# # # # #  gbsg.h5  # # # # # 


# - - Description - - #

Rotterdam & German Breast Cancer Study Group


# - - Info - - #

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2232 entries, 0 to 2231
Data columns (total 9 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   0       2232 non-null   float32
 1   1       2232 non-null   float32
 2   2       2232 non-null   float32
 3   3       2232 non-null   float32
 4   4       2232 non-null   float32
 5   5       2232 non-null   float32
 6   6       2232 non-null   float32
 7   event   2232 non-null   int32  
 8   time    2232 non-null   float32
dtypes: float32(8), int32(1)
memory usage: 78.6 KB



# - - Stats - - #

                 0            1            2            3            4            5            6        event         time
count  2232.000000  2232.000000  2232.000000  2232.000000  2232.000000  2232.000000  2232.000000  2232.000000  2232.000000
mean      0.262097     0.836021     0.588710    55.077061     5.163530   142.014786   143.925186     0.567652    44.491585
std       0.439874     0.647716     0.492178    12.258656     5.075552   274.075256   240.159775     0.495513    27.629768
min       0.000000     0.000000     0.000000    21.000000     1.000000     0.000000     0.000000     0.000000     0.262834
25%       0.000000     0.000000     0.000000    46.000000     2.000000     6.000000    10.000000     0.000000    19.121149
50%       0.000000     1.000000     1.000000    55.000000     3.000000    37.000000    54.000000     1.000000    40.229979
75%       1.000000     1.000000     1.000000    64.000000     7.000000   161.250000   173.000000     1.000000    71.104721
max       1.000000     2.000000     1.000000    90.000000    51.000000  5004.000000  3008.000000     1.000000    87.359344


# - - Reference - - #

https://github.com/jaredleekatzman/DeepSurv/blob/master/experiments/data/gbsg/gbsg_cancer_train_test.h5