python-scikit-learnSklearn model training example

import numpy as np
from sklearn import datasets, linear_model, model_selection, metrics

X, y = datasets.load_diabetes(return_X_y=True)
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y)

model = linear_model.LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

r2 = metrics.r2_score(y_test, y_pred)ctrl + cgithub

`from sklearn import` import module from scikit-learn	`import numpy` import Numpy module
`datasets.load_diabetes` loads sample diabetes database	`X, y` loaded features data (`X`) and target variable (`y`) values
`model_selection.train_test_split` splits given `X` and `y` datasets to test (25% of values by default) and train (75% of values by default) subsets	`linear_model.LinearRegression` initialize linear regression model
`.fit(` train model with a given features and target variable dataset	`.predict(` predict target variable based on given features dataset
`metrics.r2_score(` calculate R2 score to evaluate model quality (`1` is best, `0` is worst)	`y_test` target variable values from test dataset (correct values)
`y_pred` target variable predicted values by our model (values to evaluate)

Usage example

import numpy as np
from sklearn import datasets, linear_model, model_selection, metrics

X, y = datasets.load_diabetes(return_X_y=True)
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y)

model = linear_model.LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

r2 = metrics.r2_score(y_test, y_pred)

print(r2)

output

0.5225055395659151

More of Python Scikit Learn

See more codes...