Skip to content

GitLab

Commit f42429f6 authored by bailuo's avatar bailuo
Browse files

readme

parents
Hide whitespace changes
Inline Side-by-side
Showing with 4790 additions and 0 deletions
nbs/docs/tutorials/04_longhorizon.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"!pip install -Uqq nixtla datasetsforecast utilsforecast"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"from nixtla.utils import in_colab"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"IN_COLAB = in_colab()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" from nixtla.utils import colab_badge\n",
" from dotenv import load_dotenv"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Long-horizon forecasting"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Long-horizon forecasting refers to predictions far into the future, typically exceeding two seasonal periods. However, the exact definition of a 'long horizon' can vary based on the frequency of the data. For example, when dealing with hourly data, a forecast for three days into the future is considered long-horizon, as it covers 72 timestamps (calculated as 3 days × 24 hours/day). In the context of monthly data, a period exceeding two years would typically be classified as long-horizon forecasting. Similarly, for daily data, a forecast spanning more than two weeks falls into the long-horizon category.\n",
"\n",
"Of course, forecasting over a long horizon comes with its challenges. The longer the forecast horizon, the greater the uncertainty in the predictions. It is also possible to have unknown factors come into play in the long-term that were not expected at the time of forecasting.\n",
"\n",
"To tackle those challenges, use TimeGPT's specialized model for long-horizon forecasting by specifying `model='timegpt-1-long-horizon'` in your setup.\n",
"\n",
"For a detailed step-by-step guide, follow this tutorial on long-horizon forecasting."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/tutorials/04_longhorizon.ipynb)"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#| echo: false\n",
"if not IN_COLAB:\n",
" load_dotenv() \n",
" colab_badge('docs/tutorials/04_longhorizon')\n",
" import pandas as pd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Import packages\n",
"First, we install and import the required packages and initialize the Nixtla client."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from nixtla import NixtlaClient\n",
"from datasetsforecast.long_horizon import LongHorizon\n",
"from utilsforecast.losses import mae"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"nixtla_client = NixtlaClient(\n",
" # defaults to os.environ.get(\"NIXTLA_API_KEY\")\n",
" api_key = 'my_api_key_provided_by_nixtla'\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> 👍 Use an Azure AI endpoint\n",
"> \n",
"> To use an Azure AI endpoint, remember to set also the `base_url` argument:\n",
"> \n",
"> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" nixtla_client = NixtlaClient()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Load the data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Let's load the ETTh1 dataset. This is a widely used dataset to evaluate models on their long-horizon forecasting capabalities. \n",
"\n",
"The ETTh1 dataset monitors an electricity transformer from a region of a province of China including oil temperature and variants of load (such as high useful load and high useless load) from July 2016 to July 2018 at an hourly frequency.\n",
"\n",
"For this tutorial, let's only consider the oil temperature variation over time."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 314M/314M [00:14<00:00, 21.3MiB/s] \n",
"INFO:datasetsforecast.utils:Successfully downloaded datasets.zip, 314116557, bytes.\n",
"INFO:datasetsforecast.utils:Decompressing zip file...\n",
"INFO:datasetsforecast.utils:Successfully decompressed longhorizon\\datasets\\datasets.zip\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>ds</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>OT</td>\n",
" <td>2016-07-01 00:00:00</td>\n",
" <td>1.460552</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>OT</td>\n",
" <td>2016-07-01 01:00:00</td>\n",
" <td>1.161527</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>OT</td>\n",
" <td>2016-07-01 02:00:00</td>\n",
" <td>1.161527</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>OT</td>\n",
" <td>2016-07-01 03:00:00</td>\n",
" <td>0.862611</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>OT</td>\n",
" <td>2016-07-01 04:00:00</td>\n",
" <td>0.525227</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" unique_id ds y\n",
"0 OT 2016-07-01 00:00:00 1.460552\n",
"1 OT 2016-07-01 01:00:00 1.161527\n",
"2 OT 2016-07-01 02:00:00 1.161527\n",
"3 OT 2016-07-01 03:00:00 0.862611\n",
"4 OT 2016-07-01 04:00:00 0.525227"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#| eval: false\n",
"Y_df, *_ = LongHorizon.load(directory='./', group='ETTh1')\n",
"\n",
"Y_df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For this small experiment, let's set the horizon to 96 time steps (4 days into the future), and we will feed TimeGPT with a sequence of 42 days."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" Y_df = pd.read_parquet(\"../../assets/long_horizon_example_Y_df.parquet\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"test = Y_df[-96:] # 96 = 4 days x 24h/day\n",
"input_seq = Y_df[-1104:-96] # Gets a sequence of 1008 observations (1008 = 42 days * 24h/day)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Forecasting for long-horizon"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now, we are ready to use TimeGPT for long-horizon forecasting. Here, we need to set the `model` parameter to `\"timegpt-1-long-horizon\"`. This is the specialized model in TimeGPT that can handle such tasks."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Inferred freq: H\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n"
]
}
],
"source": [
"fcst_df = nixtla_client.forecast(\n",
" df=input_seq,\n",
" h=96,\n",
" level=[90],\n",
" finetune_steps=10,\n",
" finetune_loss='mae',\n",
" model='timegpt-1-long-horizon',\n",
" time_col='ds',\n",
" target_col='y'\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> 📘 Available models in Azure AI\n",
">\n",
"> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
">\n",
"> `nixtla_client.forecast(..., model=\"azureai\")`"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 2400x350 with 1 Axes>"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nixtla_client.plot(Y_df[-168:], fcst_df, models=['TimeGPT'], level=[90], time_col='ds', target_col='y')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Evaluation"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Let's now evaluate the performance of TimeGPT using the mean absolute error (MAE)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"test = test.copy()\n",
"\n",
"test.loc[:, 'TimeGPT'] = fcst_df['TimeGPT'].values"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" unique_id TimeGPT\n",
"0 OT 0.145393\n"
]
}
],
"source": [
"evaluation = mae(test, models=['TimeGPT'], id_col='unique_id', target_col='y')\n",
"\n",
"print(evaluation)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Here, TimeGPT achieves a MAE of 0.146."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
nbs/docs/tutorials/050_training.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "markdown",
"id": "6de758ee-a0d2-4b3f-acff-eed419dd17c5",
"metadata": {},
"source": [
"# Training\n",
"\n",
"This section offers tutorials related to training `TimeGPT` under specific conditions.\n",
"\n",
"### What You Will Learn\n",
"\n",
"1. **[Long Horizon Forecasting](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting)**\n",
"\n",
" - Discover how make predictions beyond two seasonal periods or even further into the future, using `TimeGPT`'s specialized model for long horizon forecasting.\n",
"\n",
"2. **[Multiple Series Forecasting](https://docs.nixtla.io/docs/tutorials-multiple_series_forecasting)**\n",
"\n",
" - Learn how to use `TimeGPT` to forecast multiple time series simultaneously."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
nbs/docs/tutorials/05_multiple_series.ipynb 0 → 100644
View file @ f42429f6
This source diff could not be displayed because it is too large. You can view the blob instead.
nbs/docs/tutorials/061_reusing_finetuned_models.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "27371399-17ac-4fcf-8e2d-19091b32cdf7",
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"!pip install -Uqq nixtla"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e428575b-700a-49a6-a0a9-6fa884119d86",
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"from nixtla.utils import in_colab"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fba11152-1fbb-43b5-b6c7-ccb5ff688ce2",
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"IN_COLAB = in_colab()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e0438f77-6a7e-400d-8739-09c9e347dcac",
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" from nixtla.utils import colab_badge\n",
" from dotenv import load_dotenv"
]
},
{
"cell_type": "markdown",
"id": "d4bcec3f-9ffe-41e0-a38b-92e77e460154",
"metadata": {},
"source": [
"# Re-using fine-tuned models\n",
"\n",
"Save and re-use fine-tuned models across all of our endpoints."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "56e9125c-53b3-41e4-bace-e920fb827c06",
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/tutorials/061_reusing_finetuned_models.ipynb.ipynb)"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#| echo: false\n",
"if not IN_COLAB:\n",
" load_dotenv() \n",
" colab_badge('docs/tutorials/061_reusing_finetuned_models')"
]
},
{
"cell_type": "markdown",
"id": "c7eb9fc0-4541-4c1e-8ffe-442d115fd638",
"metadata": {},
"source": [
"## 1. Import packages\n",
"First, we import the required packages and initialize the Nixtla client"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "89c80a4a-645d-43f9-9454-415a98685105",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from nixtla import NixtlaClient\n",
"from utilsforecast.losses import rmse\n",
"from utilsforecast.evaluation import evaluate"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "73d7516f-2a78-4be1-972e-41cb70800bcd",
"metadata": {},
"outputs": [],
"source": [
"nixtla_client = NixtlaClient(\n",
" # defaults to os.environ[\"NIXTLA_API_KEY\"]\n",
" api_key = 'my_api_key_provided_by_nixtla'\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a60ca743-7d68-4d4b-af72-10f63dbf5b26",
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" nixtla_client = NixtlaClient()"
]
},
{
"cell_type": "markdown",
"id": "83ca8dec-ca2a-4e9f-8983-886208423769",
"metadata": {},
"source": [
"## 2. Load data"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "eb5ef6b1-4756-4f79-8609-12f051503431",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>ds</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>H1</td>\n",
" <td>1</td>\n",
" <td>605.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>H1</td>\n",
" <td>2</td>\n",
" <td>586.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>H1</td>\n",
" <td>3</td>\n",
" <td>586.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>H1</td>\n",
" <td>4</td>\n",
" <td>559.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>H1</td>\n",
" <td>5</td>\n",
" <td>511.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" unique_id ds y\n",
"0 H1 1 605.0\n",
"1 H1 2 586.0\n",
"2 H1 3 586.0\n",
"3 H1 4 559.0\n",
"4 H1 5 511.0"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_parquet('https://datasets-nixtla.s3.amazonaws.com/m4-hourly.parquet')\n",
"\n",
"h = 48\n",
"valid = df.groupby('unique_id', observed=True).tail(h)\n",
"train = df.drop(valid.index)\n",
"train.head()"
]
},
{
"cell_type": "markdown",
"id": "f7b61f18-64a3-4b7f-8f86-76a78d6a0c0c",
"metadata": {},
"source": [
"## 3. Zero-shot forecast\n",
"\n",
"We can try forecasting without any finetuning to see how well TimeGPT does."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3e60cbbe-2710-4a7b-a453-27e52bf8b32b",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Querying model metadata...\n",
"WARNING:nixtla.nixtla_client:The specified horizon \"h\" exceeds the model horizon, this may lead to less accurate forecasts. Please consider using a smaller horizon.\n",
"INFO:nixtla.nixtla_client:Restricting input...\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>metric</th>\n",
" <th>TimeGPT</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>rmse</td>\n",
" <td>1504.474342</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" metric TimeGPT\n",
"0 rmse 1504.474342"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fcst_kwargs = {'df': train, 'freq': 1, 'model': 'timegpt-1-long-horizon'}\n",
"fcst = nixtla_client.forecast(h=h, **fcst_kwargs)\n",
"zero_shot_eval = evaluate(fcst.merge(valid), metrics=[rmse], agg_fn='mean')\n",
"zero_shot_eval"
]
},
{
"cell_type": "markdown",
"id": "f966407c-9c7d-4bce-8d6c-31870e00e7b5",
"metadata": {},
"source": [
"## 4. Fine-tune\n",
"\n",
"We can now fine-tune TimeGPT a little and save our model for later use. We can define the ID that we want that model to have by providing it through `output_model_id`."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6ffd8395-c30c-4522-b597-349a9d3a4b2e",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Calling Fine-tune Endpoint...\n"
]
},
{
"data": {
"text/plain": [
"'my-first-finetuned-model'"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"first_model_id = 'my-first-finetuned-model'\n",
"nixtla_client.finetune(output_model_id=first_model_id, **fcst_kwargs)"
]
},
{
"cell_type": "markdown",
"id": "1198429a-5518-43a3-bd73-2fa5d1f48cc3",
"metadata": {},
"source": [
"We can now forecast using this fine-tuned model by providing its ID through the `finetuned_model_id` argument."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "eb996e6a-37e1-44ea-af8d-3b71cf6276ae",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"WARNING:nixtla.nixtla_client:The specified horizon \"h\" exceeds the model horizon, this may lead to less accurate forecasts. Please consider using a smaller horizon.\n",
"INFO:nixtla.nixtla_client:Restricting input...\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>metric</th>\n",
" <th>TimeGPT_zero_shot</th>\n",
" <th>TimeGPT_first_finetune</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>rmse</td>\n",
" <td>1504.474342</td>\n",
" <td>1472.024619</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" metric TimeGPT_zero_shot TimeGPT_first_finetune\n",
"0 rmse 1504.474342 1472.024619"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"first_finetune_fcst = nixtla_client.forecast(h=h, finetuned_model_id=first_model_id, **fcst_kwargs)\n",
"first_finetune_eval = evaluate(first_finetune_fcst.merge(valid), metrics=[rmse], agg_fn='mean')\n",
"zero_shot_eval.merge(first_finetune_eval, on=['metric'], suffixes=('_zero_shot', '_first_finetune'))"
]
},
{
"cell_type": "markdown",
"id": "fb763ee8-07c0-4a6b-85dd-deb6c8216ddd",
"metadata": {},
"source": [
"We can see the error was reduced."
]
},
{
"cell_type": "markdown",
"id": "4b97ad55-a82c-4dd2-878c-40e2e9bf8945",
"metadata": {},
"source": [
"## 5. Further fine-tune\n",
"\n",
"We can now take this model and fine-tune it a bit further by using the `NixtlaClient.finetune` method but providing our already fine-tuned model as `finetuned_model_id`, which will take that model and fine-tune it a bit more. We can also change the fine-tuning settings, like using `finetune_depth=3`, for example."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "99ede33c-379b-4569-8e1a-996abbe8576e",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Calling Fine-tune Endpoint...\n"
]
},
{
"data": {
"text/plain": [
"'468b13fb-4b26-447a-bd87-87a64b50d913'"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"second_model_id = nixtla_client.finetune(finetuned_model_id=first_model_id, finetune_depth=3, **fcst_kwargs)\n",
"second_model_id"
]
},
{
"cell_type": "markdown",
"id": "70f0cab5-7b01-4d2d-8afe-0a2317644eed",
"metadata": {},
"source": [
"Since we didn't provide `output_model_id` this time, it got assigned an UUID.\n",
"\n",
"We can now use this model to forecast."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4cfeed2e-0a39-4211-82d1-67d1f868b311",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"WARNING:nixtla.nixtla_client:The specified horizon \"h\" exceeds the model horizon, this may lead to less accurate forecasts. Please consider using a smaller horizon.\n",
"INFO:nixtla.nixtla_client:Restricting input...\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>metric</th>\n",
" <th>TimeGPT_first_finetune</th>\n",
" <th>TimeGPT_second_finetune</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>rmse</td>\n",
" <td>1472.024619</td>\n",
" <td>1435.365211</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" metric TimeGPT_first_finetune TimeGPT_second_finetune\n",
"0 rmse 1472.024619 1435.365211"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"second_finetune_fcst = nixtla_client.forecast(h=h, finetuned_model_id=second_model_id, **fcst_kwargs)\n",
