Example mini batches

In [1]:

import pandas as pd
from river import datasets
from deep_river import regression
from torch import nn
from river import compose
from river import preprocessing
from itertools import islice
from pprint import pprint
from sklearn import metrics

import pandas as pd from river import datasets from deep_river import regression from torch import nn from river import compose from river import preprocessing from itertools import islice from pprint import pprint from sklearn import metrics

In [2]:

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 batcher(iterable, batch_size):
    iterator = iter(iterable)
    while batch := list(islice(iterator, batch_size)):
        yield batch

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 batcher(iterable, batch_size): iterator = iter(iterable) while batch := list(islice(iterator, batch_size)): yield batch

In [3]:

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 [4]:

dataset = datasets.Bikes()

model_pipeline = compose.Select(
    "clouds", "humidity", "pressure", "temperature", "wind"
)
model_pipeline |= regression.RegressorInitialized(
    module=MyModule(5), loss_fn="mse", optimizer_fn="sgd"
)
model_pipeline

dataset = datasets.Bikes() model_pipeline = compose.Select( "clouds", "humidity", "pressure", "temperature", "wind" ) model_pipeline |= regression.RegressorInitialized( module=MyModule(5), loss_fn="mse", optimizer_fn="sgd" ) model_pipeline

Out[4]:

['clouds', [...]

Select ( clouds humidity pressure temperature wind )

RegressorInitialized

RegressorInitialized ( module=MyModule( (dense0): Linear(in_features=5, 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]:

y_trues = []
y_preds = []
for batch in batcher(dataset.take(5000), 5):
    x, y = zip(*batch)
    x = pd.DataFrame(x)
    y_trues.extend(y)
    y_preds.extend(model_pipeline.predict_many(X=x).values)
    model_pipeline.learn_many(X=x, y=pd.Series(y))

y_trues = [] y_preds = [] for batch in batcher(dataset.take(5000), 5): x, y = zip(*batch) x = pd.DataFrame(x) y_trues.extend(y) y_preds.extend(model_pipeline.predict_many(X=x).values) model_pipeline.learn_many(X=x, y=pd.Series(y))

In [6]:

metrics.mean_squared_error(y_true=y_trues, y_pred=y_preds)

metrics.mean_squared_error(y_true=y_trues, y_pred=y_preds)

Out[6]:

102.4412