import sklearn
import pandas as pd
import matplotlib as plt
from fancyimpute import IterativeSVD
print("reading data...")
X = pd.read_csv("Data/train.csv").iloc[:, 1:-1].as_matrix(
) # remove first row (labels), first and last columns
test = pd.read_csv("Data/test.csv").iloc[:, 1:].as_matrix()
# ind = np.genfromtxt('Class_change_ind.csv', delimiter = ',', dtype = 'int32')
# test_incomplete = test.copy()
print X.shape
print("setting svd object...")
svd = IterativeSVD(rank=1000, convergence_threshold=0.0001)
X_svd = svd.complete(X)
# print X_svd[:,0]
print("saving data...")
np.savetxt("Data/train_isvdimp.csv", X_svd, delimiter=",")
print("imputing test...")
test_svd = svd.complete(test)
np.savetxt("Data/test_isvdimp.csv", test_svd, delimiter=",")
print '\a'
#reader = Reader(line_format='user item rating', sep='\t')
# A reader is still needed but only the rating_scale param is requiered.
data.split(n_folds=10) # data can now be used normally
data_full = data.build_full_trainset()
#
obj = IterativeSVD(rank=20,
max_iters=700,
min_value=limits[0],
max_value=limits[1],
verbose=True)
datamat_filled_SVD_fancy = obj.complete(datamat_missing)
obj = SoftImpute(shrinkage_value=None,
max_iters=700,
max_rank=20,
n_power_iterations=1,
init_fill_method="zero",
min_value=limits[0],
max_value=limits[1],
normalizer=None,
verbose=True)
datamat_filled_SOFT_fancy = obj.complete(datamat_missing)
obj = NuclearNormMinimization(require_symmetric_solution=False,
min_value=limits[0],