"second_finetune_eval = evaluate(second_finetune_fcst.merge(valid), metrics=[rmse], agg_fn='mean')\n",
"first_finetune_eval.merge(second_finetune_eval, on=['metric'], suffixes=('_first_finetune', '_second_finetune'))"
]
},
{
"cell_type": "markdown",
"id": "a2bc7c72-47be-4cc5-b774-f75980e8d70b",
"metadata": {},
"source": [
"We can see the error was reduced a bit more."
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "611406fe-2379-4b92-bdd4-5f9a86438d91",
"metadata": {},
"source": [
"## 6. Listing fine-tuned models\n",
"\n",
"We can list our fine-tuned models with the `NixtlaClient.finetuned_models` method."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c9648bb4-74ad-4a94-8c8a-74625e9795d7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[FinetunedModel(id='468b13fb-4b26-447a-bd87-87a64b50d913', created_at=datetime.datetime(2024, 12, 30, 17, 57, 31, 241455, tzinfo=TzInfo(UTC)), created_by='user', base_model_id='my-first-finetuned-model', steps=10, depth=3, loss='default', model='timegpt-1-long-horizon', freq='MS'),\n",
" FinetunedModel(id='my-first-finetuned-model', created_at=datetime.datetime(2024, 12, 30, 17, 57, 16, 978907, tzinfo=TzInfo(UTC)), created_by='user', base_model_id='None', steps=10, depth=1, loss='default', model='timegpt-1-long-horizon', freq='MS')]"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"finetuned_models = nixtla_client.finetuned_models()\n",
"finetuned_models"
]
},
{
"cell_type": "markdown",
"id": "95e591c8-80b0-43f8-afed-dfa760597af8",
"metadata": {},
"source": [
"While that representation may be useful for programmatic use, in this exploratory setting it's nicer to see them as a dataframe, which we can get by providing `as_df=True`."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0cacc468-0aa3-42af-85d9-7c31bfd2a4f3",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>id</th>\n",
" <th>created_at</th>\n",
" <th>created_by</th>\n",
" <th>base_model_id</th>\n",
" <th>steps</th>\n",
" <th>depth</th>\n",
" <th>loss</th>\n",
" <th>model</th>\n",
" <th>freq</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>468b13fb-4b26-447a-bd87-87a64b50d913</td>\n",
" <td>2024-12-30 17:57:31.241455+00:00</td>\n",
" <td>user</td>\n",
" <td>my-first-finetuned-model</td>\n",
" <td>10</td>\n",
" <td>3</td>\n",
" <td>default</td>\n",
" <td>timegpt-1-long-horizon</td>\n",
" <td>MS</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>my-first-finetuned-model</td>\n",
" <td>2024-12-30 17:57:16.978907+00:00</td>\n",
" <td>user</td>\n",
" <td>None</td>\n",
" <td>10</td>\n",
" <td>1</td>\n",
" <td>default</td>\n",
" <td>timegpt-1-long-horizon</td>\n",
" <td>MS</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id created_at \\\n",
"0 468b13fb-4b26-447a-bd87-87a64b50d913 2024-12-30 17:57:31.241455+00:00 \n",
"1 my-first-finetuned-model 2024-12-30 17:57:16.978907+00:00 \n",
"\n",
" created_by base_model_id steps depth loss \\\n",
"0 user my-first-finetuned-model 10 3 default \n",
"1 user None 10 1 default \n",
"\n",
" model freq \n",
"0 timegpt-1-long-horizon MS \n",
"1 timegpt-1-long-horizon MS "
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nixtla_client.finetuned_models(as_df=True)"
]
},
{
"cell_type": "markdown",
"id": "9697c759-1b08-4192-a14f-5df1fdb03191",
"metadata": {},
"source": [
"We can seee that the `base_model_id` of our second model is our first model, along with other metadata."
]
},
{
"cell_type": "markdown",
"id": "eae29db5-de09-4954-9352-4f22eb0c3675",
"metadata": {},
"source": [
"## 7. Deleting fine-tuned models\n",
"\n",
"In order to keep things organized, and since there's a limit of 50 fine-tuned models, you can delete models that weren't so promising to make room for more experiments. For example, we can delete our first finetuned model. Note that even though it was used as the base for our second model, they're saved independently so removing it won't affect our second model, except for the dangling metadata."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7232bc3b-9096-4875-978a-430b7627688f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nixtla_client.delete_finetuned_model(first_model_id)"
]
},
{
"cell_type": "markdown",
"id": "0973b161-368f-4681-8447-c87537a46583",
"metadata": {},
"source": [
"We can verify that our first model model doesn't show up anymore in our available models."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1b80edea-8926-4a13-8fb8-ec9bbcf4d575",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>id</th>\n",
" <th>created_at</th>\n",
" <th>created_by</th>\n",
" <th>base_model_id</th>\n",
" <th>steps</th>\n",
" <th>depth</th>\n",
" <th>loss</th>\n",
" <th>model</th>\n",
" <th>freq</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>468b13fb-4b26-447a-bd87-87a64b50d913</td>\n",
" <td>2024-12-30 17:57:31.241455+00:00</td>\n",
" <td>user</td>\n",
" <td>my-first-finetuned-model</td>\n",
" <td>10</td>\n",
" <td>3</td>\n",
" <td>default</td>\n",
" <td>timegpt-1-long-horizon</td>\n",
" <td>MS</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id created_at \\\n",
"0 468b13fb-4b26-447a-bd87-87a64b50d913 2024-12-30 17:57:31.241455+00:00 \n",
"\n",
" created_by base_model_id steps depth loss \\\n",
"0 user my-first-finetuned-model 10 3 default \n",
"\n",
" model freq \n",
"0 timegpt-1-long-horizon MS "
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nixtla_client.finetuned_models(as_df=True)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
nbs/docs/tutorials/06_finetuning.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "02134a5e",
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"!pip install -Uqq nixtla"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c6d8f223",
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"from nixtla.utils import in_colab"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3c6c0333",
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"IN_COLAB = in_colab()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ce98fab5",
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" from nixtla.utils import colab_badge\n",
" from dotenv import load_dotenv"
]
},
{
"cell_type": "markdown",
"id": "da753996-54f8-4244-a34e-7316b0c01827",
"metadata": {},
"source": [
"# Fine-tuning"
]
},
{
"cell_type": "markdown",
"id": "75a62889-d81e-462e-b235-c1eba1096da9",
"metadata": {},
"source": [
"Fine-tuning is a powerful process for utilizing TimeGPT more effectively. Foundation models such as TimeGPT are pre-trained on vast amounts of data, capturing wide-ranging features and patterns. These models can then be specialized for specific contexts or domains. With fine-tuning, the model's parameters are refined to forecast a new task, allowing it to tailor its vast pre-existing knowledge towards the requirements of the new data. Fine-tuning thus serves as a crucial bridge, linking TimeGPT's broad capabilities to your tasks specificities.\n",
"\n",
"Concretely, the process of fine-tuning consists of performing a certain number of training iterations on your input data minimizing the forecasting error. The forecasts will then be produced with the updated model. To control the number of iterations, use the `finetune_steps` argument of the `forecast` method."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "448eaf77-0a40-4b5b-88a2-31de99f404bc",
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/tutorials/06_finetuning.ipynb)"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#| echo: false\n",
"if not IN_COLAB:\n",
" load_dotenv() \n",
" colab_badge('docs/tutorials/06_finetuning')"
]
},
{
"cell_type": "markdown",
"id": "10ec4f03",
"metadata": {},
"source": [
"## 1. Import packages\n",
"First, we import the required packages and initialize the Nixtla client"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "98942108-d427-42d6-81f8-fa0bb5859395",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from nixtla import NixtlaClient\n",
"from utilsforecast.losses import mae, mse\n",
"from utilsforecast.evaluation import evaluate"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "64178d1c-957e-4a04-ab64-fde332b1840c",
"metadata": {},
"outputs": [],
"source": [
"nixtla_client = NixtlaClient(\n",
" # defaults to os.environ.get(\"NIXTLA_API_KEY\")\n",
" api_key = 'my_api_key_provided_by_nixtla'\n",
")"
]
},
{
"cell_type": "markdown",
"id": "b57a38e6",
"metadata": {},
"source": [
"> 👍 Use an Azure AI endpoint\n",
"> \n",
"> To use an Azure AI endpoint, remember to set also the `base_url` argument:\n",
"> \n",
"> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5cd61549-0b00-4a42-a98e-239fa4fae5e5",
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" nixtla_client = NixtlaClient()"
]
},
{
"cell_type": "markdown",
"id": "8c2e5387",
"metadata": {},
"source": [
"## 2. Load data"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b78cc83e-7d34-4c37-906d-8c7ed1a977fb",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>timestamp</th>\n",
" <th>value</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1949-01-01</td>\n",
" <td>112</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1949-02-01</td>\n",
" <td>118</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1949-03-01</td>\n",
" <td>132</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1949-04-01</td>\n",
" <td>129</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1949-05-01</td>\n",
" <td>121</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" timestamp value\n",
"0 1949-01-01 112\n",
"1 1949-02-01 118\n",
"2 1949-03-01 132\n",
"3 1949-04-01 129\n",
"4 1949-05-01 121"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv('https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/air_passengers.csv')\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"id": "09be4766",
"metadata": {},
"source": [
"## 3. Fine-tuning"
]
},
{
"cell_type": "markdown",
"id": "7f5b9060",
"metadata": {},
"source": [
"Here, `finetune_steps=10` means the model will go through 10 iterations of training on your time series data."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a683abc7-190c-40a6-a4e8-41a4c64bd773",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Inferred freq: MS\n",
"INFO:nixtla.nixtla_client:Querying model metadata...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n"
]
}
],
"source": [
"timegpt_fcst_finetune_df = nixtla_client.forecast(\n",
" df=df, h=12, finetune_steps=10,\n",
" time_col='timestamp', target_col='value',\n",
")"
]
},
{
"cell_type": "markdown",
"id": "ac469746",
"metadata": {},
"source": [
"> 📘 Available models in Azure AI\n",
">\n",
"> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
">\n",
"> `nixtla_client.forecast(..., model=\"azureai\")`\n",
"> \n",
"> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
"> \n",
"> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "545ffdac-f166-417b-993f-78f51b0db6a1",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABtYAAAFpCAYAAAAIvRx5AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8fJSN1AAAACXBIWXMAAA9hAAAPYQGoP6dpAADXn0lEQVR4nOzdd3jTZffH8XeS7t0yWsosG9qyl+ytIqIgguJCcE9UHhUn+vPB8ThwTwQUEVwgiMreW3bZo1BGS6F07zbf3x+h1cpqadKU9vO6rlza5P7e90kLpc3JOcdkGIaBiIiIiIiIiIiIiIiIiFyU2dkBiIiIiIiIiIiIiIiIiFwJlFgTERERERERERERERERKQYl1kRERERERERERERERESKQYk1ERERERERERERERERkWJQYk1ERERERERERERERESkGJRYExERERERERERERERESkGJdZEREREREREREREREREikGJNREREREREREREREREZFiUGJNREREREREREREREREpBiUWBMREREREbuYMmUKJpOJw4cPOzuUYjOZTIwfP/6S6+z53CZMmMDs2bNLvc/FfPjhhzRt2hR3d3fCwsJ45ZVXyM3NdeiZIiIiIiIilYESayIiIiIiYhfXXXcda9eupUaNGs4OpdjWrl3LPffcU6ZnOjqx9t///pfHH3+cIUOGMH/+fB566CEmTJjAww8/7LAzRUREREREKgsXZwcgIiIiIiIVQ7Vq1ahWrZqzwyiRTp06OTsEu0pISOC1117j3nvvZcKECQD07NmT3NxcXnjhBcaMGUPz5s2dHKWIiIiIiMiVSxVrIiIiIiKV1MiRI6lXr945948fPx6TyVT4sclk4pFHHuHbb7+lWbNmeHl50bJlS3777bci152vXaJhGLz11lvUrVsXDw8P2rRpwx9//EHPnj3p2bPnRa8FWLZsGSaTiWXLlhW5f9GiRfTp0wc/Pz+8vLzo0qULixcvLvHn4HytINetW0eXLl3w8PAgNDSUcePG2a2NoslkIj09nalTp2IymTCZTIWfh4yMDMaOHUtYWBgeHh4EBQXRrl07vv/++2Lv/+eff5KVlcXdd99d5P67774bwzAc3oJSRERERESkolPFmoiIiIiIXNK8efPYuHEjr776Kj4+Prz11lsMHjyYvXv3Ur9+/Qte98orr/DKK68wevRohg4dytGjR7n33nvJz8+nSZMmlxXLtGnTuPPOO7nhhhuYOnUqrq6ufP7551x99dXMnz+fPn36XO7TZNeuXfTp04d69eoxZcoUvLy8+OSTT5g+ffo5a61WK1ar9ZJ7mkwmLBYLYGs92bt3b3r16sWLL74IgJ+fHwBPPvkk3377La+99hqtW7cmPT2dqKgoEhISih1/VFQUAJGRkUXur1GjBlWrVi18XERERERERC6PEmsiIiIiInJJmZmZLFq0CF9fXwDatGlDaGgoP/zwA88+++x5r0lKSuLNN99k8ODBfPXVV4X3h4eH06VLl8tKrGVkZPD4448zcOBAZs2aVXj/gAEDaNOmDc899xzr168v8b4FXn31VQzDYMmSJQQHBwO22XERERHnrB01ahRTp0695J49evQorLjr1KkTZrOZatWqndOGcvXq1fTv358nnnii8L7rrruuRPEnJCTg7u6Ot7f3OY8FBQWVKEknIiIiIiIi51JiTURERERELqlXr16FSTWA4OBgqlevzpEjRy54zdq1a8nKyuK2224rcn/nzp2pW7fuZcWxZs0azpw5w1133UVeXl6Rx6655hreeust0tPTz5tYKo6lS5fSp0+fwqQagMViYfjw4bzyyitF1o4fP55HHnnkknv+8/N2MR06dOC7777j2Wef5ZprrqFjx454enqW7AlAkTaeJXlMRERERERELk2JNRERERERuaQqVaqcc5+7uzuZmZkXvKagOiokJOScx853X3GcPHkSgKFDh15wzZkzZy47sZaQkFDseOvUqUOtWrUuuWdxk1kffPABtWrVYubMmbz55pt4eHhw9dVX87///Y9GjRoVa48qVaqQlZVFRkYGXl5eRR47c+YMbdu2LdY+IiIiIiIicn5mZwcgIiIiIiLO4eHhQXZ29jn3nz592i77FyTj4uLiznns3/d5eHgAnBPPv2OpWrUqAB9++CEbN2487+2f1WaXE3Nx4gVbK0hXV9dL3oo7883b25tXXnmFPXv2EBcXx6effsq6deu4/vrrix1/wWy1HTt2nBP/6dOnz9vSUkRERERERIpPFWsiIiIiIpVUvXr1iI+P5+TJk4XJqJycHObPn2+X/Tt16oSHhwffffcdN910U+H9a9as4ciRI9SrV69ILADbt28vMnttzpw5Rfbs0qULAQEB7Nq1q1htGEuqV69ezJkzp8jnJD8/n5kzZ56z9nJbQV6q0g9srTZHjhzJtm3bmDhx4nkr0M7nmmuuwcPDgylTptCxY8fC+6dMmYLJZOLGG2+85B4iIiIiIiJyYUqsiYiIiIhUUsOHD+ell17illtu4T//+Q9ZWVl88MEH5Ofn22X/wMBAxo4dy2uvvcY999zDzTffzNGjRxk/fvw5rRXbt29PkyZNGDt2LHl5eQQGBjJr1ixWrVpVZJ2Pjw8ffvghd911F2fOnGHo0KFUr16dU6dOsW3bNk6dOsWnn3562TG/8MILzJkzh969e/PSSy/h5eXFxx9/THp6+jlr69WrVyQ5WFyRkZEsW7aMuXPnUqNGDXx9fWnSpAkdO3Zk4MCBtGjRgsDAQHbv3s23337LVVddVaykGkBQUBAvvPACL774IkFBQfTv35+NGzcyfvx47rnnHpo3b17ieEVERERERORvagUpIiIiIlJJhYWF8euvv5KUlMTQoUP5z3/+w80338ydd95ptzNeffVVXn/9dRYsWMCgQYP48MMP+eyzz4pUpQFYLBbmzp1L06ZNeeCBB7jzzjtxd3fno48+OmfP22+/naVLl5KWlsb9999P3759efzxx9m8eXOx2y5eSEREBIsWLcLPz4+77rqL++67jxYtWvDiiy+Wat9/ev/992nUqBG33HIL7du35/777wegd+/ezJkzh7vvvpv+/fvz1ltvceeddzJ37twS7f/8888zceJEfvrpJ/r378+HH37Is88+y8cff2y35yAiIiIiIlJZmQzDMJwdhIiIiIiIVC49e/YEYNmyZU6NQ0RERERExN4MwyAvL89u3UDE8SwWCy4uLphMpkuuVStIERERERERERERERERO8jJySE2NpaMjAxnhyIl5OXlRY0aNXBzc7voOiXWRERERESkwsnLy7vo42azGbP5yumMbxjGJd/tarFYivXuShERERERcQyr1Up0dDQWi4XQ0FDc3Nz0M/oVwDAMcnJyOHXqFNHR0TRq1Oiivy+qFaSIiIiIiFQohw8fJiws7KJrXn75ZcaPH182AdnBsmXL6NWr10XXTJ48mZEjR5ZNQCIiIiIico6srCyio6OpW7cuXl5ezg5HSigjI4MjR44QFhaGh4fHBdepYk1ERERERCqU0NBQNm7ceMk1V5K2bdte8jldKpkoIiIiIiJl40rqjiF/K+7XTYk1ERERERGpUNzc3GjXrp2zw7ArX1/fCvecRERERERErkRKm4qIiIiIiIiIiIiIiIgUgyrWsA0UPHHiBL6+vhokKCIiIiIiIiIiIiJSQRiGQWpqKqGhoWrR6ED16tVjzJgxjBkzxtmhOJwSa8CJEyeoXbu2s8MQEREREREREREREREHOHr0KLVq1XJ2GFIBKLGGbV4B2P5i+fn5OTkaERERERERERERERGxh5SUFGrXrl2YBxApLSXWoLD9o5+fnxJrIiIiIiIiIiIiIiIVjDPGQBmGQVZWbpmfC+Dh4Vrs5/z555/z6quvcvTo0SLtMgcNGkRgYCAvvfQSTz75JOvWrSM9PZ1mzZrx+uuv07dv3/Pud/jwYcLCwtiyZQutWrUCICkpicDAQJYuXUrPnj0B2LVrF2PHjmXFihV4e3vTv39/3nvvPapWrVqq5+5oSqyJiIiIiIiIiIiIiIjYWVZWLn36jXfK2YsXjsfT061Ya2+++WYee+wxli5dSp8+fQBITExk/vz5zJ07l7S0NAYMGMBrr72Gh4cHU6dO5frrr2fv3r3UqVPnsuKLjY2lR48e3Hvvvbz77rtkZmbyzDPPMGzYMJYsWXJZe5YVJdZEREREREREREREREQqqaCgIK655hqmT59emFj78ccfCQoKok+fPlgsFlq2bFm4/rXXXmPWrFnMmTOHRx555LLO/PTTT2nTpg0TJkwovO/rr7+mdu3a7Nu3j8aNG5fuSTmQUxNr9erV48iRI+fc/9BDD/Hxxx9jGAavvPIKX3zxBYmJiXTs2JGPP/6Y8PDwwrXZ2dmMHTuW77//nszMTPr06cMnn3yiIYQiIiIiIiIiIiIiIuI0Hh6uLF443mlnl8Rtt93GfffdxyeffIK7uzvfffcdt9xyCxaLhfT0dF555RV+++03Tpw4QV5eHpmZmcTExFx2fJs2bWLp0qX4+Pic89jBgweVWLuQjRs3kp+fX/hxVFQU/fr14+abbwbgrbfe4t1332XKlCk0btyY1157jX79+rF3797CQYNjxoxh7ty5zJgxgypVqvDUU08xcOBANm3ahMViccrzEhERERERERERERGRys1kMhW7HaOzXX/99VitVubNm0f79u1ZuXIl7777LgD/+c9/mD9/Pm+//TYNGzbE09OToUOHkpOTc969Cua0GYZReF9ubtFZc1arleuvv54333zznOtr1Khhr6flEE5NrFWrVq3Ix2+88QYNGjSgR48eGIbBxIkTef755xkyZAgAU6dOJTg4mOnTp3P//feTnJzMpEmT+PbbbwuH5E2bNo3atWuzaNEirr766jJ/TiIiIiIiIiIiIiIiIlcST09PhgwZwnfffceBAwdo3Lgxbdu2BWDlypWMHDmSwYMHA5CWlsbhw4cvuFdB7ic2NpbWrVsDsHXr1iJr2rRpw88//0y9evVwcbmyppaZnR1AgZycHKZNm8aoUaMwmUxER0cTFxdH//79C9e4u7vTo0cP1qxZA9hKBXNzc4usCQ0NJSIionDN+WRnZ5OSklLkJiIiIiIiIiIiIiIiUlnddtttzJs3j6+//prbb7+98P6GDRvyyy+/sHXrVrZt28aIESOwWq0X3MfT05NOnTrxxhtvsGvXLlasWMELL7xQZM3DDz/MmTNnuPXWW9mwYQOHDh1iwYIFjBo1qkinw/Ko3CTWZs+eTVJSEiNHjgQgLi4OgODg4CLrgoODCx+Li4vDzc2NwMDAC645n9dffx1/f//CW+3ate34TERERERERERERERERK4svXv3JigoiL179zJixIjC+9977z0CAwPp3Lkz119/PVdffTVt2rS56F5ff/01ubm5tGvXjscff5zXXnutyOOhoaGsXr2a/Px8rr76aiIiInj88cfx9/cvbCVZXpWb+rpJkyZx7bXXEhoaWuR+k8lU5GPDMM65798utWbcuHE8+eSThR+npKQouSYiIiIiIiIiIiIiF2UYBtbsfPKz87Fm5ZOflUd+Vj4mswmfBv6YzBd/7VqkPLNYLJw4ceKc++vVq8eSJUuK3Pfwww8X+fjfrSGbNWvG2rVri9z3z5lrAI0aNeKXX34pRcTOUS4Sa0eOHGHRokVFPoEhISGArSrtn4Pq4uPjC6vYQkJCyMnJITExsUjVWnx8PJ07d77gee7u7ri7u9v7aYiIiIiIiIiIiIhIBZJ1MoPELafIz7Ql0KzZ+WCcf21Bck1EKrZyUU83efJkqlevznXXXVd4X1hYGCEhISxcuLDwvpycHJYvX16YNGvbti2urq5F1sTGxhIVFXXRxJqIiIiIiIiIiIiIyKUkbj1NVmwGuUk5WLP+TqqZXM24+LriXs0TF19XALLiM50YqYiUFadXrFmtViZPnsxdd92Fi8vf4ZhMJsaMGcOECRNo1KgRjRo1YsKECXh5eRX29vT392f06NE89dRTVKlShaCgIMaOHUtkZCR9+/Z11lMSERERERERERERkSucYTXIjs8AoGq3UNyC3LF4WLC4u2Cy/N3yMe1gMqdWnCAnIctZoYpIGXJ6Ym3RokXExMQwatSocx57+umnyczM5KGHHiIxMZGOHTuyYMECfH19C9e89957uLi4MGzYMDIzM+nTpw9TpkzBYrGU5dMQERERERERERERkQokOyELI8/A7GbGp4EfJtP556e5VfEAIOdMFobV0Jw1kQrOZPx7WlwllJKSgr+/P8nJyfj5+Tk7HBERERERERERERFxsuQdCZz5Kx6v2j4E9619wXWG1eDId3sx8gxqDq6PW4B7GUYpl1KWr/9nZWURHR1NWFgYHh4eDj1L7K+4X79yMWNNRERERERERERERKQ8yTppawPpEex10XUmswm3oLNVa2oHKVLhKbEmIiIiIiIiIiIiIvIPhmH8nVgLuXhiDcD9bDvIbCXWRCo8JdZERERERERERERERP4hNykba44Vk4upcIbaxRTOWVNiTaTCU2JNREREREREREREROQfsuJs1Wru1b0wmU2XXP/PijXDMBwam4g4lxJrIiIiIiIiIiIiIiL/kHUyEwCPYM9irXcNcMdkMWHkWslLzXVkaCJlbvz48bRq1crZYZQbSqyJiIiIiIiIiIiIiJxVZL5a8KXnqwGYzCZcA90BtYOUK4vJZLrobeTIkYwdO5bFixeXSTwpKSm8+OKLhIeH4+npSZUqVWjfvj1vvfUWiYmJhet69uxZGKO7uzuNGzdmwoQJ5OfnM3LkyEs+r9JwKe2TFBERERERERERERGpKPLScsnPyAMzuFcrXsUagHuQBzmns8hOyMI7zM+BEYrYT2xsbOH/z5w5k5deeom9e/cW3ufp6YmPjw8+Pj4Oj+XMmTN07dqVlJQU/u///o+2bdvi5ubGgQMHmD59OtOnT+fhhx8uXH/vvffy6quvkpWVxW+//cZjjz2GxWLh/fff54033ihcV6NGDSZPnsw111xjlziVWBMREREREREREREROatwvlpVT8wuxW/65nZ2zpoq1qSAYRgYec6ZuWdyKV5lVkhISOH/+/v7YzKZitwHtlaQs2fPZuvWrQCMHDmSpKQkOnTowPvvv092djZPPPEEzz//POPGjWPSpEl4eXnx6quvMmrUqMJ9jh8/zpNPPsmCBQswm8107dqV999/n3r16gHw3HPPERMTw969e6lZs2bhdU2bNmXgwIHnzC/08vIqjPWRRx7h119/Zfbs2TzzzDP4+/sXWRsQEHDO87pcSqyJiIiIiIiIiIiIiJxV0jaQBdzPJtayE7IwDKPU7ebkymfkGRyZtvfSCx2g7u1NMLk67s/gkiVLqFWrFitWrGD16tWMHj2atWvX0r17d9avX8/MmTN54IEH6NevH7Vr1yYjI4NevXrRrVs3VqxYgYuLC6+99hrXXHMN27dvx8XFhZkzZ3L77bcXSar906X+Tnl6ehZpF+komrEmIiIiIiIiIiIiInJWQcVaSRNrroHuYAJrdr6tlaRIBRYUFMQHH3xAkyZNGDVqFE2aNCEjI4PnnnuORo0aMW7cONzc3Fi9ejUAM2bMwGw289VXXxEZGUmzZs2YPHkyMTExLFu2jFOnTpGUlESTJk2KnNO2bdvCVpS33nrreWOxWq38+eefzJ8/nz59+jj8uatiTUREREREREREREQEyMvIJS81FwD36sWfrwZgdjHjFuBOTmI22QlZuHi7OiJEuYKYXEzUvb3JpRc66GxHCg8Px2z+u3YrODiYiIiIwo8tFgtVqlQhPj4egE2bNnHgwAF8fX2L7JOVlcXBgwdp2bKlLe5/VaXNmjWLnJwcnnnmGTIzM4s89sknn/DVV1+Rk5MDwB133MHLL79svyd5AUqsiYiIiIiIiIiIiIgAWSdtL9y7BbljcbeU+Hq3Kh7kJGaTk5CFdx3fS18gFZrJZHJoO0ZncnUtmjg2mUznvc9qtQK2qrK2bdvy3XffnbNXtWrV8PX1JSAggD179hR5rE6dOgD4+vqSlJRU5LHbbruN559/Hnd3d0JDQ7FYSv539nKoFaSIiIiIiIiIiIiICJB9mfPVCridnbOWk5Blt5hEKoI2bdqwf/9+qlevTsOGDYvc/P39MZvNDBs2jGnTpnH8+PFi7env70/Dhg2pXbt2mSXVQIk1ERERERERERERERHgH/PVQi4vseZ+NrGWrcSaSBG33XYbVatW5YYbbmDlypVER0ezfPlyHn/8cY4dOwbAhAkTqFmzJh07duTrr79m+/btHDx4kFmzZrF27doyTZ5djFpBioiIiIiIiIiIiEill5+dT05iNlCKirUgd9teGXnkZ+Zh8dRL8CIAXl5erFixgmeeeYYhQ4aQmppKzZo16dOnD35+fgBUqVKFDRs28Oabb/K///2P6OhozGYzjRo1Yvjw4YwZM8a5T+Isk2EYhrODcLaUlBT8/f1JTk4u/AKKiIiIiIiIiIiISOWRcTSVk4uO4ernRq2bGlz2Psd+OUhucg7B/WrjVcvHjhHK5SjL1/+zsrKIjo4mLCwMDw8Ph54l9lfcr59aQYqIiIiIiIiIiIhIpZcVlwmAe7BnqfbRnDWRik2JNRERERERERERERGp9LJOlm6+WgH3oLNz1s4osSZSESmxJiIiIiIiIiIiIiKVmjXPSvZpW8Xa5c5XK6CKNZGKTYk1EREREREREREREanUsuMzwQCLlwsuPq6l2qsgsZaXmkt+dr49whORckSJNRERERERERERERGp1P7ZBtJkMpVqL4u7pTA5l6N2kJWSYRjODkEuQ3G/bkqsiYiIiIiIiIiIiEilVphYK2UbyAJqB1k5ubraEqoZGRlOjkQuR8HXreDreCEuZRGMiIiIiIiIiIiIiEh5ZFgNsk/ZZ75aAfcqHmQcSSVbibVKxWKxEBAQQHx8PABeXqWvgBTHMwyDjIwM4uPjCQgIwGKxXHS9EmsiIiIiIiIiIiIiTpCYmAZAYKCPkyOp3LITsjDyDMzuFlwD3OyypyrWKq+QkBCAwuSaXDkCAgIKv34Xo8SaiIiIiIiIiIiISBnLzs7l9jvfJyMjh8cfu44bBrVXZYuTZMUVtIH0tNvXwP1sYi03OQdrrhWzq6YyVRYmk4kaNWpQvXp1cnNznR2OFJOrq+slK9UKKLEmIiIiIiIiIiIiUsZ27TpKYmI6AG/9bzYbNuzn2WcG4+dnn1aEUnzZdp6vBmDxdMHi5UJ+Rh45Z7LsurdcGSwWS7ETNXJlUZpcREREREREREREpIxt2RoNQGhoEC4uFpYt38mdIz9ky5ZDTo6scjEMgywHJNZA7SBFKiol1kRERERERERERETK2OYttsTabSO68fln91O7VhXi45N59PFJfPHlQvLy8p0cYeWQm5iNNceKycVUmAizl4J2kNlnlFgTqUiUWBMREREREREREREpQzk5eURFxQDQulUYzZrWYvLXj3DdgLZYrQZTpi7loUe+JDY20cmRVnwF1Wru1b0wme07484tSBVrIhWREmsiIiIiIiIiIiIiZWj37mPk5OQRGOhN3brVAPDycuf5527ilfHD8fZ2JyoqhjtHfsDCRducHG3FlnUyE7B/G0j4u2ItJzEba57V7vuLiHM4PbF2/Phxbr/9dqpUqYKXlxetWrVi06ZNhY8bhsH48eMJDQ3F09OTnj17snPnziJ7ZGdn8+ijj1K1alW8vb0ZNGgQx44dK+unIiIiIiIiIiIiInJJBfPVWrUMw2QqWiXVr29LvpnyGJGRdUhPz+bl8TP58KPfnRFmhWcYBllxZ+erhXjafX+LtwtmdwsYkJuUbff9RcQ5nJpYS0xMpEuXLri6uvLHH3+wa9cu3nnnHQICAgrXvPXWW7z77rt89NFHbNy4kZCQEPr160dqamrhmjFjxjBr1ixmzJjBqlWrSEtLY+DAgeTnqw+xiIiIiIiIiIiIlC8FibXWrcPO+3iNGoF8/OG9jLq7NwDfz1hFcnJGmcVXWeSl5pKfmQdmE+5V7Z9YM5n+ntuWrXaQIhWGUxNrb775JrVr12by5Ml06NCBevXq0adPHxo0aADY3jEwceJEnn/+eYYMGUJERARTp04lIyOD6dOnA5CcnMykSZN455136Nu3L61bt2batGns2LGDRYsWOfPpiYiIiIiIiIiIiBSRl5dfZL7ahbi4WLhndF/q1KkKQNTOmDKJrzLJPJYGgHs1D8wujnmpvLAdpBJrIhWGUxNrc+bMoV27dtx8881Ur16d1q1b8+WXXxY+Hh0dTVxcHP379y+8z93dnR49erBmzRoANm3aRG5ubpE1oaGhREREFK75t+zsbFJSUorcRERERERERERERBxtz57jZGbm4O/vRVhY9Uuuj4yoC8COHUqs2VvaYdvrwt51fR12hpsSayIVjlMTa4cOHeLTTz+lUaNGzJ8/nwceeIDHHnuMb775BoC4uDgAgoODi1wXHBxc+FhcXBxubm4EBgZecM2/vf766/j7+xfeateube+nJiIiIiIiIiIiInKOv+er1cNsvvTLs5GRdQCIijri0Lgqm7z0XLJPZgLgXc/PYecUVqwlZmNYDYedIyJlx6mJNavVSps2bZgwYQKtW7fm/vvv59577+XTTz8tsu7fAzwNwzjnvn+72Jpx48aRnJxceDt69GjpnoiIiIiIiIiIiIhIMWzZcjaxdpE2kP8UGWFLrO3afYy8vHyHxVXZpEfbqtXcgz1x8XZ12Dkuvq6YXM0Y+Qa5SdkOO0dEyo5TE2s1atSgefPmRe5r1qwZMTG2suaQkBCAcyrP4uPjC6vYQkJCyMnJITEx8YJr/s3d3R0/P78iNxERERERERERERFHysvLZ/v2wwC0bl28xFrdutXw9fEgKyuXAwfO36FLSq4gseYT5tjXhk0mU2HVWrbaQYpUCE5NrHXp0oW9e/cWuW/fvn3UrWvrGxwWFkZISAgLFy4sfDwnJ4fly5fTuXNnANq2bYurq2uRNbGxsURFRRWuEREREREREREREXG2fftjycjMwdfHgwb1Q4p1jdlsJuJs1doOtYO0i9zUHLJPZ4HJsW0gC7gFac6aSEXi1MTaE088wbp165gwYQIHDhxg+vTpfPHFFzz88MOALZs/ZswYJkyYwKxZs4iKimLkyJF4eXkxYsQIAPz9/Rk9ejRPPfUUixcvZsuWLdx+++1ERkbSt29fZz49ERERERERERERkUJbz7aBbNmyHhZL8V+aLUys7YhxSFyVTUG1mkeIFxZPF4ef51ZQsXZGiTWRisDx3zUuon379syaNYtx48bx6quvEhYWxsSJE7ntttsK1zz99NNkZmby0EMPkZiYSMeOHVmwYAG+vr6Fa9577z1cXFwYNmwYmZmZ9OnThylTpmCxWJzxtERERERERERERETOsWVryearFYiMtHX42hGlxJo9FCTWvB3cBrJAQSvInIQsDMPAZDKVybki4hgmwzAMZwfhbCkpKfj7+5OcnKx5ayIiIiIiIiIiImJ3+flWrr3uNdLSsvj6q4dp2rRmsa/NyMim/zWvYrUazP7lGapX93dgpBVbbnI2x345BCaoc0sjLB6Orz0xrAZHpu3FyDeoOaQ+bv7uDj9T/qbX/8XenNoKUkRERERERERERKQyOHAwjrS0LLy93WnUqEaJrvXycqdhQ9s1UapaK5W0s9VqnqHeZZJUAzCZTYVz1rJiM8rkTBFxHCXWRERERERERERERBxs69k2kC1alGy+WoHIgjlrSqyVSlm3gSzgVdc22ijtQHKZnisi9qfEmoiIiIiIiIiIiIiDbd5yCIDWJZyvVqAwsbbjiN1iqmxyErPITcoBswmvOr5lerZPA38wQfapTHKSssv0bBGxLyXWRERERERERERERBzIarWybdthoBSJtci6AOzdd4Ls7Fx7hVapFFSredX0xuJuKdOzXbxc8KrlA0DaflWtiVzJlFgTERERERERERERcaBDh06SkpKJp6cbTZqEXtYeISEBVK3iS36+lT17jts5worPMAzSDjmnDWQBn0b+AKQdTMKwGk6JQURKT4k1EREREREREREREQfacna+WmRkXVxcLq9SymQyERGpOWuXKychi7zUXEyWsm8DWcCrli9mdwv5mflkHk9zSgwiUnpKrImIiIiIiIiIiIg4UEFirU3ry2sDWSAywtYOckeU5qyVVHp0KgCetX0wuzrnZXGTxYRPQ1vVWuo+tYMUuVIpsSYiIiIiIiIiIiLiIIZhsHXrYeDy56sViIg4W7G2IwbDUCvB4jIMg/TDtjaQPk5qA1nA92xiLeNoKvlZeU6NRUQujxJrIiIiIiIiIiIilcyZxDQ++fRPXnp5BukZ2c4Op0I7fDiepKR03N1dadq0Zqn2atI4FFdXC0lJ6Rw/fsZOEVZ82aeyyEvLxeRixrOWj1NjcQvywK2qBxiQdjDFqbGIyOVxcXYAIiIiIiIiIiIiUjYSElL5bvpKZs1eT3Z2LgBt2tTnxhs6ODmyiqtwvlpEHVxdS/dyrJubC02b1mTHjhh27DhCrVpV7BFihZcebUtgedXxwezi/FoT34b+JJzOInV/En7NAzGZTM4OSURKwPnfRURERERERERERMShTp9O4f0P5nHTzf9jxsxVZGfn4uPjAcCOHZrX5UhbttgSa61LOV+twN9z1mLssl9F9882kN5ObgNZwLu+PyaLidzEbHISspwdjoiUkCrWREREREREREREKqhTp1OYNm05v87ZSE6ObZ5TeHhtRt/dB0zw5FNT2LZdiTVHMQyjsGKtVSnnqxWILJizpsRasWSdzCQ/Iw+zmxmvmt7ODgcAi7sFrzq+pEenkLo/Gfeqns4OSURKQIk1ERERERERERGRCiYlJYOvJi1izty/ChNqkZF1GHV3Hzq0b4jJZCItLQuTycSJE2dISEilShVfJ0dd8cQcPc2ZM2m4ubnQvFktu+wZcTaxdujQSdLSsgorD+X8/m4D6YvJUn4auPk08ic9OoX0Q8kEta9eLlpUikjx6G+riIiIiIiIiIhIBfPGW7P46ed15OTk0bJFXd5/bxSffXI/HTs0Kpzn5OPjQYP6wQBsVztIhyhoAxnevDbu7q522bNKFV9CQ4MwDIOdu47aZc+KyrCWvzaQBTxreGPxdsGaYyUjJtXZ4YhICSixJiIiIiIiIiIiUoFkZ+eyZs1eACb8dwSffHwf7c9Wqf1bZKRtXpcSa46xdat956sViIw82w5SX7eLyorLwJqVj9ndgmdo+WgDWcBkNuHb0B+AtP3JTo5GREpCiTUREREREREREZEKZMvWaHJy8qhWzY8e3cPPm1Ar0KKFLbG2Q3PW7O6f89XsnljTnLViSTvbBtK7ri8m84X/HjiLT8MAADJPpJOXluvcYESk2JRYExERERERERERqUDWrdsHQKeOjS+aVANocbZibe++E2Rl5Tg8tsrk+IkznDqVgqurhYjwOnbdOzLC9nXbufMo+flWu+5dURhWg4wjthaL5a0NZAFXPzc8QrwASD2gqjWRK4USayIiIiIiIiIiIhXIuvVnE2udGl9ybUhIANWq+ZGfb2X37mOODq1S2Xp2vlrzZrXsNl+tQP36wXh5upGRkU109Em77l1RpB1Mxpqdj8XTUpi8Ko98CtpBHkjCMAwnRyMixaHEmoiIiIiIiIiISAVx4sQZYmJOY7GYade2wSXXm0ymwqq1bWoHaVebthwCoFUr+7aBBLBYzISHqx3khVhz8kncFA+AX/OgctkGsoB3PT9MLmbyUnPJOpnh7HBEpBiUWBMREREREREREakg1m/YD0BEeG18fT2LdU3k2cTajh1KrNlLdnYuq1btBqBjx0YOOSMy0pZYi1Ji7RyJW0+Tn5mPq58b/uFBzg7nosyuZrzDfAFI2692kCJXAiXWREREREREREREKoi1BfPVOjUp9jUFFWtRUTFYrZrXZQ9r1+0lPT2b4Or+hZ9fe4uIUMXa+eQkZpOy6wwAQZ2CMVnK/0vgvo0CAEg/nII1N9+5wYjIJZX/7yoiIiIiIiIiIiJySbm5eWzadBCATiWokmrYMARPTzdS07KIPhzvqPAqlQULtwHQt29LzGbHvAQb3rw2JpOJY8cSOJOY5pAzrjSGYZCwPg4M8Krjg1dNH2eHVCzu1T1x9XfDyDNIj051djgicglKrImIiIiIiIiIiFQA23ccITMzh8BAbxo1qlHs61xcLDRvXguAHZqzVmppaVmsWbMXgP79WjrsHF9fT8LCqgNqB1kg43AqWbEZmCwmgjoEOzucYjOZTPg09AcgdX+Sc4MRkUtSYk1ERERERERERKQCWLfONl+tU8fGJa6SKmhXuH2HEjSltXzFTnJy8girV52GDUMcelZE+Nl2kPq6Yc21krDhJAD+kVVw9XVzckQl49PQH0yQHZ9JTlK2s8MRkYtQYk1ERERERERERKQCWLfeNl+tY8fGJb42sjCxpoq10ipoA9mvX0tMJpNDz4qMtCXWoqL0dUvafpr8jDxcfFzxj6zi7HBKzMXLFa9attaVqfuSnBuMiFyUEmsiIiIiIiIiIiJXuFOnkjl4MA6TyUSH9g1LfH1EeB1MJhMnTpzh9OkUB0RYOSQkpBbOuevX13FtIAtERtgSorv3HCc3N8/h55VXuck5JEedASCoQzBmlyvzZW/fxgEApB1Ixsi3OjcYEbmgK/M7jIiIiIiIiIiIiBRav97WBrJZ05oEBHiX+HofHw8aNrC1LVTV2uVbvGQHVqtBREQdatYMcvh5tWtXwd/fi5ycPPbti3X4eeWRYRgkrI8Dq4FnTW+86vg4O6TL5lnLB4uXC9bsfNKPpDk7HBG5ACXWRERERERERERErnAFbSA7dSp5G8gCBW0FNa/r8i1YsBWA/v0cX60GYDKZiIw4+3WrpO0gM4+mkXk8HcxQpWOww9tvOpLJbMK3kT8AqfuTnBuMiFyQS3EWPfnkkyXe+IUXXiAoyPHvyhAREREREREREanM8vLy2bjxAACdLmO+WoEWkXX5ZdZ6VaxdpmPHEti1+xgWi5nevSLK7NyIiLqsWr2HHTtiuGV4mR1bLljzrCSsPwmAf3gVXP3dnRxR6fk0CiBpWwJZJ9LJTc3B1dfN2SGJyL8Uq2Jt4sSJrF+/ni1bthTr9uGHH5KUlHTJfcePH4/JZCpyCwkJKXzcMAzGjx9PaGgonp6e9OzZk507dxbZIzs7m0cffZSqVavi7e3NoEGDOHbsWMk+CyIiIiIiIiIiIleoXbuOkZqWhZ+fJ82a1brsfSJb2OZ17dt3gqysHHuFV2ksXLQNgHZtGxAU5Ftm5xZUGm7dFk1eXn6ZnVseJEclkJeWi8XLhYCWVZ0djl24+rrhEWpr55q6L8m5wYjIeRWrYg1g1qxZVK9evVhrfX2L/w9HeHg4ixYtKvzYYrEU/v9bb73Fu+++y5QpU2jcuDGvvfYa/fr1Y+/evYVnjBkzhrlz5zJjxgyqVKnCU089xcCBA9m0aVORvURERERERERExPEMw2DZ8p18/MmfhDevxSvjb3F2SBVeQRvIDu0bYbFc/uSXkOAAqlXz49SpFHbtOkabNvXtFWKFZxgG88u4DWSB8Oa1CQz0JjExnSVLdtC/f6syPd9ZclNzSN6eAEBQ++qYXSvO1CO/xgFknUgnbX8yga2rYTJfue0tRSqiYn23mTx5Mv7+/sXe9PPPPyc4OLhYa11cXAgJCSm8VatWDbD9YzRx4kSef/55hgwZQkREBFOnTiUjI4Pp06cDkJyczKRJk3jnnXfo27cvrVu3Ztq0aezYsaNIsk5ERERERERERBzv5Mkknhk3jedfmM6JE2dYtHgHaWlZzg6rwrPHfDWwzetqEWmrWlM7yJLZtz+WmJjTuLm50L178zI9283NhaE3XQXAd9+vxDCMMj3fGQzD4MyGkxj5Bh4hXniH+Tk7JLvyquOL2cNCfmYeGUfTnB2OiPxLsRJrd911F+7uxe9PO2LECLy9vYu1dv/+/YSGhhIWFsYtt9zCoUOHAIiOjiYuLo7+/fsXrnV3d6dHjx6sWbMGgE2bNpGbm1tkTWhoKBEREYVrzic7O5uUlJQiNxERERERERERuTz5+VZ++HENt90+kVWrdmOxmPHydMMwDHbv1sgORzqTmMaePccB6NihUan3iyxIrG1XYq0kFi60tYHs2qUp3t4eZX7+kMGd8PBwZf/+WP7662CZn1/WUvclkRGTBiao0jEYk6liVXSZLCZ8G9oKXdQOUqT8uaz62KSkJL766ivGjRvHmTNnANi8eTPHjx8v0T4dO3bkm2++Yf78+Xz55ZfExcXRuXNnEhISiIuLAzin8i04OLjwsbi4ONzc3AgMDLzgmvN5/fXX8ff3L7zVrl27RHGLiIiIiIiIiIjN/v2x3PfAZ0x8/zcyMnOIiKjDlMmP0LVrMwCidsY4OcKKbcOG/QA0bhxKlSqln+tVULEWtTMGq9Va6v0qA6vVWjhfrV+/Vk6Jwd/fi4ED2wG2qrWKLOdMFmfWnwQgsG113ILKPpFZFnwaBwCQeTyNvPRc5wYjIkWUOLG2fft2GjduzJtvvsnbb79NUlISYJvBNm7cuBLtde2113LTTTcRGRlJ3759mTdvHgBTp04tXPPvdxsYhnHJdyBcas24ceNITk4uvB09erREcYuIiIiIiIiIVHZZWTl88umfjLrnY3bvPoa3tzv/GXsDn31yHw3qhxAebnsjc9ROve7iSOvW2xJrnTqWvloNoGHDEDw93UhLyyI6Ot4ue1Z027Yd5tSpFHx9PLiqlO04S+OWYV0wm01s2LCf/ftjnRaHI1lzrcQvO46Rb+BZ0xv/iCBnh+Qwbv7uuAd7ggGp+5OcHY6I/EOJE2tPPvkkI0eOZP/+/Xh4/P1ugGuvvZYVK1aUKhhvb28iIyPZv38/ISEhAOdUnsXHxxdWsYWEhJCTk0NiYuIF15yPu7s7fn5+RW4iIiIiIiIiIlI8f206yO13vM+071aQn2+lZ89wpn/3BINv7IjZbHu5KTy8DgA7d8ZUiplPzmC1WtmwwTZfrWNH+yR0XFwshDe3JUU1Z614FpxtA9mzVwRubi5OiyM0NIhePSMAmD6jYlatJayPIzc5B4uXC9W6h1a4FpD/5tvY1qktbX9yib6PqsJNxLFKnFjbuHEj999//zn316xZ86LtF4sjOzub3bt3U6NGDcLCwggJCWHhwoWFj+fk5LB8+XI6d+4MQNu2bXF1dS2yJjY2lqioqMI1IiIiIiIiIiJiP7FxiTw1dgonYhOpXt2fN9+4gwmv3Ua1qkXfuNyoYQhubi6kpGRy7FiCk6Kt2PbsPUFSUgbe3u5ERtSx274tWpyds6bE2iXl5uaxZGkUAP37tXRyNDBiRDcAFi3azsmTSc4Nxs7SDiaTtj8ZTFCteygWD+clMcuKdz1fzG5m8tJyyTyRXqxrMo6mcezng6TsSbz0YhG5LCVOrHl4eJCSknLO/Xv37qVatWol2mvs2LEsX76c6Oho1q9fz9ChQ0lJSeGuu+7CZDIxZswYJkyYwKxZs4iKimLkyJF4eXkxYsQIAPz9/Rk9ejRPPfUUixcvZsuWLdx+++2FrSVFRERERERERMS+fv99M7m5+YQ3r81308bQ7ewstX9zdXWhSZNQQO0gHWX9elu1Wvt2DXFxsdht38izc9Z2bFdi7VLWrd9PamomVav60aplmLPDoVnTWrRpHUZ+vpUfflzj7HDsJjc5m9NrbO0tA1pWxbOGt5MjKhtmFzM+DfwBSN2bdMn1mcfTiF96DCPfICs2XdXCIg5S4sTaDTfcwKuvvkpurq2c1GQyERMTw7PPPstNN91Uor2OHTvGrbfeSpMmTRgyZAhubm6sW7eOunVt/3g//fTTjBkzhoceeoh27dpx/PhxFixYgK/v34NY33vvPW688UaGDRtGly5d8PLyYu7cuVgs9vthQkREREREREREbK0H5/2+CYChQ6/C28v9ousj/tEOUuxv3Xr7toEsEBFeG7PZxInYRE6fPvcN9vK3BQu3AtC3TwsslhK/1OoQI0Z0B+DXORtJS8tycjSlZ807O1ctz8AjxIuAllWdHVKZ8m0cAEBGTCr5mXkXXJcZm87JxbakmlcdH6r1qFnhW2WKOEuJv9u//fbbnDp1iurVq5OZmUmPHj1o2LAhvr6+/Pe//y3RXjNmzODEiRPk5ORw/Phxfv75Z5o3b174uMlkYvz48cTGxpKVlcXy5cuJiIgosoeHhwcffvghCQkJZGRkMHfuXGrXrl3SpyUiIiIiIiIiIpewefMh4uKS8PHxoGeP8EuuDw+3vUajijX7S0nJZOfZz2unjo3sure3twcN6ocAagd5MekZ2axatQcoH20gC1zVqTFhYdXJyMhm9q8bnB1OqZ3ZGE/OmWzM7haq9QjFZK5cySK3IA/cq3qAAakHks+7Jisug5OLjmLkG3jW8qF6z1qV7vMkUpZKnFjz8/Nj1apV/Pzzz7zxxhs88sgj/P777yxfvhxv78pRgisiIiIiIiIiUhn9Ns9Wrdavb0vc3V0vub6gYu3gwTgyM3McGltls3HjfqxWg7Cw6gQHB9h9/8hI29duu9pBXtDKlbvIzs6lTu2qhW1PywOTycSIW22z1n74cQ25uReucirv0g+nkHp2Vli17qG4eF36+05F5NskAIC0fUnntHfMis8gbuFRjDwDz5reVO9VE5NFSTURR7rs+uTevXszduxYnn76ac0zExERERERERGp4FJSMlm2fCcAAwe2LdY11av7U62aH/n5VvbsPe7I8Cqddev3A9DJzm0gC7Q4O2dNFWsXtnDhNgD69WtZ7lru9e/XkqpV/Th9OoUFZ+O80uSm5nB6tW2umn9EEF61fJwckfN4h/lhcjGRm5JD1smMwvuzT2cSt+AoRp4VjxpeVO9dC7NL+WhJKlKRuZT0gldfffWij7/00kuXHYyIiIiIiIiIiJRPixZvIycnjwYNQmjapGaxrwsPr82yZTvZufMorVuFOTDCysMwDNafna/mqMRaZAtbYm3//lgyM3Pw9HRzyDlXqsTENDZsPADYKjjLG1dXF4bd3JlPPv2T6d+vZMC1bcpd8u9iDKvBqeUnsOZYca/mSWDb6s4OyanMrha86/uTti+J1L1JeIZ4k52QRdz8GIxcKx4hXgT3ra2kmkgZKXFibdasWUU+zs3NJTo6GhcXFxo0aKDEmoiIiIiIiIhIBfTbb7Y2kAOva1uiF+gjwuucTazFOCq0SufgwThOJ6Ti4eFKy5b1HHJGSHAA1ar5cepUCrt2H6VtmwYOOedKlJ9vZeYPa8jPt9K0aU3q1Knq7JDO68YbOjBl6lKio+NZu24fna9q4uyQii1x8ymyT2VidjNXyrlq5+PXOIC0fUlkHEklMy6D+CXHbInH6p5KqomUsRIn1rZs2XLOfSkpKYwcOZLBgwfbJSgRERERERERESk/9u+PZc/e47i4WOjfr2TVOQVz1qJ2HsUwjCuqaqa8mr/A1tqvXdsGuLmV+OW9YjGZTLRoUZfFi3ewffsRJdYAq9XKsmU7+errRRw+fAqAAde2cXJUF+bj48Gg69szY+Yqpk9fccUk1vKz8kjZdQaAql1q4OqrakkAt6oeuAW6k5OYTdyfR8AA92oehPSrjdlVSTWRsmSXf3n9/Px49dVXGThwIHfccYc9thQRERERERGRSi4rK4czZ9Jst0TbfxPP/jcnJ4+Rd/WiRo1AZ4dZKcz73Vat1rVrUwIDSzbnqEmTUCwWMwkJqcSdTKJGiL5mpZGdncvc3zYCMHBgO4ee1SLSlljbsaNyVxsahsGq1Xv46qtF7D9gm/nl6+vJbSO6M2RwRydHd3HDh3Xmx5/WsHlLNLv3HKNZ01rODumS0g6mYOQbuAW541XX19nhlBsmkwnfxgEkrD8JBrhV8SC4Xx3MbhZnhyZS6djtLS1JSUkkJyfbazsRERERERERqYR27jzKhDd+5uTJZDIysi+6Nic3j5dfHFZGkVVeOTl5zF+wFYCB15U8kePu7kqjRjXYs+c4O3ceVWKtlBYs3EZKSiY1agTSpXNTh57VItI2Zy1qZwz5+VYslspVFWObZbefLyctYvfuYwB4e7szfFgXbhneFR8fDydHeGnBwQH07duC+fO3Mv37lfzfK7c6O6SLMgyD1L2JAPg2CVSF6794N/AneecZLJ4WgvvVweKupJqIM5Q4sfbBBx8U+dgwDGJjY/n222+55ppr7BaYiIiIiIiIiFQuhmEw8f3fiI6OL7zPzc2FwEAfgoJ8CAr0IaiKDy4WM7Nmb2Dlil1kZeXg4aE2YY60avVukpMzqFrVjw7tG17WHhHhtQsTa337tLBzhJWHYRj89NNaAG4a3Mnhia4GDULw9HQjLS2Lg4fiaNwo1KHnlSdbthzi8y8Wsn3HEQA8PFwZdnNnRtzaDT8/LydHVzIjbunG/PlbWbo0ihP3nyE0NMjZIV1Q9slMcpNzMLmY8Knv5+xwyh2Lu4VaQ21tWZV0FHGeEifW3nvvvSIfm81mqlWrxl133cW4cePsFpiIiIiIiIiIVC7r1+9n566juLu78tkn91GzZhW8vd3PefHQMAzWrd9PbGwiq1bvUaLGwebNs7WBHHBta1xcLq86IiK8Dj/9vI6onZW7pWBpbd12mP0HYnF3d2XgwLYOP8/FxULbNvVZtXoPixZtrzSJtXXr9/HkU1MAW3J/yOBO3H57d4JK2Aa1vGjUqAYdOjRiw4b9/PzLOh59ZICzQ7qglH22ajXvMD+1OLwAJdREnK/Eb2uJjo4ucjt48CDr1q1jwoQJ+Pqq562IiIiIiIiIlJxhGEyavBiAwTd2pEmTmvj4eJz3BUSTyUS/vi0BW1s8cZz4+GTWb9gPXF4byALh4XUA2LfvBDk5eXaJrTIqqFa7un+rMquaGjCgDQB//LmFvLz8MjnTmaxWK5988icAPXuE8+MPY3ns0QFXbFKtwOAbOgCwbPlODMNwcjTnl5+VR8bhVAD8mqhlrIiUX5WrMbKIiIiIiIiIlEvrN+xn586juLm5cNuIbpdc37+fLbG2bt0+UlIyHB1epfXHn1uwWg1atapHrVpVLnuf0NBAAgK8yc3NZ9++E3aMsPI4eTKJFSt3AXDz0KvK7NwunZsSEOBFQkIq69fvL7NznWXRou0cOBiHj48Hzz4zmGpVK0Y7wo4dG+Hu7kpsbCIHDsQ5O5zzSjuYgpFv4BbkjlvV8j+/TkQqr2K1ghwyZEixN/zll18uOxgRERERERERqXwMw2DS12er1QZ3pEqVS3fEqV8/mEYNa7D/QCxLl+3khkHtHR1mpWMYBr/N+wsoXbUa2KoMI8Jrs2r1HnbuOkpERB17hFipzJq9gfx8K21ah9GgQUiZnevq6sLVV7dm5szV/DbvL7p0aVpmZ5e1vLx8vpy0COCKnKV2MR4ebnTo0JCVK3ezYuUuGjWq4eyQijAMg9S9tjaQvk0C1e5QRMq1YlWs+fv7F/smIiIiIiIiIlIS/6xWu31E92Jf1+9s1drChVsdFFnltnXbYY4fP4OXpxu9ekaUer+CdpCas1Zy2dm5zJm7AYChZVitVmDgdbZ5bqtW7+FMYlqZn19W5v72F8ePnyEw0JthN3d2djh2171bc4DCysfyJPtkJrnJOZhcTPjUrxhVgiJScRWrYm3y5MmOjkNEREREREREKiHDMPh68hKg+NVqBfr2acEnn/7Jlq2HiY9Ppnp1veHXnubN2wRAn74t8PR0K/V+ERG1Adi582ip96psFi/ZQVJSBsHV/enapVmZn9+gfgjNm9Vi1+5jzJ+/lVtv6VrmMThaVlYOk89+L7p7ZG+8vNydHJH9dencFLPZxP79scTGJlKjRvmZY5ayz1at5h3mh9nN4uRoREQuTjPWRERERERERMRpNmw8QFRUTImr1QBCQgJo2bIehmGwaPF2B0VYOaWnZ7Fk6Q6g9G0gCzRtWguz2URcXBKnT6fYZc/KwDAMfvxxDQCDB3fCxcU5SYeCqrXffvsLwzCcEoMj/fjTWk4npFKjRmCFbS0bEOBNyxb1gPJVtZafnU/G4VQA/JqUn2SfiMiFXFZi7aeffmLYsGF06tSJNm3aFLmJiIiIiIiIiBRHkdlqN5asWq1A/8J2kNvsGltlt3jJDrKycqlbtxoR4bXtsqe3lzv1w4IBVa2VRFRUDHv3ncDNzYVB19snyXk5+vZtiZubC9GH49m9+5jT4nCE1NRMpn23AoB7RvXB1bVYTb6uSN2729pBrixHibW0A8kY+QZuQe64VfVwdjgiIpdU4sTaBx98wN1330316tXZsmULHTp0oEqVKhw6dIhrr73WETGKiIiIiIiISAX0z2q120Z0u6w9evWMwGIxs3ffCQ4fibdzhJXXb2fbQA68ri0mk8lu+4afTdJFKbFWbD/+tBaAfn1bEhDg7bQ4fHw86NXLNmuv4M9HRfHd9JWkpmYSFlad/v1bOTsch+rW1dZKdOu2wyQnZzjkjJJUNBqGQepeWxtI3yaBdv1+IyLiKCVOrH3yySd88cUXfPTRR7i5ufH000+zcOFCHnvsMZKTkx0Ro4iIiIiIiIhUMLbZan9Xq1Wt6ndZ+wQEeNOxYyNAVWv2cvhwPFFRMVgsZq65urVd9w4PrwPAzl0xdt23ojp1OoWly6IAGDr0KidH83c7yIWLtpGVlePkaOwjISGVH35cDcB99/bHYqnYk3NCQ4No1LAGVqvB6jV7HHJG0tbTnF4bhzXXesm12SczyU3OweRiwqf+5f07ICJS1kr8L0VMTAydO3cGwNPTk9RUW//bO+64g++//96+0YmIiIiIiIhIhbTxrwPs2FG6arUC/fva2kEuWLitQs5+KmvzfrdVI3Xu3OSy2nNeTESErWJt9+7j5OXl23XviujXXzeQn2+lZYu6NGkc6uxwaN0qjNAagaSnZ7Ns+U5nh2MXU79ZSlZWLuHNa9O9WzNnh1Mmup19nitW2L8dZF5aLknbTpO6J5Hjvx4i6+TFq+JS9tmq1bzD/DC7OWd+oIhISZU4sRYSEkJCQgIAdevWZd26dQBER0frh1cRERERERERuaR/zla78YYOl12tVqBbt+Z4eLhy/PiZCjf7qawZhsGiRdsBGHBtW7vvX6d2VXx9PMjOzuXgwTi771+R5OTkMfvXDQAMvcn51WoAZrOZ685WrVWEdpAnTpxh9q8bAbj//v6Vpg1hwZy19Rv2l7jycOYPq5n09WLS0rLO+7iLjysh/etg8XYhLzWX2N+PcGZjPNa8c6vX8rPzyThsK9rwaxJYwmchIuI8JU6s9e7dm7lz5wIwevRonnjiCfr168fw4cMZPHiw3QMUERERERERkYrln9Vqt9/WvdT7eXq60b2b7YXiBWoHWSr79sdyMj4ZDw9XOp1tsWlPZrOZ5s01Z604lizdwZkzaVSr5kePHuHODqfQgGvbYDKZ2Lz5EMeOJzg7nFKZ9PVi8vLyad++Ie3aNnB2OGWmUcMahIQEkJ2dy8a/Dhb7utTUTL7+ejGTvl7MmrV7L7jOM9SbWjfWx6ehPwDJUQmcmHuY7NOZRdalHUjGyDdwC3LHrarH5T0ZEREnKHFi7YsvvuD5558H4IEHHmDKlCk0a9aMV155hU8//dTuAYqIiIiIiIhIxWEYBl9/vQSwT7VagX79bO0gFy3eTn7+pef6yPmtXGlrDdexQyPc3V0dckZ4uC2xtlOJtYv66ae1gO3viYtL+WmRFxwcQIf2DQH4/ffNTo7m8h08FMef87cC8MD9/Z0bTBkzmUx061rydpAzf1hNaloWYfWq06d35EXXmt0sVOsWSvU+tTB7WMhNyubEb4dJ3HIKw2pgGAape21tIH2bBFaaakERqRhKnFgzm824uLgUfjxs2DA++OADHnvsMdzc3OwanIiIiIiIiIhULH/9dZDtO47YZqvZoVqtQMcOjfD39+LMmTQ2bz5kt30rm5WrdgO29pqOEhFeB4CdO2McdsaVbteuo+zafQxXVws33NDB2eGcY+DZdpC//7H5ik1kf/HlQgzDoGfPcJo1reXscMpcQTvIVat3F2veYUpKBjN/WA3A6FF9sFiK97Kydx1fag2uj1c9XzAgaetpTvx2mNR9SeQm52ByMeFT3z5vsBARKSslTqyFhYXx4osvsmfPHkfEIyIiIiIiIiIV1D9nq90wqD3V7FStBuDiYqF3rwhA7SAvV2xcIvv3x2I2m+h8VROHnVPQCvLosQSSkzMcds6V7MefbdVqffu0ICjQx8nRnKtbt+b4+XkSH5/Mxr8OODucEouKimHlyt2YzSbuu6efs8NxipYt6uHr60lycgY7oi6d5J7+/UrS07Np2CCEnj1L1prU4uFC9Z41qdYjFLObmZyELBLW2GYseof5YXYrPxWZIiLFUeLE2qOPPsqff/5J8+bNadu2LRMnTiQ2NtYRsYmIiIiIiIhIBbJn7/HCarXbb+9h9/0L2kEuWx5Fdnau3fev6FadrVaLjKxLQIC3w87x8/Okbt1qAESpau0cp06nsHjxDgCGDr3KydGcn5ubC/37twJg3rxNzg2mhAzD4LMvFgBw7TVtqFevupMjcg4XFwtduzQFYMXKi7eDTExM48ezrUnvuacvZnOJX1LGZDLhU9+fmoPr41nz7+8vfk0CS7yXiIizlfi74JNPPsnGjRvZs2cPAwcO5NNPP6VOnTr079+fb775xhExioiIiIiIiEgFsGRJFADdujaza7VagRaRdQmu7k96ejZr1+21+/4V3cqVZ9tAnp295Eias3Z+mZk5jBs3jby8fCIi6pTrFoUF7SBXrNxVZpWHJ06cYc7cjaRnZF/2HkuW7GDz5kO4uloYPaqPHaO78nQ/2/J15YpdGIZxwXXfTV9JZmYOTZvWLPX3BxcvV4L71aZ6r5pU61kT92qepdpPRMQZSv72grMaN27MK6+8wt69e1m5ciWnTp3i7rvvtmdsIiIiIiIiIlJBGIbB0qW2KpxeZ1s22pvZbKZvX1vV2oIFagdZEqmpmWzZGg38/WK7I0U0V2Lt3/Ly8nnx5e/ZtfsYfn6ePDduiLNDuqjGjUJp3DiU3Nx8Fizc6tCzEhPTeG/iXG4Z8R5vvDmLZ579ltzcvBLvc/z4Gd54axYAt43oTkhIgJ0jvbJ06NAINzcXTsQmcvBg3HnXJCSk8vMv6wC4d3RfTCZTqc81mUx41/PDJ0yz1UTkynTZiTWADRs2MGbMGAYPHszevXsZOnSoveISERERERERsbsvv1rIQ498wYyZq0hISHV2OJXK3r0nOBGbiLu7K1d1ctz8rv5n20GuWbuX1NRMh51T0axdt4/8fCth9apTq1YVh58XHl4HgJ27jpKfb3X4eeWdYRj87+1fWbNmL25uLvzvzTupV7f8tygsqFr7zUHtIDMzc5g8ZQk3D3+HH39aS15ePhaLmc2bD/G/t3+9aJXVv+Xm5vHiy9+Tnp5Ni8i6jLq7t0NivpJ4errRoUMj4MLtIL/5dhnZ2bmEh9emU6fGZRidiEj5VeLE2r59+3j55Zdp1KgRXbp0YdeuXbzxxhucPHmSmTNnOiJGERERERERkVKLioph8pSlbN16mA8+/J0bBr/BE09OZv6CrWRm5jg7vApv6TJbG8jOVzXB09PNYec0bBhCWFh1cnLyWL7i4nOD5G8rV9k+V926Ob4NJED9+sF4erqRkZHNkSOnyuTM8mzS14uZ+9tfmM0m/u/VW4mMrOvskIqlf7+WuLm5sH9/LHv3nbDbvnl5+cyevZ5ht7zDl18tIiMjm8aNQ3n/vVG8+cYdmM0mfpu3iWnfrSj2np98Np89e47j5+fJK+OH4+JisVu8V7KCCtUVZ1vB/lN8fDK/ztkIwH339LNLtZqISEXgUtILmjZtSrt27Xj44Ye55ZZbCAkJcURcIiIiIiIiInZjGAYfffwHAK1bhZGTm8fOnUdZv2E/6zfsx9PTje7dm3PN1a1p26a+XnC1M8MwWHK2DWRvB7WBLGAymejfrxWff7GAhQu3FVbUyIXl5uaxbt0+ALp2KZvEmsViplmzWmzefIionTHUrx9cJueWR7Nnr+fryUsAGPvUDWUy485e/Py86N6tOYsWb2fevL9o0nhQqfYzDIMVK3bx6efziYk5DUBojUDuu68/fftEYjbbagTGPD6Qd9+by6efzadmzSB694q86L6rVu1m5szVALzw3FCCgwNKFWdF0qVzE8xmE/v2nSA2LpEaIYGFj039Zhk5OXm0alWPdu0aODFKEZHypcQVa3v27ClsAWnPpNrrr7+OyWRizJgxhfcZhsH48eMJDQ3F09OTnj17snPnziLXZWdn8+ijj1K1alW8vb0ZNGgQx44ds1tcIiIiIiIicuVbsWIX23ccwd3dlfEvD+PLzx/khxlPMeru3tSsGURmZg7z52/liScnM/imt/jm2+UlajEmF7dvfyzHj5/Bzc2Fq65yXBvIAv36tgBg0+aDnD6d4vDzrnSbt0STnp5NlSq+NG9eq8zOjQiveHPWxj03jRsGv8FXkxZxJjHtkutXrNzF2+/OAWDU3b258YYOjg7R7gYOtCWv/5y/lbS0rMveJzYukfsf/Jxxz39HTMxpAgK8GPP4QL6f/gT9+7UsTKoBDL3pKoYOvQqAV//vR3btuvCfoZMnk3htwk8ADB/eha5XUOKyLAQG+tCiha1CcuU/qtZi4xKZ+9tfANyrajURkSJKnFhr3Nj+vXQ3btzIF198QYsWLYrc/9Zbb/Huu+/y0UcfsXHjRkJCQujXrx+pqX/3wR8zZgyzZs1ixowZrFq1irS0NAYOHEh+fr7d4xQREREREZErT15ePp98+icAt97SlWrV/AGoVasK94zuyw8znuLzzx5gyOCO+Pt7kZCQymefz2f9hv3ODLtCWbr07zaQXl7uDj8vNDSIiIg6WK0GixZvd/h5V7qVZ2crdenctEjywtEK5qxt3nIIq/XKn7N2+Eg8y1fs4tSpFL6evIQhN73FG2/O4vCR+POu37HjCC+9PAOr1eD669sxelSfMo7YPtq1bUBYveqkpWXx409rLnuft9/+laioGDw8XBl5Vy9+nDmWYTd3xtX1/A23HntkAFdd1YScnDyefvZbYuMSz1mTl5fPy+NnkpKSSdOmNXnogasvO76K7O92kH+3z50yZSl5efm0b9eQ1q3CnBWaiEi5VKyfloKCgjh9+nSxN61Tpw5Hjhwp1tq0tDRuu+02vvzySwID/y41NgyDiRMn8vzzzzNkyBAiIiKYOnUqGRkZTJ8+HYDk5GQmTZrEO++8Q9++fWndujXTpk1jx44dLFq06IJnZmdnk5KSUuQmIiIiIiIiFdOvv27g6LEEAgK8uW1Et3MeN5lMREbUYexTNzBn9rNcP7AdQGHbMCkdwzBYerYNZC8Ht4H8p6v7twLgjz+2lNmZVyLDMFi1eg9QdvPVCrRpHYa3tzvHj59h5ao9ZXq2IxRU+zRoEEKzZrXIycljztyNjLhtIv95+hu2bDlUWAl7+Eg8/3nmG3Jy8ujSuSn/eeqGK7YiyGw2c9ddvQCYMXM16RnZJd5j586jrF23D4vFzNeTHua+e/vh7e1x0WtcXCy8+sotNGwQwpkzafzn6W/OqZib9PVitu84gre3O6++cssFk3SVXbeutsTatm2HSU7O4NjxBH7/YzMA99zT15mhiYiUS8VKrCUlJfHHH38wZ86cYt0SEhKKXTH28MMPc91119G3b9Fv0tHR0cTFxdG/f//C+9zd3enRowdr1tje/bJp0yZyc3OLrAkNDSUiIqJwzfm8/vrr+Pv7F95q165drFhFRERERETkypKensWks7OLRo/qc8kXal1dXbjzjp6YTCbWb9hPdPTJsgizQjtwII6jxxJwc3Ohc+emZXZuv74tcHW1sP9ALPv2nyizc680e/eeID4+GU9PN9q1LdsZSt7eHtw0pBMA33y77Ipvv1pQ7TNkcEe++uJBPvn4Xrp1a4bJZGL1mj08/OhXjL7nE+b+9hdPPDmFlJRMwpvX5tVXbrni5zr26R1JnTpVSU3N5Oef15X4+q8nLwbgmqtbU69u9WJf5+3lzv/eupMqVXw5dOgkL770PXl5ttckN2zczzffLgfg2acHU6tmlRLHVVnUrBlEwwYh5OdbWbNmD5MnLyE/38pVnRoTGVHH2eGJiJQ7xX6bxl133WX3w2fMmMGmTZv466+/znksLi4OgODgosNrg4ODC6vh4uLicHNzK1LpVrCm4PrzGTduHE8++WThxykpKUquiYiIiIiIVEDfTltBUlI6dWpX5YZB7Yt1Tc2aQXTv1ozlK3Yx84c1PPvMYAdHWbEtOVut1qljY7zLoA1kAT8/L7p3a87iJTuYN28TjceEltnZV5JVq21VVh07NMLd3bXMzx82rAszZq5m9+5j/PXXQdq3b1jmMdjD6dMphbPiuna1JdNatQyjVcswYmJOM/OHVcz7fTN79h7n9Td+AaB2rSr876078fR0c2bodmGxmBl5Vy9e/b8fmTFzJUNv6lTstq//rFa7666eJT47ODiAt968g4ce/pL1G/bz3sTfGHV3b1559QcMw+DGGzrQp0+LS29UyXXv3pwDB+P44cc17D8QC6haTUTkQopVsWa1Wkt8q1+//kX3PHr0KI8//jjfffcdHh4Xfsfgv8vgDcO4ZGn8pda4u7vj5+dX5CYiIiIiIiIVS3x8MjNmrgLgwQevKVFFyPDhXQD4c/4WkpLSHRJfZWBrA2mbr9a7DNtAFhhwbRsAFizcRm5uXpmffyUoaF/YtWvZtoEsEBTow6CzSe+p3y5zSgz2sGqV7fMY3rw21aoWfZ2pTp2q/Gfsjcz6+WnuGd2HgABvgoMDeO/duwkI8HZGuA7Rt08LatWqQlJSBrNmry/2dQXValdf3eqyq8qaNa3F+JeHYzKZmDV7Pffc9ymJiek0aBDC449dd1l7Vjbdzn4P2LvvBFarQbduzWjWtJaToxIRKZ/KbiLtv2zatIn4+Hjatm2Li4sLLi4uLF++nA8++AAXF5fCSrV/V57Fx8cXPhYSEkJOTg6JiYkXXCMiIiIiIiKV05dfLSInJ4+WLerSvYSzo1q2qEeTxqHk5OQx+9cNDoqw4jt06CQxR0/j5uZCly5l1wayQPv2DalaxZfk5AzWrNlb5ueXd7Gxiew/EIvZbKLzVU2cFseIW7phsZjZvPkQO6JinBZHaaw4m6Ds3r35BdcEBvow6u4+/DZnHD/OfIrQ0KCyCq9MuLhYuOvOngB8N30lWVk5l7xm166/q9VG3tmrVOf36N6chx+8BoCTJ5Pw8HDl/165xSmVmFeixo1DCa7uX/jxPaNUrSYiciFOS6z16dOHHTt2sHXr1sJbu3btuO2229i6dSv169cnJCSEhQsXFl6Tk5PD8uXL6dy5MwBt27bF1dW1yJrY2FiioqIK14iIiIiIiEjlc+BALL//sRmARx4ecMnOJ/9mMpkKq9Z++WWdqp0uU0EbyA4dGl1yvp0juLhYuOaa1gDM+31TmZ9f3q08W2XVokVdp1ZOhYQEcO3Zr9O33y5zWhyXKy0ti782HQQunlgrYDabr/iZahdydf9WhNYIJCkpvVhvSiiYgXn11a2oVav0M9BuvbUrw4d1wcPDlWefHky9esWf11bZmUwmeva0VRb36hlBo0Y1nByRiEj55bTEmq+vLxEREUVu3t7eVKlShYiICEwmE2PGjGHChAnMmjWLqKgoRo4ciZeXFyNGjADA39+f0aNH89RTT7F48WK2bNnC7bffTmRkJH376l0VIiIiIiIildXHn/yJYRj07hVBePjlzdTu0zuSqlV8OZ2QyqLFO+wcYeWwdJnz2kAWKGgHuXbdPs6cSXVaHOXRylW7AOjW9dLJIEe7/bYemEwmVq3ew4Gz852uFGvX7SUvL5+6datRt041Z4fjVC4uFu78R9VadnbuBdfu2nWUtWv32qVarYDJZOLxx65j/h8v0r9/K7vsWZncM7oPTz1xvWaLiohcgtMSa8Xx9NNPM2bMGB566CHatWvH8ePHWbBgAb6+voVr3nvvPW688UaGDRtGly5d8PLyYu7cuVgsFfOdPyIiIiIiInJxGzbuZ/2G/bi4WHjggasvex9XVxduuukqAGb+sBrDMOwVYqVw6NBJDh8+haurha5dnDO/C6BeveqEN69Nfr6VP+dvdVoc5U1KSiZbtx4GoFsJW6U6Qp06VQsTsN9OW+7kaEpmxUpbgrJ7N+cnKMuDa69pTXBwAAkJqcyZu/GC6wqr1frbp1rtn1xdXey6X2Xh7e3BTTddha+vp7NDEREp18pVYm3ZsmVMnDix8GOTycT48eOJjY0lKyuL5cuXExFR9F1uHh4efPjhhyQkJJCRkcHcuXOpXfvy3o0oIiIiIiIiV7b8fCsff/wnAEMGd6RWzdK9WHvjDR1wd3dl374TbN0abY8QK43CNpDtG+HjU/ZtIP/pugG2qrXf/9isBOlZa9ftJT/fSlhY9VL/PbGXO+7oAcDiJTs4dizBydEUT05OHmvX7gOUWCvg6urCXWe/lt9OW3HeqrVdu4/9Xa12l32q1URERMpKiRNrFouF+Pj4c+5PSEhQlZiIiIiIiIg41fwFW9l/IBYfHw/uHtm71Pv5+3sVzn6a+cOaUu9XmSxd6vw2kAX69GmBm5sLhw6dZO/eE84Op1xYdXa+Wreuzq9WK9C4UShXXdUEq9Vg2ncrnB1OsWzefIiMjGyqVvGlWbOazg6n3BgwoC3Vq/tz+nTKeecbfj15MQD9+7W0e7WaiIiIo5U4sXahd3ZlZ2fj5uZW6oBERERERERELkd2di5ffLkQgDvv6Im/v5dd9h12c2cAVq7azbHjV0YVjbNFR58k+nA8Li4WupaDxI2vr2dhNdH5XuSvbHJy8li7zlZlVR7mq/3TXXf0BGzVhfHxyc4NphgK2kB269YMs7lcNYZyKjc3F+64rTsA3367nNzcvMLHdu0+xpo1ezGbTapWExGRK1KxGw5/8MEHgK0941dffYWPj0/hY/n5+axYsYKmTZvaP0IRERERERGRYvj5l3XExycTXN2fm4deZbd969WrTqeOjVm3fh8//riGJ8Zcb7e9K6qly2zVau3bNyw3s3quu64tixZvZ8HCbTz6yADc3CrvDKbNW8pvlVWLFnVp1aoeW7ce5vsZq3j8seucHdIFWa1WVhZU/qkN5DkGDmzH1G+WcTI+mXm/b+bGGzoAf1erXd2/FbVrV3VmiCIiIpel2D9Fvvfee4CtYu2zzz4r0vbRzc2NevXq8dlnn9k/QhEREREREZFLsFqtzJq9HoCRI3vj7u5q1/2HD+/CuvX7mDdvE/fe08/pM8PKuyXlqA1kgXZtG1Ctmh+nTqWwatVueveOdHZITrNypS0Z1KVL03JZZXXnHT3ZunUKv87ZwJ139CAw0OfSFznBzl3HSEhIxdvbnbZt6js7nHLH3d2V227rzvsfzOObb5cx8Lq27Nsfq2o1ERG54hX7p6fo6Giio6Pp0aMH27ZtK/w4OjqavXv3Mn/+fDp27OjIWEVERERERETOa/OWaI4fP4OXlzv9+7W0+/4d2jckLKw6GZk5zJm70e77VySHj8Rz6NBJXFws5arNoMViLpyXN++PzU6OxnkMw2DV6vJdZdWxQyOaNqlJVlYuP/601tnhXNCKFbY2kJ2vaoKra+WtgLyYGwa1JyjIh7i4JP78cwuTJy8BoH8/VauJiMiVq8RvS1q6dCmBgYHk5OSwd+9e8vLyLn2RiIiIiIhIJWC1Wp0dQqX165wNAFzdvyWenvaf/20ymRg+rAsAP/60lry8fLufUVEsPVut1r5dA/z8ykcbyAIDrm0LwPr1+zh9OsXJ0TjHnr3HOXUqBU9Pt3JbZWUymbjzzh4A/PTzWtLTs5wc0bkMw2DFip0AhfP75FweHm6MuLUbAJ98Np/Va/aoWk1ERK54JU6sZWZmMnr0aLy8vAgPDycmJgaAxx57jDfeeMPuAYqIiIiIiFwJ/vhzC337v8LE938jN1dvQCxLSUnphZUjg65v77Bzru7fioAAL06eTGLFyl0OO+dKV5BY69Wz/LSBLFCnTlUiI+tgtRr8OX+rs8MpsaNHT5ORkV2qPRYs3AbYqsLs3TLVnrp3a07dutVIS8vil1nrnR3OOY4cOcXRYwm4ulro1Kmxs8Mp1wbf2JGAAG+SktIB6NevJXXqqFpNRESuXCVOrD377LNs27aNZcuW4eHxd0/5vn37MnPmTLsGJyIiIiIiciXIy8vn8y8WkJWVyw8/ruGhR77k5MkkZ4dVafzx5xZyc/Np2qQmTZrUdNg57u6u3HiDbQTCzB9WO+ycK1lMzGkOHIzDYjHTvXv5rOIpqFr7/Y9NGIbh5GiKb83avdwy4j2G3/ouS5buKHHsqamZvPJ/PzBzpu3Pbs9ymPj8J7PZzJ2326rWZsxcRXZ2rsPP3BEVw7p1+4q1tiC53q5tA7y9NXPxYjw9/65aU7WaiIhUBCVOrM2ePZuPPvqIrl27YjKZCu9v3rw5Bw8etGtwIiIiIiIiV4Jly3cSH5+Mr68nPj4e7Nx5lLtHf8T6DfudHVqFZxhGYRvIQde3c/h5QwZ3xMXFwo4dMezaddTh511pli6zVau1a9sAPz8vJ0dzfn16R+Lu7srhw6fYteuYs8MptilTl2IYBgkJqbzw4vc8/cy3xMUlFevazZsPceddHzB//tbCxEa/vi0cG7Ad9OvXkpCQABIT0/ntt78cetaSJTt48KHPeXLsFN763+xLVh4XVMmW1zl15c1NQzrRr28LHn7oWurWqebscEREREqlxIm1U6dOUb169XPuT09PL5JoExERERERqSwKqpduHnoVkyc9QuPGoSQlZfDkU1OY9PVi8vM1e81Rtm0/TEzMaTw8XOnXr6XDz6ta1a8wITFjZsWpWluwcBsPPvwFk6cs4cSJM5e1R2pqJosWbwegV6/yWw3l4+NBjx7hgK1q7UqwY8cRoqJicHW1MOLWbri4WFi9Zg+33TGRmT+svuD3mJycPD76+A8efXwSJ+OTCQ0N4tOP7+O+e/tdEa/huLhYuO1spdP3My/8PEtr5ardvPzKTKxWWxXg7F838NjjkzhzJvW860+dSmbX7mOYTCa6dW3mkJgqGk9PN14Zfwu33tLV2aGIiIiUWokTa+3bt2fevHmFHxf8IPbll19y1VVX2S8yERERERGRK0BUVAw7dx7F1dXC4Bs7UrNmEJ9/ej+Drm+PYRhM+noxT/1nauFsGbGvOXNsVSz9+rYss3Zsw4d3AWzVWRWh5Wd+vpWPPvqdbdsO8+VXixg67G0eePBzZs9eT0pKxkWvTU7O4Lff/uKpsVO47voJHCxoA1nOq3iuu7YNAAsXbS+TFoOl9d30lQBcc01rHnn4WqZOfoQWkXXJzMzh/Q/mce/9n7Jv/4ki1xw8GMc9937C9O9XYhgG1w9sx9QpjxIZWdcZT+GyDRjQFj8/T06cOOOQ2YbrN+znhRenk59vpX+/lrz5xh14e7uzbfsRRt/zCXv3Hj/nmpWrdgMQHl6bKlV87R6TiIiIlG8lTqy9/vrrPP/88zz44IPk5eXx/vvv069fP6ZMmcJ///tfR8QoIiIiIiJSbv3w4xrAltgpeIHV3d2VZ58ZzAvPD8Xd3ZUNG/YzctRHREXFODPUCiclJZMlS3cAMOj69mV2buNGobRpHUZ+vpWff1lXZuc6yl+bDnI6IRVfX0/at2uIyWRi+44jvPX2r1x/w+uMe24ay5ZHkZNja4135kwqs2ev5/ExXzNw0AQmvPELa9ftIy8vn7B61Xn6PzcSEODt5Gd1cW3b1ie4uj9paVkOSdbYU0zM6cJETkG1T1hYMJ98fC9Pj70BHx8P9uw5zuh7PuHjT/4gIyOb72esYtQ9H3PgYBwBAV68PuF2xj07BG8vd2c+lcvi6enGkMGdAJg+faVd5+Jt2XKIZ8dNIzc3n549wnnh+aF069qML794kDq1q3IyPpn7H/ycBQu3Fblu+dk2kOU9gSwiIiKO4VLSCzp37szq1at5++23adCgAQsWLKBNmzasXbuWyMhIR8QoIiIiIiJSLsXHJxfOlBo2rPM5jw+4tg1NGofy3PPfcfRYAg8+/AWPPjKAm4dedUW0YSvv5i/YQk5OHg0ahNC8ea0yPXvYsC5s3hLNr3M2cvfI3nh6upXp+fb05/wtAPTr24KxT93AqVPJLFy0nfnzt7L/QCzLV+xi+Ypd+Pp4UKduNXbvPlbYMg+gUcMa9OwZTq+eEdSrd+7oiPLIbDZz7bVtmDJ1Kb//vpl+fR3fRvRyzZi5CsMw6NqlKfXq/v35NZvN3HhjR7p2bcbE939jydIovpu+kp9/WUdWlq0Kr3PnJjz37BCCgq7sqqqhN3Xiu+kr2LnrKDt2xNCiRemr7nZExTD26W/Izs6lc+cmvDJ+OC4uFgDq1a3Ol188yPhXf2Dt2r2Mf2UmBw7Ecv99/cnIyGbz5kMA9OiuxJqIiEhlVOLEGkBkZCRTp061dywiIiIiIiJXlJ9/WUd+vpU2rcNo3Cj0vGsaNAjh60kPM+H1X1i6LIqJ7/+G1WrlluGaM1MahmEwZ66tDeQNg9qXeaKyS+em1KwZxPHjZ/j9j83cNKRTmZ5vLxkZ2SxfvhOAa65uDUC1av6MuLUbI27txsGDccxfsJUFC7cRH5/Mzp1HAWjWrBY9e9iSabVqVXFa/KUx4GxibcPGAxw7nkCtmuXveZxJTOP3PzYDMGJEt/OuqVrVj9f+bwSrV+/h7Xd+5WR8Mh4erjz2yABuuKFDhUjiBwX5cs01rZk79y+mf7+y1Im1PXuO8+RTk8nMzKF9u4b89/9G4Opa9CUyX19P3nrjDr74ciHfTlvOtO9WcPBgHJ07NyU/30pYverUrl21VHGIiIjIlanEibWUlJTz3m8ymXB3d8fN7cp9l56IiIiIiEhxZWXlMPvXDYCteulivL09eO3/bmXK1KV8+dUivvhyId27NSc0NKgsQq2Qdu48ysGDcbi5udC/X6syP99iMTPs5s68N/E3fvhhNYNv7IDZXOJpC063fMUusrJyqV2rCuHhtc95vEGDEB568BoeuL8/W7ZGE3sikbbtGlAjJNAJ0dpXrVpV6NSxMevW7+OrSYsZ/9IwZ4d0jl9+WUdOTh7Nm9WiZYt6F13bpUtTWrcOY8mSHbRqHVYuE4Wlcevwrsyd+xcrV+3m6NHTl53UOngwjjFPfk16ejYtW9bjjddvx93d9bxrLRYzDz5wNQ0ahPD62Zana9ftA6Cb2kCKiIhUWiX+qT8gIIDAwMBzbgEBAXh6elK3bl1efvllrFarI+IVEREREREpF/74cwupqZmEhgbRpXPTS643mUyMvKsXrVuFkZWVy9vvzLHrrKDKZs7cjQD07hWJn5+nU2K4bkBbfHw8OHosgbVr9zklhtL6809bG8irr2510coms9lM2zYNGDiwXYVIqhW4795+ACxcuI2DB+McckZ2di579x5n4aJtnDmTWuzrsrJyCmf4jRjRrViVZ15e7gwc2K7CJdUA6tWrTufOTTAMgxkzV1/WHoePxPPYmEmkpGQS3rw2b//vrmK1ce3fryWffXIfwdX9C+/rrjaQIiIilVaJE2tTpkwhNDSU5557jtmzZzNr1iyee+45atasyaeffsp9993HBx98wBtvvOGIeEVERERERJzOarXyw49rALh56FVYLMX71cpkMvH00zfi6mph3fp9LFy03ZFhVljp6VksWmz73N0wqL3T4vDycmfQ9bbzZ/ywymlxXK5Tp5L5a9NBAK7u39rJ0ThH06Y16d0rAsMw+PyLBaXayzAMTp5MYvXqPUz9Zhkvvvw9I25/j779X+Hu0R/z8viZ3Hv/Z8TGJhZrv3m/byY5OYPQ0CB6dA8vVWwVxYhbbO0w5/2+icTEtBJde+x4Ao89/jWJiek0bhzKu++MxNvLvdjXN2lSk0mTHqZ7t+b069uCpk3O3/5XREREKr4St4KcOnUq77zzDsOG/d0iYdCgQURGRvL555+zePFi6tSpw3//+1+ee+45uwYrIiIiIiJSHmzYcIAjR07ZqkOua1uia+vWqcbIu3rx5VeLmPj+b3Ts0Ah/fy8HRVoxLVi4jaysXOrVq1bqWUulddNNnZgxcxWbNh3iwIFYGjas4dR4SmLBwm0YhkHLFnWpWbPytiW9995+LF+xi1Wr97BjxxEiI0v2Z+rMmVTe/N9stm6JJjUt67xr/P29MJlMxMYm8vCjX/LRB/dctBVsfr6VGTNtydpbh3cpdvK+omvdOoymTWqyZ+9xZs1ez6i7+xTrupSUDMY8MZnTp1OoXz+Yie/eja9vyStdgwJ9eOP120t8nYiIiFQsJf7JbO3atbRufe472Vq3bs3atWsB6Nq1KzExMaWPTkREREREpBya+YOtDdn1A9vh7e1R4utvv607YfWqk5SUzkcf/2Hv8Cq8OXNsbSCvH9i+WO3xHKlGSCA9e9iqiWb+sMapsZSEYRj8UdgGsnJWqxWoW6caA65tA8Bnny8oUYtWwzD474SfWblyN6lpWVgsZurXD6Z/v5Y89OA1vPv2SH6d/Sy///Y8Uyc/Qp3aVYmLS+LhR7/i+PEzF9x3xcpdHD9+Bj8/TwYMKFnyviIzmUzcemtXAH76eR3Z2bmXvCY/38rL42dy4sQZQmsE8v57owgI8HZ0qCIiIlKBlTixVqtWLSZNmnTO/ZMmTaJ2bdug44SEBAIDK07PdRERERERkQLR0SdZv2E/JpOJoTdddVl7uLq68OwzgwFbS7OCdnxyaXv2HGfvvhO4ulq49prykRAaPtz2Qv+ChVtLNEPLmfYfiOXQoZO4ulro3SvS2eE43ai7e+Pm5sKWrdGs37C/2Nf9+usG1q7bh5ubCx9+MJrFC8cz7ZvHGf/ycG6/rTudOjWmWlU/TCYT1ar58+GH91CnTlVOnkzikUe/5NjxhHP2NAyD6dNXAnDTkE7FmgFWmfTqGUFwcABJSen8OX/rJdd/+dVC1m/Yj4eHK2+8fjtVqvg6PkgRERGp0EqcWHv77bd57733aNmyJffccw/33nsvrVq1YuLEibzzzjsAbNy4keHDh9s9WBEREREREWf78Sdbp47u3ZqVqn1eZGRdBt/YEYC3/je7WJUXAnPm2qrVenQPLzdVJ5ERdQhvXpvc3Hx+mbXe2eEUy59/bgWga5dm+PmVvCVeRRMcHMDgwba/j59/vgCr1XrJa44dS+CDj34H4IH7+9O2TQPc3C4+caNaVT8++uAe6tatxsn4ZB559CuOHSuaXNu+/Qg7dx3Fzc2Fm4Z0usxnVHG5uFgYPqwzAN/PWHnRr9XSZVF88+1yAMY9O+SKatUqIiIi5VeJE2uDBg1i3759DBgwgDNnznD69GmuvfZa9uzZw8CBAwF48MEHeffdd+0erIiIiIiIiDMlJ2cUts8bNqxLqfd78IGrqVrFl2PHEpgydWmp96voMjKyWbBwGwCDBrV3cjRFDR9u+/Pwy6z15T5JmpeXz8JFts/jNeWk6q88uPP2Hnh5urF33wmWLdt50bV5efm88n8/kJWVS5s29Rl2c+din1P1bHKtXr1qxMcn8/CjX3L06OnCx7/73latdu01rQkKUnXV+Vx/fXt8fDyIiTnNmjV7z7smOvok//3vTwDcektX+vVtWZYhioiISAVWosRabm4uvXr1Ijs7m9dff51ffvmFWbNm8frrr1OvXj0HhSgiIiIiIlI+/DpnI9nZuTRuHEqrlvVKvZ+PjwdPPnk9ANO+W8HBQ3Gl3rMiW7JkBxkZ2dSqVYU2rcOcHU4RPXuEE1zdn6SkdBaeTf6VV39tOkhCQir+/l506tjI2eGUG4GBPtxyi62t5xdfLiQvL/+Ca6d9t4KdO4/i7e3OC88NxWwu2fuWq1Tx5aMP7iGsXnVOnUrh4Ue/IibmNEdiTrFq1W5MJlNhLHIuby93bhjUAYDpM1ae83haWhbPjptGRmYObdvW58EHri7rEEVERKQCK9FPfq6urkRFRTl9OLSIiIiIiEhZy8vL5+dfbG0gh9/c2W6/F/XoHk63bs3Iz7fyxpuzyM+/dAu6yurXObY2kNcPbFfiRIajubhYuOnszL2ZP67BMAwnR3Rhf56tuuzbpwWurhdvXVjZ3HpLV/z9vYg5eprf/9h83jV79x5n0teLAXjyiUGEhARc1llBQb58+OE9hIVV5/TpFB559Es+PNtasmvXptStU+2y9q0sht18FRaLma1bD7Nr97HC+61WK6+8+gNHjyUQHBzAq+NvwcXF4sRIRUREpKIp8W8id955J5MmTXJELCIiIiIiIuXWkqVRnDqVQlCQD336tLDbviaTiaeeGISXlzs7dx5l9uwrY0ZXSeTl5ZeqPWJKSgbzF2xl566jWCxmrhvQxo7R2c+g69vj4eHKwYNxbNp00NnhnFd6RjbLV+wCbK0GpShvbw/uvKMnAF9PXnLOn9vs7Fxe/b8fyc+30rNnONdc3apU5wUF+vDRB/fQoEEIpxNSC9sajrilW6n2rQyqVfOnfz9be8fv/1G19vXkJaxeswc3Nxde/+9tBAb6OCtEERERqaBK/Na0nJwcvvrqKxYuXEi7du3w9i46LFqz1UREREREpKIxDIOZP6wGYMjgjri52bfKp3p1fx68vz/vvDeXTz9fQLduzale3d+uZzhLUlI6d478kDNnUqlTpyoNGoTQsEENGjYIoWHDEKpX9y9S/WcYBrGxiWzbfoTt2w+zfccRoqPjCx/v1rVZuZ075efnyXUD2vLzL+uY8cNq2rVrWCbnnklMIy42kWbNal2yknL58p1kZ+dSp3ZVmjWrVSbxXWmGDO7IzB9WEx+fzC+z1nPrP1oyfvbFAqIPxxMU5MPTY2+0S+VqYKAPH0wcxeNjvubAwTjCm9emRYu6pd63MrhleFf++HMLS5dGEftAIgcOxvH15CUAPP2fG2natKaTIxQREZGKqMS/DUZFRdGmje3dgfv27SvymFpEioiIiIhIRbRt+2F27z6Gq6uFG2/s6JAzbryxI38u2MrOnUd59725vPH67Q45p6xN+24Fp0+nAHD48CkOHz7F4sU7Ch/39fGgQcMQGtQPITExje07YgrX/1Od2lVp2bIeI0f2KrPYL8ewmzvzy6z1rFmzlyMxpxzWzs8wDDZvOcTs2RtYvmIXeXn5dOrYmLFPDSI0NOiC1xW0gbz66lb6Hf4C3N1dGT2qD6+/8QvffLuMQde3w9vbg782HWTmTFuCfdyzQwgI8L74RiUQGOjDhx/cwy+z1tG7d6S+NsXUqFEN2rdvyMaNB3j/g3ls2myrFB16UycGXFs+K1tFRETkymcyynPj9zKSkpKCv78/ycnJ+Pn5OTscEREREREpZx5/4ms2bjzAoOvb8+wzgx12zsGDcYwc9ZFt3trrt9O9W3OHnVUWTp9OYeiwt8nJyeOlF28mwN+bAwfjOHAwjoMH4zh8OP68M+UsFjNNm9akRWRdWrSoR2RkHYKuoHZuTz/zDatW72HwjR35z9gb7Lp3SkoGv/+xmdm/biAm5nTh/WazCavVwMPDlXtG9WXYsM7nzJWKj09m8E1vYRgGP//4H2rUCLRrbBVJXl4+t9/5PjExpxl1d2+GD+vCnXd9wMn4ZG4Y1J5nnnbc9wEpmfUb9vPEk5MLP27Zoi4ffnCP5qqJiEghvf4v9qYpxSIiIiIiIhexIyqGjRsPYLGYuevOng49q0GDEEbc2o1vpy3no4//4KpOjXF1vXJ/bZv6zTJycvKIjKzD1f1tFVKdOjUufDw3N4/Dh09x4GAchw6dxNvbnZYt6tKsWS08PNycGHnpDB/ehVWr9/DHn5u5/75++Pl5lWo/wzCIOjt/b/GSHeTk5AHg5enG1Ve34oYbOuDu7spbb81my9ZoPvrkDxYs2sYzT99Is6Z/t3ucv2ArhmHQqlU9JdUuwcXFwn339OOFl75nxoxVHDgQx8n4ZGrWDOLRRwY4Ozz5hw7tG9KgQQgHD8ZRtaofr/3fCCXVRERExKEu6ze0jRs38uOPPxITE0NOTk6Rx3755Zdi7/Ppp5/y6aefcvjwYQDCw8N56aWXuPbaawHbLw+vvPIKX3zxBYmJiXTs2JGPP/6Y8PDwwj2ys7MZO3Ys33//PZmZmfTp04dPPvmEWrXUK15EREREREpvyhTbvJ5rr2ldJsmIO+/sybzfN3HsWAI//7KOW4Z3vfRF5VBsbCK/ztkIwP339j9vaztXVxcaNapBo0Y1yjo8h2rTuj4NG4Rw4GAcs3/dyJ139LjsvbZtO8w7787hwMG4wvsaNazB4Bs70K9/K7y93Avv/+jDe5g3bxMffvwH+/ad4N77PuXmoZ25956+eHq68ed8WxvIa65ufflPrhLp2TOcJo1D2bvvBCtW7sJsNvHSi8Pw+sfnXJzPZDLx1JPXM3XqMu6/rz9VqpTPGYwiIiJScZhLesGMGTPo0qULu3btYtasWeTm5rJr1y6WLFmCv3/JhmvXqlWLN954g7/++ou//vqL3r17c8MNN7Bz504A3nrrLd59910++ugjNm7cSEhICP369SM1NbVwjzFjxjBr1ixmzJjBqlWrSEtLY+DAgeTn55f0qYmIiIiIiBSxa/cx1q7bh8Vi5k4HV6sV8PZy5757+wEwefISkpMzyuRce/t68hLy8vJp17YBbdrUd3Y4ZcpkMnHLLbaE6HffLSchIfUSV5xfamomz73wHQcOxuHm5sKAAW348vMHmTL5EW68sWORpFrBuQMHtuP76U/Qv19LrFaDmT+s5rY73mf69yuJjo7Hzc2FXj0jSv0cKwOz2cz99/cv/Pj223oQGVHHiRHJhbRqGcZ7795N06Y1nR2KiIiIVAIlTqxNmDCB9957j99++w03Nzfef/99du/ezbBhw6hTp2Q/YF5//fUMGDCAxo0b07hxY/773//i4+PDunXrMAyDiRMn8vzzzzNkyBAiIiKYOnUqGRkZTJ8+HYDk5GQmTZrEO++8Q9++fWndujXTpk1jx44dLFq0qKRPTURERESkXMrLy+eRR79kwMDXeP/DeRyJOeXskCqNgmq1/v1aUqtmlTI797oBbWnYIITUtCwmTV5cZufaS0zMaf74czMA99/X/xKrK6b+/VrStElNUtOymPjBb5e1x+dfLCAxMZ26dasxZ/Y4XnhuKOHhtc9b/fdPQYE+jH95OO++PZIaNQI5eTKJjz/5E4CuXZri6+t5WfFURh07NOLWW7oy4No2jB7V29nhiIiIiEg5UOLE2sGDB7nuuusAcHd3Jz09HZPJxBNPPMEXX3xx2YHk5+czY8YM0tPTueqqq4iOjiYuLo7+/f/+Jczd3Z0ePXqwZs0aADZt2kRubm6RNaGhoURERBSuOZ/s7GxSUlKK3EREREREyqvffvuLzVuiSUrKYObM1dw64j0eeewrFi/eTm5unrPDq7D27jvBqtV7MJtN3HVnrzI922Ix89ijtjlOs2at5/CR+DI9v7S+mrQIq9Wga5emhIfXdnY4TuHiYuGZZwZjsZhZvHgHq9fsKdH1u3YfY9bsDQCMfWoQfn4lT4Z16tSYad88zohbu2Gx2H79H3hduxLvU5mZTCYefWQALzw/9IqedygiIiIi9lPixFpQUFBhK8aaNWsSFRUFQFJSEhkZJW9RsmPHDnx8fHB3d+eBBx5g1qxZNG/enLg4W//44ODgIuuDg4MLH4uLi8PNzY3AwMALrjmf119/HX9//8Jb7dqV8xc9ERERESn/0tOz+OIrWzeGwTd2pGvXZpjNJjZvPsSLL8/gxiFv8tnn8zlx4oyTI614Jk+2Vav17duSOnWqlvn57do1pGuXpuTnW/n44z/L/PzLdeBALIsWbwfg3nv6OTka52rSOJThw7oA8PY7c8jIyC7Wdfn5Vt5++1cMw+Dqq1vRtk2Dy47B09ONRx6+lm+mPMp7795Np06NL3svEREREREpQWJt1KhRpKam0q1bNxYuXAjAsGHDePzxx7n33nu59dZb6dOnT4kDaNKkCVu3bmXdunU8+OCD3HXXXezatavw8X+3uDAM45JtLy61Zty4cSQnJxfejh49WuK4RURERETKwtRvlpGUlE6dOlV5YsxA3nrjDn764T/cPbIXVav4kpiYzjffLufm4e/w5FNT2Lz5kLNDrhD2749lxcpdmEwmRpbRbLXzefjha7FYzKxes4eNGw84LY6S+HKSLRHcp3ckjRrVcHI0zjd6VJ/CdoxfflW8kQWzZq9nz97j+Pp48OjD19oljrCwYDp2aGSXvUREREREKrNiJ9amTp1KZmYmH330EbfccgtgS1CNHTuWkydPMmTIECZNmlTiANzc3GjYsCHt2rXj9ddfp2XLlrz//vuEhIQAnFN5Fh8fX1jFFhISQk5ODomJiRdccz7u7u74+fkVuYmIiIiIlDcnTpxh5g+rAXj04QG4uFgACAkJ4N57+vHLz08z4b8j6NChEYZhsG79Ph4bM4ldu/TGsdKaMnUpAL17R1CvXnWnxVG3TjWGDO4IwAcf/U5+vtVpsRTHrl1HWblyN2azidGjS/7Gy4rI09ON/zx1AwA//rSGXbuPXXT96dMpfP7FAgDuv78/QUG+Do9RRERERESKr9iJNcMwAFsryNDQUNvFZjNPP/00c+bM4d133z2nJePlMAyD7OxswsLCCAkJKayOA8jJyWH58uV07twZgLZt2+Lq6lpkTWxsLFFRUYVrRERERESuVJ9+Np/c3HzatW1A585NznncxcVCzx4RTHz3bn6Y8RRXXdUEq9Vgwhu/aPZaKRw8FMfSZbaW9yPvKtvZauczelQffH09OXgwjt/mbXJ2OBf1+Ze2382uuaY19eo6LyFZ3nTq1Jj+/VpitRq8+eYs8vLyL7j2w49+Jz09m6ZNa3LDoA5lGKWIiIiIiBRHiWasXaoFY0k999xzrFy5ksOHD7Njxw6ef/55li1bxm233YbJZGLMmDFMmDCBWbNmERUVxciRI/Hy8mLEiBEA+Pv7M3r0aJ566ikWL17Mli1buP3224mMjKRv3752jVVEREREpCxt336ExUt2YDKZeOzRAZf8WbxWrSq8+PxQAgK8OXToJN98u7yMIq14pk5dBkDPnuE0qB/i3GAAPz8vRt3dG4AvvlxAenqWkyM6vy1bDrFx4wFcXCyMvlvVav/22GPX4efnyf4DsYWVqP+2ceMBFi7ajtls4umxN2KxlHgsuoiIiIiIOJhLSRY3btz4kr/QnzlT/KHpJ0+e5I477iA2NhZ/f39atGjBn3/+Sb9+tgHXTz/9NJmZmTz00EMkJibSsWNHFixYgK/v360w3nvvPVxcXBg2bBiZmZn06dOHKVOmYLFYSvLURERERETKDavVygcfzgNg4MC2NGxYvDlVAQHePPnE9bz08gymfrOs3CSGriSHj8SzeMkOoHxUqxUYMrgjv/yyjqPHEvh22nIeuP9qh56Xk5NHVFQMGzbuZ8/eE9QPC6ZH9+ZERNQ5b7LHMAy+OFutdv3AdtSoUfpuJhVNUKAPjz4ygP9O+JmvJi2mZ48IatYMKnw8JyePd96dA9i+3k2b1nRWqCIiIiIichEmo6DH4yWYzWYmTpyIv7//RdfddddddgmsLKWkpODv709ycrLmrYmIiIiI081fsJVXXv0BL0+3/2/vvqOjqr42jn8nlTTSgIRAEIHQm1KldxDpIB1EUHqTJvpTAQsIKtKk9yIoIgjSexGB0Ks0Qw8thISQnrnvH0hekRZgkknC81krC+bOuefuO8lOOXvOOfy0qD/e3knfY8kwDAZ/PJ/t209QoEB2pkzqkrg3mzzdsC9+Zu3ag1SsWICRI9pZO5wHbNt+nMEfzcfBwY6FCz6waPHKMAyCgq6zJ/A0gYFnOHAwiOjouIfaeXq6ULFCQSpXKkiJErlxcLj3Xs1du07Rb8BsHBzsWPzzADJn0t9Vj2IYBr36zGD//r8pVSoPY0a/m/jm1VmzNzFt+ga8vd1YuOADXF0zWDlaERERkfRB4/9iac80Y61ly5ZkyaJ18kVEREREkkt0dCyTJq8FoF27Ks9UVIN7y7cP6N+QAweCOHHiEj//vJPWrSsmR6jpzsWLN1m//hAAHTtUs3I0D6tYoQCvv56L/fv/ZtLktXw+rOUL9WcYBlu3HWP79hME7j3LzZvhDzzv5eVKqVJ5KFTQn6PHLrJz51+Eht5l+YpAlq8IxNnZkTfeyEvlSoX48cftADRtUlZFtScwmUx8OLAR7d4ZR2DgGdauO0id2q9x6XIIc+ZuAaBXz7oqqomIiIiIpGJJLqxZen81ERERERF52MJFO7h+PQwfHw9atij/XH1kzpSRXj3rMuLrX5k6fT0VKxbA3z+ThSNNf+bM3YLZbFC+XH7y5Ut9y/Dd32/v3Y4/sGHjYd5+uxxFCud47v5+/XUX332/IvGxo6M9xYvlpFSpPJQulYfcuX0T/w5s1vQN4uLiOXAwiK1bj7N9+3Fuhtxh48YjbNx4b+lMZycH2rap9GI3+RLw98/Eux2qMWXqOsaNX0nZMnkZPXoFsbHxlCyRm5o1ilo7RBEREREReYIkF9aSuGKkiIiIiIg8p5s3w5m/YBsA3brWxtHR/rn7qvdWCTZsOEzg3jOMGPkrE8a9h43Nw3tjyT2XLoewdt1BAN7tkHr2VvuvvAF+vFX3dX5fuY9x41YyZXKX5/q8RkbGMGPWJgDq1n2dOrWKU6TIK0/8mrO3t6N0qQBKlwqgf7/6HD9+ia3bjrNt2zEuXgqhQ4dqeHq6Pve9vUxat6rA+g2H+Pvva/TqM4OzZ69ib2/LgP4N9aZWEREREZFULsl/gZnNZi0DKSIiIvKSMQyDw4fPM+qbZTRr/i2/Lt1l7ZDStanT1hMVFUuhQv4vPGvFZDLx4aBGZMhgz8GD51j22x4LRZm+xMXFEx4exezZm0lIMFO2TF4KFvS3dlhP1Pn9mjg5OXDs+EXWrD34XH38vHgnt2/fJXt2bwYPakzJknmeqZBrY2ND4cI56NG9DosW9mPt6k81W+0Z2NvbMXhQY0wmE2fPXgWgbZtK5MihmaUiIiIiIqndM+2xJiIiIiIvh/MXbrB27UHWrTvIleDQxONjx62kRIncvJIjsxWjS59OnrrCylX7Aejd6y2LzFrx8/Oia5fajBn7OxMnrqHcG/nx9fV44X5To+joWG7dirj3EXrv39B//g25dYfw8CiiomKJioohKjKWyKhYoqJiiY9PeKCfd99NfXur/VemTBl5t0M1Jk5aw4QfVlOxQgHc3JySfH54eCQ/Lry3J9p7nWpgZ2f7QvGYTKZnur7cU7hwDpo2KcMvS3bh5+dF+3ZVrB2SiIiIiIgkgQprIiIiIgLArdAINm48zJq1Bzlx4lLicWcnB6pUKUxwcCgHDgYxctRSLStoYYZhMH7CKgzDoEb1oi+0b9Z/NWtalo2bDnPkyAVGfbOM7759J10tNTd9xgYW/fQHkZExL9SPvb0ttWsVt+hrn5xaNC/HylX7OH/+BtNmbKBf3/pJPnfBj9uJiIgmd25falQvkoxRytP06P4mvj6elCuX74WWfhURERERkZSjwpqIiIjIS+7GzXC++fY3/vzzJAkJZgBsbW0oXTqA2rWKU6liATJkcCD4aiht2o7h4MFz/L5yHw3ql7Jy5OnHtu0n2L//bxwc7OjWrbZF+7axseGjwU3o8O4Edu0+xZo1B3jzzdcteg1r+euvy8yavTlxP2gHBzu8vFzx8nTFy8sVz3/9393dBRdnR5ycHHBydsDJyQFnp38eOzm88KytlGZvb0e/vvXp88FMfv11F/XfKklAQNannhcScoefF+8EoMv7NVUgtzJHR3tat65o7TBEREREROQZqLAmIiIi8hK7du02PXtP5/LlWwAUKJCd2rWKU6NGUbw8XR9om9XXk87v12Tc+FX88MNqypfLj7e3mzXCTldCQu4w6pulALRsUZ6svp4Wv0bOV7LQ8d1qTJ6yjjHjVlK6dECa/9yZzWZGj1mBYRhUr16EwYMa4+zsmK5m4z1NqVJ5qFa1MJs2H+W70cuZNLHzU+9/ztzNxMTEUaiQP+XL50+hSEVERERERNIPvT1RRERE5CUVHBxKj57TuHz5Fn5ZPZk3pzczpnWn+dvlHiqq3des6Rvkz5eNOxHRjBn3ewpHnP6YzWY+/2IxoaF3yZ3bl3c7JN/+Xq1bVSRvXj/u3Iniu++XJ87ySqvWrj3I0aMXcHJyoHfPuri4ZHipimr39epZlwwZ7Dl85Dxr1hx4Ytvg4FCW/RYIQNcutV7K10tERERERORFqbAmIiIi8hK6dDmE7j2ncSU4lOzZvflhwvvkzu371PPs7Gz58MPG2NrasHHjEf7Y+VcKRJt+zZu/jcC9Z8iQwZ4vhrVM1j2W7Oxs+fijJtja2rBly7GnFmFSs7t3o5k4eS0AHd6pSubM7laOyHp8fDwSC7ITJq7mzp2ox7adMWsj8fEJlCqZhxKv506pEEVERERERNIVFdZEREREXjIXLtykR89pXLt2mxw5MvHD+Pfw8fFI8vn58vrRonl5AL79bjmRkTHJFGn6dujQOaZNXw9Avw8akDNnlmS/Zt4APzp1rA7Ad6OXc+lSSLJfMznMmr2ZkJA7+Gf3TvxafJm1bFGeHDkyERp6l+kzNjyyzblz1xOLqV0610zJ8ERERERERNIVFdZEREREXiLnzl2nZ69p3LgRzqs5s/DD+Pefa7ZPp47VyZrVk2vXbjPtMQP58nhhYZEMGfYTZrNBrVrFeavu6yl27XZtK1O8eE4io2IZOuwn4uMTUuzalnDu/HV++vkPAPr0qYeDg7aNtre3o98H9QFY8usuTp8OfqjNtOkbMJsNKlUsSMGC/ikdooiIiIiISLqhwpqIiIjIS+Ls31fp0WsaN0PukDu3L+PHv4e3t9tz9eXk5MDAAQ0BWLx4J8dPXLJkqOmaYRh8NWIJ16+H4Z/dm4EDGqboXle2tjZ89klz3FwzcPzEJWbM3Jhi135RhmEwZuxKEhLMlC+Xn3Jv5LN2SKlG6VIBVK1SGLPZYPR/9tA7efIym7ccxWQy8f77NawYpYiIiIiISNqnwpqIiIjIS+D06WB69Z5OaOhdAgKyMn5sJ7w8XV+oz7Jl8lKrVnHMZoORI5emuZlP1vLz4p3s2HECe3tbvviiFS7Ojikeg6+vB4MGNgJg7rytHDgYlOIxPI9t20+wZ89p7O1t6dP7LWuHk+r07lWXDBnsOXT4PGvWHkw8PnXavSVHa9YsRu5cT99LUURERERERB5PhTURERGRdO7kycv06jOd27cjyZ8/G+PHdsLDw8UifffuVZeMGZ04fSY4cXk+ebwTf13ih4lrAOjVsy55A/ysFkv16kWpW/d1DMPg889/Jjw8ymqxJEVMTBzjxq8EoFXLimTP7m3liFIfHx8POrxTDYAfJq4mIiKag4eC+HPXKWxtbXjvn/31RERERERE5PmpsCYiIiJWFRoawbjxqxj04VxCQu5YO5x0JT4+gQU/bqNr96mEh0dRqKA/Y7/vSMaMzha7hpenK7161gVg+oyNXL58y2J9pzd370bz2ZBFxMcnULlSQZo2KWvtkPigb32yZfPi2vUwvvl22QPLBya38PBIxo1fxYBBc/j9971ERcU+sf2PC7cTHBxK5swZead9lZQJMg1q1bI8OfwzcetWBNNnbGDKlHUA1K9XUsVIERERERERCzAZKfnXcyoVHh6Ou7s7YWFhZMyY0drhiIiIvBSiomL56ec/mL9gG5GRMQBUKJ+fkV+3S9H9ptKr4ycuMXLUUk6fDgagVKk8DP+yNS4uGSx+LcMw6N13Bvv2/U3p0gF8/10HfQ7/wzAMhgz9iQ0bD+Pj48GcWb3ImNHJ2mEBcPz4Rbp0m0JCgpn/fdyUt+qWSNbrJSSYWbEikCnT1hMWFpl43NU1A3XqvEajBqXJlcvngXOCr4bSus0YYmLiGDa0BTVrFEvWGNO63XtO80G/WYmPHRzsWPxTfzJndrdiVCIiIiIi1qHxf7E0O2sHICIiIi+X+PgEfl+5j5kzN3LznxlqAXmycu78dXb88Rdr1hzgzTdft3KUye9uZAzbth7DZGPCKYMDTs4OODk54pTB/t6/zg44ZXAgQwb7ZypSRUbGMG36Bhb/shOz2cDNzYlePevyVt3Xk63YZTKZ+HBgY9q2H8uePadZveYAdV+Cz+GzWPH7XjZsPIytrQ2fD2uZaopqAAUL+vNepxpMmbqO0d+voFjRnMk2s+nQoXOMHrMiseCbK5cPVSoXYu26g1y+fItffvmTX375k2LFctKoYWmqVC6Eo6M9EyasJiYmjteKv0qN6kWTJbb0pEzpAKpUKcSWLccAaNqkrIpqIiIiIiIiFqIZa6hiLSIikhIMw2DbtuNMmrKWCxduApA1qydd3q9JjRpFmb9gO5OnrMXVNQML5vVJ94PAX371C6tW739qO3t7W4oWfYWyZfJSpnQAuXP7PrZAtmPHCb4bvZxr18MAqFWrOL171cXL09WisT/O3HlbmDxlHQ4Odkye2IX8+bOlyHWTS1hYJD17T8dsNlO7VnFq1ixGVl/PZ+ojMjKGHX/8xYivfyUmJo5uXWvTrm3lZIr4+SUkmOndZwYHDgZRoEB2pkzqgp2drcX6v3EjjB8mrmHd+kMAuLlm4P33a9KoYWns7Gwxm83s3XeWZcv2sH3HCRISzAC4uztT7o18rF5zABsbE7Nn9iRPnqwWiys9u3r1Nu3eGYutrQ2LfuxnsX0VRURERETSGo3/i6WpsIYSS0REJLkdOnSOHyat4ejRC8C9wfIO71SlcaMyODjcm0AfH59A125TOH7iEm+Uzcu337yTbpcTvHjxJq3afI/ZbFCiRC5iYuKJjoolMiqWqKgYoqPjHrvfVKZMGSlTOoAyZQIoXSoPGTM6c/NmON+P+Z3NW44C4JfVkwEDGlK2TN6UvC0SEswMGjyPP/88SebMGZkxrTuZMqXd363uFwr/7bXir1K7dnGqVimMm9ujZ51FRETzx86/2Lz5KLt2nyI2Nh64N4vou2/fwcYmdW5zfO3abdq/M447EdG0b1eFrl1qvXCfMTFx/PTzH8yZu4WoqFhMJhMNG5Ti/fdq4PmYgu+Nm+H8/vteflseyPV/isQAzZqWpd8HDV44ppfJ9ethmGxMZE7DeSgiIiIi8qI0/i+WpsIaSiwREZHkcuHCTX6YtJrt208A4OhoT8sW5WnTuhKurg/v9XXu3HU6dJxAbGw8Hw9uQr16JVM65BTx+ReLWbP2ABXK52fUyPaPbGM2m4mJiefa9dsEBp5h1+7T7N//NzExcYltbGxMFMifnfMXbhAREY2trQ0tW1SgU8dqZMjgkFK384CIiGg6d53EuXM3KFTQnwnj38PR0d4qsbyI+PgE3m7+Ldeuh1G/fkkuXwph/4GgxOcdHOwoXy4/tWsX542yeYmKimXb9hNs2XqUwMAzxMUlJLbNls2LalWL0K5t5Ud+3acmmzYd4ZPPFmIymRg/thOvv57rufs6cDCI4SOWcPnyLQCKFMlBv771yZcvaTMZ4+MT2LXrFL8tDyQmJo4vv2idqpbQFBERERGRtEHj/2JpKqyhxBIREbG0sLBIZszayNKlu0lIMGNra0O9t0rQsWP1p86c+PHH7UyYuBoXF0fmzemDr69HygSdQi5cuEnrtvdmq82c3uOZlkuMiYnj8OHz7Np9it17TvP339cSn8ufPxuDP2xM3gC/5Aj7mVy6FEKn9ydy504UtWsX57NP3k5zsw83bznK/z75EQ8PZ5Yu+RBHR3uuXr3N+g2HWLP2AEFB1xPburpmICoqNnH5QoBXXslM1SqFqVqlMHnyPH75ztToq+FLWLlqHx4eLkyb0o1s2byeuY+zZ6/SpetkIqNiyeTtRo8eb1KrZrE09TqIiIiIiEj6oPF/sTQV1lBiiYiIWEpsbDy//PIns+duJiIiGoBy5fLRo1sdXn3VJ0l9JCSY6dZjKkePXqBUqTyMGf1uuhqMT8pstaS6fj2MPYFncMpgT5UqhbG1TT1LDO7dd5YP+s0iIcFM9251aNumkrVDeiY9ek7jwMEg3mlfhS6dH1wS0TAMTp8JZs2ag6zfcIiQkDsA5MntS9WqhalSuVCSv95To6ioWLr3mMrJU1fImTMzUyZ1feyyl49y+/ZdOr0/keDgUEqUyMXXI9rh4uyYjBGLiIiIiIg8nsb/xdJUWEOJJSIi8qIMw2Dz5qNMnLSGK8GhwL0iQ6+edSlVKs8z93fhwk3adxhHbGw8gwY2olHD0pYO2SpeZLZaWrRkyZ989/0KTCYTo75uR/ny+a0dUpKcORNM+w7jsbW1YcnigWTJ4v7YtgkJZo6fuISHuzP+/plSMMrkdeNGGO91nsSNG+GULJGb0d91wM7O9qnnxcXF0/eDWRw4GES2bF7MmNadjBmdUyBiERERERGRR9P4v1ha6nlbs4iIiKRJR49eoGv3KXzy2UKuBIeSyduNjwc3YdbMns9VVAPIkSMT3brWBmDChFUE/1OsS+tmz9mM2WxQoXz+dF9UA2jSpCyNG5XGMAyGDF30wNKVqdniJX8CULlSwScW1QBsbW0oUjhHuiqqAWTO7M43o9rj5OTA3n1n+ea733ja+/EMw2D09ys4cDAIZ2dHRn3dTkU1ERERERERSXdUWBMREZHntmXrUTp3ncyRIxfIkMGeju9WY9HCftSrV/KFlyV8u9kbFCuWk8ioWL4asQSz2fz0k1Kx8xdusG79QQA6vlvdusGkEJPJxAd96/P6a68SGRXLoMHzCAuLtHZYTxQeHsm6dYcAaNbsDStHY115A/z4fGhLbGxMrFixl4ULdzyx/ZJfd/Hb8kBMJhOfD2uZppfDFBEREREREXkcFdZERETkuYSHR/Htd8sBqFqlMD8t7Md7nWrgbKG9lGxsbPjfR03JkMGe/fv/ZunS3Rbp11oSZ6tVKPBSzFa7z87Oli+/aI1fVk+uXLnF/z5ZQHx8grXDeqwVv+8lJiaOgDxZKVY0p7XDsbry5fPTq2ddAH6YtIatW489st3evWcYO24lAD261aHcG/lSLEYRERERERGRlKTCmoiIiDyXiZPWcOtWBK+8kpkhnzUnc+YnL5n3PLJn96Z7tzrAvUH9S5dDLH6NlHD+wg3Wr783C6rTu9WsHE3K8/BwYdTI9jg7ObD/QBDfj1lh7ZAeKSHBzK//FHCbNXsDk8lk5YhSh+Zvl6Npk7IYhsHQz3/mxF+XHnj+4sWb/O/ThSQkmHmzzmu0alXBSpGKiIiIiIiIJD8V1kREROSZHTgYxPIVgQB8OKgRDg52yXatJo3L8PprrxIdHcdXw5ek6tlOj/Pv2Wr58r08s9X+LVcuH4YNbYnJZGLpsj2sWr3f2iE95I+dfxEcHErGjE7UqlnM2uGkGiaTiT6936JsmbzExMQx6MN5XLt2G4CIiGgGDZ7HnTtRFCrkz6CBjVSQFBERERERkXTNqoW1ESNGUKpUKdzc3MiSJQuNGjXi5MmTD7QxDIOhQ4fi5+eHk5MTVapU4dixB5egiYmJoVevXmTKlAkXFxcaNGjApUsPvpNWRERELCMmJo6Ro5YC0LBBKYoXezVZr2djY8PHHzXFycmBQ4fOMWDQXO7ciUrWa1rSyz5b7d/Kl8/Pe53u7S83evRyLl1KXTMQf/nlTwDq1yuFo6O9laNJXezsbPni85bkzu1LSMgdBv6Th58NWcT58zfIksWdr4e31esmIiIiIiIi6Z5VC2tbt26lR48e7Nq1i/Xr1xMfH0+tWrW4e/duYptRo0YxevRoJkyYQGBgIL6+vtSsWZM7d+4ktunbty9Lly5l0aJF7Nixg4iICOrVq0dCQtp7R7uIiEhqN2/+Vi5cuIm3t1viMo3Jzc/Pi2FDWpAhgz179pymc9fJaWZZSM1We1D7dlUoXjwnkVGxDB32k8VnIEZGxnDmTDBbtx7j58U7H1q28HGCgq6xd99ZbGxMNGlSxqIxpRcuLhn4ZmR7vLxcOXP2Kq3bjmHX7lM4OtozckRbvL3drB2iiIiIiIiISLIzGYZhWDuI+27cuEGWLFnYunUrlSpVwjAM/Pz86Nu3Lx9++CFwb3aaj48PI0eOpEuXLoSFhZE5c2bmzZtHixYtALhy5Qr+/v6sWrWK2rVrP/W64eHhuLu7ExYWRsaMGZP1HkVERNKyoKBrvPPuBOLjE/jyi1ZUq1okRa9/8uRlBg2ex40b4bi7OzP8qza8Vjx5Z8y9iPMXbtCm7RjMZoNZM3qosPaPq1dv806HcdyJiOad9lXo0rnWM/dx4cJNjh67wJUrt7h0+RZXrtzi8uUQQkPvPtDOZDLRvl1lOnWsjp2d7WP7++bb31i6bDeVKhbk6xFtnzmel8nxE5fo0XMaMTFxAHz5eSuqVUvZ7wUiIiIiIiJJpfF/sbTk2xDlOYSFhQHg5eUFQFBQEFevXqVWrf8fbHF0dKRy5crs3LmTLl26sG/fPuLi4h5o4+fnR+HChdm5c+cjC2sxMTHExMQkPg4PD0+uWxIRkWQUExPHuvWHuH377hPbOTjYUbVKYbJkcU+hyNIns9nMyFHLiI9PoEL5/FStUjjFY8iXLxvTp3Xnw8Hz+Ouvy/TpO5NBAxtR760SKR5LUsyardlqj+Lr68GggY34dMgi5s7bSunSAc9UIF2z9gBffvULZvOj3x+WMaMT2bJ54+TkwP79fzNn7hb27jvLsCEt8PPzeqh9REQ0a9YeAODtt994vpt6iRQskJ1hQ1vw/fcrePvtciqqiYiIiIiIyEsl1RTWDMOgX79+VKhQgcKF7w3UXb16FQAfH58H2vr4+HD+/PnENg4ODnh6ej7U5v75/zVixAiGDRtm6VsQEZEUFBkZw6AP57L/QFCS2k+fsYE+vevxVt3XMZlMyRxd+vTb8kAOHzmPs5MD/fs1sNrrmDlTRiZOeJ8vv/qFTZuPMnzEEs6du063rrWxtU3eVa4TEsyEhd3l1q0IwsOjMHj8xP/w8Cg2bPhnb7WO1ZM1rrSoevWi7Np9mpWr9vH55z8zZ3ZvMmZ0eup5v6/cx4ivf8UwDAoWyE6ePFnJls2LbH5eZMvmhZ+fF25u/9/Pho2HGfXNMo4du8g7745nYP+G1KpV/IE+V67aR1RULLly+fD6a7ksfavpUqWKBalYoYC+n4qIiIiIiMhLJ9UU1nr27Mnhw4fZsWPHQ8/99w92wzCe+kf8k9p89NFH9OvXL/FxeHg4/v7+zxG1iIhYw9270fQfMOdekcfZkSqVC8ETfiycPXOVk6euMHzEErZuPcaHgxqRKVP6nvpvGAaGYWBjY5lC042b4UyctAaAzp1r4ePjYZF+n1eGDA58PqwlOXNuYuasTfy4cDsXLt5k6GfNcXZ2fKG+79yJYs3aA1y9eptboRHcuhVB6K0IboVGcPv23cfOknqcihULkC+v3wvFlF590Lcehw6f49KlEL75dhmfD2v5xN/xlv22h1HfLAOgcaMy9O9X/6lf4zWqF6VQQX+Gfv4TR45cYOjnP7N7z2n69WuAi7MjZrOZX5b8CUCzJmVVKHoGeq1ERERERETkZZQqCmu9evVi+fLlbNu2jezZsyce9/X1Be7NSsuaNWvi8evXryfOYvP19SU2NpbQ0NAHZq1dv36dcuXKPfJ6jo6OODq+2KCbiIhYR0RENB/0n8WxYxdxdc3AmNHvUrDgk98ckZBg5seF25k+YwN/7PyLNu3G0v+D+tSsWSxdDgzv3/83341eTvidKDq0r0LDhqWfuLdUUnw/ZgV378ZQsEB2mjYpa6FIX4yNjQ3vdapBjhyZGT5iCTt2nKBrtymMGtkeX1+P5+ozLCySXr2nc+bso2e93+fh4UzGjM7YPqWo4+ziSPdudZ4rlpeBs7MjQ4e0oEvXyWzcdIQyZfI+dlnPJUv+5LvvVwDwdrM36NunXpLzN2tWT34Y/z6z52xm9pzNrF5zgMNHzjNsaEtCQyO4fPkWbq4ZqF37NYvdm4iIiIiIiIikTybDMJ7tbdcWZBgGvXr1YunSpWzZsoWAgICHnvfz8+ODDz5g0KBBAMTGxpIlSxZGjhxJly5dCAsLI3PmzMyfP5/mzZsDEBwcTPbs2Vm1atUj91j7L21eKCKSNoSHR9G330z++usybm5OjP2+I/nzJ33fqrN/X+XLL3/h5KkrAFSpUogB/Rvi5emaXCGnqLCwSCb8sJqVq/Y9cDx7dm+6vF+TatWKPFchcdv24wz+aD62tjbMmtGDPHmyPv2kFHb06AUGfzyfW7ci8PJyZdTI9hQskP3pJ/7LnTtR9O4zg5OnruDl5UrtWsXx8nLFy9MVTy/XxP97eLi8cKFSHjR33hYmT1mHk5MDs2f2xN8/0wPPL/ppB+PGrwKgVcsK9Ozx5nMXxQ8eCmLYsJ+5dj0MW1sbsmRxJzg4lJYtKtC7V90XvRURERERERFJZTT+L5Zm1cJa9+7d+fHHH/ntt9/Ily9f4nF3d3ecnO7tjTFy5EhGjBjBrFmzCAgIYPjw4WzZsoWTJ0/i5uYGQLdu3fj999+ZPXs2Xl5eDBgwgJCQEPbt24et7dMHvpRYIiKpX1hYJL37zuD06WDc3Z0ZN6YTAQHPXuCJj09g7rwtzJq9mYQEMx4eLgwa2JAqlQtbPugUYhgGa9YcYPwPq7h9OxKAxo1KkzNnFmbP2Uxo6F0AChTITvdutSnxeu4k9333bjSt247hxo1w2rWtTLeuT3/DirVcvXqbQR/O5czZqzg62jPks7eT/Hm9ezeaPn1ncvzEJTw8XPhh/Hu8+qrP008Ui0hIMNO7zwwOHAyiQIHsTJnUJbF4OX/BtsRlSNu3q0yXzrVeeKZpeHgUI0ctZfOWo8C9JQ1/XtSfbNm8XuxGREREREREJNXR+L9YmlULa48bFJk1axYdOnQA7g0WDhs2jClTphAaGkqZMmX44YcfKFz4/wfKoqOjGThwID/++CNRUVFUr16diRMnJnnfNCWWiEjqdis0gj59Z3L27FU8PV0YN7YTuXP5vlCfJ09d4YsvF/P339cAqFWzGP37NcDNzckSIaeYixdvMurbZezb9zcAuXL58OGgxhQpnAOAu5ExLFy4nYWLdhAVFQvAG2Xz0q1r7STNPBv9/XJ+WbKLbNm8mD+3D46O9sl3MxZwNzKGzz5byJ+7TmEymejRrQ6tWlV4YiEmMjKGD/rP4siRC2TM6MSEce+lyll56d21a7dp32E8d+5E0b5dZbp2qc3sOZuZOm09AB3frUanjtUttnyrYRj8vnIfkyavoVrVIgzo39Ai/YqIiIiIiEjqovF/sTSrFtZSCyWWiEjqFRJyh959ZhB07jre3m6MH9uJnDmzWKTv2Nh4Zs7ayPwF2zCbDfLnz8a4MZ1wdc1gkf6TU1xcPPMXbGPO3C3Exsbj4GBHx3er07pVhUcuU3jr1h1mztrEb8sDSUgwYzKZqFO7OLVrFyc8PIqQkDvcuhVByK073Ar5599bEYSE3AFg7PcdKVUqT0rf5nOJj09gzNjf+XXpbgAaNSxNvw/qP/J1iY6Opf+AORw4GISbawbGje1EvnxJX15ULGvT5iN88ulCTCYTNWsUZd36QwC8/14N3u1QLVmuef9X4fS436KIiIiIiIho/F8sT4U1lFgiIqnVjZvh9Oo9nQsXbpI5c0bGj32PHDkyPf3EZ3T06AUGDZ7L7duRFCrkz5jvO+Li7Gjx61hCZGQMGzYeZuGiHZw/fwOA0qUDGNi/YZKWsbt48SZTpq5j0+ajSb5mWtx7yjAMfl68k3HjV2EYBqVLB/Dl560eKJrGxMQx6MN5BO49g7OzI+PGdKRgwaTNdpfkM3zEEn5f+f/7BHbrWpt2bStbMSIRERERERFJyzT+L5amwhpKLBGRZ/HLkj+ZN38rzd8uR8sWFbC1tbFo/yEhd9gTeIbAwDPs2n2S27cj8cnizvjx75E9m7dFr/Vvp08H07P3dO7ciaJYsZyM/rYDTk4OyXa9Z3X27FWWLtvNmrUHiYyMAcDT04W+fepRo3rRZ55tc/z4RWbM2sTlSyF4ebvi7eWGl5cr3t5ueHm54e3lipe3G5m83fD2dkuOW0oR23ecYMjQRURHx/Hqq1n49pt3yOrrSWxsPIM/ms+u3adwcnJgzOh3KVLkFWuHK9wrHnd6fyLnz9+gd6+6tGxRwdohiYiIiIiISBqm8X+xNBXWUGKJiCTVkaMX6N5jKgkJZgCKFMnBJx83w9//+WeRRUfHcvDQOfbsOUPg3jOcPXv1geezZfNi7Pcd8fN7+mysF/XXX5fp3XcGERHRvP56Lr4d1Z4MGaxXXIuJiWPT5qMs+203R45cSDyePbs3jRqUpn79kmluTzhr+Ouvywz6cC43Q+7g5eXK8C/bMH/BVnb88ReOjvaM/q4DrxV/1dphyr9ERcVy82b4C31vEREREREREQGN/4vlqbCGEktEJCnu3o3mnQ7juRIcSpEiOTh79hqRkTE4OtrTrWttmjUti41N0mavhYdHsXrNfnb8cYLDh88TF5fwwPP58vpRqlQeSpfKQ9GiOXFwsEuOW3qkY8cu0ueDmURGxlC6dAAjR7TF0dE+xa5vGAbnzl1nxe/7WLV6H+HhUQDY2tpQsWIBGjcsQ4kSuZL8Wss9167dZuCguZz5V+HWwcGOb0e1p2TJtLF3nIiIiIiIiIg8O43/i6WpsIYSS0QebfmKQNauPYj5Kd8mM3m70bZNJfLly5ZCkVnHsC9+Zu3ag2TN6smcWb24ExHFiBG/snffWQBef+1V/vdxM7Jm9XxsH6dOX2HJr7tYt+4QMTFxicd9srjfK6SVDqBkidx4eLgk+/08yaFD5+g3YDZRUbGUK5ePEV+1wd4+eYp7MTFxnDx5hSNHz3PkyAWOHD1PaOjdxOd9srjToEEp6tUrSeZM+hn1Iu5GxvDZZwv5c9cp7O1tGTmiHWXL5rV2WCIiIiIiIiKSjDT+L5amwhpKLBF52KzZm5g2fcMznVOrZjE6v18zRZYsTGnr1h1k6Oc/Y2NjYuKEzhQtem8vKrPZzNJle/hh4mqio+NwdnKgZ8+6NGxQKnHPr7i4eLZsPcaSJbs4fOR8Yp+5c/tS760SlC2blxz+mZ55j7Dktn//3/QfOIeYmDgqVSzIl1+0ws7O9oX7vRUawcGDQRw5eoGjRy5w8tQV4uMfnLFnZ2dL6dJ5aNywDGXL5rX4PnYvs/j4BNasOUCuXD4ULOhv7XBEREREREREJJlp/F8sTYU1lFgi8v8Mw2DGzI3MnLUJgNatKlKwYPYnnADbdpxg3bqDwL2CSJPGZXinfRU8PV1TIOLkd+XKLd55dzx378bQ8d1qvNepxkNtLl0O4avhSzh06BwAZUoH0LlzTf744y9+Wx5ISMgd4N5yhlWqFKJpk7IUK5oz1RXT/mtP4GkGfTiP2Nh4qlUtzNAhLV6ouLZp8xE+/2IxsbHxDxz38nKlSOEcFC6cgyKFXyFfPr8UXX5SRERERERERCS90vi/WJoKayixROQewzCYMnUdc+dtBaBb19q0a1s5SeeePHWFSZPXsmfPaQCcnR1p26YSLZqXx8nJIdliTm7x8Qn06DWNI0cuUKRIDn4Y//5jC0sJCWYW/7KTyVPWPVQ4yuTtRsOGpWnYoBSZ0thyhjv/PMngj+YTH59AzRpF+d/HzZ5rz7flKwIZ9c0yzGaDnDkz81rxXBQpcq+Q5ufnmeqLjCIiIiIiIiIiaZHG/8XSVFhDiSUi94pqP0xcw48LtwPQu1ddWrao8Mz9BAaeYeKkNZw8dQUAb283Or1bjXr1SlpkGcGUNmPmRmbM3IiLiyNzZvVK0jKX585f56uvlnDs+EWKF89J08ZlqVy5UJq8//u2bT/O/z75kYQEM/ny+jF0aAteyZE5yef/+ON2JkxcDUCD+qUYOKChlncUEREREREREUkBGv8XS1NhDSWWyMvOMAzGjlvJz4t3AtDvg/o0a/rGc/dnNpvZsPEIU6eu40pwKAC5cvkw9vuOeHu7WSTmlHD48Hm695yK2Www9LPm1KpVPMnnms1mbodF4pVOlsOEezPXPv/iZ8LDo8iQwZ5+fevz1lslnjjT7L+zINu0rkT3brU1O01EREREREREJIVo/F8sTYU1lFgiLzOz2czo71fw69LdAAwa0JBGjcpYpO+4uHiWLtvD7DmbuH07kgIFsvPD+PfIkCH1Lw0ZERFN+w7juHr1NrVrF2fIp82tHVKqcONGGMO+WMz+/X8DUL1aEQYNbISbm9NDbc1mM9+NXsHSZfe+trp2qU37dklbWlRERERERERERCxD4/9iaVqHSkReWmazmVHf/MavS3djMpn4eHATixXVAOzt7Wj+djmmTu6Gu7szJ05c4vMvFmM2my12jeTy7Xe/cfXqbfyyejKgXwNrh5NqZM7sztjvO9K1S21sbW3YuOkI7TuM5/Dh8w+0i49PYNjnP7N02b2vrUEDGqqoJiIiIiIiIiIikg6osCYiL6WEBDPDv/6V5SsCsbEx8cn/mlGvXslkuVb27N58Pbwt9va2bNl6jEmT1ybLdV5UaGgE23ec4NvvfmPd+kPY2towZEgLXFwyWDu0VMXW1ob27SozZVIX/Py8uHbtNt17TmXGzI3ExycQHR3L4I/ns37DYWxtbRg6pLlFC7YiIiIiIiIiIiJiPVoKEk0FlZR34GAQU6eu49r1sCe2M5lMvFb8VTp1rE7WrJ4pFF36ZxgGX49ayooVe7G1teHTT96mVs1iyX7ddesOMvTznwHLLjn5PBISzJw7d50jR85z5OgFjh69wMVLIQ+0ea9TdTq+W91KEaYNd+9G8+3o5axdexCAYkVfAZOJQ4fO4eBgx/Cv2lDujXzWDVJERERERERE5CWm8X+xNBXWUGJJyrl16w4TfljDmrUHnuk8e3tbmjQpyzvtquDh4ZJM0b08Jk1ey7z5W7GxMTFsSAuqVy+aYteeNXsT06ZvwNbWhm9Gtadsmbwpct2IiGiOHb+YWEg7fvwid+/GPNQuZ87MFCn8CqVK5aF6tSKYTKYUiS+tW7P2AN9+t5zIyHuvqYuLI9+Mak/xYq9aOTIRERERERERkZebxv/F0lRYQ4klyS8hwczSZbuZOm09ERHRmEwmGjUsRd03S2CyeXzhIiIiivnzt7F331ng3mB9u7aVaf52OTJkcEip8FOcYRjJVtD58cftTJi4GoCPBjehfjIt//g4hmHw5Ve/sHrNAZydHZkyuQu5c/la/BoXL4Zw9NiFxEJaUNB1/vvt3snJgYIFs1Ok8CsUKZyDQoVykDGjk0VjeZlcuhzC8BFLuH4tjK++akO+vH7WDklERERERERE5KWn8X+xNBXWUGJJ8jp69ALfjl7OqVNXAMifPxsD+jekYIHsSTrfMAz2BJ5h4qQ1nD4dDECmTBl5r1N16r75OnZ2tskWe0o7fuISw0cs4cb1MF57LRelSuWhdKk8ZM/ubZFC2++/72X4178C0L1bHdq2qfTCfT6P2Nh4Pug3iwMHg/Dx8WDalK5kyvTi33tOnw5m2owNHD16ntu3Ix963s/Pi8KFc1CkcA6KFMlBrld90tXXT2qRnIVhERERERERERF5Nhr/F0tTYQ0lliSPsLBIJk5ew4oVewFwc81A1661aVC/FLa2Ns/cn9lsZv2Gw0ydtp7g4FDg3rJ9XbvUpmKFAml6IN8wDH5evJMfJq4hPj7hoeezZvWkVMl7RbaSJXOTMaPzM19j69Zj/O/THzGbDdq0rkiP7m9aIvTnFh4eSecuk7lw8Sb582fjh/Hv4+T0/LMQg6+G0um9idy+fRcABwc78ufLllhIK1w4B97ebpYKX0REREREREREJE3Q+L9YmgprKLHEssxmMytX7eeHiasJD48CoG7d1+nerQ5enq4v3H9sbDxLl+1m9pzNhIXdm5X0xhv5GPJp8zS5jF94eBTDRyxh2/bjAFSpXIgWzctz8NA5AgNPc/jIhQeKbSaTifz5s1G5UkEaNSyTpHveu+8s/QfMJi4ugfr1SjL4w8apohB56XIInbtM4vbtSCpXKsiXX7R+rqJrZGQM3bpP5fSZYALyZGXggIbkzeuHg4NdMkQtIiIiIiIiIiKSdmj8XyxNhTWUWC+LmJg4duw4gb2DHdmyeeGX1euFZgg9yrnz1xn1zTIOHjwHQO7cvgzo14BixXJa9DoAERHRzF+wjUU/7SA2Nh4/Py++Ht6GPHmyWvxayeX48Yt8OmQRwcGh2Nvb0qtnXZo2KftA0SsyMuafItsZ9uw5TdC564nPOTs50KBBaVq2KE+WLO6PvMaJvy7Rq9d0IqNiqVypIF983ipVLX94+PB5evWZTlxcAk0al+GDvvWfqbhmNpv55NOFbNl6DE9PF2ZM64Gvr0fyBSwiIiIiIiIiIpKGaPxfLE2FNZRYL4OTp67w+ec/P1CUAfD2diObnxd+fl73im1+Xvhn9yZ//mzPVHyJjY1n3vytzJ23hbi4BDJksOe9TjVo/na5ZC/inDp9hY8+XkBwcCgZMtjz0eAm1KxRLFmv+aL+u/Sjn58XX37eivz5sz313Bs3wvhz1ykW//InZ89eBcDOzpbatYrTpnVFcubMktj23PnrdO8xldu3IylRIhffjnoHR0f7ZLuv57V+wyGGDP0JgEoVCzLks+ZJLvpOn7GBmbM2YW9vy4Rx71GkyCvJGaqIiIiIiIiIiEiaovF/sTQV1lBipWcJCWYW/LiN6TM2Eh+fgKenCz5ZPLh8OYQ7EdGPPc/T04VatYpTt87rBAQ8eQbYwUNBjBy1jPPnbwDwRtm8DOjfkKxZPS16L08SHh7JZ0N/Ys+e0wC0bFGB7t1qp6qZWfeFh0fx1Yhf2L79BABVqxTmo8FNcHXN8Ez9GIbBrl2nmL9gGwcOBiUer1ixAO3aVCZTpox07T6F69fDyJ8/G+PHvYeLs6NF78WS1m84xFfDlxAbG0/+/NkY9XU7MmV68vejjRsP8+mQRQD87+OmvFW3REqEKiIiIiIiIiIikmZo/F8sTYU1lFjp1ZUrt/jiy8UcOnweuLd316CBjfDwcAHuFaMuX7nF5cu3uPLPv5cvh3D272uJe5cBBARkpe6br1OzZrEH9kgLD49i4qQ1LF8RCICXlyt9+9SjerUiVtm/KyHBzLTp65k7bysAr7+eiy+GtcTTAvu6WUJsbDwrft/LnLlbuHkzHHt7W3r3rEuT/yz9+DyOHr3A/AXbEvdpg3vLREZGxZIjRyYmT+yS+HlPzQ4fPs+HH80jLCwSnyzufPvNO+TO7fvItidPXqZr96nExMTRskUFeveqm8LRioiIiIiIiIiIpH4a/xdLU2ENJVZ6YxgGq9ccYPT3K4iMjMHZyYEPPqhP3TdfT1IBJz4+gd27T7Ny9T7++OMv4uISALC1teGNN/JR983XiItLYOy4ldy6FQFAg/ql6N6tDhkzOiXrvSXFlq1H+fLLX4iMisUniztffdWGggWyWy2emJg4Vvy+l3nzt3LjRjgA2bLdW/oxX76nL/34LM6du86CH7ezdt1B4uMT8MnizuRJXfDx8bDodZLTpUshDBg4hwsXb+Ls7MiXn7eibNm8D7QJCblDp/cncv16GGXL5OWbUe2faV82ERERERERERGRl4XG/8XSVFhDiZWehIVFMvKbpWzZcgyAokVe4dNP3iZbNq/n6i88PJL1Gw6zavV+Tpy49NDzr7ySmQ8HNaJ4sVdfKG5LCwq6xkcfL+DCxZs4ONgxoF8D6tUrmaIxxMTE8dvyQOYv2MbNm/cKapkzZ6R928rUq1cyWfc6u349jG3bj1OhfAF8fT2S7TrJJTw8ko//t4D9B4KwtbXhg771aNK4LHDvde3ZezrHjl3klVcyM21Kt2deRlNERERERERERORlofF/sTQV1lBipXWxsfEcOXqewMAzrFq1n5shd7C1teH992rQpnUli83kCQq6xqrVB1i77iDh4ZG0a1uZdm0r4+BgZ5H+LS0iIprPv1zMjh339jKrVbMY/T6oT8aMzs/cV3h4JDNnbeLipRCy+Xni5+dFtmzeZPPzws/PkwwZHBLbxsTEsey3PcxfsI2QkDsA+GRxp127ytR7q2Sqfb1Sm7i4eEaOWsaq1fuBe/vm9eheh6+GL2HN2gO4uTkxfWo3/P0zWTlSERERERERERGR1Evj/2JpKqyhxEprDMPg76BrBAaeITDwDAcOBhEdHZf4fM6cmRnyaXOLLzN4n9lsxmQyWWUftWdlNpuZO28r02dswGw2yOTtxocfNqZ8ufxJ7mPzlqN8N3p54rKXj5LJ2w0/Py98s3qyd++ZxLY+Ph68064ydeuWUEHtORiGwZy5W5g6bT1w72v73Lkb2NraMPrbDpQqlcfKEYqIiIiIiIiIiKRuGv8XS1NhDSVWWnDr1h32/FNICww8w81/ZkLd5+XlSqlSeShdKoBqVQsn6zKDadHx4xf54qtfOH/+BgD13ipB715vPXEJwZCQO3z3/fLEZTVz5sxM40ZluHEjnCtXbnH58i0uX7lFRET0Q+dmzepJ+3ZVqPvma9jbq6D2otatP8TwEUuIjY0HoN8H9WnW9A0rRyUiIiIiIiIiIpL6afxfLE2FNZRYacHY8Sv56ac/Eh87OtpTvFhOSpXKQ5nSAeTK5ZMmZpBZU0xMHFOnrWfRT39gGAY+Wdz5+KOmD816MgyDNWsOMGbcSu7cicLW1oZ2bSvT4Z2qD806MwyDO3eiuHT5Fpcvh3DlSig+Pu7UqF4UOzvblLy9dO/w4fN8N3o55cvn5/33aujrXUREREREREREJAk0/i+WpsIaSqy0YNfuU0yZso7SpQMoVSoPRQrn0Ky053To0Dm+HP4Lly/fAqBxozL06F4HZ2dHrl69zahvlrFr9ykA8ub14+OPmpA3wM+aIYuIiIiIiIiIiIg8F43/i6XZWPPi27Zto379+vj5+WEymVi2bNkDzxuGwdChQ/Hz88PJyYkqVapw7NixB9rExMTQq1cvMmXKhIuLCw0aNODSpUspeBeSEsqWycusmT3p1rU2JUvkVlHtBRQrlpO5s3vTtElZAJYu2037DuOZPmMDbduNYdfuUzg42NG1Sy2mT+2mopqIiIiIiIiIiIiIyD+sWli7e/cuxYoVY8KECY98ftSoUYwePZoJEyYQGBiIr68vNWvW5M6d/99fq2/fvixdupRFixaxY8cOIiIiqFevHgkJCSl1GyJpjpOTA/37NWDcmI74+Hhw5cotZs7aRGRULEWK5GD2rJ60b1dFyzmKiIiIiIiIiIiIiPxLqlkK0mQysXTpUho1agTcm63m5+dH3759+fDDD4F7s9N8fHwYOXIkXbp0ISwsjMyZMzNv3jxatGgBwJUrV/D392fVqlXUrl07SdfWVFB5md29G834CavZ+edJ2rapRNMmZbG1tWrNXURERERERERERMQiNP4vlmZn7QAeJygoiKtXr1KrVq3EY46OjlSuXJmdO3fSpUsX9u3bR1xc3ANt/Pz8KFy4MDt37nxsYS0mJoaYmJjEx+Hh4cl3IyKpnItLBgZ/2NjaYYiIiIiIiIiIiIiIpHqpdlrK1atXAfDx8XnguI+PT+JzV69excHBAU9Pz8e2eZQRI0bg7u6e+OHv72/h6EVERERERERERERERCS9SbWFtftMJtMDjw3DeOjYfz2tzUcffURYWFjix8WLFy0Sq4iIiIiIiIiIiIiIiKRfqbaw5uvrC/DQzLPr168nzmLz9fUlNjaW0NDQx7Z5FEdHRzJmzPjAh4iIiIiIiIiIiIiIiMiTpNrC2quvvoqvry/r169PPBYbG8vWrVspV64cACVKlMDe3v6BNsHBwRw9ejSxjYiIiIiIiIiIiIiIiIgl2Fnz4hEREZw5cybxcVBQEAcPHsTLy4scOXLQt29fhg8fTkBAAAEBAQwfPhxnZ2dat24NgLu7O506daJ///54e3vj5eXFgAEDKFKkCDVq1LDWbYmIiIiIiIiIiIiIiEg6ZNXC2t69e6latWri4379+gHwzjvvMHv2bAYNGkRUVBTdu3cnNDSUMmXKsG7dOtzc3BLP+f7777Gzs6N58+ZERUVRvXp1Zs+eja2tbYrfj4iIiIiIiIiIiIiIiKRfJsMwDGsHYW3h4eG4u7sTFham/dZERERERERERERERNIJjf+LpaXaPdZEREREREREREREREREUhMV1kRERERERERERERERESSwKp7rKUW91fDDA8Pt3IkIiIiIiIiIiIiIiJiKffH/bUrlliKCmtASEgIAP7+/laORERERERERERERERELO3OnTu4u7tbOwxJB1RYA7y8vAC4cOGCEkvkBYSHh+Pv78/Fixe1EajIC1AuiViGcknEMpRLIpahXBJ5ccojEct5mfLJMAzu3LmDn5+ftUORdEKFNcDG5t5Wc+7u7un+m4hISsiYMaNyScQClEsilqFcErEM5ZKIZSiXRF6c8kjEcl6WfNKEGrEkG2sHICIiIiIiIiIiIiIiIpIWqLAmIiIiIiIiIiIiIiIikgQqrAGOjo4MGTIER0dHa4cikqYpl0QsQ7kkYhnKJRHLUC6JWIZySeTFKY9ELEf5JPL8TIZhGNYOQkRERERERERERERERCS104w1ERERERERERERERERkSRQYU1EREREREREREREREQkCVRYExEREREREREREREREUkCFdZEREREREREREREREREkkCFNREREREREREREREREZEkUGFNREREREREREREREREJAnSfWEtPj4+8f+GYVgxEpH0Q7kkIiLWFh0dbe0QRNKFS5cuERwcDOh3PJEXobEHEctTLomISGplMtLpT6nY2Fg+++wzbt26RdasWRk8eDBOTk7WDkskzYmNjeX777/HxcWFIkWKULlyZWuHJJImxcXFMX/+fDw8PChQoAD58+e3dkgiac79X1t79+7N8ePHWbx4MV5eXlaOSiRtiouLo2fPnqxevZqePXsyaNAga4ckkiZp7EHEMjT2IGIZGnsQSRnpcsbasmXLeOWVV9izZw8ZMmTgm2++oXPnzhiGoXe7iDyD1atX4+fnx7Jly5g1axaNGzfmk08+0SwBkWc0ZcoUfHx8mDlzJn379qVp06b8/PPPAJjNZitHJ5J2mEwmbt++zS+//MLmzZsT80hEns3FixcpX748R44cYfHixbRq1Up/K4k8B409iFiGxh5ELENjDyIpJ93NWIuJiaFx48a89tprfPXVVwD89ttvtG7dmpCQEDJkyGDlCEXSjubNm+Pl5cXkyZMJDQ1l48aNtG3blq+//pouXbronZgiTxEfH8+ECROYOXMmgwcPpnXr1hw+fJjp06ezc+dO9uzZg41NunyPi0iy2bFjB5MnTyZv3ryMHTuWgwcP4u/vb+2wRNKUGTNmsGjRItatW4fJZOLSpUv4+Phgb29v7dBE0gyNPYhYjsYeRF6Mxh5EUl66y6gjR46wZcsWqlevnnjs6tWrdO7cWZV5kae4X2c3DIOgoCB27txJxYoVAfD09KRZs2Z07tyZ+fPns2PHDmuGKpKq3c+lmJgYIiIiaNasGS1btgSgaNGiFCpUCDs7O27cuGHNMEVSvfu5ZDabE/9vb2/PmTNn+OCDD3Bzc2PEiBHWDFEkTbifPwkJCQDs3buXYsWKcfv2bZo3b07NmjUpXbo0nTt35urVq9YMVSRV+/f7kjX2IPL87v88AjT2IPIC7ueSxh5EUl6aL6zNnTuXM2fOJD4uWbIk3t7eTJgwgdWrVzNw4EC6d+/Opk2bCAgIYNKkSYnfTNLZZD2RF/LRRx8xfvx44N5SWzlz5iQ+Pp7w8HAAoqKiABgyZAh3795l9erVREREWC1ekdTq37nk4uJCmzZt+Oyzz7CxsUn8uePp6UlERARZsmSxZqgiqdq/c8nGxgaTyQTcKwgEBATg5ubGl19+yYwZM9i7dy+TJ0/m7Nmz1gxZJFX6dy7Z2toCcOzYMQDGjBkDwIQJE+jatSsrVqxgyJAhXL58GdDfSyL/9u9cAo09iDyvTz/9lE8//TTxscYeRJ7Pp59+yieffAJo7EHEGtJsYc1sNtOkSRM6dOjAsmXLHlh3ecGCBWTNmpWhQ4eybNky1q9fz+LFi+nevTvff/89q1evBkgcoBF5mU2ePBk3NzfWrl1LzZo1E4+bzWYaN27M5MmTAXByciIuLg5vb286dOjAL7/8Qnx8vLXCFkl1HpdLr776KnAvp+7/3FmzZg2vvfYaJpOJuLg4q8Qrklo96efSfZ6engC0bduWnDlzUrp0aRYsWJDisYqkZo/Kpfvvam7cuDFjxoxh0aJFDBo0iOrVq9OlSxdGjBjBH3/8wYEDBwD9vSQCj86l+wOWGnsQSbrffvsNX19f1q9fT7Zs2QgNDQU09iDyrP6dS9mzZ+fWrVuAxh5EUlqaLKyZzWZsbGzIli0bJUuWZPTo0Rw/fjzx+UqVKjF27Fg8PDz49NNPqVatGnnz5uV///sfDg4OnDx50orRi6QOZ86coUyZMnz44YdMmzaN/fv3U6BAgcTnbW1tqVGjBrGxsYwdOxb4/0HNTp06cfPmTY4ePWqV2EVSk6flEtwbfLGxsSEhIYH4+HgOHTqUuNTJv/ez0bJB8jJ7Wi7d3xPgr7/+omDBgpw+fZrChQtz48YNTCYTXbt2JXfu3NYKXyTVeFIu3Z+xVrlyZYoWLUpsbCx+fn6J53bo0IHbt29z6dIlq8Qukpo8KZfuD1hq7EEkae7evcuMGTPo0aMHu3btokePHolvlLK1taVmzZrExMRo7EHkKR6VS15eXg+00diDSMpIk4U1Gxsbbt68ya5du9iwYQPOzs788MMPiRV6gBs3bhAYGEiVKlWAe+/ODAsLw8nJCRcXFytFLpJ6BAYGcubMGb744gtatmzJ7du3WbBgAdu3b+fUqVMAVKhQgVq1avHdd99x5coVHB0dAThw4ACZM2fGzc3Nmrcgkio8KZfuL1V8f/DF1taWmzdvcv36dSpXrgzAwYMH6dChA4A2E5aXWlJyKT4+HltbW/r06UOhQoWoVKkSp0+f5v3332fIkCGEhIRY+S5ErO9JuXT69GkA8ubNS+vWrbl48SJ//PFH4rk3btzAy8tLv+OJkLSfS6CxB5Gk2LJlC7t27eJ///sfoaGhDB48mJEjRyauOFC9enWNPYgkweNyaeHChYmzqQ3D0NiDSApIk1mUkJCAq6srzs7OuLq6Mnz4cObOnUtQUBAAt2/fJkuWLOTIkYOuXbty+PBhLl26RP/+/bl79y4NGza08h2IWF+rVq2oU6cO69evp3PnzhQtWpQJEybQtGlTqlSpwsaNG/Hx8aFr167kyJGDt956iwULFnDmzBlmzpxJ3rx5CQgIsPZtiFjdk3KpUqVKbN68+YF3g23YsIFXX30VPz8/OnXqROnSpbl9+zZms1n7b8hL7Wm5tGnTJuzs7MifPz8dO3bkzz//ZOLEiXh7e/PJJ59w5coVDh8+bO3bELG6J+VS5cqV2bRpE66urrz//vs0aNCA/v37M3ToUA4ePMhHH32EnZ0d1apVs/ZtiFhdUn7Huz828corr2jsQeQR7v99c+3aNcqXL8/mzZspUaIEBw8eZOfOnbzzzjv06tULs9lMv379yJ49u8YeRB7habnUrl07+vTpw5UrVxLf2KuxB5HkZTJScSYtXryYdevWUbhwYapVq0aRIkUSnzt79iw1atTgwIEDeHh4UK1aNa5du0ZYWBh9+/ZlwIABbN++nWbNmuHh4UFkZCQBAQFMnTqVPHnyWPGuRFLe43Jpy5YtdOrUCV9fXwYOHEiZMmWIjIzk008/JTAwkBUrVpA/f36uXbtGhw4dOH/+POHh4eTMmZP58+eTM2dO696YSAp7nlzat28fv/76K4UKFQLuDdIsXrwYZ2dn8uXLx7x588ifP781b0skxT1PLu3Zs4c1a9aQO3duzGZz4pJ294WFheHu7m6N2xGxmuf9HW/ZsmUUKlSIuLg4BgwYwB9//EFERAS+vr7MmDFDy6rKS+d5cmnv3r0sX76c/Pnza+xB5B+Py6VFixbRtWtX2rRpQ6ZMmfjkk0+wt7dnzpw5TJo0ibfffpv+/ftr7EHkH8+TS5MnT6Zx48YMGjQI0NiDSLIzUqGbN28azZo1M3x9fY2uXbsaFSpUMPz8/Iw5c+Ykttm4caPRpk0bwzAM4/Tp00aRIkUMk8lkNGnSxLh161ZiuwsXLhh79uwx9uzZk+L3IWJtj8ul2bNnJ7aZPHmysWnTpgfOi4mJMVxcXIxp06YlHouOjjaCg4ONI0eOpFj8IqnFi+bS9OnTDcMwjPj4eKNVq1ZGzpw5jZUrV6boPYikBpbKpYSEhBSNWyS1sVQu3RcREWGcOXMmRWIXSU0s+feSxh7kZfa0XDKbzUbhwoUNk8lkzJo1K/E8s9lsNG3a1OjUqZMRExNjGIbGHuTl9qK59N577xlxcXGG2WzW2INIMrOzdmHvUTZv3syFCxfYu3cv2bJlA6BRo0YMHToUFxcXmjZtSmRkJHv37qV9+/YsWrSILl26ULBgQY4cOcLNmzcTN0H19/fH39/fmrcjYjWPy6Vhw4bh6upK06ZNad++PU5OTonnGIaBjY0NWbNm5dixY4nHHR0d8fX1xdfXN8XvQ8TaXjSX7m+2bWtry7Bhw7SUiby0LJVL2hNAXnaWyqX7XFxcNEtNXkqW/HtJYw/yMntSLrm7u9OoUSO6d+9Ojx49iIyMJD4+Hjs7O0wmE25ubhw/fhwHBwcAHBwcNPYgL60XzaWjR49iZ3dvuF9jDyLJK1WOSvz4449kz56dbNmyERERAUDjxo05d+4ckyZNIjQ0FBcXF+7cuUNwcDCbNm1i/PjxzJ07lxMnTjBjxgzi4uKsfBci1ve0XLp58yZOTk4PrK1sMpnYunUr9vb2tGvXzlqhi6Qqlswl/WIrLzP9XBKxDOWSiGUol0Qs40m5NGHCBEJCQujSpQs1a9Zk/PjxbNq0CYCrV69y5coVOnbsmNjX/f2hRF5GL5pLnTp1SuxLYw8iycvqhbVt27axdu1a4uPjE48FBAQkvvPL1dUVgL/++otq1aoRGRnJypUrKVeuHL/99hvLly+nQoUKxMfH4+DgwOLFi+nQoQP29vZWuR8Ra3nWXIqOjmbp0qXAvV9cg4ODOX36NJMnT6Zjx45Uq1aNfPnyaUNTeekol0QsQ7kkYhnKJRHLUC6JWMaz5lJUVBS//vorNjY2LFiwgCxZstC6dWvq1q1L8eLFiYuL46233rLKvYhYk3JJJI2zwvKThmEYxo0bN4z27dsbJpPJKFasmBEUFJT43NmzZ43MmTMblStXNkaOHGm88cYbxquvvmps3LjRKFasmPHJJ5881J/ZbE7B6EVSjxfJpU8//dQwDMOIiooy5syZYwQEBBivvvqqMW/ePCvdjYj1KJdELEO5JGIZyiURy1AuiVjGi47jxcfHG4ZhGNeuXTPWrVtnfPPNN8bSpUutczMiVqRcEkkfrDJjLT4+nsWLF3Pt2jUWLlzI6dOnWbRoETExMQDkypWLpUuXkjdvXn766SdKlCjBnj17qFatGkWLFuXEiRMP9amp4vIyetFcOn78OAAZMmTgzTff5Ntvv+Xvv/+mbdu21rwtkRSnXBKxDOWSiGUol0QsQ7kkYhmWGMeztbUFIEuWLNSsWZMBAwbQqFEjK96VSMpTLomkH3ZWuaidHa+//jr+/v7Uq1ePkydPMnr0aOrUqUPx4sUBKF++POXLlyc2NjZxA9Pr169z4MABWrZsCYDZbNbm9fJSs2QuZc6cmQYNGljrVkSsSrkkYhnKJRHLUC6JWIZyScQyNI4nYhnKJZH0w2oZWLp0aerVqwfAZ599hr29PZMmTeLOnTsAieuUOzg4EB0dTVxcHEuWLMHe3j7xl1l9AxFRLolYinJJxDKUSyKWoVwSsQzlkohlKJdELEO5JJI+WC0L7y/dGBsbC8CYMWOYOXMmu3bteuD5y5cvM2vWLMqVK8cnn3zCwIEDKVKkiHWCFkmFlEsilqFcErEM5ZKIZSiXRCxDuSRiGcolEctQLomkDybjfhk8FShXrhwuLi4sWLCALFmycOPGDTJnzszChQu5cuUK/fv3t3aIImmCcknEMpRLIpahXBKxDOWSiGUol0QsQ7kkYhnKJZG0J1UU1uLj47Gzs+PYsWMUK1aM0aNHc/bsWXbs2MGcOXMoXLiwtUMUSROUSyKWoVwSsQzlkohlKJdELEO5JGIZyiURy1AuiaRdqaKw9m+lS5dm79695MiRgylTplC7dm1rhySSJimXRCxDuSRiGcolEctQLolYhnJJxDKUSyKWoVwSSVtSzU6HZ8+epUiRIhw7doxp06Zx7tw5fQMReQ7KJRHLUC6JWIZyScQylEsilqFcErEM5ZKIZSiXRNKmVFNYs7W1pWnTpty8eZNOnTpZOxyRNEu5JGIZyiURy1AuiViGcknEMpRLIpahXBKxDOWSSNqU6paCFBEREREREREREREREUmNUs2MNREREREREREREREREZHUTIU1ERERERERERERERERkSRQYU1EREREREREREREREQkCVRYExEREREREREREREREUkCFdZEREREREREREREREREkkCFNREREREREREREREREZEkUGFNREREREREREREREREJAlUWBMRERERkScaOnQoxYsXT/HrbtmyBZPJhMlkolGjRklqe/v27RSJLa3o0KFD4mu4bNkya4cjIiIiIiKS5qmwJiIiIiLyErtfdHncR4cOHRgwYAAbN260WownT55k9uzZiY+rVKlC3759H2hTrlw5goODcXd3T9ng/iU1FvfGjh1LcHCwtcMQERERERFJN+ysHYCIiIiIiFjPv4suP/30E5999hknT55MPObk5ISrqyuurq7WCA+ALFmy4OHh8cQ2Dg4O+Pr6pkxAaYi7u7tVi40iIiIiIiLpjWasiYiIiIi8xHx9fRM/3N3dMZlMDx3771KQHTp0oFGjRgwfPhwfHx88PDwYNmwY8fHxDBw4EC8vL7Jnz87MmTMfuNbly5dp0aIFnp6eeHt707BhQ86dO/dM8Xbo0IGtW7cyduzYxFl1586de2i22OzZs/Hw8OD3338nX758ODs706xZM+7evcucOXPImTMnnp6e9OrVi4SEhMT+Y2NjGTRoENmyZcPFxYUyZcqwZcuWxOfPnz9P/fr18fT0xMXFhUKFCrFq1SrOnTtH1apVAfD09Eyc7QewZs0aKlSogIeHB97e3tSrV4+zZ88m9nnu3DlMJhM///wzFStWxMnJiVKlSnHq1CkCAwMpWbIkrq6u1KlThxs3bjz0eRg2bBhZsmQhY8aMdOnShdjY2Gd6TUVERERERCTpVFgTEREREZFntmnTJq5cucK2bdsYPXo0Q4cOpV69enh6erJ79266du1K165duXjxIgCRkZFUrVoVV1dXtm3bxo4dOxKLRc9SCBo7dixvvPEG77//PsHBwQQHB+Pv7//ItpGRkYwbN45FixaxZs0atmzZQpMmTVi1ahWrVq1i3rx5TJ06lV9++SXxnHfffZc//viDRYsWcfjwYd5++23q1KnD6dOnAejRowcxMTFs27aNI0eOMHLkSFxdXfH392fJkiXAvaUrg4ODGTt2LAB3796lX79+BAYGsnHjRmxsbGjcuDFms/mBeIcMGcInn3zC/v37sbOzo1WrVgwaNIixY8eyfft2zp49y2efffbAORs3buTEiRNs3ryZhQsXsnTpUoYNG5bk11NERERERESejZaCFBERERGRZ+bl5cW4ceOwsbEhX758jBo1isjISD7++GMAPvroI77++mv++OMPWrZsyaJFi7CxsWH69OmYTCYAZs2ahYeHB1u2bKFWrVpJuq67uzsODg44Ozs/denHuLg4Jk2aRO7cuQFo1qwZ8+bN49q1a7i6ulKwYEGqVq3K5s2badGiBWfPnmXhwoVcunQJPz8/AAYMGMCaNWuYNWsWw4cP58KFCzRt2pQiRYoAkCtXrgdeE3h46cqmTZs+ENeMGTPIkiULx48fp3DhwonHBwwYQO3atQHo06cPrVq1YuPGjZQvXx6ATp06PbDXHNxbAnPmzJk4OztTqFAhPv/8cwYOHMgXX3yBjY3eRykiIiIiImJpKqyJiIiIiMgzK1So0AOFGx8fnweKRLa2tnh7e3P9+nUA9u3bx5kzZ3Bzc3ugn+jo6AeWRbQkZ2fnxKLa/Rhz5sz5wH5xPj4+iTHu378fwzDImzfvA/3ExMTg7e0NQO/evenWrRvr1q2jRo0aNG3alKJFiz4xjrNnz/Lpp5+ya9cubt68mThT7cKFCw+8Zv/ux8fHByCxgPffWO8rVqwYzs7OiY/feOMNIiIiuHjxIq+88soT4xIREREREZFnp8KaiIiIiIg8M3t7+wcem0ymRx67X0Qym82UKFGCBQsWPNRX5syZU02Mtra27Nu3D1tb2wfa3S/Gvffee9SuXZuVK1eybt06RowYwXfffUevXr0eG0f9+vXx9/dn2rRp+Pn5YTabKVy48ENLYP47tvuz+v577L/LRz7O/fNFRERERETEslRYExERERGRZPf666/z008/kSVLFjJmzPhCfTk4OJCQkGChyP7fa6+9RkJCAtevX6dixYqPbefv75+4h9xHH33EtGnT6NWrFw4ODgAPxBYSEsKJEyeYMmVKYp87duywWMyHDh0iKioKJycnAHbt2oWrqyvZs2e32DVERERERETk/2nRfRERERERSXZt2rQhU6ZMNGzYkO3btxMUFMTWrVvp06cPly5deqa+cubMye7duzl37twDSyu+qLx589KmTRvat2/Pr7/+SlBQEIGBgYwcOZJVq1YB0LdvX9auXUtQUBD79+9n06ZNFChQAIBXXnkFk8nE77//zo0bN4iIiMDT0xNvb2+mTp3KmTNn2LRpE/369bNIvACxsbF06tSJ48ePs3r1aoYMGULPnj21v5qIiIiIiEgy0V9bIiIiIiKS7Jydndm2bRs5cuSgSZMmFChQgI4dOxIVFfXMM9gGDBiAra0tBQsWJHPmzFy4cMFicc6aNYv27dvTv39/8uXLR4MGDdi9ezf+/v7AvdloPXr0oECBAtSpU4d8+fIxceJEALJly8awYcMYPHgwPj4+iQWuRYsWsW/fPgoXLswHH3zAN998Y7F4q1evTkBAAJUqVaJ58+bUr1+foUOHWqx/EREREREReZDJMAzD2kGIiIiIiIj815YtW6hatSqhoaF4eHhYO5xUp0OHDty+fZtly5Y9ta3JZGLp0qU0atQo2eMSERERERFJzzRjTUREREREUrXs2bPTqlUra4eRJnXt2hVXV1drhyEiIiIiIpJuaMaaiIiIiIikSlFRUVy+fBkAV1dXfH19rRxR6pKUGWvXr18nPDwcgKxZs+Li4pJC0YmIiIiIiKRPKqyJiIiIiIiIiIiIiIiIJIGWghQRERERERERERERERFJAhXWRERERERERERERERERJJAhTURERERERERERERERGRJFBhTURERERERERERERERCQJVFgTERERERERERERERERSQIV1kRERERERERERERERESSQIU1ERERERERERERERERkSRQYU1EREREREREREREREQkCf4PQXBV9h15+TcAAAAASUVORK5CYII=",
"text/plain": [
"<Figure size 1600x350 with 1 Axes>"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nixtla_client.plot(\n",
" df, timegpt_fcst_finetune_df, \n",
" time_col='timestamp', target_col='value',\n",
")"
]
},
{
"cell_type": "markdown",
"id": "62fc9cba-7c6e-4aef-9c68-e05d4fe8f7ba",
"metadata": {},
"source": [
"Keep in mind that fine-tuning can be a bit of trial and error. You might need to adjust the number of `finetune_steps` based on your specific needs and the complexity of your data. Usually, a larger value of `finetune_steps` works better for large datasets.\n",
"\n",
"It's recommended to monitor the model's performance during fine-tuning and adjust as needed. Be aware that more `finetune_steps` may lead to longer training times and could potentially lead to overfitting if not managed properly. \n",
"\n",
"Remember, fine-tuning is a powerful feature, but it should be used thoughtfully and carefully."
