所以下面是我的问题的一个非常简单的方法,只是为了处理事物的手段。更强大的实现可能涉及利用scikit学习中的Imputer类,这意味着它也可以执行模式,中值等,并且在处理稀疏/密集矩阵方面会更好。
这是基于Vivek Kumar对原始问题的评论,建议将数据拆分为堆栈并将其重新组装。
import numpy as np
from sklearn.base import BaseEstimator, TransformerMixin
class WithinClassMeanImputer(BaseEstimator, TransformerMixin):
def __init__(self, replace_col_index, class_col_index = None, missing_values=np.nan):
self.missing_values = missing_values
self.replace_col_index = replace_col_index
self.y = None
self.class_col_index = class_col_index
def fit(self, X, y = None):
self.y = y
return self
def transform(self, X):
y = self.y
classes = np.unique(y)
stacks = []
if len(X) > 1 and len(self.y) = len(X):
if(self.class_col_index == None):
# If we're using the dependent variable
for aclass in classes:
with_missing = X[(y == aclass) &
(X[:, self.replace_col_index] == self.missing_values)]
without_missing = X[(y == aclass) &
(X[:, self.replace_col_index] != self.missing_values)]
column = without_missing[:, self.replace_col_index]
# Calculate mean from examples without missing values
mean = np.mean(column[without_missing[:, self.replace_col_index] != self.missing_values])
# Broadcast mean to all missing values
with_missing[:, self.replace_col_index] = mean
stacks.append(np.concatenate((with_missing, without_missing)))
else:
# If we're using nominal values within a binarised feature (i.e. the classes
# are unique values within a nominal column - e.g. sex)
for aclass in classes:
with_missing = X[(X[:, self.class_col_index] == aclass) &
(X[:, self.replace_col_index] == self.missing_values)]
without_missing = X[(X[:, self.class_col_index] == aclass) &
(X[:, self.replace_col_index] != self.missing_values)]
column = without_missing[:, self.replace_col_index]
# Calculate mean from examples without missing values
mean = np.mean(column[without_missing[:, self.replace_col_index] != self.missing_values])
# Broadcast mean to all missing values
with_missing[:, self.replace_col_index] = mean
stacks.append(np.concatenate((with_missing, without_missing)))
if len(stacks) > 1 :
# Reassemble our stacks of values
X = np.concatenate(stacks)
return X
您可以根据'pclass'拆分数据,为它们计算'fare',然后再堆叠它们以创建完整的数据。 –
谢谢@VivekKumar!我会考虑将其作为我的管道的一部分 – TheJokersThief
您可以查看[此示例](http://scikit-learn.org/stable/auto_examples/hetero_feature_union.html#sphx-glr-auto-examples-hetero- feature-union-py)来获得实现你自己的类的提示,这可以在管道中使用 –