Метрики для оценки алгоритмов машинного обучения в Python

 (.env) [boris@fedora34server YANDEXQ]$ cat predict.py

import pandas

from sklearn import model_selection

from sklearn.linear_model import LogisticRegression

from sklearn.metrics import classification_report

url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv"

names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']

dataframe = pandas.read_csv(url, names=names)

array = dataframe.values

X = array[:,0:8]

Y = array[:,8]

test_size = 0.33

seed = 7

X_train, X_test, Y_train, Y_test = model_selection.train_test_split(X, Y, test_size=test_size, random_state=seed)

model = LogisticRegression(solver='lbfgs', max_iter=120)

model.fit(X_train, Y_train)

predicted = model.predict(X_test)

report = classification_report(Y_test, predicted)

print(report)

(.env) [boris@fedora34server YANDEXQ]$ python predict.py

              precision    recall  f1-score   support

         0.0       0.81      0.88      0.84       162

         1.0       0.74      0.63      0.68        92

    accuracy                           0.79       254

   macro avg       0.78      0.75      0.76       254

weighted avg       0.78      0.79      0.78       254

(.env) [boris@fedora34server YANDEXQ]$ cat regres01.py

import pandas

from sklearn import model_selection

from sklearn.linear_model import LinearRegression

url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/housing.data"

names = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']

dataframe = pandas.read_csv(url, delim_whitespace=True, names=names)

array = dataframe.values

X = array[:,0:13]

Y = array[:,13]

seed = 7

kfold = \ model_selection.KFold(n_splits=10,shuffle=True,random_state=seed)

model = LinearRegression()

scoring = 'neg_mean_absolute_error'

results = model_selection.cross_val_score(model, X, Y, cv=kfold, scoring=scoring)

print(("MAE: %.3f (%.3f)") % (results.mean(), results.std()))

(.env) [boris@fedora34server YANDEXQ]$ python regres01.py

MAE: -3.387 (0.667)

(.env) [boris@fedora34server YANDEXQ]$ cat regres02.py

# Cross Validation Regression MSE

import pandas

from sklearn import model_selection

from sklearn.linear_model import LinearRegression

url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/housing.data"

names = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']

dataframe = pandas.read_csv(url, delim_whitespace=True, names=names)

array = dataframe.values

X = array[:,0:13]

Y = array[:,13]

seed = 7

kfold = \ model_selection.KFold(n_splits=10,shuffle=True,random_state=seed)

model = LinearRegression()

scoring = 'neg_mean_squared_error'

results = model_selection.cross_val_score(model, X, Y, cv=kfold, scoring=scoring)

print(("MSE: %.3f (%.3f)") % (results.mean(), results.std()))

(.env) [boris@fedora34server YANDEXQ]$ python regres02.py

MSE: -23.747 (11.143)

(.env) [boris@fedora34server YANDEXQ]$ cat regres03.py

import pandas

from sklearn import model_selection

from sklearn.linear_model import LinearRegression

url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/housing.data"

names = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']

dataframe = pandas.read_csv(url, delim_whitespace=True, names=names)

array = dataframe.values

X = array[:,0:13]

Y = array[:,13]

seed = 7

kfold    \ =  model_selection.KFold(n_splits=10,shuffle=True,random_state=seed)

model = LinearRegression()

scoring = 'r2'

results = model_selection.cross_val_score(model, X, Y, cv=kfold, scoring=scoring)

print(("R^2: %.3f (%.3f)") % (results.mean(), results.std()))

(.env) [boris@fedora34server YANDEXQ]$ python regres03.py

R^2: 0.718 (0.099)

References

https://machinelearningmastery.com/metrics-evaluate-machine-learning-algorithms-python/