Created
February 24, 2016 22:58
-
-
Save evanfeinberg/df45077cc80a178efa1d to your computer and use it in GitHub Desktop.
Random Forests for interpreting tICs
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.ensemble import RandomForestClassifier, RandomForestRegressor | |
import numpy as np | |
def compute_random_forests(features, projected_tica_coords, rf_dir, n_trees=500, | |
n_tica_components=25, start_tIC=0): | |
features = np.concatenate(features) | |
tics = np.concatenate(projected_tica_coords) | |
for j in range(start_tIC, np.shape(tics)[1]): | |
#os.system("rm %s/tIC.%d_rfr.pkl" %(rf_dir, j)) | |
rfr = RandomForestRegressor(n_estimators=n_trees, max_features="sqrt", | |
n_jobs=-1, verbose=1) | |
print(("Fitting tree for tIC %d" %(j+1))) | |
rfr.fit(features, tics[:,j]) | |
print("Done fitting RF model. Saving now...") | |
with open(os.path.join(rf_dir, "tIC.%d_rfr.pkl" %j), "wb") as f: | |
pickle.dump(rfr.feature_importances_, f) | |
print("Saved random forest feature importances") | |
return |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment