def linear_regression(x_train,y_train,x_test,y_test,axis,figname):
lin_reg_model = linear_model.LinearRegression();
lin_reg_model.fit(x_train, y_train);
y_pred = lin_reg_model.predict(x_test);
RMSE = np.sqrt( np.mean( (y_test - y_pred) ** 2.0 ) );
# Format required by the evaluation function
dict_test = dict();
dict_pred = dict();
for ID in range( len(y_pred) ):
dict_test[ID] = int(y_test[ID]);
dict_pred[ID] = y_pred[ID];
# Actually evaluating the results
plot.error_boxplot( dict_test, dict_pred, 5, axis, figname);
return RMSE
# Tools
from utils import data
from evaluation import plot
print "> Loading"
root = data.getParent(__file__)
print "loading review scores"
target = data.loadFile(root + "/computed/reviews_score.pkl")
print "loading predicted scores"
predict = data.loadFile(root + "/computed/linear_regression_predict.pkl")
RMSE = 0
for review in target:
RMSE += (target[review] - predict[review]) ** 2
RMSE /= len(target)
print "RMSE:", RMSE
plot.error_boxplot(target, predict)
