pip install --upgrade scikit-learn

conda install scikit-learn

from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import plot_roc_curve
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification
import matplotlib.pyplot as pltX, y = make_classification(random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)svc = SVC(random_state=42)
svc.fit(X_train, y_train)
rfc = RandomForestClassifier(random_state=42)
rfc.fit(X_train, y_train)svc_disp = plot_roc_curve(svc, X_test, y_test)
rfc_disp = plot_roc_curve(rfc, X_test, y_test, ax=svc_disp.ax_)
rfc_disp.figure_.suptitle("ROC curve comparison")plt.show()

from sklearn.datasets import load_iris
from sklearn.svm import LinearSVC
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import make_pipeline
from sklearn.ensemble import StackingClassifier
from sklearn.model_selection import train_test_splitX, y = load_iris(return_X_y=True)
estimators = [('rf', RandomForestClassifier(n_estimators=10, random_state=42)),('svr', make_pipeline(StandardScaler(),LinearSVC(random_state=42)))
]
clf = StackingClassifier(estimators=estimators, final_estimator=LogisticRegression()
)
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=42
)
clf.fit(X_train, y_train).score(X_test, y_test)

from sklearn.ensemble import RandomForestClassifier
from sklearn.inspection import permutation_importanceX, y = make_classification(random_state=0, n_features=5, n_informative=3)
rf = RandomForestClassifier(random_state=0).fit(X, y)
result = permutation_importance(rf, X, y, n_repeats=10, random_state=0,n_jobs=-1)fig, ax = plt.subplots()
sorted_idx = result.importances_mean.argsort()
ax.boxplot(result.importances[sorted_idx].T,vert=False, labels=range(X.shape[1]))
ax.set_title("Permutation Importance of each feature")
ax.set_ylabel("Features")
fig.tight_layout()
plt.show()

from sklearn.experimental import enable_hist_gradient_boosting  # noqa
from sklearn.ensemble import HistGradientBoostingClassifier
import numpy as npX = np.array([0, 1, 2, np.nan]).reshape(-1, 1)
y = [0, 0, 1, 1]gbdt = HistGradientBoostingClassifier(min_samples_leaf=1).fit(X, y)
print(gbdt.predict(X))

from tempfile import TemporaryDirectory
from sklearn.neighbors import KNeighborsTransformer
from sklearn.manifold import Isomap
from sklearn.pipeline import make_pipelineX, y = make_classification(random_state=0)with TemporaryDirectory(prefix="sklearn_cache_") as tmpdir:estimator = make_pipeline(KNeighborsTransformer(n_neighbors=10, mode='distance'),Isomap(n_neighbors=10, metric='precomputed'),memory=tmpdir)estimator.fit(X)# We can decrease the number of neighbors and the graph will not be# recomputed.estimator.set_params(isomap__n_neighbors=5)estimator.fit(X)

from sklearn.impute import KNNImputerX = [[1, 2, np.nan], [3, 4, 3], [np.nan, 6, 5], [8, 8, 7]]
imputer = KNNImputer(n_neighbors=2)
print(imputer.fit_transform(X))

X, y = make_classification(random_state=0)rf = RandomForestClassifier(random_state=0, ccp_alpha=0).fit(X, y)
print("Average number of nodes without pruning {:.1f}".format(np.mean([e.tree_.node_count for e in rf.estimators_])))rf = RandomForestClassifier(random_state=0, ccp_alpha=0.05).fit(X, y)
print("Average number of nodes with pruning {:.1f}".format(np.mean([e.tree_.node_count for e in rf.estimators_])))

from sklearn.datasets import fetch_openmltitanic = fetch_openml('titanic', version=1, as_frame=True)
print(titanic.data.head()[['pclass', 'embarked']])

from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeRegressor
from sklearn.utils.estimator_checks import parametrize_with_checks@parametrize_with_checks([LogisticRegression, DecisionTreeRegressor])
def test_sklearn_compatible_estimator(estimator, check):check(estimator)

from sklearn.datasets import make_classification
from sklearn.svm import SVC
from sklearn.metrics import roc_auc_scoreX, y = make_classification(n_classes=4, n_informative=16)
clf = SVC(decision_function_shape='ovo', probability=True).fit(X, y)
print(roc_auc_score(y, clf.predict_proba(X), multi_class='ovo'))