Imputation

pip install autoimpute

from autoimpute.imputations import SingleImputer, MultipleImputer, MiceImputer
si = SingleImputer() # pass through data once
mi = MultipleImputer() # pass through data multiple times
# mice
mice = MiceImputer() # pass through data multiple times and iteratively optimize imputations in each column

# mice
mice = MiceImputer()
mice.fit_transform(data)

# create a complex instance of the MiceImputer
# Here, we specify strategies by column and predictors for each column
# We also specify what additional arguments any `pmm` strategies should take
imp = MiceImputer(
    n=10,
    strategy={"salary": "pmm", "gender": "bayesian binary logistic", "age": "norm"},
    predictors={"salary": "all", "gender": ["salary", "education", "weight"]},
    imp_kwgs={"pmm": {"fill_value": "random"}},
    visit="left-to-right",
    return_list=True
)

# Because we set return_list=True, imputations are done all at once, not evaluated lazily.
# This will return M*N, where M is the number of imputations and N is the size of original dataframe.
imp.fit_transform(data)

from autoimpute.analysis import MiLinearRegression

# By default, use statsmodels OLS and MiceImputer()
simple_lm = MiLinearRegression()

# fit the model on each multiply imputed dataset and pool parameters
simple_lm.fit(X_train, y_train)

# get summary of fit, which includes pooled parameters under Rubin's rules
# also provides diagnostics related to analysis after multiple imputation
simple_lm.summary()

# make predictions on a new dataset using pooled parameters
predictions = simple_lm.predict(X_test)

# Control both the regression used and the MiceImputer itself
mice_imputer_arguments = dict(
    n=3,
    strategy={"salary": "pmm", "gender": "bayesian binary logistic", "age": "norm"},
    predictors={"salary": "all", "gender": ["salary", "education", "weight"]},
    imp_kwgs={"pmm": {"fill_value": "random"}},
    visit="left-to-right"
)
complex_lm = MiLinearRegression(
    model_lib="sklearn", # use sklearn linear regression
    mi_kwgs=mice_imputer_arguments # control the multiple imputer
)

# fit the model on each multiply imputed dataset
complex_lm.fit(X_train, y_train)

# get summary of fit, which includes pooled parameters under Rubin's rules
# also provides diagnostics related to analysis after multiple imputation
complex_lm.summary()

# make predictions on new dataset using pooled parameters
predictions = complex_lm.predict(X_test)

pip install fancyimpute

from fancyimpute import KNN, NuclearNormMinimization, SoftImpute, BiScaler

# X is the complete data matrix
# X_incomplete has the same values as X except a subset have been replace with NaN

# Use 3 nearest rows which have a feature to fill in each row's missing features
X_filled_knn = KNN(k=3).fit_transform(X_incomplete)

# matrix completion using convex optimization to find low-rank solution
# that still matches observed values. Slow!
X_filled_nnm = NuclearNormMinimization().fit_transform(X_incomplete)

# Instead of solving the nuclear norm objective directly, instead
# induce sparsity using singular value thresholding
X_incomplete_normalized = BiScaler().fit_transform(X_incomplete)
X_filled_softimpute = SoftImpute().fit_transform(X_incomplete_normalized)

# print mean squared error for the  imputation methods above
nnm_mse = ((X_filled_nnm[missing_mask] - X[missing_mask]) ** 2).mean()
print("Nuclear norm minimization MSE: %f" % nnm_mse)

softImpute_mse = ((X_filled_softimpute[missing_mask] - X[missing_mask]) ** 2).mean()
print("SoftImpute MSE: %f" % softImpute_mse)

knn_mse = ((X_filled_knn[missing_mask] - X[missing_mask]) ** 2).mean()
print("knnImpute MSE: %f" % knn_mse)