Я просто пытаюсь сделать простой пример RandomForestRegressor. Но при тестировании точности я получаю эту ошибку
/Users/noppanit/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.pyc
in precision_score (y_true, y_pred, normalize, sample_weight) 177 178 # Вычислить точность для каждого возможного представления → 179 y_type, y_true, y_pred = _check_targets (y_true, y_pred) 180, если y_type.startswith('multilabel'): 181 отличаются = 181 = разные count_nonzero (y_true - y_pred, axis = 1)
/Users/noppanit/anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.pyc
в _check_targets (y_true, y_pred) 90 if (y_type не в ["binary", "multiclass", "multilabel-pointer", 91 "multilabel-sequence"]): ---> 92 повысить ValueError ("{0} равно не поддерживается ".format(y_type)) 93 94, если y_type в [" binary "," multiclass "]:
ValueError: continuous is not supported
Это образец данных. Я не могу показать реальные данные.
target, func_1, func_2, func_2, ... func_200
float, float, float, float, ... float
Вот мой код.
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.