Last active
November 10, 2018 19:42
-
-
Save havron/1d7d313d3e5378b54b89f700bd8f0828 to your computer and use it in GitHub Desktop.
Easier cross validation algorithm than what I could find on the WWW.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sklearn.model_selection import KFold | |
from sklearn.base import clone | |
def cross_validate(features, labels, nsplits, model): | |
'''Returns tuple of (scores : list, average_score : float) over K folds. | |
Keyword arguments: | |
nsplits : int -- the number of folds to perform cross validation on. | |
model -- an object that is the model for CV. Assumes fit() and score() methods, | |
akin to sklearn model APIs. | |
features : pandas.DataFrame -- a Pandas DataFrame containing preprocessed training data features. | |
labels : pandas.Series -- a Pandas Series containing the labels for the training data. | |
''' | |
kf = KFold(n_splits=nsplits) | |
scores = [] | |
for train_index, test_index in kf.split(features): | |
X_train, X_test = features.loc[train_index], features.loc[test_index] | |
Y_train, Y_test = labels.loc[train_index], labels.loc[test_index] | |
model = clone(model) # clean copy of the model | |
model.fit(X_train, Y_train) | |
scores.append(model.score(X_test, Y_test)) | |
return scores, sum(scores) / float(len(scores)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment