The Imputer is used to fill missing values with some statistics (e.g. mean, median, ...) of the data. To avoid data leakage during cross-validation, it computes the statistic on the train data during the fit, stores it and uses it on the test data, during the transform.
from sklearn.preprocessing import Imputer
obj = Imputer(strategy='mean')
obj.fit([[1, 2, 3], [2, 3, 4]])
# array([ 1.5, 2.5, 3.5])
X = obj.transform([[4, np.nan, 6], [5, 6, np.nan]])
# array([[ 4. , 2.5, 6. ],
# [ 5. , 6. , 3.5]])
You can follow both steps in one if your train and test data are identical:
X = obj.fit_transform([[1, 2, np.nan], [2, 3, 4]])
# array([[ 1. , 2. , 4. ],
# [ 2. , 3. , 4. ]])
The data distribution may change from the training data to the testing data, and you don't want the information of the testing data to be already present during the fit.
Hope this answer helps you!