Ji+oamkqkpasMB/DvlFF5nPFywwHy+6SIqt58sA7/mNlQuVcNePqL4HcbE2xcXaFNSlHYLYnoZhqLzK7Zegm4m7S6Xex0pzcbzaiXxJjfdLK1xmmUrzPcOQDEMqqXSppNKlXYXljcaSGh/rm3ufneJQdrI5B7/mY3YKiTsAAIhMJOQdzN7iCt391jpJ0lXH91d2ctMWvGo2w5B27vRPyL3LDezcWV2msfMbKxcq4a4f3INgC2J7WiwWxdttirfbpKQgxCb/JL+kwqmCsirfYnl5vsfqLe7yiipU6XSroKxKBWVV2pDXcBd9SlyML2nvnBynLM9jds3F9ZLjzN8JAACggyAh70CqXG5d/eIa7S2u0EGdk3TpuBD1jgNAM9VM8jslORotbxiGCsuc2u2de++bj28m7TVfVzjdKix3qrC8uEmJe3aKf++6X297skMZSXYlO9h/HgAAhB8JeQdRXuXSNYvW6JONexUfa9Oj5x7GEE4AHZbFYlFqQqxSE2J1UOf6x/YbhqHCcqdnET2zl73mInre17UT942NJO6xNovSa+097/2puTJ+osNc8M58NBe0i4u1yR5jlY3F6wAAQCuRkHcAW/aV6NqXvtOqLQdkt1n19/MO0yFdImcLNwCoj8ViUWp8rFLjYzWgiYl7Xq0edu+q+OZjhcqqXKpyGb6h8y0VY7XIEWOVPcYqR4xNjlir7DarHLHma+9zu80sY4+p8bzmMc9rh99rW51zHLWvEWNVfKyNle0BAOjAOkRC/thjj+mBBx7Qrl27NGzYMP3tb3/TqFGjwh1WyO3IL9Ozn2/Wgk83q9LpVnJcjJ664Agd1S8z3KEBQLvS1MRdksoqXdpfWr3PfO3H4gqnisurVOJZtK64wpwXX1ThVKXT7buO023I6VnATmr6HvXB5l3ZPtER4/mp3rKu5r7zgXr7k+I8zz3nJXn2p2c4PwAAbaPdJ+SLFi3StddeqyeeeEJHHnmk5s2bp4kTJ2r9+vXKzs4Od3hBYxiGcgvK9dOuQv24o1Arft6j1VsP+LYmGts/U3+ZMkR9OiWGN1AA6ODi7TZ1s8erW1rT9p+vyelyq8LpVqXTfKxwuvyeV3ifV7lV6XKrosqlSpdZ3vfjqj6/vvf8ngc65nku+a9sr1b0+HtZLfIl7Ql2m2I9PfIxVotibVbF2qyKsXmfWxRjNd+zWi2yWiSb1SKLxSKbxeJ5Ltks3vctslklq8X73DzH954l8HVqDgCovaRh7TUOjRolAq1/6KuzRgwWi/e496fGa288Fk88NWK2ect7fqemXNtikYL1dYevfazVddg8cVks4osVAOgA2n1C/vDDD+uyyy7TRZ4tt5544gm9/fbb+te//qWbbropzNEFh2EYOmrOhwG3CBrbP1PTj+qtCQM7t/3/WBMSJKfTfB4T43+8qeeHU7jrB/cg2GjPsIuxWRVjsyqx8XXrQs7tNlThdHu2nvP25FdvT1e9LZ1TxRUuc8s6T49/cY3nJZ73ij1b17kNqajcqaJyZ7h/RbRSzS8WvIm61ep5bq3+0sRmtfi+VKl5zFZPWe8XD5KZ+JvPPI8WyeJ55XvPV6b624jq8hbf67rXslR/eVHzGr56Alzf+16tExstXyse1Shb5/fx+92q4/c+CVS+oWt5DwSKL9A1asfZ8O9T91rV5zXc9rWvpYDlG2ibWjfbUqtO3/XruVbtGOv7fUL113Eo9ocJ9qYzRgiiDMXGOKFoy5zUOI3snRGCK7c9i2G03/2IKisrlZCQoFdeeUVTpkzxHZ8+fbry8/P13//+t845FRUVqqio7iEoLCxUjx49VFBQoJSU9jvvevLfPtHa3EL1z0rSITnJGtk7Q8cdnKXu6fwBDgAIPbfbUFmVyy9RL65wyul2q8rlVpXLUJXLLafnscplyOk2e+vdhiG3Ibnchtxuz3PDkGEYcrkNz3PP+4ZZxuU5x+055nLLcx3zHG9573Vq/9kd6Dvq2odql/F+4RCoHu8x7+9hGJ4Ya8TlF2+t91xu1TjH8NXjq8NTrv3+1QUAHccpg7to/u9GhDuMBhUWFio1NbXRPLRd95Dv3btXLpdLnTt39jveuXNn/fTTTwHPmTNnju688862CC+onrxghDKT7HLEsHI6AKDtWa0W31zzyJkQFrmMml+CeBJ/t+dLAlfN197ntY673NU/Ts8xp6uB9zxftngf3UZ135z3SwZDRo3n/m8aNcsFOib/92pf1/u6oTprtk1TyjcYYyN1ek+oHXezY2xinar5Xmtj9CtX9z0Fun6AY7WvpYDxtOJeN1BnoBiDNZDUEqw+9yBcJnjTW4J0nSBFFIx4Du7S8HoxHUm7Tshb4uabb9a1117re+3tIW/vurZgLiMAAIhO5vxxsf0eAHRw7Toh79Spk2w2m3bv3u13fPfu3erSpUvAcxwOhxyOdjC5r6OrqpKef96cQ26xSDabdP755nvPP28+nn++FBvb8PmNlQuVcNcP7kGw0Z4AAAARp10n5Ha7XSNGjNCyZct8c8jdbreWLVumq666KrzBRTrDkDZvllwu87XNVj1WaPPm6jKNnd9YuVAJd/3gHgQb7QkAABBx2nVCLknXXnutpk+friOOOEKjRo3SvHnzVFJS4lt1HQAAAACAjqjdJ+Rnn3229uzZo9tvv127du3S8OHD9d5779VZ6A0AAAAAgI6k3SfkknTVVVcxRB0AAAAAEFGs4Q4AAAAAAIBoREIOAAAAAEAYdIgh6wiT2FhzyzPvtmc1jzf1/HAKd/3gHgQb7QkAABBRLIYR2fvnFBYWKjU1VQUFBUpJSQl3OAAAAACACNfUPJQh6wAAAAAAhAEJOQAAAAAAYcAccgTmdEqLFkkul/naZpPOPtt8vmiR+Xj22VJMPR8h7/mNlQuVcNcP7kGw0Z4AAAARh7/oEJjbLW3Y4J+Qu93m8w0bqss0dn5j5UIl3PWDexBstCcAAEDEYcg6AAAAAABhQEIOAAAAAEAYkJADAAAAABAGJOQAAAAAAIQBCTkAAAAAAGEQ8ausG4YhSSosLAxzJB1MZaVUUeG/yrq3DSsqzMfCQslub/j8xsqFSrjrB/cg2GhPAACADsObf3rz0fpYjMZKdHDbt29Xjx49wh0GAAAAACDKbNu2Td27d6/3/YhPyN1ut3bu3Knk5GRZLJZwh9MuFBYWqkePHtq2bZtSUlLCHQ6aiPvWMXHfOibuW8fEfeuYuG8dE/etY+K+tR3DMFRUVKSuXbvKaq1/pnjED1m3Wq0NfiMRzVJSUviH2AFx3zom7lvHxH3rmLhvHRP3rWPivnVM3Le2kZqa2mgZFnUDAAAAACAMSMgBAAAAAAgDEvIo5HA4NHv2bDkcjnCHgmbgvnVM3LeOifvWMXHfOibuW8fEfeuYuG/tT8Qv6gYAAAAAQHtEDzkAAAAAAGFAQg4AAAAAQBiQkAMAAAAAEAYk5AAAAAAAhAEJeYR67LHH1Lt3b8XFxenII4/UV1991WD5l19+WYcccoji4uI0ZMgQvfPOO20UKWpqzn17+umnNW7cOKWnpys9PV0nnnhio/cZodHcf29eL774oiwWi6ZMmRLaABFQc+9bfn6+Zs6cqZycHDkcDh100EH8tzIMmnvf5s2bp4MPPljx8fHq0aOHrrnmGpWXl7dRtFixYoUmT56srl27ymKxaPHixY2es3z5ch1++OFyOBzq37+/Fi5cGPI44a+59+21117ThAkTlJWVpZSUFB111FFasmRJ2wQLn5b8e/P69NNPFRMTo+HDh4csPgRGQh6BFi1apGuvvVazZ8/W6tWrNWzYME2cOFF5eXkBy3/22Wc699xzdckll+jbb7/VlClTNGXKFP34449tHHl0a+59W758uc4991x99NFH+vzzz9WjRw+ddNJJ2rFjRxtHHt2ae9+8Nm/erOuuu07jxo1ro0hRU3PvW2VlpSZMmKDNmzfrlVde0fr16/X000+rW7dubRx5dGvufXvhhRd00003afbs2Vq3bp3++c9/atGiRZo1a1YbRx69SkpKNGzYMD322GNNKr9p0yadeuqpOv7447VmzRpdffXVuvTSS0nu2lhz79uKFSs0YcIEvfPOO1q1apWOP/54TZ48Wd9++22II0VNzb1vXvn5+brwwgs1fvz4EEWGBhmIOKNGjTJmzpzpe+1yuYyuXbsac+bMCVh+2rRpxqmnnup37MgjjzSuuOKKkMYJf829b7U5nU4jOTnZeOaZZ0IVIgJoyX1zOp3GmDFjjH/84x/G9OnTjTPOOKMNIkVNzb1v8+fPN/r27WtUVla2VYgIoLn3bebMmcYJJ5zgd+zaa681xo4dG9I4EZgk4/XXX2+wzA033GAMGjTI79jZZ59tTJw4MYSRoSFNuW+BDBw40LjzzjuDHxCapDn37ez/b+/eg6Iq3ziAf5F1AZEVbyw4mSiKGmoBeUEdUSQhHVKK0DRCksCUMRtTMGjQ+OmQMdTkoGY1K13AUKlxEglQmQypvCxooyAXRRsBx5QCsbg9vz8cd1pRkzX2oHw/M2eG8573nPOcfWZn32ffs4f58yUuLk7i4+PlySef7NS4qD3OkD9impqacPz4cfj6+hraevToAV9fXxQWFt5xn8LCQqP+AODn53fX/vTfMyVvt2tsbERzczP69evXWWHSbUzN27vvvgsHBwcsWbLEHGHSbUzJ2969e+Hl5YXly5dDq9VizJgx2LhxI1pbW80VdrdnSt4mT56M48ePG25rr6ysRFZWFmbPnm2WmKnjOCZ5NLS1taG+vp5jkoeATqdDZWUl4uPjlQ6l21IpHQD9t65cuYLW1lZotVqjdq1Wi5KSkjvuU1NTc8f+NTU1nRYnGTMlb7eLjo7GoEGD2g1kqPOYkrcff/wRn332GYqKiswQId2JKXmrrKzEwYMHsWjRImRlZaG8vBzLli1Dc3MzBzFmYkreFi5ciCtXrmDq1KkQEbS0tGDp0qW8Zb0Lu9uY5M8//8SNGzdgY2OjUGTUEUlJSWhoaEBwcLDSodA9lJWVISYmBocPH4ZKxbJQKZwhJ3oEJCYmYufOnfjmm29gbW2tdDh0F/X19QgJCcEnn3yCAQMGKB0OdUBbWxscHBywfft2eHp6Yv78+YiNjcW2bduUDo3uIT8/Hxs3bsSWLVtw4sQJZGZmYt++fUhISFA6NKJHVlpaGtavX4+MjAw4ODgoHQ7dRWtrKxYuXIj169fD1dVV6XC6NX4V8ogZMGAALC0tUVtba9ReW1sLR0fHO+7j6OjYof703zMlb7ckJSUhMTEReXl5GDduXGeGSbfpaN4qKipw/vx5BAQEGNra2toAACqVCqWlpXBxcencoMmk95uTkxN69uwJS0tLQ9vo0aNRU1ODpqYmqNXqTo2ZTMvbO++8g5CQEISHhwMAxo4di+vXryMiIgKxsbHo0YPzEl3N3cYkGo2Gs+MPgZ07dyI8PBy7du3iHXtdXH19PY4dOwa9Xo+oqCgAN8ckIgKVSoWcnBz4+PgoHGX3wE+iR4xarYanpycOHDhgaGtra8OBAwfg5eV1x328vLyM+gNAbm7uXfvTf8+UvAHApk2bkJCQgOzsbDz99NPmCJX+oaN5GzVqFE6dOoWioiLD8txzzxmeJjx48GBzht9tmfJ+mzJlCsrLyw1foADA2bNn4eTkxGLcTEzJW2NjY7ui+9aXKiLSecGSyTgmeXilp6cjLCwM6enpmDNnjtLh0L/QaDTtxiRLly7FyJEjUVRUhIkTJyodYveh8EPlqBPs3LlTrKysZMeOHXL69GmJiIgQe3t7qampERGRkJAQiYmJMfQvKCgQlUolSUlJcubMGYmPj5eePXvKqVOnlLqEbqmjeUtMTBS1Wi27d++W6upqw1JfX6/UJXRLHc3b7fiUdWV0NG8XLlwQOzs7iYqKktLSUvnuu+/EwcFB/ve//yl1Cd1SR/MWHx8vdnZ2kp6eLpWVlZKTkyMuLi4SHBys1CV0O/X19aLX60Wv1wsASU5OFr1eL1VVVSIiEhMTIyEhIYb+lZWV0qtXL1m9erWcOXNGUlJSxNLSUrKzs5W6hG6po3n76quvRKVSSUpKitGYpK6uTqlL6JY6mrfb8SnrymBB/ojavHmzPP7446JWq2XChAny008/GbZ5e3tLaGioUf+MjAxxdXUVtVotbm5usm/fPjNHTCIdy9uQIUMEQLslPj7e/IF3cx19v/0TC3LldDRvR44ckYkTJ4qVlZUMGzZMNmzYIC0tLWaOmjqSt+bmZlm3bp24uLiItbW1DB48WJYtWybXrl0zf+Dd1KFDh+74WXUrT6GhoeLt7d1un6eeekrUarUMGzZMdDqd2ePu7jqaN29v73v2J/Mw5f32TyzIlWEhwnu2iIiIiIiIiMyNvyEnIiIiIiIiUgALciIiIiIiIiIFsCAnIiIiIiIiUgALciIiIiIiIiIFsCAnIiIiIiIiUgALciIiIiIiIiIFsCAnIiIiIiIiUgALciIiIiIiIiIFsCAnIiIiIiIiUgALciIiok62ePFiWFhYtFv8/f2VDs1k06dPx8qVK9u179ixA/b29maPh4iI6GGkUjoAIiKi7sDf3x86nc6ozcrKqlPP2dTUBLVa3annICIiItNxhpyIiMgMrKys4OjoaLT07dvXsN3CwgKffvopAgMD0atXL4wYMQJ79+41Osavv/6KZ599Fr1794ZWq0VISAiuXLli2D59+nRERUVh5cqVGDBgAPz8/AAAe/fuxYgRI2BtbY0ZM2YgNTUVFhYWqKurw/Xr16HRaLB7926jc3377bewtbVFfX39A113fn4+JkyYAFtbW9jb22PKlCmoqqoCAFRUVGDu3LnQarXo3bs3xo8fj7y8PKP9q6urMWfOHNjY2GDo0KFIS0uDs7MzPvzwQ0Ofuro6hIeHY+DAgdBoNPDx8UFxcfEDxU1ERGQOLMiJiIi6iPXr1yM4OBgnT57E7NmzsWjRIly9ehXAzaLTx8cH7u7uOHbsGLKzs1FbW4vg4GCjY6SmpkKtVqOgoADbtm3DuXPnEBQUhHnz5qG4uBiRkZGIjY019Le1tcWCBQvazd7rdDoEBQXBzs7O5OtpaWnBvHnz4O3tjZMnT6KwsBARERGwsLAAADQ0NGD27Nk4cOAA9Ho9/P39ERAQgAsXLhiO8corr+DSpUvIz8/Hnj17sH37dly+fNnoPC+++CIuX76M/fv34/jx4/Dw8MDMmTMNrx0REVGXJURERNSpQkNDxdLSUmxtbY2WDRs2GPoAkLi4OMN6Q0ODAJD9+/eLiEhCQoLMmjXL6LgXL14UAFJaWioiIt7e3uLu7m7UJzo6WsaMGWPUFhsbKwDk2rVrIiLy888/i6WlpVy6dElERGpra0WlUkl+fv5dr8nb21veeOONdu06nU769OkjIiK///67ALjncW7n5uYmmzdvFhGRM2fOCAA5evSoYXtZWZkAkA8++EBERA4fPiwajUb++usvo+O4uLjIxx9/fN/nJSIiUgJ/Q05ERGQGM2bMwNatW43a+vXrZ7Q+btw4w9+2trbQaDSG2eDi4mIcOnQIvXv3bnfsiooKuLq6AgA8PT2NtpWWlmL8+PFGbRMmTGi37ubmhtTUVMTExODLL7/EkCFDMG3atA5epbF+/fph8eLF8PPzwzPPPANfX18EBwfDyckJwM0Z8nXr1mHfvn2orq5GS0sLbty4YZghLy0thUqlgoeHh+GYw4cPN7rVv7i4GA0NDejfv7/RuW/cuIGKiooHip+IiKizsSAnIiIyA1tbWwwfPvyefXr27Gm0bmFhgba2NgA3i9eAgAC899577fa7VeDeOo8pwsPDkZKSgpiYGOh0OoSFhRluLb8TjUaDP/74o117XV0d+vTpY1jX6XRYsWIFsrOz8fXXXyMuLg65ubmYNGkS3nrrLeTm5iIpKQnDhw+HjY0NgoKC0NTUdN9xNzQ0wMnJCfn5+e228WnvRETU1bEgJyIiegh4eHhgz549cHZ2hkp1/x/fI0eORFZWllHb0aNH2/V7+eWXsWbNGnz00Uc4ffo0QkND//W4OTk57dpPnDhhmK2/xd3dHe7u7li7di28vLyQlpaGSZMmoaCgAIsXL0ZgYCCAm8X1+fPnjc7R0tICvV5vmPkvLy/HtWvXDH08PDxQU1MDlUoFZ2fne8ZMRETU1fChbkRERGbw999/o6amxmj55xPS/83y5ctx9epVvPTSSzh69CgqKirw/fffIywsDK2trXfdLzIyEiUlJYiOjsbZs2eRkZGBHTt2AIDRDHjfvn3x/PPPY/Xq1Zg1axYee+yxe8bz+uuv4+zZs1ixYgVOnjyJ0tJSJCcnIz09HatWrQIAnDt3DmvXrkVhYSGqqqqQk5ODsrIyjB49GgAwYsQIZGZmoqioCMXFxVi4cKHhjgAAGDVqFHx9fREREYFffvkFer0eERERsLGxMcTu6+sLLy8vzJs3Dzk5OTh//jyOHDmC2NhYHDt27L5fXyIiIiWwICciIjKD7OxsODk5GS1Tp0697/0HDRqEgoICtLa2YtasWRg7dixWrlwJe3t79Ohx94/zoUOHYvfu3cjMzMS4ceOwdetWw1PWb/8/6EuWLEFTUxNeffXVf41n2LBh+OGHH1BSUgJfX19MnDgRGRkZ2LVrF/z9/QEAvXr1QklJCV544QW4uroiIiICy5cvR2RkJAAgOTkZffv2xeTJkxEQEAA/Pz+j34sDwOeffw6tVotp06YhMDAQr732Guzs7GBtbQ3g5pcKWVlZmDZtGsLCwuDq6ooFCxagqqoKWq32vl9fIiIiJViIiCgdBBEREZnPhg0bsG3bNly8eNGo/YsvvsCbb76JS5cuQa1WKxTdvf32228YPHgw8vLyMHPmTKXDISIieiD8DTkREdEjbsuWLRg/fjz69++PgoICvP/++4iKijJsb2xsRHV1NRITExEZGdmlivGDBw+ioaEBY8eORXV1NdasWQNnZ+cHfgI8ERFRV8Bb1omIiB5xZWVlmDt3Lp544gkkJCRg1apVWLdunWH7pk2bMGrUKDg6OmLt2rXKBXoHzc3NePvtt+Hm5obAwEAMHDgQ+fn57Z5IT0RE9DDiLetERERERERECuAMOREREREREZECWJATERERERERKYAFOREREREREZECWJATERERERERKYAFOREREREREZECWJATERERERERKYAFOREREREREZECWJATERERERERKeD/eAWTK6E48d0AAAAASUVORK5CYII=", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Percentile analysis:\n", - "5th percentile: 0.018\n", - "10th percentile: 0.021\n", - "25th percentile: 0.028\n", - "50th percentile: 0.048\n", - "75th percentile: 0.106\n", - "90th percentile: 0.282\n", - "95th percentile: 0.434\n" - ] - } - ], - "source": [ - "# 1. KDE with Percentile Analysis\n", - "plt.figure(figsize=(12, 6))\n", - "kde = stats.gaussian_kde(data[\"usage\"])\n", - "x_range = np.linspace(data[\"usage\"].min(), data[\"usage\"].max(), 1000)\n", - "plt.plot(x_range, kde(x_range), label=\"KDE\")\n", - "percentiles = [5, 10, 25, 50, 75, 90, 95]\n", - "for p in percentiles:\n", - " value = np.percentile(data[\"usage\"], p)\n", - " plt.axvline(value, color=\"r\", linestyle=\"--\", alpha=0.5)\n", - " plt.text(value, plt.ylim()[1], f\"{p}th\", rotation=90, va=\"top\")\n", - "plt.title(\"Energy Usage Distribution with Percentiles\")\n", - "plt.xlabel(\"Energy Usage\")\n", - "plt.ylabel(\"Density\")\n", - "plt.legend()\n", - "plt.show()\n", - "\n", - "print(\"Percentile analysis:\")\n", - "for p in percentiles:\n", - " print(f\"{p}th percentile: {np.percentile(data['usage'], p):.3f}\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 2. PELT Change Point Detection\n", - "model = Pelt(model=\"rbf\", jump=1).fit(data[\"usage\"].values)\n", - "change_points = model.predict(pen=10)\n", - "plt.figure(figsize=(12, 6))\n", - "plt.plot(data.index, data[\"usage\"])\n", - "for cp in change_points:\n", - " plt.axvline(data.index[cp], color=\"r\", linestyle=\"--\", alpha=0.5)\n", - "plt.title(\"Energy Usage with Change Points\")\n", - "plt.xlabel(\"Time\")\n", - "plt.ylabel(\"Energy Usage\")\n", - "plt.show()\n", - "\n", - "print(\"\\nDetected change points:\")\n", - "for cp in change_points:\n", - " print(f\"Change point at: {data.index[cp]}\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n", - "Dominant frequencies (cycles per hour):\n", - "0.0833 (period: 12.00 hours)\n", - "0.0417 (period: 24.00 hours)\n" - ] - } - ], - "source": [ - "# 3. Fast Fourier Transform (FFT)\n", - "fft_result = fft(data[\"usage\"].values)\n", - "frequencies = np.fft.fftfreq(len(data), d=0.25) # 0.25 hours between samples\n", - "plt.figure(figsize=(12, 6))\n", - "plt.plot(frequencies[: len(frequencies) // 2], np.abs(fft_result)[: len(frequencies) // 2])\n", - "plt.title(\"FFT of Energy Usage\")\n", - "plt.xlabel(\"Frequency (cycles per hour)\")\n", - "plt.ylabel(\"Magnitude\")\n", - "plt.xlim(0, 0.5) # Focus on lower frequencies\n", - "plt.show()\n", - "\n", - "print(\"\\nDominant frequencies (cycles per hour):\")\n", - "top_frequencies = frequencies[np.argsort(np.abs(fft_result))[-5:]]\n", - "for freq in top_frequencies:\n", - " if freq > 0:\n", - " print(f\"{freq:.4f} (period: {1/freq:.2f} hours)\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "# 4. Seasonal Decomposition\n", - "stl = STL(data[\"usage\"], period=96) # 96 quarters in a day\n", - "result = stl.fit()\n", - "fig = result.plot()\n", - "plt.suptitle(\"Seasonal Decomposition of Energy Usage\")\n", - "plt.tight_layout()\n", - "plt.show()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n", - "Vacation Period Analysis (2023-08-11 to 2023-08-28):\n", - "Average usage during vacation: 0.025\n", - "Average usage during regular periods: 0.109\n", - "Standby usage estimate (5th percentile):\n", - " During vacation: 0.011\n", - " During regular periods: 0.018\n" - ] - } - ], - "source": [ - "# 5. Vacation Period Analysis\n", - "def analyze_vacation_period(start_date, end_date):\n", - " vacation_data = data.loc[start_date:end_date]\n", - " regular_data = data.drop(vacation_data.index)\n", - "\n", - " print(f\"\\nVacation Period Analysis ({start_date} to {end_date}):\")\n", - " print(f\"Average usage during vacation: {vacation_data['usage'].mean():.3f}\")\n", - " print(f\"Average usage during regular periods: {regular_data['usage'].mean():.3f}\")\n", - " print(\"Standby usage estimate (5th percentile):\")\n", - " print(f\" During vacation: {np.percentile(vacation_data['usage'], 5):.3f}\")\n", - " print(f\" During regular periods: {np.percentile(regular_data['usage'], 5):.3f}\")\n", - "\n", - "\n", - "# Example usage:\n", - "analyze_vacation_period(\"2023-08-11\", \"2023-08-28\")" - ] } ], "metadata": { diff --git a/openenergyid/baseload/__init__.py b/openenergyid/baseload/__init__.py index cbf7ffb..c13131d 100644 --- a/openenergyid/baseload/__init__.py +++ b/openenergyid/baseload/__init__.py @@ -5,6 +5,7 @@ EnergySchema, load_data, calculate_base_load, + Granularity, ) __all__ = [ @@ -12,4 +13,5 @@ "EnergySchema", "load_data", "calculate_base_load", + "Granularity", ] diff --git a/openenergyid/baseload/main.py b/openenergyid/baseload/main.py index fb2dcf1..e5bd804 100644 --- a/openenergyid/baseload/main.py +++ b/openenergyid/baseload/main.py @@ -10,26 +10,27 @@ load_data(path: str) -> pl.LazyFrame: Loads and validates energy usage data from an NDJSON file. - calculate_base_load(lf: pl.LazyFrame, timeframe: TimeFrame = TimeFrame.DAILY) -> pl.DataFrame: - Calculates base load metrics from energy usage data aggregated by the specified timeframe. + calculate_base_load(lf: pl.LazyFrame, granularity: Granularity = Granularity.DAILY) -> pl.DataFrame: + Calculates base load metrics from energy usage data aggregated by the specified granularity. - main(file_path: str, timeframe: TimeFrame) -> pl.DataFrame: - Processes energy data and returns base load metrics for the specified timeframe. + main(file_path: str, granularity: Granularity) -> pl.DataFrame: + Processes energy data and returns base load metrics for the specified granularity. """ -from enum import Enum from typing import NamedTuple import polars as pl import pandera.polars as pa +from openenergyid.enums import Granularity ## VERY important to use pandera.polars instead of pandera to avoid pandas errors - -class TimeFrame(Enum): - HOURLY = "1h" - DAILY = "1d" - WEEKLY = "1w" - MONTHLY = "1mo" - YEARLY = "1y" +# Map Granularity to polars format +GRANULARITY_TO_POLARS = { + Granularity.PT15M: "15m", + Granularity.PT1H: "1h", + Granularity.P1D: "1d", + Granularity.P1M: "1mo", + Granularity.P1Y: "1y", +} class BaseLoadMetrics(NamedTuple): @@ -74,12 +75,15 @@ def load_data(path: str) -> pl.LazyFrame: return pl.LazyFrame(validated_df) -def calculate_base_load(lf: pl.LazyFrame, timeframe: TimeFrame = TimeFrame.DAILY) -> pl.DataFrame: - """Calculate base load metrics aggregated by specified timeframe""" +def calculate_base_load( + lf: pl.LazyFrame, granularity: Granularity = Granularity.P1D +) -> pl.DataFrame: + """Calculate base load metrics aggregated by specified granularity""" + polars_interval = GRANULARITY_TO_POLARS[granularity] return ( lf.filter(pl.col("total") >= 0) .sort("timestamp") - .group_by_dynamic("timestamp", every=timeframe.value) + .group_by_dynamic("timestamp", every=polars_interval) .agg( [ pl.col("total").sum().alias("total_usage"), @@ -98,12 +102,12 @@ def calculate_base_load(lf: pl.LazyFrame, timeframe: TimeFrame = TimeFrame.DAILY ) -def main(file_path: str, timeframe: TimeFrame) -> pl.DataFrame: - """Process energy data and return base load metrics for specified timeframe""" - return calculate_base_load(load_data(file_path), timeframe) +def main(file_path: str, granularity: Granularity) -> pl.DataFrame: + """Process energy data and return base load metrics for specified granularity""" + return calculate_base_load(load_data(file_path), granularity) # Example usage: if __name__ == "__main__": - results = main("data/energy_use.ndjson", TimeFrame.MONTHLY) + results = main("data/PP/energy_use_test1.ndjson", Granularity.P1M) print(results) diff --git a/performance_testing.ipynb b/performance_testing.ipynb new file mode 100644 index 0000000..fd9035e --- /dev/null +++ b/performance_testing.ipynb @@ -0,0 +1,164 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "import polars as pl\n", + "import json" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# General Performance Testing\n", + "\n", + "In here we test and try some general things for the codebase.\n", + "Fe. the polars efficiency, we try to document and reference relevant docs where needed to keep it peer reviewed." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Some speedtests regarding polars reading in of files/frames/\n", + "\n", + "references:\n", + "* [pandasVSpolars speed test, apr 2023](https://medium.com/cuenex/pandas-2-0-vs-polars-the-ultimate-battle-a378eb75d6d1)\n", + "* [input/output in polars](https://docs.pola.rs/api/python/stable/reference/io.html)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## test 1 reading in a newline delimited json to check efficiency\n" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "9.57 μs ± 218 ns per loop (mean ± std. dev. of 7 runs, 100,000 loops each)\n" + ] + } + ], + "source": [ + "%%timeit\n", + "energy_use_df = pl.scan_ndjson(\n", + " \"data/PP/energy_use_test1.ndjson\",\n", + " schema={\"timestamp\": pl.Datetime(time_zone=\"Europe/Brussels\"), \"total\": pl.Float64},\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "shape: (5, 2)
timestamptotal
datetime[μs, Europe/Brussels]f64
2023-01-01 00:00:00 CET0.025
2023-01-01 00:15:00 CET0.017
2023-01-01 00:30:00 CET0.023
2023-01-01 00:45:00 CET0.024
2023-01-01 01:00:00 CET0.023
" + ], + "text/plain": [ + "shape: (5, 2)\n", + "┌───────────────────────────────┬───────┐\n", + "│ timestamp ┆ total │\n", + "│ --- ┆ --- │\n", + "│ datetime[μs, Europe/Brussels] ┆ f64 │\n", + "╞═══════════════════════════════╪═══════╡\n", + "│ 2023-01-01 00:00:00 CET ┆ 0.025 │\n", + "│ 2023-01-01 00:15:00 CET ┆ 0.017 │\n", + "│ 2023-01-01 00:30:00 CET ┆ 0.023 │\n", + "│ 2023-01-01 00:45:00 CET ┆ 0.024 │\n", + "│ 2023-01-01 01:00:00 CET ┆ 0.023 │\n", + "└───────────────────────────────┴───────┘" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "energy_use_lf_1 = pl.scan_ndjson(\n", + " \"data/PP/energy_use_test1.ndjson\",\n", + " schema={\"timestamp\": pl.Datetime(time_zone=\"Europe/Brussels\"), \"total\": pl.Float64},\n", + ")\n", + "energy_use_lf_1.collect().head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Test 2, reading in the \"smaller version of the json\" and tranforming it into polars." + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "34.5 ms ± 1.31 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n" + ] + } + ], + "source": [ + "%%timeit\n", + "# Read