Scikit-learn： "The least populated class in y has only 1 member"

Question

我正在尝试使用Scikit-learn进行随机森林回归。使用 Pandas 加载数据后的第一步是将数据拆分为测试集和训练集。但是，我收到错误：

y 中填充最少的类只有 1 个成员

我已经搜索了Google并找到了此错误的各种实例，但是我似乎仍然无法理解此错误的含义。

training_file = "training_data.txt"
data = pd.read_csv(training_file, sep='t')
y = data.Result
X = data.drop('Result', axis=1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=123, stratify=y)
pipeline = make_pipeline(preprocessing.StandardScaler(), RandomForestRegressor(n_estimators=100))
hyperparameters = { 'randomforestregressor__max_features' : ['auto', 'sqrt', 'log2'],
'randomforestregressor__max_depth' : [None, 5, 3, 1] }
model = GridSearchCV(pipeline, hyperparameters, cv=10)
model.fit(X_train, y_train)
prediction = model.predict(X_test)
joblib.dump(model, 'ms5000.pkl')

train_test_split方法生成以下堆栈跟踪：

Traceback (most recent call last):
File "/Users/justin.shapiro/Desktop/IPML_Model/model_definition.py", line 18, in <module>
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.22, random_state=123, stratify=y)
File "/Library/Python/2.7/site-packages/sklearn/model_selection/_split.py", line 1700, in train_test_split
train, test = next(cv.split(X=arrays[0], y=stratify))
File "/Library/Python/2.7/site-packages/sklearn/model_selection/_split.py", line 953, in split
for train, test in self._iter_indices(X, y, groups):
File "/Library/Python/2.7/site-packages/sklearn/model_selection/_split.py", line 1259, in _iter_indices
raise ValueError("The least populated class in y has only 1"
ValueError: The least populated class in y has only 1 member, which is too few. The minimum number of groups for any class cannot be less than 2.

这是我的数据集的示例：

var1    var2    var3    var4    var5    var6    var7    var8    Result
high    5000.0  0       60      1000    75      0.23    0.75    17912.0
mid     5000.0  0       60      1000    50      0.23    0.75    18707.0
low     5000.0  0       60      1000    25      0.23    0.75    17912.0
high    5000.0  5       60      1000    75      0.23    0.75    18577.0
mid     5000.0  5       60      1000    50      0.23    0.75    19407.0
low     5000.0  5       60      1000    25      0.23    0.75    18577.0

这个错误是什么，我怎样才能摆脱它？

Answer 1

此行中引发的错误：

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.22, random_state=123, stratify=y)

尝试删除stratify=y