]
},
{
"cell_type": "markdown",
"id": "8c546351",
"metadata": {},
"source": [
"For a detailed guide on using a specific loss function for fine-tuning, check out the [Fine-tuning with a specific loss function](https://docs.nixtla.io/docs/tutorials-fine_tuning_with_a_specific_loss_function) tutorial.\n",
"\n",
"Read also our detailed tutorial on [controlling the level of fine-tuning](https://docs.nixtla.io/docs/tutorials-finetune_depth_finetuning) using `finetune_depth`."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
nbs/docs/tutorials/07_loss_function_finetuning.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"!pip install -Uqq nixtla utilsforecast"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"from nixtla.utils import in_colab"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"IN_COLAB = in_colab()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" from nixtla.utils import colab_badge\n",
" from dotenv import load_dotenv"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Fine-tuning with a specific loss function"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"When fine-tuning, the model trains on your dataset to tailor its predictions to your particular scenario. As such, it is possible to specify the loss function used during fine-tuning.\\\n",
"\\\n",
"Specifically, you can choose from:\n",
"\n",
"* `\"default\"` - a proprietary loss function that is robust to outliers\n",
"* `\"mae\"` - mean absolute error\n",
"* `\"mse\"` - mean squared error\n",
"* `\"rmse\"` - root mean squared error\n",
"* `\"mape\"` - mean absolute percentage error\n",
"* `\"smape\"` - symmetric mean absolute percentage error"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/tutorials/07_loss_function_finetuning.ipynb)"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#| echo: false\n",
"if not IN_COLAB:\n",
" load_dotenv() \n",
" colab_badge('docs/tutorials/07_loss_function_finetuning')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Import packages\n",
"First, we import the required packages and initialize the Nixtla client."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from nixtla import NixtlaClient\n",
"from utilsforecast.losses import mae, mse, rmse, mape, smape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"nixtla_client = NixtlaClient(\n",
" # defaults to os.environ.get(\"NIXTLA_API_KEY\")\n",
" api_key = 'my_api_key_provided_by_nixtla'\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> 👍 Use an Azure AI endpoint\n",
"> \n",
"> To use an Azure AI endpoint, remember to set also the `base_url` argument:\n",
"> \n",
"> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" nixtla_client = NixtlaClient()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Load data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Let's fine-tune the model on a dataset using the mean absolute error (MAE).\\\n",
"\\\n",
"For that, we simply pass the appropriate string representing the loss function to the `finetune_loss` parameter of the `forecast` method."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>timestamp</th>\n",
" <th>value</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>1949-01-01</td>\n",
" <td>112</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>1949-02-01</td>\n",
" <td>118</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>1949-03-01</td>\n",
" <td>132</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>1949-04-01</td>\n",
" <td>129</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>1949-05-01</td>\n",
" <td>121</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" unique_id timestamp value\n",
"0 1 1949-01-01 112\n",
"1 1 1949-02-01 118\n",
"2 1 1949-03-01 132\n",
"3 1 1949-04-01 129\n",
"4 1 1949-05-01 121"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv('https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/air_passengers.csv')\n",
"df.insert(loc=0, column='unique_id', value=1)\n",
"\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Fine-tuning with Mean Absolute Error"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Let's fine-tune the model on a dataset using the Mean Absolute Error (MAE).\\\n",
"\\\n",
"For that, we simply pass the appropriate string representing the loss function to the `finetune_loss` parameter of the `forecast` method."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Inferred freq: MS\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n"
]
}
],
"source": [
"timegpt_fcst_finetune_mae_df = nixtla_client.forecast(\n",
" df=df, \n",
" h=12, \n",
" finetune_steps=10,\n",
" finetune_loss='mae', # Set your desired loss function\n",
" time_col='timestamp', \n",
" target_col='value',\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> 📘 Available models in Azure AI\n",
">\n",
"> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
">\n",
"> `nixtla_client.forecast(..., model=\"azureai\")`\n",
"> \n",
"> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
"> \n",
"> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 2400x350 with 1 Axes>"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nixtla_client.plot(\n",
" df, timegpt_fcst_finetune_mae_df, \n",
" time_col='timestamp', target_col='value',\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now, depending on your data, you will use a specific error metric to accurately evaluate your forecasting model's performance.\\\n",
"\\\n",
"Below is a non-exhaustive guide on which metric to use depending on your use case.\\\n",
"\\\n",
"**Mean absolute error (MAE)**\\\n",
"\\\n",
"<img src=\"https://latex.codecogs.com/svg.image?\\mathrm{MAE}(\\mathbf{y}_{\\tau}, \\mathbf{\\hat{y}}_{\\tau}) = \\frac{1}{H} \\sum^{t+H}_{\\tau=t+1} |y_{\\tau} - \\hat{y}_{\\tau}|\" />\n",
"\n",
"- Robust to outliers\n",
"- Easy to understand\n",
"- You care equally about all error sizes\n",
"- Same units as your data\n",
"\n",
"**Mean squared error (MSE)**\\\n",
"\\\n",
"<img src=\"https://latex.codecogs.com/svg.image?\\mathrm{MSE}(\\mathbf{y}_{\\tau}, \\mathbf{\\hat{y}}_{\\tau}) = \\frac{1}{H} \\sum^{t+H}_{\\tau=t+1} (y_{\\tau} - \\hat{y}_{\\tau})^{2}\" />\n",
"\n",
"- You want to penalize large errors more than small ones\n",
"- Sensitive to outliers\n",
"- Used when large errors must be avoided\n",
"- *Not* the same units as your data\n",
"\n",
"**Root mean squared error (RMSE)**\\\n",
"\\\n",
"<img src=\"https://latex.codecogs.com/svg.image?\\mathrm{RMSE}(\\mathbf{y}_{\\tau}, \\mathbf{\\hat{y}}_{\\tau}) = \\sqrt{\\frac{1}{H} \\sum^{t+H}_{\\tau=t+1} (y_{\\tau} - \\hat{y}_{\\tau})^{2}}\" />\n",
"\n",
"- Brings the MSE back to original units of data\n",
"- Penalizes large errors more than small ones\n",
"\n",
"**Mean absolute percentage error (MAPE)**\\\n",
"\\\n",
"<img src=\"https://latex.codecogs.com/svg.image?\\mathrm{MAPE}(\\mathbf{y}_{\\tau}, \\mathbf{\\hat{y}}_{\\tau}) = \\frac{1}{H} \\sum^{t+H}_{\\tau=t+1} \\frac{|y_{\\tau}-\\hat{y}_{\\tau}|}{|y_{\\tau}|}\" />\n",
"\n",
"- Easy to understand for non-technical stakeholders\n",
"- Expressed as a percentage\n",
"- Heavier penalty on positive errors over negative errors\n",
"- To be avoided if your data has values close to 0 or equal to 0\n",
"\n",
"**Symmmetric mean absolute percentage error (sMAPE)**\\\n",
"\\\n",
"<img src=\"https://latex.codecogs.com/svg.image?\\mathrm{SMAPE}_{2}(\\mathbf{y}_{\\tau}, \\mathbf{\\hat{y}}_{\\tau}) = \\frac{1}{H} \\sum^{t+H}_{\\tau=t+1} \\frac{|y_{\\tau}-\\hat{y}_{\\tau}|}{|y_{\\tau}|+|\\hat{y}_{\\tau}|}\" />\n",
"\n",
"- Fixes bias of MAPE\n",
"- Equally senstitive to over and under forecasting\n",
"- To be avoided if your data has values close to 0 or equal to 0\n",
"\n",
"With TimeGPT, you can choose your loss function during fine-tuning as to maximize the model's performance metric for your particular use case.\\\n",
"\\\n",
"Let's run a small experiment to see how each loss function improves their associated metric when compared to the default setting."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"train = df[:-36]\n",
"test = df[-36:]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Inferred freq: MS\n",
"WARNING:nixtla.nixtla_client:The specified horizon \"h\" exceeds the model horizon. This may lead to less accurate forecasts. Please consider using a smaller horizon.\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n",
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Inferred freq: MS\n",
"WARNING:nixtla.nixtla_client:The specified horizon \"h\" exceeds the model horizon. This may lead to less accurate forecasts. Please consider using a smaller horizon.\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n",
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Inferred freq: MS\n",
"WARNING:nixtla.nixtla_client:The specified horizon \"h\" exceeds the model horizon. This may lead to less accurate forecasts. Please consider using a smaller horizon.\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n",
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Inferred freq: MS\n",
"WARNING:nixtla.nixtla_client:The specified horizon \"h\" exceeds the model horizon. This may lead to less accurate forecasts. Please consider using a smaller horizon.\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n",
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Inferred freq: MS\n",
"WARNING:nixtla.nixtla_client:The specified horizon \"h\" exceeds the model horizon. This may lead to less accurate forecasts. Please consider using a smaller horizon.\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n",
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Inferred freq: MS\n",
"WARNING:nixtla.nixtla_client:The specified horizon \"h\" exceeds the model horizon. This may lead to less accurate forecasts. Please consider using a smaller horizon.\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n"
]
}
],
"source": [
"losses = ['default', 'mae', 'mse', 'rmse', 'mape', 'smape']\n",
"\n",
"test = test.copy()\n",
"\n",
"for loss in losses:\n",
" preds_df = nixtla_client.forecast(\n",
" df=train, \n",
" h=36, \n",
" finetune_steps=10,\n",
" finetune_loss=loss,\n",
" time_col='timestamp', \n",
" target_col='value')\n",
"\n",
" preds = preds_df['TimeGPT'].values\n",
"\n",
" test.loc[:,f'TimeGPT_{loss}'] = preds"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> 📘 Available models in Azure AI\n",
">\n",
"> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
">\n",
"> `nixtla_client.forecast(..., model=\"azureai\")`\n",
"> \n",
"> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
"> \n",
"> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>timestamp</th>\n",
" <th>value</th>\n",
" <th>TimeGPT_default</th>\n",
" <th>TimeGPT_mae</th>\n",
" <th>TimeGPT_mse</th>\n",
" <th>TimeGPT_rmse</th>\n",
" <th>TimeGPT_mape</th>\n",
" <th>TimeGPT_smape</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>108</th>\n",
" <td>1</td>\n",
" <td>1958-01-01</td>\n",
" <td>340</td>\n",
" <td>347.134094</td>\n",
" <td>341.933563</td>\n",
" <td>347.600616</td>\n",
" <td>347.059113</td>\n",
" <td>356.154938</td>\n",
" <td>341.958679</td>\n",
" </tr>\n",
" <tr>\n",
" <th>109</th>\n",
" <td>1</td>\n",
" <td>1958-02-01</td>\n",
" <td>318</td>\n",
" <td>345.739746</td>\n",
" <td>343.268738</td>\n",
" <td>346.399963</td>\n",
" <td>345.678314</td>\n",
" <td>354.163422</td>\n",
" <td>343.929657</td>\n",
" </tr>\n",
" <tr>\n",
" <th>110</th>\n",
" <td>1</td>\n",
" <td>1958-03-01</td>\n",
" <td>362</td>\n",
" <td>394.611450</td>\n",
" <td>390.873169</td>\n",
" <td>395.436646</td>\n",
" <td>394.636627</td>\n",
" <td>396.496155</td>\n",
" <td>392.543640</td>\n",
" </tr>\n",
" <tr>\n",
" <th>111</th>\n",
" <td>1</td>\n",
" <td>1958-04-01</td>\n",
" <td>348</td>\n",
" <td>404.133545</td>\n",
" <td>400.997070</td>\n",
" <td>404.369598</td>\n",
" <td>403.498901</td>\n",
" <td>396.927185</td>\n",
" <td>402.459625</td>\n",
" </tr>\n",
" <tr>\n",
" <th>112</th>\n",
" <td>1</td>\n",
" <td>1958-05-01</td>\n",
" <td>363</td>\n",
" <td>421.236542</td>\n",
" <td>418.793365</td>\n",
" <td>422.122223</td>\n",
" <td>421.541443</td>\n",
" <td>410.335663</td>\n",
" <td>422.161255</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" unique_id timestamp value TimeGPT_default TimeGPT_mae TimeGPT_mse \\\n",
"108 1 1958-01-01 340 347.134094 341.933563 347.600616 \n",
"109 1 1958-02-01 318 345.739746 343.268738 346.399963 \n",
"110 1 1958-03-01 362 394.611450 390.873169 395.436646 \n",
"111 1 1958-04-01 348 404.133545 400.997070 404.369598 \n",
"112 1 1958-05-01 363 421.236542 418.793365 422.122223 \n",
"\n",
" TimeGPT_rmse TimeGPT_mape TimeGPT_smape \n",
"108 347.059113 356.154938 341.958679 \n",
"109 345.678314 354.163422 343.929657 \n",
"110 394.636627 396.496155 392.543640 \n",
"111 403.498901 396.927185 402.459625 \n",
"112 421.541443 410.335663 422.161255 "
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#| hide\n",
"test.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Great! We have predictions from TimeGPT using all the different loss functions. We can evaluate the performance using their associated metric and measure the improvement."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"loss_fct_dict = {\n",
" \"mae\": mae,\n",
" \"mse\": mse,\n",
" \"rmse\": rmse,\n",
" \"mape\": mape,\n",
" \"smape\": smape\n",
"}\n",
"\n",
"pct_improv = []\n",
"\n",
"for loss in losses[1:]:\n",
" evaluation = loss_fct_dict[f'{loss}'](test, models=['TimeGPT_default', f'TimeGPT_{loss}'], id_col='unique_id', target_col='value')\n",
" pct_diff = (evaluation['TimeGPT_default'] - evaluation[f'TimeGPT_{loss}']) / evaluation['TimeGPT_default'] * 100\n",
" pct_improv.append(round(pct_diff, 2))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>mae</th>\n",
" <th>mse</th>\n",
" <th>rmse</th>\n",
" <th>mape</th>\n",
" <th>smape</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Metric improvement (%)</th>\n",
" <td>8.54</td>\n",
" <td>0.31</td>\n",
" <td>0.64</td>\n",
" <td>31.02</td>\n",
" <td>7.36</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" mae mse rmse mape smape\n",
"Metric improvement (%) 8.54 0.31 0.64 31.02 7.36"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data = {\n",
" 'mae': pct_improv[0].values,\n",
" 'mse': pct_improv[1].values,\n",
" 'rmse': pct_improv[2].values,\n",
" 'mape': pct_improv[3].values,\n",
" 'smape': pct_improv[4].values\n",
"}\n",
"\n",
"metrics_df = pd.DataFrame(data)\n",
"metrics_df.index = ['Metric improvement (%)']\n",
"\n",
"metrics_df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"From the table above, we can see that using a specific loss function during fine-tuning will improve its associated error metric when compared to the default loss function.\\\n",
"\\\n",
"In this example, using the MAE as the loss function improves the metric by 8.54% when compared to using the default loss function.\\\n",
"\\\n",
"That way, depending on your use case and performance metric, you can use the appropriate loss function to maximize the accuracy of the forecasts."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
nbs/docs/tutorials/080_validation.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "markdown",
"id": "6de758ee-a0d2-4b3f-acff-eed419dd17c5",
"metadata": {},
"source": [
"# Validation"
]
},
{
"cell_type": "markdown",
"id": "5d267032-535b-4b7b-b7d3-d2db8f673af6",
"metadata": {},
"source": [
"One of the primary challenges in time series forecasting is the inherent uncertainty and variability over time, making it crucial to validate the accuracy and reliability of the models employed. `TimeGPT` offers the possibility for cross-validation and historical forecasts to help you validate your predictions.\n",
"\n",
"### What You Will Learn\n",
"\n",
"1. **[Cross-Validation](https://docs.nixtla.io/docs/tutorials-cross_validation)**\n",
"\n",
" - Learn how to perform time series cross-validation across different continuous windows of your data. \n",
"\n",
"2. **[Historical Forecasts](https://docs.nixtla.io/docs/tutorials-historical_forecast)**\n",
"\n",
" - Generate in-sample forecasts to validate how `TimeGPT` would have performed in the past, providing insights into the model's accuracy. \n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
nbs/docs/tutorials/08_cross_validation.ipynb 0 → 100644
View file @ f42429f6
This source diff could not be displayed because it is too large. You can view the blob instead.
nbs/docs/tutorials/09_historical_forecast.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "2784576e",
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"!pip install -Uqq nixtla"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5c496982",
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"from nixtla.utils import in_colab"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "08bb6d93",
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"IN_COLAB = in_colab()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "876fee25",
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" from nixtla.utils import colab_badge\n",
" from dotenv import load_dotenv"
]
},
{
"cell_type": "markdown",
"id": "7aada13c-3ac8-4664-92c3-82a96503128a",
"metadata": {},
"source": [
"# Historical forecast"
]
},
{
"cell_type": "markdown",
"id": "9de01fae-a231-4481-a080-f4c1ffe0b0cb",
"metadata": {},
"source": [
"Our time series model offers a powerful feature that allows users to retrieve historical forecasts alongside the prospective predictions. This functionality is accessible through the forecast method by setting the `add_history=True` argument."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b095960a-9a04-4ce7-b31f-babf181c1a8f",
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/tutorials/09_historical_forecast.ipynb)"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#| echo: false\n",
"if not IN_COLAB:\n",
" load_dotenv()\n",
" colab_badge('docs/tutorials/09_historical_forecast')"
]
},
{
"cell_type": "markdown",
"id": "f318762d",
"metadata": {},
"source": [
"## 1. Import packages\n",
"First, we install and import the required packages and initialize the Nixtla client."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "11bdfa31-0b38-4044-9018-ebe1c58f91d6",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from nixtla import NixtlaClient"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5f8b2b2b-4f49-479d-b709-b0db1c61fea8",
"metadata": {},
"outputs": [],
"source": [
"nixtla_client = NixtlaClient(\n",
" # defaults to os.environ.get(\"NIXTLA_API_KEY\")\n",
" api_key = 'my_api_key_provided_by_nixtla'\n",
")"
]
},
{
"cell_type": "markdown",
"id": "dce721eb",
"metadata": {},
"source": [
"> 👍 Use an Azure AI endpoint\n",
">\n",
"> To use an Azure AI endpoint, set the `base_url` argument:\n",
">\n",
"> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8d1a958b-23d9-43c1-882a-3d1348a34b54",
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" nixtla_client = NixtlaClient()"
]
},
{
"cell_type": "markdown",
"id": "9315e2a0",
"metadata": {},
"source": [
"## 2. Load data"
]
},
{
"cell_type": "markdown",
"id": "1266c856-7e04-4b0a-a54e-593d9ae5d723",
"metadata": {},
"source": [
"Now you can start to make forecasts! Let's import an example:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ee0996c2-8b1f-4ec4-9b56-1cd5e4667072",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>timestamp</th>\n",
" <th>value</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1949-01-01</td>\n",
" <td>112</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1949-02-01</td>\n",
" <td>118</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1949-03-01</td>\n",
" <td>132</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1949-04-01</td>\n",
" <td>129</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1949-05-01</td>\n",
" <td>121</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" timestamp value\n",
"0 1949-01-01 112\n",
"1 1949-02-01 118\n",
"2 1949-03-01 132\n",
"3 1949-04-01 129\n",
"4 1949-05-01 121"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv('https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/air_passengers.csv')\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "49d08019-8908-4a4c-8dd1-a2e4def0ce66",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 2400x350 with 1 Axes>"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nixtla_client.plot(df, time_col='timestamp', target_col='value')"
]
},
{
"cell_type": "markdown",
"id": "9dc47b26",
"metadata": {},
"source": [
"## 3. Historical forecast"
]
},
{
"cell_type": "markdown",
"id": "d13dc09e-f606-40d2-94a6-f3b24106e85e",
"metadata": {},
"source": [
"Let's add fitted values. When `add_history` is set to True, the output DataFrame will include not only the future forecasts determined by the h argument, but also the historical predictions. Currently, the historical forecasts are not affected by `h`, and have a fix horizon depending on the frequency of the data. The historical forecasts are produced in a rolling window fashion, and concatenated. This means that the model is applied sequentially at each time step using only the most recent information available up to that point."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3768a453-8d69-4070-b4a0-9ba19e431f0b",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:nixtla.nixtla_client:Validating inputs...\n",
"INFO:nixtla.nixtla_client:Preprocessing dataframes...\n",
"INFO:nixtla.nixtla_client:Inferred freq: MS\n",
"INFO:nixtla.nixtla_client:Calling Forecast Endpoint...\n",
"INFO:nixtla.nixtla_client:Calling Historical Forecast Endpoint...\n"
]
}
],
"source": [
"timegpt_fcst_with_history_df = nixtla_client.forecast(\n",
" df=df, h=12, time_col='timestamp', target_col='value',\n",
" add_history=True,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "6933cbb0",
"metadata": {},
"source": [
"> 📘 Available models in Azure AI\n",
">\n",
"> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
">\n",
"> `nixtla_client.forecast(..., model=\"azureai\")`\n",
"> \n",
"> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
"> \n",
"> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b6ca1274-69ac-4373-a854-827b2deaa2f7",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>timestamp</th>\n",
" <th>TimeGPT</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1951-01-01</td>\n",
" <td>135.483673</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1951-02-01</td>\n",
" <td>144.442398</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1951-03-01</td>\n",
" <td>157.191910</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1951-04-01</td>\n",
" <td>148.769363</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1951-05-01</td>\n",
" <td>140.472946</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" timestamp TimeGPT\n",
"0 1951-01-01 135.483673\n",
"1 1951-02-01 144.442398\n",
"2 1951-03-01 157.191910\n",
"3 1951-04-01 148.769363\n",
"4 1951-05-01 140.472946"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"timegpt_fcst_with_history_df.head()"
]
},
{
"cell_type": "markdown",
"id": "c9d43c9b-414b-41cd-a336-1e478d9cff46",
"metadata": {},
"source": [
"Let's plot the results. This consolidated view of past and future predictions can be invaluable for understanding the model's behavior and for evaluating its performance over time."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2e1e5281-6c6d-4215-add1-2a7066aa491a",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 2400x350 with 1 Axes>"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nixtla_client.plot(df, timegpt_fcst_with_history_df, time_col='timestamp', target_col='value')"
]
},
{
"cell_type": "markdown",
"id": "a7de0a08-d05d-4168-9b4d-523af5067434",
"metadata": {},
"source": [
"Please note, however, that the initial values of the series are not included in these historical forecasts. This is because `TimeGPT` requires a certain number of initial observations to generate reliable forecasts. Therefore, while interpreting the output, it's important to be aware that the first few observations serve as the basis for the model's predictions and are not themselves predicted values."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
nbs/docs/tutorials/100_uncertainty_quantification.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "markdown",
"id": "6de758ee-a0d2-4b3f-acff-eed419dd17c5",
"metadata": {},
"source": [
"# Uncertainty quantification\n",
"\n",
"In forecasting, it is essential to consider the full distribution of predictions rather than only a point prediction. This approach allows for a better understanding of the uncertainty surrounding the forecast. `TimeGPT` supports uncertainty quantification through quantile forecasts and prediction intervals.\n",
"\n",
"### What You Will Learn\n",
"\n",
"1. **[Quantile Forecasts](https://docs.nixtla.io/docs/tutorials-quantile_forecasts)**\n",
"\n",
" - Learn how to compute specific quantiles of the forecast distribution using `TimeGPT`. \n",
"\n",
"2. **[Prediction Intervals](https://docs.nixtla.io/docs/tutorials-prediction_intervals)**\n",
"\n",
" - Learn how to generate prediction intervals with `TimeGPT`, which give you a range of values that the forecast can take with a given probability. \n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
nbs/docs/tutorials/10_uncertainty_quantification_with_quantile_forecasts.ipynb 0 → 100644
View file @ f42429f6
This source diff could not be displayed because it is too large. You can view the blob instead.
nbs/docs/tutorials/11_uncertainty_quantification_with_prediction_intervals.ipynb 0 → 100644
View file @ f42429f6
This source diff could not be displayed because it is too large. You can view the blob instead.
nbs/docs/tutorials/120_special_topics.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "markdown",
"id": "6de758ee-a0d2-4b3f-acff-eed419dd17c5",
"metadata": {},
"source": [
"# Special topics"
]
},
{
"cell_type": "markdown",
"id": "5d267032-535b-4b7b-b7d3-d2db8f673af6",
"metadata": {},
"source": [
"`TimeGPT` is a robust foundation model for time series forecasting, with advanced capabilities such as hierarchical and bounded forecasts. To fully leverage the power of `TimeGPT`, there are specific situations that require special consideration, such as dealing with irregular timestamps or handling datasets with missing values.\n",
"\n",
"In this section, we will cover these special topics.\n",
"\n",
"### What You Will Learn\n",
"\n",
"1. **[Irregular Timestamps](https://docs.nixtla.io/docs/capabilities-forecast-irregular_timestamps)**\n",
"\n",
" - Learn how to deal with irregular timestamps for correct usage of `TimeGPT`.\n",
"\n",
"2. **[Bounded Forecasts](https://docs.nixtla.io/docs/tutorials-bounded_forecasts)**\n",
"\n",
" - Explore `TimeGPT`'s capability to make forecasts within a specified range, ideal for applications where outcomes are bounded.\n",
"\n",
"3. **[Hierarchical Forecasts](https://docs.nixtla.io/docs/tutorials-hierarchical_forecasting)**\n",
"\n",
" - Understand how to use `TimeGPT` to make coherent predictions at various levels of aggregation.\n",
"\n",
"4. **[Missing Values](https://docs.nixtla.io/docs/tutorials-missing_values)**\n",
"\n",
" - Learn how to address missing values within your time series data effectively using `TimeGPT`.\n",
"\n",
"5. **[Improve Forecast Accuracy](https://docs.nixtla.io/docs/tutorials-improve_forecast_accuracy_with_timegpt)**\n",
"\n",
" - Discover multiple techniques to boost forecast accuracy when working with `TimeGPT`."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
nbs/docs/tutorials/13_bounded_forecasts.ipynb 0 → 100644
View file @ f42429f6
This source diff could not be displayed because it is too large. You can view the blob instead.
nbs/docs/tutorials/14_hierarchical_forecasting.ipynb 0 → 100644
View file @ f42429f6
This source diff could not be displayed because it is too large. You can view the blob instead.
nbs/docs/tutorials/15_missing_values.ipynb 0 → 100644
View file @ f42429f6
This source diff could not be displayed because it is too large. You can view the blob instead.