the JSON file\n", + "with open(\"data/PP/energy_use.json\", \"r\") as file:\n", + " data = json.load(file)\n", + "\n", + "# Convert the data into a list of dictionaries\n", + "data_list = [{\"timestamp\": int(k), \"value\": v} for k, v in data.items()]\n", + "\n", + "# Create a DataFrame from the list\n", + "df = pl.DataFrame(\n", + " data_list, schema={\"timestamp\": pl.Datetime(time_zone=\"Europe/Brussels\"), \"value\": pl.Float64}\n", + ")" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "openenergyid-Nm3FK_LY-py3.11", + "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": "3.11.9" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/poetry.lock b/poetry.lock index fe83275..1694528 100644 --- a/poetry.lock +++ b/poetry.lock @@ -3481,6 +3481,21 @@ arro3-core = "*" narwhals = ">=1.13" packaging = "*" +[[package]] +name = "vl-convert-python" +version = "1.7.0" +description = "Convert Vega-Lite chart specifications to SVG, PNG, or Vega" +optional = false +python-versions = ">=3.7" +files = [ + {file = "vl_convert_python-1.7.0-cp37-abi3-macosx_10_12_x86_64.whl", hash = "sha256:90fba4356bd621bd31e72507a55e26dd13ebe79efa784715743116109afd0d47"}, + {file = "vl_convert_python-1.7.0-cp37-abi3-macosx_11_0_arm64.whl", hash = "sha256:51f99c58b1d0d74126455ece7d41972740cb4430b8dfdf7e0908270eed5be32d"}, + {file = "vl_convert_python-1.7.0-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:962100d7670b9d35f9bb9745cdf590412f62f57c134b4a142340ba93a4dbddba"}, + {file = "vl_convert_python-1.7.0-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b50c492b640abb89a54a71e2c26f0f2d2c1cedc42030cc55bcc202670334724"}, + {file = "vl_convert_python-1.7.0-cp37-abi3-win_amd64.whl", hash = "sha256:285bbadb1ce8a922c87f6e75a9544fe10a652d37bd4c1519fb93f90bab381588"}, + {file = "vl_convert_python-1.7.0.tar.gz", hash = "sha256:bc9e1f8ca0d8d3b3789c66e37cd6a8cf0a83406427d5143133346c2b5004485b"}, +] + [[package]] name = "wcwidth" version = "0.2.13" @@ -3618,4 +3633,4 @@ files = [ [metadata] lock-version = "2.0" python-versions = "^3.10" -content-hash = "f6f3d28d2fdc940738627c986006bda504c2523d1b2ea1fb337dcb32cac9f54d" +content-hash = "e9bf1db7eeb34bbd25cb8c99a0c01db53785d16eaf33e9958540ab204e1dea91" diff --git a/pyproject.toml b/pyproject.toml index 953b5da..6e2c237 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -69,3 +69,4 @@ energyid = "^0.0.17" snakeviz = "^2.2.0" plotly = "^5.24.1" vegafusion = {version = ">=1.5.0", extras = ["embed"]} +vl-convert-python = "^1.7.0" diff --git a/vis/KDE of EnUsage.png b/vis/KDE of EnUsage.png new file mode 100644 index 0000000..ad9a1a4 Binary files /dev/null and b/vis/KDE of EnUsage.png differ diff --git a/vis/heatmap.png b/vis/heatmap.png new file mode 100644 index 0000000..2f36618 Binary files /dev/null and b/vis/heatmap.png differ