Dart based forecasting

Few experiments Transformer based / Exponential based

Time Series Made Easy in Python

	import pandas as pd
	from darts import TimeSeries
	from sklearn.preprocessing import MinMaxScaler
	import numpy as np
	#ExponentialSmoothing Model
	link = 'https://raw.githubusercontent.com/Geoffrey-Z/Multivariate-Time-Series-Forecasting-with-LSTMs-in-Keras-for-CORN-SWEET-Terminal-Market-Price/master/Dataset/BI-COLOR%20CORN-SWEET%20MONTHLY%20PRICE%201998-2018.csv'
	df = pd.read_csv(link, header=0)
	df = df.dropna()
	print(df.head(5))
	import pandas as pd
	from darts import TimeSeries
	# Create a TimeSeries, specifying the time and value columns
	series = TimeSeries.from_dataframe(df, 'DATE', 'PRICE')
	# Set aside the last 36 months as a validation series
	train, val = series[:-36], series[-36:]
	from darts.models import ExponentialSmoothing
	model = ExponentialSmoothing()
	model.fit(train)
	prediction = model.predict(len(val), num_samples=100)
	import matplotlib.pyplot as plt
	series.plot()
	prediction.plot(label='forecast', low_quantile=0.05, high_quantile=0.95)
	plt.legend()
	#TransformerModel
	from darts.metrics import mape
	from darts.utils.statistics import check_seasonality, plot_acf
	#https://unit8co.github.io/darts/examples/06-Transformer-examples.html
	from darts.dataprocessing.transformers import Scaler
	from darts.models import TransformerModel, ExponentialSmoothing
	scaler = Scaler()
	train_scaled = scaler.fit_transform(train)
	val_scaled = scaler.transform(val)
	series_scaled = scaler.transform(series)
	my_model = TransformerModel(
	input_chunk_length=12,
	output_chunk_length=1,
	batch_size=32,
	n_epochs=200,
	model_name="air_transformer",
	nr_epochs_val_period=10,
	d_model=16,
	nhead=8,
	num_encoder_layers=2,
	num_decoder_layers=2,
	dim_feedforward=128,
	dropout=0.1,
	activation="relu",
	random_state=42,
	save_checkpoints=True,
	force_reset=True,
	)
	my_model.fit(series=train_scaled, val_series=val_scaled, verbose=True)
	# this function evaluates a model on a given validation set for n time-steps
	def eval_model(model, n, series, val_series):
	pred_series = model.predict(n=n)
	plt.figure(figsize=(8, 5))
	series.plot(label="actual")
	pred_series.plot(label="forecast")
	plt.title("MAPE: {:.2f}%".format(mape(pred_series, val_series)))
	plt.legend()
	eval_model(my_model, 26, series_scaled, val_scaled)

view raw dart_forecasting.py hosted with ❤ by GitHub

More reads

Key concepts

• Past Covariates denote time series whose past values are known at prediction time.
• Future Covariates These can for instance represent known future holidays, or weather forecasts.

Multi-step Time Series Forecasting with Machine Learning
Multivariate-Time-series-Analysis-using-LSTM-ARIMA
Multivariate-Time-Series-Forecasting-with-LSTMs-in-Keras-for-CORN-SWEET-Terminal-Market-Price

DeepETA

Keep Exploring!!!