Created
February 7, 2020 17:57
-
-
Save lazuxd/898ffa92a1a8c16d76a1ac9327900c96 to your computer and use it in GitHub Desktop.
Building a Sentiment Classifier using Scikit-Learn
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 RandomizedSearchCV | |
from scipy.stats import uniform | |
X_train = X_train_bigram_tf_idf | |
# Phase 1: loss, learning rate and initial learning rate | |
clf = SGDClassifier() | |
distributions = dict( | |
loss=['hinge', 'log', 'modified_huber', 'squared_hinge', 'perceptron'], | |
learning_rate=['optimal', 'invscaling', 'adaptive'], | |
eta0=uniform(loc=1e-7, scale=1e-2) | |
) | |
random_search_cv = RandomizedSearchCV( | |
estimator=clf, | |
param_distributions=distributions, | |
cv=5, | |
n_iter=50 | |
) | |
random_search_cv.fit(X_train, y_train) | |
print(f'Best params: {random_search_cv.best_params_}') | |
print(f'Best score: {random_search_cv.best_score_}') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment