def objective(trial):
iris = load_iris()
X, y = iris.data, iris.target
X, y = da.from_array(X,
chunks=len(X) // 5), da.from_array(y,
chunks=len(y) // 5)
solver = trial.suggest_categorical(
"solver", ["admm", "gradient_descent", "proximal_grad"])
C = trial.suggest_float("C", 0.0, 1.0)
if solver == "admm" or solver == "proximal_grad":
penalty = trial.suggest_categorical("penalty",
["l1", "l2", "elastic_net"])
else:
# 'penalty' parameter isn't relevant for this solver,
# so we always specify 'l2' as the dummy value.
penalty = "l2"
classifier = LogisticRegression(max_iter=200,
solver=solver,
C=C,
penalty=penalty)
X_train, X_valid, y_train, y_valid = train_test_split(X, y)
classifier.fit(X_train, y_train)
score = classifier.score(X_valid, y_valid)
return score
def objective(trial):
iris = load_iris()
X, y = iris.data, iris.target
X, y = da.from_array(X,
chunks=len(X) // 5), da.from_array(y,
chunks=len(y) // 5)
solver = trial.suggest_categorical(
'solver', ['admm', 'gradient_descent', 'proximal_grad'])
C = trial.suggest_uniform('C', 0.0, 1.0)
if solver == 'admm' or solver == 'proximal_grad':
penalty = trial.suggest_categorical('penalty',
['l1', 'l2', 'elastic_net'])
else:
# 'penalty' parameter isn't relevant for this solver,
# so we always specify 'l2' as the dummy value.
penalty = 'l2'
classifier = LogisticRegression(max_iter=200,
solver=solver,
C=C,
penalty=penalty)
X_train, X_test, y_train, y_test = train_test_split(X, y)
classifier.fit(X_train, y_train)
score = classifier.score(X_test, y_test)
return score
def simple_example():
X, y = make_classification(n_samples=10000, n_features=2, chunks=50)
X = dd.from_dask_array(X, columns=["a","b"])
y = dd.from_array(y)
lr = LogisticRegression()
lr.fit(X.values, y.values)
print('Predictions =', lr.predict(X.values).compute())
print('Probabilities =', lr.predict_proba(X.values).compute())
print('Scores =', lr.score(X.values, y.values).compute())
X_train, X_test, y_train, y_test = train_test_split(to_dask_array(X),
to_dask_array(y),
random_state=99)
###################################################################################
# Fitting the Logistic Regression Classifier
from dask_ml.linear_model import LogisticRegression
lr = LogisticRegression()
with ProgressBar():
lr.fit(X_train, y_train)
print('Logistic Regression Score : ', lr.score(X_test, y_test).compute())
##### OUTPUT --------> Logistic Regression Score : 0.70025
#####################################################################################
# Fitting the Naive Bayes Classifier
from sklearn.naive_bayes import BernoulliNB
from dask_ml.wrappers import Incremental
nb = BernoulliNB()
parallel_nb = Incremental(nb)
with ProgressBar():
parallel_nb.fit(X_train, y_train, classes=np.unique(y_train.compute()))