Simple Classification Model¶

In [1]:

from river import metrics, datasets, compose, preprocessing
from deep_river.classification import Classifier
from torch import nn
from tqdm import tqdm

from river import metrics, datasets, compose, preprocessing from deep_river.classification import Classifier from torch import nn from tqdm import tqdm

In [2]:

dataset = datasets.Phishing()
metric = metrics.Accuracy()


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, 2)
        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


model_pipeline = compose.Pipeline(
    preprocessing.StandardScaler,
    Classifier(
        module=MyModule, loss_fn="binary_cross_entropy", optimizer_fn="adam"
    ),
)
model_pipeline

dataset = datasets.Phishing() metric = metrics.Accuracy() 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, 2) 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 model_pipeline = compose.Pipeline( preprocessing.StandardScaler, Classifier( module=MyModule, loss_fn="binary_cross_entropy", optimizer_fn="adam" ), ) model_pipeline

Out[2]:

StandardScaler

StandardScaler ( with_std=True )

Classifier

Classifier ( module=None loss_fn="binary_cross_entropy" optimizer_fn="adam" lr=0.001 output_is_logit=True is_class_incremental=False is_feature_incremental=False device="cpu" seed=42 )

In [3]:

for x, y in tqdm(dataset.take(5000)):
    y_pred = model_pipeline.predict_one(x)  # make a prediction
    metric.update(y, y_pred)  # update the metric
    model_pipeline.learn_one(x, y)  # make the model learn
print(f"Accuracy: {metric.get()}")

for x, y in tqdm(dataset.take(5000)): y_pred = model_pipeline.predict_one(x) # make a prediction metric.update(y, y_pred) # update the metric model_pipeline.learn_one(x, y) # make the model learn print(f"Accuracy: {metric.get()}")

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

1it [00:01,  1.06s/it]

132it [00:01, 156.37it/s]

261it [00:01, 320.51it/s]

395it [00:01, 494.88it/s]

523it [00:01, 648.83it/s]

655it [00:01, 794.83it/s]

787it [00:01, 918.74it/s]

920it [00:01, 1021.64it/s]

1055it [00:01, 1107.63it/s]

1185it [00:01, 1134.86it/s]

1250it [00:02, 618.42it/s] 

Accuracy: 0.7264

In [ ]: