Created
September 28, 2022 02:43
-
-
Save ekerstein/149099bb0f9cda53d3f97fdda83db879 to your computer and use it in GitHub Desktop.
GluonTS - feat_dynamic_real example
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from gluonts.dataset.common import ListDataset | |
from gluonts.model.deepar import DeepAREstimator | |
from gluonts.evaluation import make_evaluation_predictions, Evaluator | |
from gluonts.mx import Trainer | |
from itertools import tee | |
import pandas as pd | |
import random | |
import json | |
#################################################### | |
# Settings | |
N_PERIODS = 100 | |
PREDICTION_LENGTH = 5 | |
FREQUENCY = 'M' | |
NUM_SAMPLES = 10000 | |
EPOCHS = 10 | |
# Set the future dynamic features | |
# Choose 0 or 1. When dynamic_real == 1, target == 3. When dynamic_real == 0, target == 10 | |
FUTURE_DYNAMIC_REAL = 1 | |
#################################################### | |
print('\n', '*' * 80, '\n', '1. Make Datasets', '\n') | |
# Make datasets | |
FEAT_DYNAMIC_REAL = [random.randint(0,1) for x in range(N_PERIODS)] + [FUTURE_DYNAMIC_REAL] * PREDICTION_LENGTH # 100 items past + 5 items future = 105 items | |
TARGET = [3 if x == 1 else 10 for x in FEAT_DYNAMIC_REAL][:N_PERIODS] # 100 items | |
START = pd.Timestamp("2000-01-01", freq=FREQUENCY) | |
ds_train = ListDataset( | |
[{ | |
"item_id": "item_1", | |
"start": START, | |
"target": TARGET[:N_PERIODS - PREDICTION_LENGTH], # 95 items | |
"feat_dynamic_real": [FEAT_DYNAMIC_REAL[:N_PERIODS - PREDICTION_LENGTH]], # 95 items | |
}], | |
freq=FREQUENCY | |
) | |
ds_current = ListDataset( | |
[{ | |
"item_id": "item_1", | |
"start": START, | |
"target": TARGET[:N_PERIODS], # 100 items | |
"feat_dynamic_real": [FEAT_DYNAMIC_REAL[:N_PERIODS]], # 100 items | |
}], | |
freq=FREQUENCY | |
) | |
ds_future = ListDataset( | |
[{ | |
"item_id": "item_1", | |
"start": START, | |
"target": TARGET[:N_PERIODS], # 100 items | |
"feat_dynamic_real": [FEAT_DYNAMIC_REAL[:N_PERIODS + PREDICTION_LENGTH]], # 105 items | |
}], | |
freq=FREQUENCY | |
) | |
# Log datasets | |
print(f"\n* Dataset metadata: target is {N_PERIODS} long, feat_dynamic_real is {N_PERIODS+PREDICTION_LENGTH} long. Prediction length is {PREDICTION_LENGTH}.") | |
print('\nds_train\n', ds_train) | |
print('\nds_current\n', ds_current) | |
print('\nds_future\n', ds_future) | |
# Make estimator | |
estimator = DeepAREstimator( | |
freq=FREQUENCY, | |
prediction_length=PREDICTION_LENGTH, | |
use_feat_dynamic_real=True, | |
num_parallel_samples=NUM_SAMPLES, | |
trainer=Trainer( | |
epochs=EPOCHS, | |
) | |
) | |
#################################################### | |
print('\n', '*' * 80, '\n', '2a. Train / Test Split', '\n') | |
# Using train/test split on past data | |
# No future dynamic features are needed for this | |
# Train model and make predictions | |
predictor = estimator.train(ds_train) | |
forecast_it, ts_it = make_evaluation_predictions( | |
dataset=ds_current, | |
predictor=predictor, | |
num_samples=NUM_SAMPLES | |
) | |
# Make a copy of the iterators | |
ts_it, targets = tee(ts_it) | |
forecast_it, predictions = tee(forecast_it) | |
# Calc metrics | |
evaluator = Evaluator(quantiles=[0.05, 0.5, 0.95]) | |
agg_metrics, item_metrics = evaluator( | |
ts_it, | |
forecast_it, | |
num_series=len(ds_current) | |
) | |
# Log metrics | |
print('\nagg_metrics:\n', json.dumps(agg_metrics, indent=4)) | |
print('\nitem_metrics:\n', item_metrics) | |
# Log predictions | |
for item_index, item in enumerate(list(predictions)): | |
df_target = list(targets)[item_index] | |
prediction_actuals = df_target.iloc[-PREDICTION_LENGTH:, 0] | |
prediction_averages = [sum(sub_list) / len(sub_list) for sub_list in zip(*item.samples)] | |
print( | |
f'\n{item.item_id} - Predictions for next {PREDICTION_LENGTH} periods:', | |
json.dumps({str(item.start_date + (item.freq * i)):f'{v:.1f} (should be {prediction_actuals[i]})' for i, v in enumerate(prediction_averages)}, indent=4) | |
) | |
#################################################### | |
print('\n', '*' * 80, '\n', '2b. Train / Predict', '\n') | |
# Using train/predict on current data | |
# Need future dynamic features for this | |
# Train model and make predictions | |
predictor = estimator.train(ds_current) # train on current data, no future dynamic_feat | |
predictions = predictor.predict(ds_future) # predict on current data + future dynamic_feat | |
# Log predictions | |
for item in list(predictions): | |
prediction_averages = [sum(sub_list) / len(sub_list) for sub_list in zip(*item.samples)] | |
print( | |
f'\n{item.item_id} - Predictions for next {PREDICTION_LENGTH} periods:', | |
json.dumps({str(item.start_date + (item.freq * i)):f'{v:.1f} (should be {3 if FUTURE_DYNAMIC_REAL else 10})' for i, v in enumerate(prediction_averages)}, indent=4) | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment