Permanent error not supported in RandomForestRegressor

Question

I'm just trying to make a simple RandomForestRegressor example. But when testing accuracy, I get this error

/Users/noppanit/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.pyc 

in precision_score (y_true, y_pred, normalize, sample_weight) 177 178 # Calculate the accuracy for each possible view → 179 y_type, y_true, y_pred = _check_targets (y_true, y_pred) 180 if y_type.startswith ('multilabel'): 181 = different count_nonzero (y_true - y_pred, axis = 1)

 /Users/noppanit/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.pyc 

in _check_targets (y_true, y_pred) 90 if (y_type is not in ["binary", "multiclass", "multilabel-pointer", 91 "multilabel-sequence"]): ---> 92 raise ValueError ("{0} is equal to ".format (y_type)) 93 94 is not supported if y_type in [" binary "," multiclass "]:

 ValueError: continuous is not supported 

This is sample data. I can not show real data.

 target, func_1, func_2, func_2, ... func_200 float, float, float, float, ... float 

Here is my code.

 import pandas as pd import numpy as np from sklearn.preprocessing import Imputer from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor, ExtraTreesRegressor, GradientBoostingRegressor from sklearn.cross_validation import train_test_split from sklearn.metrics import accuracy_score from sklearn import tree train = pd.read_csv('data.txt', sep='\t') labels = train.target train.drop('target', axis=1, inplace=True) cat = ['cat'] train_cat = pd.get_dummies(train[cat]) train.drop(train[cat], axis=1, inplace=True) train = np.hstack((train, train_cat)) imp = Imputer(missing_values='NaN', strategy='mean', axis=0) imp.fit(train) train = imp.transform(train) x_train, x_test, y_train, y_test = train_test_split(train, labels.values, test_size = 0.2) clf = RandomForestRegressor(n_estimators=10) clf.fit(x_train, y_train) y_pred = clf.predict(x_test) accuracy_score(y_test, y_pred) # This is where I get the error. 

Answer 1

This is because accuracy_score is for classification purposes only. For regression, you should use something else, for example:

 clf.score(X_test, y_test) 

Where X_test are samples, y_test are the corresponding truth values. He will calculate the forecasts inside.

Answer 2

Since you are performing the classification task, you should use the metric R-square (joint definition) instead of the accuracy rating (the accuracy rating is used for classification purposes).

To avoid confusion, I suggest you use a different variable name, for example reg / rfr.

R-squared can be computed by calling the score function provided by RandomForestRegressor, for example:

 rfr.score(X_test,Y_test)