nbs/docs/tutorials/16_computing_at_scale.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Computing at scale"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Handling large datasets is a common challenge in time series forecasting. For example, when working with retail data, you may have to forecast sales for thousands of products across hundreds of stores. Similarly, when dealing with electricity consumption data, you may need to predict consumption for thousands of households across various regions.\n",
"\n",
"Nixtla's `TimeGPT` enables you to use several distributed computing frameworks to manage large datasets efficiently. `TimeGPT` currently supports `Spark`, `Dask`, and `Ray` through `Fugue`.\n",
"\n",
"In this notebook, we will explain how to leverage these frameworks using `TimeGPT`. \n",
"\n",
"**Outline:**\n",
"\n",
"1. [Getting Started](#1-getting-started)\n",
"\n",
"2. [Forecasting at Scale](#2-forecasting-at-scale) \n",
"\n",
"3. [Important Considerations](#3-important-considerations) "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Getting started \n",
"\n",
"To use `TimeGPT` with any of the supported distributed computing frameworks, you first need an API Key, just as you would when not using any distributed computing.\n",
"\n",
"Upon [registration](https://dashboard.nixtla.io/), you will receive an email asking you to confirm your signup. After confirming, you will receive access to your dashboard. There, under`API Keys`, you will find your API Key. Next, you need to integrate your API Key into your development workflow with the Nixtla SDK. For guidance on how to do this, please refer to the [Setting Up Your Authentication Key tutorial](https://docs.nixtla.io/docs/getting-started-setting_up_your_api_key)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Forecasting at Scale "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Using `TimeGPT` with any of the supported distributed computing frameworks is straightforward and its usage is almost identical to the non-distributed case. \n",
"\n",
"1. Instantiate a `NixtlaClient` class.\n",
"2. Load your data as a `pandas` DataFrame.\n",
"3. Initialize the distributed computing framework. \n",
" - [Spark](https://docs.nixtla.io/docs/tutorials-spark)\n",
" - [Dask](https://docs.nixtla.io/docs/tutorials-dask)\n",
" - [Ray](https://docs.nixtla.io/docs/tutorials-ray)\n",
"4. Use any of the `NixtlaClient` class methods.\n",
"5. Stop the distributed computing framework, if necessary. \n",
"\n",
"These are the general steps that you will need to follow to use `TimeGPT` with any of the supported distributed computing frameworks. For a detailed explanation and a complete example, please refer to the guide for the specific framework linked above."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"::: {.callout-important}\n",
"Parallelization in these frameworks is done along the various time series within your dataset. Therefore, it is essential that your dataset includes multiple time series, each with a unique id. \n",
":::"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Important Considerations "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### When to Use a Distributed Computing Framework\n",
"\n",
"Consider using a distributed computing framework if your dataset:\n",
"\n",
"- Consists of millions of observations over multiple time series.\n",
"- Is too large to fit into the memory of a single machine.\n",
"- Would be too slow to process on a single machine.\n",
"\n",
"### Choosing the Right Framework\n",
"\n",
"When selecting a distributed computing framework, take into account your existing infrastructure and the skill set of your team. Although `TimeGPT` can be used with any of the supported frameworks with minimal code changes, choosing the right one should align with your specific needs and resources. This will ensure that you leverage the full potential of `TimeGPT` while handling large datasets efficiently."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
nbs/docs/tutorials/17_computing_at_scale_spark_distributed.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"!pip install -Uqq nixtla fugue[spark]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"from nixtla.utils import in_colab"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"IN_COLAB = in_colab()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" from nixtla.utils import colab_badge\n",
" from dotenv import load_dotenv"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Spark\n",
"\n",
"> Run TimeGPT distributedly on top of Spark"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"[Spark](https://spark.apache.org/) is an open-source distributed computing framework designed for large-scale data processing. In this guide, we will explain how to use `TimeGPT` on top of Spark. \n",
"\n",
"**Outline:** \n",
"\n",
"1. [Installation](#installation)\n",
"\n",
"2. [Load Your Data](#load-your-data)\n",
"\n",
"3. [Initialize Spark](#initialize-spark) \n",
"\n",
"4. [Use TimeGPT on Spark](#use-timegpt-on-spark)\n",
"\n",
"5. [Stop Spark](#stop-spark)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/tutorials/16_computing_at_scale_spark_distributed.ipynb)"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#| echo: false\n",
"if not IN_COLAB:\n",
" load_dotenv()\n",
" colab_badge('docs/tutorials/17_computing_at_scale_spark_distributed')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Installation "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Install Spark through [Fugue](https://fugue-tutorials.readthedocs.io/). Fugue provides an easy-to-use interface for distributed computing that lets users execute Python code on top of several distributed computing frameworks, including Spark. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"::: {.callout-note}\n",
"You can install `fugue` with `pip`:\n",
" \n",
"```shell\n",
"pip install fugue[spark]\n",
"```\n",
":::"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"If executing on a distributed `Spark` cluster, ensure that the `nixtla` library is installed across all the workers."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Load Data "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can load your data as a `pandas` DataFrame. In this tutorial, we will use a dataset that contains hourly electricity prices from different markets. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>ds</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 00:00:00</td>\n",
" <td>70.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 01:00:00</td>\n",
" <td>37.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 02:00:00</td>\n",
" <td>37.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 03:00:00</td>\n",
" <td>44.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 04:00:00</td>\n",
" <td>37.10</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" unique_id ds y\n",
"0 BE 2016-10-22 00:00:00 70.00\n",
"1 BE 2016-10-22 01:00:00 37.10\n",
"2 BE 2016-10-22 02:00:00 37.10\n",
"3 BE 2016-10-22 03:00:00 44.75\n",
"4 BE 2016-10-22 04:00:00 37.10"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv(\n",
" 'https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/electricity-short.csv',\n",
" parse_dates=['ds'],\n",
") \n",
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Initialize Spark "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Initialize `Spark` and convert the pandas DataFrame to a `Spark` DataFrame. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from pyspark.sql import SparkSession"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"spark = SparkSession.builder.getOrCreate()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"spark_df = spark.createDataFrame(df)\n",
"spark_df.show(5)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. Use TimeGPT on Spark "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Using `TimeGPT` on top of `Spark` is almost identical to the non-distributed case. The only difference is that you need to use a `Spark` DataFrame. \n",
"\n",
"First, instantiate the `NixtlaClient` class. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from nixtla import NixtlaClient"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"nixtla_client = NixtlaClient(\n",
" # defaults to os.environ.get(\"NIXTLA_API_KEY\")\n",
" api_key = 'my_api_key_provided_by_nixtla'\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> 👍 Use an Azure AI endpoint\n",
">\n",
"> To use an Azure AI endpoint, set the `base_url` argument:\n",
">\n",
"> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"if not IN_COLAB:\n",
" nixtla_client = NixtlaClient()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Then use any method from the `NixtlaClient` class such as [`forecast`](https://nixtlaverse.nixtla.io/nixtla/nixtla_client.html#nixtlaclient-forecast) or [`cross_validation`](https://nixtlaverse.nixtla.io/nixtla/nixtla_client.html#nixtlaclient-cross-validation)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"fcst_df = nixtla_client.forecast(spark_df, h=12)\n",
"fcst_df.show(5)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> 📘 Available models in Azure AI\n",
">\n",
"> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
">\n",
"> `nixtla_client.forecast(..., model=\"azureai\")`\n",
"> \n",
"> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
"> \n",
"> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"cv_df = nixtla_client.cross_validation(spark_df, h=12, n_windows=5, step_size=2)\n",
"cv_df.show(5)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can also use exogenous variables with `TimeGPT` on top of `Spark`. To do this, please refer to the [Exogenous Variables](https://docs.nixtla.io/docs/tutorials-exogenous_variables) tutorial. Just keep in mind that instead of using a pandas DataFrame, you need to use a `Spark` DataFrame instead."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 5. Stop Spark "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"When you are done, stop the `Spark` session. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"spark.stop()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
nbs/docs/tutorials/18_computing_at_scale_dask_distributed.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"!pip install -Uqq nixtla fugue[dask]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"from nixtla.utils import in_colab"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"IN_COLAB = in_colab()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" from nixtla.utils import colab_badge\n",
" from dotenv import load_dotenv"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Dask\n",
"\n",
"> Run TimeGPT distributedly on top of Dask"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"[Dask](https://www.dask.org/get-started) is an open source parallel computing library for Python. In this guide, we will explain how to use `TimeGPT` on top of Dask. \n",
"\n",
"**Outline:** \n",
"\n",
"1. [Installation](#installation)\n",
"\n",
"2. [Load Your Data](#load-your-data)\n",
"\n",
"3. [Import Dask](#import-dask) \n",
"\n",
"4. [Use TimeGPT on Dask](#use-timegpt-on-dask)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/tutorials/17_computing_at_scale_dask_distributed.ipynb)"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#| echo: false\n",
"if not IN_COLAB:\n",
" load_dotenv()\n",
" colab_badge('docs/tutorials/18_computing_at_scale_dask_distributed')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Installation "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Install Dask through [Fugue](https://fugue-tutorials.readthedocs.io/). Fugue provides an easy-to-use interface for distributed computing that lets users execute Python code on top of several distributed computing frameworks, including Dask. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"::: {.callout-note}\n",
"You can install `fugue` with `pip`:\n",
" \n",
"```shell\n",
"pip install fugue[dask]\n",
"```\n",
":::"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"If executing on a distributed `Dask` cluster, ensure that the `nixtla` library is installed across all the workers."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Load Data "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can load your data as a `pandas` DataFrame. In this tutorial, we will use a dataset that contains hourly electricity prices from different markets. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>ds</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 00:00:00</td>\n",
" <td>70.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 01:00:00</td>\n",
" <td>37.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 02:00:00</td>\n",
" <td>37.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 03:00:00</td>\n",
" <td>44.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 04:00:00</td>\n",
" <td>37.10</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" unique_id ds y\n",
"0 BE 2016-10-22 00:00:00 70.00\n",
"1 BE 2016-10-22 01:00:00 37.10\n",
"2 BE 2016-10-22 02:00:00 37.10\n",
"3 BE 2016-10-22 03:00:00 44.75\n",
"4 BE 2016-10-22 04:00:00 37.10"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv(\n",
" 'https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/electricity-short.csv',\n",
" parse_dates=['ds'],\n",
") \n",
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Import Dask"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Import Dask and convert the `pandas` DataFrame to a Dask DataFrame. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import dask.dataframe as dd"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div><strong>Dask DataFrame Structure:</strong></div>\n",
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>ds</th>\n",
" <th>y</th>\n",
" </tr>\n",
" <tr>\n",
" <th>npartitions=2</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>string</td>\n",
" <td>string</td>\n",
" <td>float64</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4200</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8399</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
"<div>Dask Name: to_pyarrow_string, 2 graph layers</div>"
],
"text/plain": [
"Dask DataFrame Structure:\n",
" unique_id ds y\n",
"npartitions=2 \n",
"0 string string float64\n",
"4200 ... ... ...\n",
"8399 ... ... ...\n",
"Dask Name: to_pyarrow_string, 2 graph layers"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dask_df = dd.from_pandas(df, npartitions=2)\n",
"dask_df "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. Use TimeGPT on Dask "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Using `TimeGPT` on top of `Dask` is almost identical to the non-distributed case. The only difference is that you need to use a `Dask` DataFrame, which we already defined in the previous step. \n",
"\n",
"First, instantiate the `NixtlaClient` class. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from nixtla import NixtlaClient"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"nixtla_client = NixtlaClient(\n",
" # defaults to os.environ.get(\"NIXTLA_API_KEY\")\n",
" api_key = 'my_api_key_provided_by_nixtla'\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> 👍 Use an Azure AI endpoint\n",
">\n",
"> To use an Azure AI endpoint, set the `base_url` argument:\n",
">\n",
"> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"if not IN_COLAB:\n",
" nixtla_client = NixtlaClient()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Then use any method from the `NixtlaClient` class such as [`forecast`](https://nixtlaverse.nixtla.io/nixtla/nixtla_client.html#nixtlaclient-forecast) or [`cross_validation`](https://nixtlaverse.nixtla.io/nixtla/nixtla_client.html#nixtlaclient-cross-validation)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>ds</th>\n",
" <th>TimeGPT</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>BE</td>\n",
" <td>2016-12-31 00:00:00</td>\n",
" <td>45.190453</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>BE</td>\n",
" <td>2016-12-31 01:00:00</td>\n",
" <td>43.244446</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>BE</td>\n",
" <td>2016-12-31 02:00:00</td>\n",
" <td>41.958389</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>BE</td>\n",
" <td>2016-12-31 03:00:00</td>\n",
" <td>39.796486</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>BE</td>\n",
" <td>2016-12-31 04:00:00</td>\n",
" <td>39.204533</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" unique_id ds TimeGPT\n",
"0 BE 2016-12-31 00:00:00 45.190453\n",
"1 BE 2016-12-31 01:00:00 43.244446\n",
"2 BE 2016-12-31 02:00:00 41.958389\n",
"3 BE 2016-12-31 03:00:00 39.796486\n",
"4 BE 2016-12-31 04:00:00 39.204533"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fcst_df = nixtla_client.forecast(dask_df, h=12)\n",
"fcst_df.compute().head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> 📘 Available models in Azure AI\n",
">\n",
"> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
">\n",
"> `nixtla_client.forecast(..., model=\"azureai\")`\n",
"> \n",
"> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
"> \n",
"> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>ds</th>\n",
" <th>cutoff</th>\n",
" <th>TimeGPT</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>BE</td>\n",
" <td>2016-12-30 04:00:00</td>\n",
" <td>2016-12-30 03:00:00</td>\n",
" <td>39.375439</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>BE</td>\n",
" <td>2016-12-30 05:00:00</td>\n",
" <td>2016-12-30 03:00:00</td>\n",
" <td>40.039215</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>BE</td>\n",
" <td>2016-12-30 06:00:00</td>\n",
" <td>2016-12-30 03:00:00</td>\n",
" <td>43.455849</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>BE</td>\n",
" <td>2016-12-30 07:00:00</td>\n",
" <td>2016-12-30 03:00:00</td>\n",
" <td>47.716408</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>BE</td>\n",
" <td>2016-12-30 08:00:00</td>\n",
" <td>2016-12-30 03:00:00</td>\n",
" <td>50.31665</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" unique_id ds cutoff TimeGPT\n",
"0 BE 2016-12-30 04:00:00 2016-12-30 03:00:00 39.375439\n",
"1 BE 2016-12-30 05:00:00 2016-12-30 03:00:00 40.039215\n",
"2 BE 2016-12-30 06:00:00 2016-12-30 03:00:00 43.455849\n",
"3 BE 2016-12-30 07:00:00 2016-12-30 03:00:00 47.716408\n",
"4 BE 2016-12-30 08:00:00 2016-12-30 03:00:00 50.31665"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cv_df = nixtla_client.cross_validation(dask_df, h=12, n_windows=5, step_size=2)\n",
"cv_df.compute().head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can also use exogenous variables with `TimeGPT` on top of `Dask`. To do this, please refer to the [Exogenous Variables](https://docs.nixtla.io/docs/tutorials-exogenous_variables) tutorial. Just keep in mind that instead of using a pandas DataFrame, you need to use a `Dask` DataFrame instead."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
nbs/docs/tutorials/19_computing_at_scale_ray_distributed.ipynb 0 → 100644
View file @ f42429f6
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"!pip install -Uqq nixtla fugue[ray]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"from nixtla.utils import in_colab"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"IN_COLAB = in_colab()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide\n",
"if not IN_COLAB:\n",
" from nixtla.utils import colab_badge\n",
" from dotenv import load_dotenv"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Ray \n",
"\n",
"> Run TimeGPT distributedly on top of Ray"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"[Ray](https://www.ray.io/) is an open source unified compute framework to scale Python workloads. In this guide, we will explain how to use `TimeGPT` on top of Ray. \n",
"\n",
"**Outline:** \n",
"\n",
"1. [Installation](#installation)\n",
"\n",
"2. [Load Your Data](#load-your-data)\n",
"\n",
"3. [Initialize Ray](#initialize-ray) \n",
"\n",
"4. [Use TimeGPT on Ray](#use-timegpt-on-ray)\n",
"\n",
"5. [Shutdown Ray](#shutdown-ray)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/tutorials/19_computing_at_scale_ray_distributed.ipynb)"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#| echo: false\n",
"if not IN_COLAB:\n",
" load_dotenv()\n",
" colab_badge('docs/tutorials/19_computing_at_scale_ray_distributed')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Installation "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Install Ray through [Fugue](https://fugue-tutorials.readthedocs.io/). Fugue provides an easy-to-use interface for distributed computing that lets users execute Python code on top of several distributed computing frameworks, including Ray. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"::: {.callout-note}\n",
"You can install `fugue` with `pip`:\n",
" \n",
"```shell\n",
"pip install fugue[ray]\n",
"```\n",
":::"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"If executing on a distributed `Ray` cluster, ensure that the `nixtla` library is installed across all the workers."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Load Data "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can load your data as a `pandas` DataFrame. In this tutorial, we will use a dataset that contains hourly electricity prices from different markets. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>ds</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 00:00:00</td>\n",
" <td>70.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 01:00:00</td>\n",
" <td>37.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 02:00:00</td>\n",
" <td>37.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 03:00:00</td>\n",
" <td>44.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>BE</td>\n",
" <td>2016-10-22 04:00:00</td>\n",
" <td>37.10</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" unique_id ds y\n",
"0 BE 2016-10-22 00:00:00 70.00\n",
"1 BE 2016-10-22 01:00:00 37.10\n",
"2 BE 2016-10-22 02:00:00 37.10\n",
"3 BE 2016-10-22 03:00:00 44.75\n",
"4 BE 2016-10-22 04:00:00 37.10"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv(\n",
" 'https://raw.githubusercontent.com/Nixtla/transfer-learning-time-series/main/datasets/electricity-short.csv',\n",
" parse_dates=['ds'],\n",
") \n",
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Initialize Ray"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Initialize `Ray` and convert the pandas DataFrame to a `Ray` DataFrame. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import ray\n",
"from ray.cluster_utils import Cluster"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2024-05-10 11:09:17,240\tWARNING cluster_utils.py:157 -- Ray cluster mode is currently experimental and untested on Windows. If you are using it and running into issues please file a report at https://github.com/ray-project/ray/issues.\n",
"2024-05-10 11:09:19,076\tINFO worker.py:1564 -- Connecting to existing Ray cluster at address: 127.0.0.1:63694...\n",
"2024-05-10 11:09:19,092\tINFO worker.py:1740 -- Connected to Ray cluster. View the dashboard at \u001b[1m\u001b[32m127.0.0.1:8265 \u001b[39m\u001b[22m\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "1205bee3f172455d9d3f706c2b0ae98b",
"version_major": 2,
"version_minor": 0
},
"text/html": [
"<div class=\"lm-Widget p-Widget lm-Panel p-Panel jp-Cell-outputWrapper\">\n",
" <div style=\"margin-left: 50px;display: flex;flex-direction: row;align-items: center\">\n",
" <div class=\"jp-RenderedHTMLCommon\" style=\"display: flex; flex-direction: row;\">\n",
" <svg viewBox=\"0 0 567 224\" fill=\"none\" xmlns=\"http://www.w3.org/2000/svg\" style=\"height: 3em;\">\n",
" <g clip-path=\"url(#clip0_4338_178347)\">\n",
" <path d=\"M341.29 165.561H355.29L330.13 129.051C345.63 123.991 354.21 112.051 354.21 94.2307C354.21 71.3707 338.72 58.1807 311.88 58.1807H271V165.561H283.27V131.661H311.8C314.25 131.661 316.71 131.501 319.01 131.351L341.25 165.561H341.29ZM283.29 119.851V70.0007H311.82C331.3 70.0007 342.34 78.2907 342.34 94.5507C342.34 111.271 331.34 119.861 311.82 119.861L283.29 119.851ZM451.4 138.411L463.4 165.561H476.74L428.74 58.1807H416L367.83 165.561H380.83L392.83 138.411H451.4ZM446.19 126.601H398L422 72.1407L446.24 126.601H446.19ZM526.11 128.741L566.91 58.1807H554.35L519.99 114.181L485.17 58.1807H472.44L514.01 129.181V165.541H526.13V128.741H526.11Z\" fill=\"var(--jp-ui-font-color0)\"/>\n",
" <path d=\"M82.35 104.44C84.0187 97.8827 87.8248 92.0678 93.1671 87.9146C98.5094 83.7614 105.083 81.5067 111.85 81.5067C118.617 81.5067 125.191 83.7614 130.533 87.9146C135.875 92.0678 139.681 97.8827 141.35 104.44H163.75C164.476 101.562 165.622 98.8057 167.15 96.2605L127.45 56.5605C121.071 60.3522 113.526 61.6823 106.235 60.3005C98.9443 58.9187 92.4094 54.9203 87.8602 49.0574C83.3109 43.1946 81.0609 35.8714 81.5332 28.4656C82.0056 21.0599 85.1679 14.0819 90.4252 8.8446C95.6824 3.60726 102.672 0.471508 110.08 0.0272655C117.487 -0.416977 124.802 1.86091 130.647 6.4324C136.493 11.0039 140.467 17.5539 141.821 24.8501C143.175 32.1463 141.816 39.6859 138 46.0505L177.69 85.7505C182.31 82.9877 187.58 81.4995 192.962 81.4375C198.345 81.3755 203.648 82.742 208.33 85.3976C213.012 88.0532 216.907 91.9029 219.616 96.5544C222.326 101.206 223.753 106.492 223.753 111.875C223.753 117.258 222.326 122.545 219.616 127.197C216.907 131.848 213.012 135.698 208.33 138.353C203.648 141.009 198.345 142.375 192.962 142.313C187.58 142.251 182.31 140.763 177.69 138L138 177.7C141.808 184.071 143.155 191.614 141.79 198.91C140.424 206.205 136.44 212.75 130.585 217.313C124.731 221.875 117.412 224.141 110.004 223.683C102.596 223.226 95.6103 220.077 90.3621 214.828C85.1139 209.58 81.9647 202.595 81.5072 195.187C81.0497 187.779 83.3154 180.459 87.878 174.605C92.4405 168.751 98.9853 164.766 106.281 163.401C113.576 162.035 121.119 163.383 127.49 167.19L167.19 127.49C165.664 124.941 164.518 122.182 163.79 119.3H141.39C139.721 125.858 135.915 131.673 130.573 135.826C125.231 139.98 118.657 142.234 111.89 142.234C105.123 142.234 98.5494 139.98 93.2071 135.826C87.8648 131.673 84.0587 125.858 82.39 119.3H60C58.1878 126.495 53.8086 132.78 47.6863 136.971C41.5641 141.163 34.1211 142.972 26.7579 142.059C19.3947 141.146 12.6191 137.574 7.70605 132.014C2.79302 126.454 0.0813599 119.29 0.0813599 111.87C0.0813599 104.451 2.79302 97.2871 7.70605 91.7272C12.6191 86.1673 19.3947 82.5947 26.7579 81.6817C34.1211 80.7686 41.5641 82.5781 47.6863 86.7696C53.8086 90.9611 58.1878 97.2456 60 104.44H82.35ZM100.86 204.32C103.407 206.868 106.759 208.453 110.345 208.806C113.93 209.159 117.527 208.258 120.522 206.256C123.517 204.254 125.725 201.276 126.771 197.828C127.816 194.38 127.633 190.677 126.253 187.349C124.874 184.021 122.383 181.274 119.205 179.577C116.027 177.88 112.359 177.337 108.826 178.042C105.293 178.746 102.113 180.654 99.8291 183.44C97.5451 186.226 96.2979 189.718 96.3 193.32C96.2985 195.364 96.7006 197.388 97.4831 199.275C98.2656 201.163 99.4132 202.877 100.86 204.32ZM204.32 122.88C206.868 120.333 208.453 116.981 208.806 113.396C209.159 109.811 208.258 106.214 206.256 103.219C204.254 100.223 201.275 98.0151 197.827 96.97C194.38 95.9249 190.676 96.1077 187.348 97.4873C184.02 98.8669 181.274 101.358 179.577 104.536C177.879 107.714 177.337 111.382 178.041 114.915C178.746 118.448 180.653 121.627 183.439 123.911C186.226 126.195 189.717 127.443 193.32 127.44C195.364 127.443 197.388 127.042 199.275 126.259C201.163 125.476 202.878 124.328 204.32 122.88ZM122.88 19.4205C120.333 16.8729 116.981 15.2876 113.395 14.9347C109.81 14.5817 106.213 15.483 103.218 17.4849C100.223 19.4868 98.0146 22.4654 96.9696 25.9131C95.9245 29.3608 96.1073 33.0642 97.4869 36.3922C98.8665 39.7202 101.358 42.4668 104.535 44.1639C107.713 45.861 111.381 46.4036 114.914 45.6992C118.447 44.9949 121.627 43.0871 123.911 40.301C126.195 37.515 127.442 34.0231 127.44 30.4205C127.44 28.3772 127.038 26.3539 126.255 24.4664C125.473 22.5788 124.326 20.8642 122.88 19.4205ZM19.42 100.86C16.8725 103.408 15.2872 106.76 14.9342 110.345C14.5813 113.93 15.4826 117.527 17.4844 120.522C19.4863 123.518 22.4649 125.726 25.9127 126.771C29.3604 127.816 33.0638 127.633 36.3918 126.254C39.7198 124.874 42.4664 122.383 44.1635 119.205C45.8606 116.027 46.4032 112.359 45.6988 108.826C44.9944 105.293 43.0866 102.114 40.3006 99.8296C37.5145 97.5455 34.0227 96.2983 30.42 96.3005C26.2938 96.3018 22.337 97.9421 19.42 100.86ZM100.86 100.86C98.3125 103.408 96.7272 106.76 96.3742 110.345C96.0213 113.93 96.9226 117.527 98.9244 120.522C100.926 123.518 103.905 125.726 107.353 126.771C110.8 127.816 114.504 127.633 117.832 126.254C121.16 124.874 123.906 122.383 125.604 119.205C127.301 116.027 127.843 112.359 127.139 108.826C126.434 105.293 124.527 102.114 121.741 99.8296C118.955 97.5455 115.463 96.2983 111.86 96.3005C109.817 96.299 107.793 96.701 105.905 97.4835C104.018 98.2661 102.303 99.4136 100.86 100.86Z\" fill=\"#00AEEF\"/>\n",
" </g>\n",
" <defs>\n",
" <clipPath id=\"clip0_4338_178347\">\n",
" <rect width=\"566.93\" height=\"223.75\" fill=\"white\"/>\n",
" </clipPath>\n",
" </defs>\n",
" </svg>\n",
"</div>\n",
"\n",
" <table class=\"jp-RenderedHTMLCommon\" style=\"border-collapse: collapse;color: var(--jp-ui-font-color1);font-size: var(--jp-ui-font-size1);\">\n",
" <tr>\n",
" <td style=\"text-align: left\"><b>Python version:</b></td>\n",
" <td style=\"text-align: left\"><b>3.10.14</b></td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left\"><b>Ray version:</b></td>\n",
" <td style=\"text-align: left\"><b>2.20.0</b></td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left\"><b>Dashboard:</b></td>\n",
" <td style=\"text-align: left\"><b><a href=\"http://127.0.0.1:8265\" target=\"_blank\">http://127.0.0.1:8265</a></b></td>\n",
"</tr>\n",
"\n",
"</table>\n",
"\n",
" </div>\n",
"</div>\n"
],
"text/plain": [
"RayContext(dashboard_url='127.0.0.1:8265', python_version='3.10.14', ray_version='2.20.0', ray_commit='5708e75978413e46c703e44f43fd89769f3c148b')"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#| output: false\n",
"ray_cluster = Cluster(\n",
" initialize_head=True,\n",
" head_node_args={\"num_cpus\": 2}\n",
")\n",
"ray.init(address=ray_cluster.address, ignore_reinit_error=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "43bbf566465c45368606a5fb057bf534",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"MaterializedDataset(\n",
" num_blocks=1,\n",
" num_rows=8400,\n",
" schema={unique_id: object, ds: object, y: float64}\n",
")"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ray_df = ray.data.from_pandas(df)\n",
"ray_df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. Use TimeGPT on Ray"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Using `TimeGPT` on top of `Ray` is almost identical to the non-distributed case. The only difference is that you need to use a `Ray` DataFrame. \n",
"\n",
"First, instantiate the `NixtlaClient` class. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from nixtla import NixtlaClient"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"nixtla_client = NixtlaClient(\n",
" # defaults to os.environ.get(\"NIXTLA_API_KEY\")\n",
" api_key = 'my_api_key_provided_by_nixtla'\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> 👍 Use an Azure AI endpoint\n",
">\n",
"> To use an Azure AI endpoint, set the `base_url` argument:\n",
">\n",
"> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| hide \n",
"if not IN_COLAB:\n",
" nixtla_client = NixtlaClient()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Then use any method from the `NixtlaClient` class such as [`forecast`](https://nixtlaverse.nixtla.io/nixtla/nixtla_client.html#nixtlaclient-forecast) or [`cross_validation`](https://nixtlaverse.nixtla.io/nixtla/nixtla_client.html#nixtlaclient-cross-validation)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%capture\n",
"fcst_df = nixtla_client.forecast(ray_df, h=12)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> 📘 Available models in Azure AI\n",
">\n",
"> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
">\n",
"> `nixtla_client.forecast(..., model=\"azureai\")`\n",
"> \n",
"> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
"> \n",
"> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To visualize the result, use the `to_pandas` method to convert the output of `Ray` to a `pandas` DataFrame."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>ds</th>\n",
" <th>TimeGPT</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>55</th>\n",
" <td>NP</td>\n",
" <td>2018-12-24 07:00:00</td>\n",
" <td>55.387066</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56</th>\n",
" <td>NP</td>\n",
" <td>2018-12-24 08:00:00</td>\n",
" <td>56.115517</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>NP</td>\n",
" <td>2018-12-24 09:00:00</td>\n",
" <td>56.090714</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58</th>\n",
" <td>NP</td>\n",
" <td>2018-12-24 10:00:00</td>\n",
" <td>55.813717</td>\n",
" </tr>\n",
" <tr>\n",
" <th>59</th>\n",
" <td>NP</td>\n",
" <td>2018-12-24 11:00:00</td>\n",
" <td>55.528519</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" unique_id ds TimeGPT\n",
"55 NP 2018-12-24 07:00:00 55.387066\n",
"56 NP 2018-12-24 08:00:00 56.115517\n",
"57 NP 2018-12-24 09:00:00 56.090714\n",
"58 NP 2018-12-24 10:00:00 55.813717\n",
"59 NP 2018-12-24 11:00:00 55.528519"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fcst_df.to_pandas().tail()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%capture\n",
"cv_df = nixtla_client.cross_validation(ray_df, h=12, freq='H', n_windows=5, step_size=2)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>unique_id</th>\n",
" <th>ds</th>\n",
" <th>cutoff</th>\n",
" <th>TimeGPT</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>295</th>\n",
" <td>NP</td>\n",
" <td>2018-12-23 19:00:00</td>\n",
" <td>2018-12-23 11:00:00</td>\n",
" <td>53.632019</td>\n",
" </tr>\n",
" <tr>\n",
" <th>296</th>\n",
" <td>NP</td>\n",
" <td>2018-12-23 20:00:00</td>\n",
" <td>2018-12-23 11:00:00</td>\n",
" <td>52.512775</td>\n",
" </tr>\n",
" <tr>\n",
" <th>297</th>\n",
" <td>NP</td>\n",
" <td>2018-12-23 21:00:00</td>\n",
" <td>2018-12-23 11:00:00</td>\n",
" <td>51.894035</td>\n",
" </tr>\n",
" <tr>\n",
" <th>298</th>\n",
" <td>NP</td>\n",
" <td>2018-12-23 22:00:00</td>\n",
" <td>2018-12-23 11:00:00</td>\n",
" <td>51.06572</td>\n",
" </tr>\n",
" <tr>\n",
" <th>299</th>\n",
" <td>NP</td>\n",
" <td>2018-12-23 23:00:00</td>\n",
" <td>2018-12-23 11:00:00</td>\n",
" <td>50.32592</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" unique_id ds cutoff TimeGPT\n",
"295 NP 2018-12-23 19:00:00 2018-12-23 11:00:00 53.632019\n",
"296 NP 2018-12-23 20:00:00 2018-12-23 11:00:00 52.512775\n",
"297 NP 2018-12-23 21:00:00 2018-12-23 11:00:00 51.894035\n",
"298 NP 2018-12-23 22:00:00 2018-12-23 11:00:00 51.06572\n",
"299 NP 2018-12-23 23:00:00 2018-12-23 11:00:00 50.32592"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cv_df.to_pandas().tail()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can also use exogenous variables with `TimeGPT` on top of `Ray`. To do this, please refer to the [Exogenous Variables](https://docs.nixtla.io/docs/tutorials-exogenous_variables) tutorial. Just keep in mind that instead of using a pandas DataFrame, you need to use a `Ray` DataFrame instead."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 5. Shutdown Ray"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"When you are done, shutdown the `Ray` session. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ray.shutdown()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment