我想为train和;测试集,然后仅在训练和;测试集。我正在运行以下代码,用于在两个数据集中创建虚拟变量,但得到
.
我在Jupyter笔记本的一个单元格中键入了以下内容
def get_features(train, test):
trainval = list(train.columns.values) # list train features
testval = list(test.columns.values) # list test features
features = list(set(trainval) & set(testval)) # check wich features are in common (remove the outcome column)
features.remove('Id') # remove non-usefull id column
return features
def process_features(train,test):
tables=[test,train]
for table in tables:
table['SoldDt']= table[['MoSold','YrSold']].apply(lambda x : '{}-{}'.format(x[0],x[1]), axis=1)
table['YearBuilt']= pd.to_datetime(table.YearBuilt,format="%Y")
table['YearRemodAdd']= pd.to_datetime(table.YearRemodAdd,format="%Y")
table['SoldDt']= pd.to_datetime(table.SoldDt,format="%m-%Y")
table.GarageYrBlt.fillna(1,inplace=True)
table.GarageYrBlt=table.GarageYrBlt.apply(int)
table.GarageYrBlt.replace(1,'NaT',inplace=True)
table['GarageYrBlt']= pd.to_datetime(table.GarageYrBlt,format="%Y")
del table['MoSold']
del table['YrSold']
table['MSSubClass']=table['MSSubClass'].apply(str)
table['OverallQual']=table['OverallQual'].apply(str)
table['OverallCond']=table['OverallCond'].apply(str)
table.Alley.fillna("NotAvl",inplace=True)
table.BsmtQual.fillna("NB",inplace=True)
table.BsmtCond.fillna("NB",inplace=True)
table.BsmtExposure.fillna("NB",inplace=True)
table.BsmtFinType1.fillna("NB",inplace=True)
table.BsmtFinType2.fillna("NB",inplace=True)
table.FireplaceQu.fillna("NF",inplace=True)
table.GarageType.fillna("NG",inplace=True)
table.GarageFinish.fillna("NG",inplace=True)
table.GarageQual.fillna("NG",inplace=True)
table.GarageCond.fillna("NG",inplace=True)
table.PoolQC.fillna("NP",inplace=True)
table.Fence.fillna("NFe",inplace=True)
table.MiscFeature.fillna("NotAvl",inplace=True)
table.LotFrontage.fillna(0,inplace=True)
table=table.dropna(inplace=True)
table=pd.get_dummies(table)
features = get_features(train,test)
return train,test,features
然后,我在另一个单元格中调用该函数
train = pd.read_csv('/mnt/disk2/Data/HousePrices/train.csv')
test = pd.read_csv('/mnt/disk2/Data/HousePrices/test.csv')
train,test,features = process_features(train,test)
我发现了以下错误
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-17-b2727d6cdc63> in <module>()
1 train = pd.read_csv('/mnt/disk2/Data/HousePrices/train.csv')
2 test = pd.read_csv('/mnt/disk2/Data/HousePrices/test.csv')
----> 3 train,test,features = process_features(train,test)
<ipython-input-16-dc47e5e9f9b6> in process_features(train, test)
40
41 table=table.dropna(inplace=True)
---> 42 table=pd.get_dummies(table)
43
44 print ("Getting features...")
/usr/local/lib/python3.5/dist-packages/pandas/core/reshape.py in get_dummies(data, prefix, prefix_sep, dummy_na, columns, sparse, drop_first)
1102 else:
1103 result = _get_dummies_1d(data, prefix, prefix_sep, dummy_na,
-> 1104 sparse=sparse, drop_first=drop_first)
1105 return result
1106
/usr/local/lib/python3.5/dist-packages/pandas/core/reshape.py in _get_dummies_1d(data, prefix, prefix_sep, dummy_na, sparse, drop_first)
1123 # if all NaN
1124 if not dummy_na and len(levels) == 0:
-> 1125 return get_empty_Frame(data, sparse)
1126
1127 codes = codes.copy()
/usr/local/lib/python3.5/dist-packages/pandas/core/reshape.py in get_empty_Frame(data, sparse)
1115 index = data.index
1116 else:
-> 1117 index = np.arange(len(data))
1118 if not sparse:
1119 return DataFrame(index=index)
TypeError: object of type 'NoneType' has no len()
