Simple Regression Model¶

In [1]:

from river import (
    metrics,
    compose,
    preprocessing,
    datasets,
    stats,
    feature_extraction,
)
from deep_river.regression import RegressorInitialized
from torch import nn
from pprint import pprint
from tqdm import tqdm

from river import ( metrics, compose, preprocessing, datasets, stats, feature_extraction, ) from deep_river.regression import RegressorInitialized from torch import nn from pprint import pprint from tqdm import tqdm

In [2]:

dataset = datasets.Bikes()

for x, y in dataset:
    pprint(x)
    print(f"Number of available bikes: {y}")
    break

dataset = datasets.Bikes() for x, y in dataset: pprint(x) print(f"Number of available bikes: {y}") break

{'clouds': 75,
 'description': 'light rain',
 'humidity': 81,
 'moment': datetime.datetime(2016, 4, 1, 0, 0, 7),
 'pressure': 1017.0,
 'station': 'metro-canal-du-midi',
 'temperature': 6.54,
 'wind': 9.3}
Number of available bikes: 1

In [3]:

class MyModule(nn.Module):
    def __init__(self, n_features):
        super(MyModule, self).__init__()
        self.dense0 = nn.Linear(n_features, 5)
        self.nonlin = nn.ReLU()
        self.dense1 = nn.Linear(5, 1)
        self.softmax = nn.Softmax(dim=-1)

    def forward(self, X, **kwargs):
        X = self.nonlin(self.dense0(X))
        X = self.nonlin(self.dense1(X))
        X = self.softmax(X)
        return X


def get_hour(x):
    x["hour"] = x["moment"].hour
    return x

class MyModule(nn.Module): def __init__(self, n_features): super(MyModule, self).__init__() self.dense0 = nn.Linear(n_features, 5) self.nonlin = nn.ReLU() self.dense1 = nn.Linear(5, 1) self.softmax = nn.Softmax(dim=-1) def forward(self, X, **kwargs): X = self.nonlin(self.dense0(X)) X = self.nonlin(self.dense1(X)) X = self.softmax(X) return X def get_hour(x): x["hour"] = x["moment"].hour return x

In [4]:

metric = metrics.MAE()

model_pipeline = compose.Select(
    "clouds", "humidity", "pressure", "temperature", "wind"
)
model_pipeline += get_hour | feature_extraction.TargetAgg(
    by=["station", "hour"], how=stats.Mean()
)
model_pipeline |= preprocessing.StandardScaler()
model_pipeline |= RegressorInitialized(module=MyModule(10), loss_fn="mse", optimizer_fn="sgd")
model_pipeline

metric = metrics.MAE() model_pipeline = compose.Select( "clouds", "humidity", "pressure", "temperature", "wind" ) model_pipeline += get_hour | feature_extraction.TargetAgg( by=["station", "hour"], how=stats.Mean() ) model_pipeline |= preprocessing.StandardScaler() model_pipeline |= RegressorInitialized(module=MyModule(10), loss_fn="mse", optimizer_fn="sgd") model_pipeline

Out[4]:

['clouds', [...]

Select ( clouds humidity pressure temperature wind )

get_hour

def get_hour(x): x["hour"] = x["moment"].hour return x

y_mean_by_station_and_hour

TargetAgg ( by=['station', 'hour'] how=Mean () target_name="y" )

StandardScaler

StandardScaler ( with_std=True )

RegressorInitialized

RegressorInitialized ( module=MyModule( (dense0): Linear(in_features=10, out_features=5, bias=True) (nonlin): ReLU() (dense1): Linear(in_features=5, out_features=1, bias=True) (softmax): Softmax(dim=-1) ) loss_fn="mse" optimizer_fn="sgd" lr=0.001 output_is_logit=True is_feature_incremental=False device="cpu" seed=42 )

In [5]:

for x, y in tqdm(dataset.take(5000)):
    y_pred = model_pipeline.predict_one(x)
    metric.update(y_true=y, y_pred=y_pred)
    model_pipeline.learn_one(x=x, y=y)
print(f"MAE: {metric.get():.2f}")

for x, y in tqdm(dataset.take(5000)): y_pred = model_pipeline.predict_one(x) metric.update(y_true=y, y_pred=y_pred) model_pipeline.learn_one(x=x, y=y) print(f"MAE: {metric.get():.2f}")

0it [00:00, ?it/s]

83it [00:00, 828.38it/s]

215it [00:00, 1113.79it/s]

356it [00:00, 1247.43it/s]

494it [00:00, 1293.06it/s]

635it [00:00, 1332.09it/s]

781it [00:00, 1370.73it/s]

929it [00:00, 1404.25it/s]

1071it [00:00, 1407.97it/s]

1225it [00:00, 1448.75it/s]

1374it [00:01, 1461.33it/s]

1527it [00:01, 1479.61it/s]

1681it [00:01, 1495.33it/s]

1832it [00:01, 1499.63it/s]

1982it [00:01, 1414.77it/s]

2125it [00:01, 1416.94it/s]

2273it [00:01, 1434.12it/s]

2422it [00:01, 1447.89it/s]

2568it [00:01, 1434.99it/s]

2714it [00:01, 1439.62it/s]

2859it [00:02, 1435.47it/s]

3003it [00:02, 1429.22it/s]

3147it [00:02, 1429.40it/s]

3291it [00:02, 1413.45it/s]

3433it [00:02, 1407.83it/s]

3574it [00:02, 1393.92it/s]

3714it [00:02, 1352.39it/s]

3850it [00:02, 1239.74it/s]

4002it [00:02, 1315.11it/s]

4158it [00:02, 1383.08it/s]

4305it [00:03, 1407.78it/s]

4459it [00:03, 1445.25it/s]

4607it [00:03, 1454.45it/s]

4755it [00:03, 1460.43it/s]

4902it [00:03, 1449.62it/s]

5000it [00:03, 1404.67it/s]

MAE: 6.83