def test_solver_fill_methods_with_low_rank_random_matrix():
for fill_method in ("zero", "mean", "median", "min", "random"):
imputer = SimpleFill(fill_method=fill_method)
XY_completed = imputer.fit_transform(XY_incomplete)
_, missing_mae = reconstruction_error(
XY,
XY_completed,
missing_mask,
name="Solver with fill_method=%s" % fill_method)
assert missing_mae < 5, "Error too high for Solver with %s fill method!" % fill_method
def run_impute(self, X, state='train'):
if state == 'train':
self.train_data['ave'] = np.zeros([X.shape[0], X.shape[1]])
for imp_method in self.impute_method:
if imp_method == 'mean':
imp_ope = SimpleFill()
if imp_method == 'KNN':
imp_ope = KNN()
if imp_method == 'IterativeSVD':
imp_ope = IterativeSVD()
if imp_method == 'MatrixFactorization':
imp_ope = MatrixFactorization()
X_filled = imp_ope.fit_transform(X)
self.train_data[imp_method] = X_filled
self.impute_operator[imp_method] = imp_ope
self.train_data['ave'] += X_filled
self.train_data['ave'] /= len(self.impute_method)
return 0
SimpleFill)
n = 200
m = 20
inner_rank = 4
X = np.dot(np.random.randn(n, inner_rank), np.random.randn(inner_rank, m))
print("Mean squared element: %0.4f" % (X**2).mean())
# X is a data matrix which we're going to randomly drop entries from
missing_mask = np.random.rand(*X.shape) < 0.1
X_incomplete = X.copy()
# missing entries indicated with NaN
X_incomplete[missing_mask] = np.nan
meanFill = SimpleFill("mean")
X_filled_mean = meanFill.fit_transform(X_incomplete)
# Use 3 nearest rows which have a feature to fill in each row's missing features
knnImpute = KNN(k=3)
X_filled_knn = knnImpute.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
softImpute = SoftImpute()
# simultaneously normalizes the rows and columns of your observed data,
# sometimes useful for low-rank imputation methods
