pandas 使用scikit-learn（sklearn），如何处理线性回归的缺失数据？
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/33113947/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
Using scikit-learn (sklearn), how to handle missing data for linear regression?
提问by O.rka
I tried this but couldn't get it to work for my data: Use Scikit Learn to do linear regression on a time series pandas data frame
我试过了，但无法让它对我的数据起作用： 使用 Scikit Learn to do linear regression on a time series pandas data frame
My data consists of 2 DataFrames. DataFrame_1.shape = (40,5000)and DataFrame_2.shape = (40,74). I'm trying to do some type of linear regression, but DataFrame_2contains NaNmissing data values. When I DataFrame_2.dropna(how="any")the shape drops to (2,74).
我的数据由 2 个数据帧组成。DataFrame_1.shape = (40,5000)和DataFrame_2.shape = (40,74)。我正在尝试进行某种类型的线性回归，但DataFrame_2包含NaN缺失的数据值。当我DataFrame_2.dropna(how="any")的形状下降到(2,74).
Is there any linear regression algorithm in sklearn that can handle NaNvalues?
sklearn中是否有可以处理NaN值的线性回归算法？
I'm modeling it after the load_bostonfrom sklearn.datasetswhere X,y = boston.data, boston.target = (506,13),(506,)
我在load_bostonfrom sklearn.datasetswhere之后建模X,y = boston.data, boston.target = (506,13),(506,)
Here's my simplified code:
这是我的简化代码：
X = DataFrame_1
for col in DataFrame_2.columns:
y = DataFrame_2[col]
model = LinearRegression()
model.fit(X,y)
#ValueError: Input contains NaN, infinity or a value too large for dtype('float64').
I did the above format to get the shapes to match up of the matrices
我做了上面的格式来使形状与矩阵相匹配
If posting the DataFrame_2would help, please comment below and I'll add it.
如果发布有DataFrame_2帮助，请在下面发表评论，我会添加它。
采纳答案by maxymoo
You can fill in the null values in ywith imputation. In scikit-learnthis is done with the following code snippet:
您可以y使用插补填充空值。在scikit-learn此与下面的代码片段完成：
from sklearn.preprocessing import Imputer
imputer = Imputer()
y_imputed = imputer.fit_transform(y)
Otherwise, you might want to build your model using a subset of the 74 columns as predictors, perhaps some of your columns contain less null values?
否则，您可能希望使用 74 列的子集作为预测变量来构建模型，也许您的某些列包含较少的空值？
回答by Foreever
If your variable is a DataFrame, you could use fillna. Here I replaced the missing data with the mean of that column.
如果您的变量是 DataFrame，则可以使用fillna. 在这里，我用该列的平均值替换了缺失的数据。
df.fillna(df.mean(), inplace=True)
