How to reduce dimentionality on Sparse Matrix in Python?

This recipe helps you reduce dimentionality on Sparse Matrix in Python

In [1]:

## How to reduce dimentionality on Sparse Matrix in Python
def Snippet_122():
    print()
    print(format('How to reduce dimentionality on Sparse Matrix in Python','*^82'))

    import warnings
    warnings.filterwarnings("ignore")

    # load libraries
    from sklearn.preprocessing import StandardScaler
    from sklearn.decomposition import TruncatedSVD
    from scipy.sparse import csr_matrix
    from sklearn import datasets

    # Load Digits Data And Make Sparse
    digits = datasets.load_digits()

    # Standardize the feature matrix
    X = StandardScaler().fit_transform(digits.data)
    print(); print(X)

    # Make sparse matrix
    X_sparse = csr_matrix(X)
    print(); print(X_sparse)

    # Create Truncated Singular Value Decomposition
    tsvd = TruncatedSVD(n_components=10)

    # Run Truncated Singular Value Decomposition
    X_sparse_tsvd = tsvd.fit(X_sparse).transform(X_sparse)
    print(); print(X_sparse_tsvd)

    # Show results
    print()
    print('Original number of features:', X_sparse.shape[1])
    print('Reduced number of features:', X_sparse_tsvd.shape[1])

    # Sum of first seven components' explained variance ratios
    print(); print(tsvd.explained_variance_ratio_[0:6].sum())

Snippet_122()

*************How to reduce dimentionality on Sparse Matrix in Python**************

[[ 0.         -0.33501649 -0.04308102 ... -1.14664746 -0.5056698
  -0.19600752]
 [ 0.         -0.33501649 -1.09493684 ...  0.54856067 -0.5056698
  -0.19600752]
 [ 0.         -0.33501649 -1.09493684 ...  1.56568555  1.6951369
  -0.19600752]
 ...
 [ 0.         -0.33501649 -0.88456568 ... -0.12952258 -0.5056698
  -0.19600752]
 [ 0.         -0.33501649 -0.67419451 ...  0.8876023  -0.5056698
  -0.19600752]
 [ 0.         -0.33501649  1.00877481 ...  0.8876023  -0.26113572
  -0.19600752]]

  (0, 1)	-0.3350164872543856
  (0, 2)	-0.04308101770538793
  (0, 3)	0.2740715207154218
  (0, 4)	-0.6644775126361527
  (0, 5)	-0.8441293865949171
  (0, 6)	-0.40972392088346243
  (0, 7)	-0.1250229232970408
  (0, 8)	-0.05907755711884675
  (0, 9)	-0.6240092623290964
  (0, 10)	0.4829744992519545
  (0, 11)	0.7596224512649244
  (0, 12)	-0.05842586308220443
  (0, 13)	1.1277211297338117
  (0, 14)	0.8795830595483867
  (0, 15)	-0.13043338063115095
  (0, 16)	-0.04462507326885248
  (0, 17)	0.11144272449970435
  (0, 18)	0.8958804382797294
  (0, 19)	-0.8606663175537699
  (0, 20)	-1.1496484601880896
  (0, 21)	0.5154718747277965
  (0, 22)	1.905963466976408
  (0, 23)	-0.11422184388584329
  (0, 24)	-0.03337972630405602
  (0, 25)	0.48648927722411006
  :	:
  (1796, 38)	-0.8226945146290309
  (1796, 40)	-0.061343668908253476
  (1796, 41)	0.8105536026095989
  (1796, 42)	1.3950951873625397
  (1796, 43)	-0.19072005925701047
  (1796, 44)	-0.5868275383619802
  (1796, 45)	1.3634658076459107
  (1796, 46)	0.5874903313016945
  (1796, 47)	-0.08874161717060432
  (1796, 48)	-0.035433262605025426
  (1796, 49)	4.179200682513991
  (1796, 50)	1.505078217025183
  (1796, 51)	0.0881769306516768
  (1796, 52)	-0.26718796251356636
  (1796, 53)	1.2010187221077009
  (1796, 54)	0.8692294429227895
  (1796, 55)	-0.2097851269640334
  (1796, 56)	-0.023596458909150665
  (1796, 57)	0.7715345500122912
  (1796, 58)	0.47875261517372414
  (1796, 59)	-0.020358468129093202
  (1796, 60)	0.4441643511677691
  (1796, 61)	0.8876022965425754
  (1796, 62)	-0.26113572420685327
  (1796, 63)	-0.1960075186604789

[[ 1.9142142  -0.95450588 -3.94605003 ...  1.48605508  0.1580507
  -0.81430216]
 [ 0.58898116  0.92463167  3.92473516 ...  0.55387834  1.07380158
   0.11517957]
 [ 1.3020402  -0.31720719  3.02328596 ...  1.10558107  0.86551794
  -0.91136424]
 ...
 [ 1.02259475 -0.1478891   2.47003035 ...  0.55809882  2.09899726
  -2.06791444]
 [ 1.07605326 -0.38087334 -2.45539167 ...  0.82143985  1.04432596
  -0.44841053]
 [-1.25770332 -2.22756573  0.28369586 ... -1.17449788  0.8603674
  -1.87848472]]

Original number of features: 64
Reduced number of features: 10

0.456120019803888