"""
=============================================
Multiclass classification with under-sampling
=============================================

Some balancing methods allow for balancing dataset with multiples classes.
We provide an example to illustrate the use of those methods which do
not differ from the binary case.

"""

# Authors: Guillaume Lemaitre <g.lemaitre58@gmail.com>
# License: MIT

from collections import Counter

from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

from imblearn.datasets import make_imbalance
from imblearn.metrics import classification_report_imbalanced
from imblearn.pipeline import make_pipeline
from imblearn.under_sampling import NearMiss

print(__doc__)

RANDOM_STATE = 42

# Create a folder to fetch the dataset
iris = load_iris()
X, y = make_imbalance(
    iris.data,
    iris.target,
    sampling_strategy={0: 25, 1: 50, 2: 50},
    random_state=RANDOM_STATE,
)

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=RANDOM_STATE)

print(f"Training target statistics: {Counter(y_train)}")
print(f"Testing target statistics: {Counter(y_test)}")

# Create a pipeline
pipeline = make_pipeline(
    NearMiss(version=2), StandardScaler(), LogisticRegression(random_state=RANDOM_STATE)
)
pipeline.fit(X_train, y_train)

# Classify and report the results
print(classification_report_imbalanced(y_test, pipeline.predict(X_test)))