我是机器学习领域的新手，我开始参加Kaggle比赛以获得一些实践经验。我正在竞争知识竞赛CIFAR 10-图像中的物体识别，你必须在10个类别中对数千个图像进行分类，我可以在那里找到我使用的所有数据。我试图实现Gridsearch来优化我的机器学习算法的参数，但每当我尝试将我的分类器与我的训练数据相匹配时，我就会收到错误。我发现了引发错误的函数，它与我的标签没有正确的类型有关，但我不知道如何解决它。我使用的标签是字符串，我对它们进行预处理，以便我可以将它们提供给算法。我在那里做错了吗？或者当我为网格搜索拆分数据集时可能出现问题？坦率地说，我缺乏解决这个问题的经验和知识，我绝对可以帮助你。
涉及的代码：
import glob
import os
from sklearn.svm import SVC
from sklearn import preprocessing
import pandas as pd
from sklearn import cross_validation
from sklearn import metrics
from sklearn.grid_search import GridSearchCV
def label_preprocessing(Labels):
Labels = np.array(Labels)[:,1]
le = preprocessing.LabelEncoder()
le.fit_transform(Labels)
return Labels
def model_selection(train,Labels):
parameters = {"C":[0.1,1,10,100],"gamma":[0.0001,0.001,0.01,0.1]}
X_train, X_test, y_train, y_test = cross_validation.train_test_split(train, Labels, test_size = 0.2, random_state = 0)
svm = SVC()
clf = GridSearchCV(svm,parameters)
clf = clf.fit(X_train,y_train)
print ("20 fold cv score: ",np.mean(cross_validation.cross_val_score(clf,X_test,y_test,cv = 10,scoring = "roc_auc")))
return clf
if __name__ == "__main__":
train_images = np.array(file_open(image_dir1,"*.png"))[:100]
test_images = np.array(file_open(image_dir2,"*.png"))[:100]
Labels = label_preprocessing(pd.read_csv(image_dir3)[:100])
train_set = [matrix_image(image) for image in train_images]
test_set = [matrix_image(image) for image in test_images]
train_set = np.array(train_set)
test_set = np.array(test_set)
print("selecting best model and evaluating it")
svm = model_selection(train_set,Labels)
print("predicting stuff")
result = svm.predict(test_set)
np.savetxt("submission.csv", result, fmt = "%s", delimiter = ",")
完全追溯：
Traceback (most recent call last):
File "C:\Users\Abdc\workspace\final_submission\src\SVM.py", line 49, in <module>
svm = model_selection(train_set,Labels)
File "C:\Users\Abdc\workspace\final_submission\src\SVM.py", line 35, in model_selection
clf = clf.fit(X_train,y_train)
File "C:\Python27\lib\site-packages\sklearn\grid_search.py", line 707, in fit
return self._fit(X, y, ParameterGrid(self.param_grid))
File "C:\Python27\lib\site-packages\sklearn\grid_search.py", line 493, in _fit
for parameters in parameter_iterable
File "C:\Python27\lib\site-packages\sklearn\externals\joblib\parallel.py", line 517, in __call__
self.dispatch(function, args, kwargs)
File "C:\Python27\lib\site-packages\sklearn\externals\joblib\parallel.py", line 312, in dispatch
job = ImmediateApply(func, args, kwargs)
File "C:\Python27\lib\site-packages\sklearn\externals\joblib\parallel.py", line 136, in __init__
self.results = func(*args, **kwargs)
File "C:\Python27\lib\site-packages\sklearn\grid_search.py", line 311, in fit_grid_point
this_score = clf.score(X_test, y_test)
File "C:\Python27\lib\site-packages\sklearn\base.py", line 294, in score
return accuracy_score(y, self.predict(X))
File "C:\Python27\lib\site-packages\sklearn\metrics\metrics.py", line 1064, in accuracy_score
y_type, y_true, y_pred = _check_clf_targets(y_true, y_pred)
File "C:\Python27\lib\site-packages\sklearn\metrics\metrics.py", line 123, in _check_clf_targets
raise ValueError("{0} is not supported".format(y_type))
ValueError: unknown is not supported
这是引发错误的函数。它可以在sklearn.metrics模块中找到：
def _check_clf_targets(y_true, y_pred):
"""Check that y_true and y_pred belong to the same classification task
This converts multiclass or binary types to a common shape, and raises a
ValueError for a mix of multilabel and multiclass targets, a mix of
multilabel formats, for the presence of continuous-valued or multioutput
targets, or for targets of different lengths.
Column vectors are squeezed to 1d.
Parameters
----------
y_true : array-like,
y_pred : array-like
Returns
-------
type_true : one of {'multilabel-indicator', 'multilabel-sequences', \
'multiclass', 'binary'}
The type of the true target data, as output by
``utils.multiclass.type_of_target``
y_true : array or indicator matrix or sequence of sequences
y_pred : array or indicator matrix or sequence of sequences
"""
y_true, y_pred = check_arrays(y_true, y_pred, allow_lists=True)
type_true = type_of_target(y_true)
type_pred = type_of_target(y_pred)
y_type = set([type_true, type_pred])
if y_type == set(["binary", "multiclass"]):
y_type = set(["multiclass"])
if len(y_type) > 1:
raise ValueError("Can't handle mix of {0} and {1}"
"".format(type_true, type_pred))
# We can't have more than one value on y_type => The set is no more needed
y_type = y_type.pop()
# No metrics support "multiclass-multioutput" format
if (y_type not in ["binary", "multiclass", "multilabel-indicator",
"multilabel-sequences"]):
raise ValueError("{0} is not supported".format(y_type))
if y_type in ["binary", "multiclass"]:
y_true = column_or_1d(y_true)
y_pred = column_or_1d(y_pred)
return y_type, y_true, y_pred
有关标签的更多信息：
标签和dtype的内容：
In [21]:
Labels = np.array(Labels)[:,1]
Labels
Out[21]:
array(['frog', 'truck', 'truck', ..., 'truck', 'automobile', 'automobile'], dtype=object)
预处理后的标签内容
In [25]:
Labels = np.array(Labels)[:,1]
Labels
le = preprocessing.LabelEncoder()
Labels = le.fit_transform(Labels)
Labels
Out[25]:
array([6, 9, 9, ..., 9, 1, 1])
预处理后的标签形状：
In [18]:
Labels = np.array(Labels)[:,1]
Labels.shape
le = preprocessing.LabelEncoder()
Labels = le.fit_transform(Labels)
Labels.shape
Out[18]:
(50000L,)
原始内容可在此处找到：https://www.kaggle.com/c/cifar-10/data。其中包含数据点的ID及其类Label。所以它是一个nx2矩阵。