def xs(self, key):
"""
Returns a row from the DataMatrix as a Series object.
Parameters
----------
key : some index contained in the index
Returns
-------
Series
"""
if key not in self.index:
raise Exception('No cross-section for %s' % key)
loc = self.index.indexMap[key]
theSlice = self.values[loc, :].copy()
xsIndex = self.columns
result = Series(theSlice, index=xsIndex)
if self.objects is not None and len(self.objects.columns) > 0:
result = result.append(self.objects.getXS(key))
return result
def xs(self, key):
"""
Returns a row from the DataMatrix as a Series object.
Parameters
----------
key : some index contained in the index
Returns
-------
Series
"""
if key not in self.index:
raise Exception('No cross-section for %s' % key)
loc = self.index.indexMap[key]
theSlice = self.values[loc, :].copy()
xsIndex = self.columns
result = Series(theSlice, index=xsIndex)
if self.objects is not None and len(self.objects.columns) > 0:
result = result.append(self.objects.getXS(key))
return result
def model_cross_validation(flag):
if flag == 5:
train_set,train_label_set,test_df,test_label = cross_validation_data_preprocess()
else:
train_set,train_label_set,test_df,test_label = cross_validation_data_preprocess_2()
myLOGGER.debug('Cross validation varify on train data....')
bf1_RF = -1.0
index_RF = 0
bf1_SVM = -1.0
index_SVM = 0
bf1_DT = -1.0
index_DT = 0
bf1_KNN = -1.0
index_KNN = 0
for i in range(len(train_set)):
train_merge = DataFrame()
train_label_merge = Series()
for j in range(len(train_set)):
if i != j :
train_label_merge = train_label_merge.append(train_label_set[j])
train_merge = train_merge.append(train_set[j])
myLOGGER.debug("Train shape {0}, train label {1},test shape {2}, test label shape {3}.".format(train_merge.shape, len(train_label_merge), train_set[i].shape,len(train_label_set[i])))
f1_RF = model_RandomForest(train_merge, train_label_merge, train_set[i], train_label_set[i])
if f1_RF > bf1_RF:
bf1_RF = f1_RF
index_RF = i
f1_RF = model_SVM(train_merge, train_label_merge, train_set[i], train_label_set[i])
if f1_RF > bf1_SVM:
bf1_SVM = f1_RF
index_SVM = i
f1_DT = model_DT(train_merge, train_label_merge, train_set[i], train_label_set[i])
if f1_DT > bf1_DT:
bf1_DT = f1_DT
index_DT = i
f1_KNN = model_KNN(train_merge, train_label_merge, train_set[i], train_label_set[i])
if f1_KNN > bf1_KNN:
bf1_KNN = f1_KNN
index_KNN = i
myLOGGER.debug("Cross validation varify: f1_RF = {0}, f1_SVM = {1}, f1_DT = {2}, f1_KNN = {3}.".format(bf1_RF, bf1_SVM, bf1_DT, bf1_KNN))
myLOGGER.debug('Cross validation varify on test data....')
train_merge = DataFrame()
train_label_merge = Series()
for j in range(len(train_set)):
if j != index_RF :
train_label_merge = train_label_merge.append(train_label_set[j])
train_merge = train_merge.append(train_set[j])
f1_RF = model_RandomForest(train_merge, train_label_merge, test_df, test_label)
train_merge = DataFrame()
train_label_merge = Series()
for j in range(len(train_set)):
if j != index_SVM :
train_label_merge = train_label_merge.append(train_label_set[j])
train_merge = train_merge.append(train_set[j])
f1_SVM = model_SVM(train_merge, train_label_merge, test_df, test_label)
train_merge = DataFrame()
train_label_merge = Series()
for j in range(len(train_set)):
if j != index_DT :
train_label_merge = train_label_merge.append(train_label_set[j])
train_merge = train_merge.append(train_set[j])
f1_DT = model_DT(train_merge, train_label_merge, test_df, test_label)
train_merge = DataFrame()
train_label_merge = Series()
for j in range(len(train_set)):
if j != index_KNN :
train_label_merge = train_label_merge.append(train_label_set[j])
train_merge = train_merge.append(train_set[j])
f1_KNN = model_KNN(train_merge, train_label_merge, test_df, test_label)
