Scikit-learn, sklearn

Machine learning에서 가장 많이 쓰이는 library이다.

 

Homepage : https://scikit-learn.org/stable/user_guide.html

Manual : https://scikit-learn.org/stable/_downloads/scikit-learn-docs.pdf

 

사용할 기능

Classification

- SVM : https://scikit-learn.org/stable/modules/svm.html

- Ensemble (Random forest) : https://scikit-learn.org/stable/modules/ensemble.html

 

SVM:

import numpy as np
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler

from sklearn import svm # Support Vector Machine

X = [[0, 0], [2, 2]]
y = [0.5, 2.5]
regr = svm.SVR()
regr.fit(X, y) # SVR()
regr.predict([[1, 1]]) # array([1.5])

https://scikit-learn.org/stable/modules/svm.html

from sklearn.svm import SVC # Support Vector Classification

X = np.array([[-1, -1], [-2, -1], [1, 1], [2, 1]])
y = np.array([1, 1, 2, 2])
clf = make_pipeline(StandardScaler(), SVC(gamma='auto'))
clf.fit(X, y) # Pipeline(steps=[('standardscaler', StandardScaler()),('svc', SVC(gamma='auto'))])
print(clf.predict([[-0.8, -1]])) # [1]

https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html#sklearn.svm.SVC

from sklearn.svm import SVR # Support Vector Regression

n_samples, n_features = 10, 5
rng = np.random.RandomState(0)
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
regr = make_pipeline(StandardScaler(), SVR(C=1.0, epsilon=0.2))
regr.fit(X, y) # Pipeline(steps=[('standardscaler', StandardScaler()),('svr', SVR(epsilon=0.2))])

https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVR.html#sklearn.svm.SVR

 

Random forest:

https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html#examples-using-sklearn-ensemble-randomforestclassifier

from sklearn.ensemble import RandomForestClassifier

clf = RandomForestClassifier(random_state=0)
X = [[ 1,  2,  3],  # 2 samples, 3 features
     [11, 12, 13]]
y = [0, 1]  # classes of each sample
clf.fit(X, y)

https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html#sklearn.ensemble.RandomForestClassifier

from sklearn.datasets import make_classification

X, y = make_classification(n_samples=1000, n_features=4,
                           n_informative=2, n_redundant=0,
                           random_state=0, shuffle=False)
clf = RandomForestClassifier(max_depth=2, random_state=0)
clf.fit(X, y)
print(clf.predict([[0, 0, 0, 0]])) # [1]

https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_classification.html?highlight=make_classification#sklearn.datasets.make_classification