Spaces:
Sleeping
Sleeping
File size: 4,877 Bytes
79e1719 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 |
## TODO
## Make the cross validation model get saved as well and log the params and model as mlflow artifacts
import pandas as pd
from modules.neuralforecast.core import NeuralForecast
from modules.neuralforecast.models import TSMixer, TSMixerx, NHITS, MLPMultivariate, NBEATSx
from modules.neuralforecast.losses.pytorch import MSE, MAE, MAPE
from sklearn.preprocessing import StandardScaler
import numpy as np
import os
horizon = 30
input_size = horizon*2
models = [
TSMixer(h=horizon,
input_size=input_size,
n_series=1,
max_steps=1000,
val_check_steps=100,
early_stop_patience_steps=5,
scaler_type='identity',
loss=MAPE(),
valid_loss=MAPE(),
random_seed=12345678,
),
TSMixerx(h=horizon,
input_size=input_size,
n_series=1,
max_steps=1000,
val_check_steps=100,
early_stop_patience_steps=5,
scaler_type='identity',
dropout=0.7,
loss=MAPE(),
valid_loss=MAPE(),
random_seed=12345678,
futr_exog_list=['Gas', 'DXY', 'BrFu', 'BrDa'],
),
NBEATSx(h=horizon,
input_size=horizon,
max_steps=1000,
val_check_steps=100,
early_stop_patience_steps=5,
scaler_type='identity',
loss=MAPE(),
valid_loss=MAPE(),
random_seed=12345678,
futr_exog_list=['Gas', 'DXY', 'BrFu', 'BrDa']
),
]
nf = NeuralForecast(
models=models,
freq='D')
Y_hat_df = nf.cross_validation(df=df,
val_size=val_size,
test_size=test_size,
n_windows=None
)
Y_hat_df = Y_hat_df.reset_index()
# Start from here
# Using MLflow
# Log your neuralforecast experiments to MLflow
# Installing dependencies
# To install Neuralforecast refer to https://nixtlaverse.nixtla.io/neuralforecast/examples/installation.html.
# To install mlflow: pip install mlflow
# Imports
import logging
import os
import warnings
import matplotlib.pyplot as plt
import mlflow
import mlflow.data
import numpy as np
import pandas as pd
from mlflow.client import MlflowClient
from mlflow.data.pandas_dataset import PandasDataset
from utilsforecast.plotting import plot_series
from neuralforecast.core import NeuralForecast
from neuralforecast.models import NBEATSx
from neuralforecast.utils import AirPassengersDF
from neuralforecast.losses.pytorch import MAE
os.environ['NIXTLA_ID_AS_COL'] = '1'
logging.getLogger("mlflow").setLevel(logging.ERROR)
logging.getLogger("pytorch_lightning").setLevel(logging.ERROR)
warnings.filterwarnings("ignore")
# Splitting the data
# Split data and declare panel dataset
Y_df = AirPassengersDF
Y_train_df = Y_df[Y_df.ds<='1959-12-31'] # 132 train
Y_test_df = Y_df[Y_df.ds>'1959-12-31'] # 12 test
Y_df.tail()
# unique_id ds y
# 139 1.0 1960-08-31 606.0
# 140 1.0 1960-09-30 508.0
# 141 1.0 1960-10-31 461.0
# 142 1.0 1960-11-30 390.0
# 143 1.0 1960-12-31 432.0
# MLflow UI
# Run the following command from the terminal to start the UI: mlflow ui. You can then go to the printed URL to visualize the experiments.
# Model training
mlflow.pytorch.autolog(checkpoint=False)
with mlflow.start_run() as run:
# Log the dataset to the MLflow Run. Specify the "training" context to indicate that the
# dataset is used for model training
dataset: PandasDataset = mlflow.data.from_pandas(Y_df, source="AirPassengersDF")
mlflow.log_input(dataset, context="training")
# Define and log parameters
horizon = len(Y_test_df)
model_params = dict(
input_size=1 * horizon,
h=horizon,
max_steps=300,
loss=MAE(),
valid_loss=MAE(),
activation='ReLU',
scaler_type='robust',
random_seed=42,
enable_progress_bar=False,
)
mlflow.log_params(model_params)
# Fit NBEATSx model
models = [NBEATSx(**model_params)]
nf = NeuralForecast(models=models, freq='M')
train = nf.fit(df=Y_train_df, val_size=horizon)
# Save conda environment used to run the model
mlflow.pytorch.get_default_conda_env()
# Save pip requirements
mlflow.pytorch.get_default_pip_requirements()
mlflow.pytorch.autolog(disable=True)
# Save the neural forecast model
nf.save(path='./checkpoints/test_run_1/',
model_index=None,
overwrite=True,
save_dataset=True)
#Seed set to 42
#Forecasting the future
Y_hat_df = nf.predict(futr_df=Y_test_df)
plot_series(Y_train_df, Y_hat_df, palette='tab20b')
|