def _yield_datasets(model: Estimator):
"""Generates datasets for a given model."""
from sklearn import datasets as sk_datasets
from river import base, compose, datasets, preprocessing, stream, utils
# Recommendation models can be regressors or classifiers, but they have requirements as to the
# structure of the data
if isinstance(utils.inspect.extract_relevant(model), Recommender):
if utils.inspect.isregressor(model):
yield _DummyDataset(
({"user": "******", "item": "Superman"}, 8),
({"user": "******", "item": "Terminator"}, 9),
({"user": "******", "item": "Star Wars"}, 8),
({"user": "******", "item": "Notting Hill"}, 2),
({"user": "******", "item": "Harry Potter"}, 5),
({"user": "******", "item": "Superman"}, 8),
({"user": "******", "item": "Terminator"}, 9),
({"user": "******", "item": "Star Wars"}, 8),
({"user": "******", "item": "Notting Hill"}, 2),
)
return
# Multi-output regression
elif utils.inspect.ismoregressor(model):
# 1
yield stream.iter_sklearn_dataset(sk_datasets.load_linnerud())
# 2
class SolarFlare:
"""One-hot encoded version of `datasets.SolarFlare"""
def __iter__(self):
oh = (
compose.SelectType(str) | preprocessing.OneHotEncoder()
) + compose.SelectType(int)
for x, y in datasets.SolarFlare().take(200):
yield oh.transform_one(x), y
yield SolarFlare()
# Regression
elif utils.inspect.isregressor(model):
yield datasets.TrumpApproval().take(200)
# Multi-output classification
if utils.inspect.ismoclassifier(model):
yield datasets.Music().take(200)
# Classification
elif utils.inspect.isclassifier(model):
yield datasets.Phishing().take(200)
yield ((x, np.bool_(y)) for x, y in datasets.Phishing().take(200))
# Multi-class classification
if model._multiclass and base.tags.POSITIVE_INPUT not in model._tags:
yield datasets.ImageSegments().take(200)
def yield_datasets(model):
from river import base
from river import compose
from river import datasets
from river import preprocessing
from river import stream
from river import utils
from sklearn import datasets as sk_datasets
# Multi-output regression
if utils.inspect.ismoregressor(model):
# 1
yield stream.iter_sklearn_dataset(sk_datasets.load_linnerud())
# 2
class SolarFlare:
"""One-hot encoded version of `datasets.SolarFlare"""
def __iter__(self):
oh = (compose.SelectType(str) | preprocessing.OneHotEncoder()) + compose.SelectType(
int
)
for x, y in datasets.SolarFlare().take(200):
yield oh.transform_one(x), y
yield SolarFlare()
# Regression
elif utils.inspect.isregressor(model):
yield datasets.TrumpApproval().take(200)
# Multi-output classification
if utils.inspect.ismoclassifier(model):
yield datasets.Music().take(200)
# Classification
elif utils.inspect.isclassifier(model):
yield datasets.Phishing().take(200)
yield ((x, np.bool_(y)) for x, y in datasets.Phishing().take(200))
# Multi-class classification
if model._multiclass and base.tags.POSITIVE_INPUT not in model._tags:
yield datasets.ImageSegments().take(200)
def evo_led_accuracy_track(n_samples=10_000, seed=42):
dataset = synth.LEDDrift(seed=seed, noise_percentage=.1, n_drift_features=4).take(n_samples)
track = EvoTrack("LEDDrift()", dataset, metrics.Accuracy(), n_samples)
return track
def evo_hyperplane_accuracy_001_track(n_samples=10_000, seed=42):
dataset = synth.Hyperplane(seed=seed,n_features=50,n_drift_features=25,mag_change=.001).take(n_samples)
track = EvoTrack("Hyperplane(50,0.001)", dataset, metrics.Accuracy(), n_samples)
return track
def evo_hyperplane_accuracy_0001_track(n_samples=10_000, seed=42):
dataset = synth.Hyperplane(seed=seed,n_features=50,n_drift_features=25,mag_change=.0001).take(n_samples)
track = EvoTrack("Hyperplane(50, 0.0001)", dataset, metrics.Accuracy(), n_samples)
return track
def evo_sine_accuracy_track(n_samples=10_000, seed=42):
dataset = synth.Sine(seed=seed).take(n_samples)
track = EvoTrack("SINE()", dataset, metrics.Accuracy(), n_samples)
return track
def evo_elec2_accuracy_track(n_samples=10_000, seed=42):
dataset = Elec2().take(n_samples)
track = EvoTrack("Elec", dataset, metrics.Accuracy(), n_samples)
return track
def evo_covtype_accuracy_track(n_samples=10_000, seed=42):
dataset = stream.iter_sklearn_dataset(sk_datasets.fetch_covtype())
track = EvoTrack('Covtype', dataset, metrics.Accuracy(), n_samples)
return track
from river import linear_model
from river import optim
from river import preprocessing
from sklearn import datasets
from sklearn import metrics
from river import stream
scaler = preprocessing.StandardScaler()
optimizer = optim.SGD(lr=0.01)
log_reg = linear_model.LogisticRegression(optimizer)
y_true = []
y_pred = []
for xi, yi in stream.iter_sklearn_dataset(datasets.load_breast_cancer(), shuffle=True, seed=42):
# Scale the features
xi_scaled = scaler.learn_one(xi).transform_one(xi)
# Test the current model on the new "unobserved" sample
yi_pred = log_reg.predict_proba_one(xi_scaled)
# Train the model with the new sample
log_reg.learn_one(xi_scaled, yi)
# Store the truth and the prediction
y_true.append(yi)
y_pred.append(yi_pred[True])
print(f'ROC AUC: {metrics.roc_auc_score(y_true, y_pred):.3f}')
# Define the steps of the model
model = pipeline.Pipeline(
[
('scale', preprocessing.StandardScaler()),
('lin_reg', linear_model.LogisticRegression(solver='lbfgs'))
]
)
# Define a determistic cross-validation procedure
cv = model_selection.KFold(n_splits=5, shuffle=True, random_state=42)
#Conpute the MSE values
scorer = metrics.make_scorer(metrics.roc_auc_score)
scores = model_selection.cross_val_score(model, X, y, scoring=scorer, cv=cv)
# Display the average score and it's standard deviation
print(f'ROC AUC: {scores.mean():.3f} (+/- {scores.std():.3f})')
for xi, yi in zip(X, y):
# This is where the model learns
xi = dict(zip(dataset.feature_names, xi))
print(xi['mean area'])
from river import stream
for xi, yi in stream.iter_sklearn_dataset(datasets.load_breast_cancer()):
pass