Clean and Organize data for the I-SPY1 Clinical Trial



In [1]:

    
# load module by Julio and pandas
from ispy1 import clean_data
import pandas as pd

file = './data/I-SPY_1_All_Patient_Clinical_and_Outcome_Data.xlsx'
df = clean_data.clean_my_data(file)
df.head(2)

# save clean data in new  csv file
df.to_csv('./data/I-SPY_1_clean_data.csv')

df.head(2)









    Out[1]:







  
    
      
      age
      White
      ER+
      PR+
      HR+
      Bilateral
      Right_Breast
      MRI_LD_Baseline
      MRI_LD_1_3dAC
      MRI_LD_Int_Reg
      MRI_LD_PreSurg
      Alive
      Survival_length
      RFS
      RFS_code
      PCR
      RCB
    
    
      SUBJECTID
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
    
  
  
    
      1001
      38.73
      Yes
      Yes
      No
      Yes
      No
      No
      88.0
      78.0
      30.0
      14.0
      No
      1264
      751
      1
      No
      2.0
    
    
      1002
      37.79
      Yes
      Yes
      Yes
      Yes
      No
      Yes
      29.0
      26.0
      66.0
      16.0
      No
      1155
      1043
      1
      No
      3.0

	age	White	ER+	PR+	HR+	Bilateral	Right_Breast	MRI_LD_Baseline	MRI_LD_1_3dAC	MRI_LD_Int_Reg	MRI_LD_PreSurg	Alive	Survival_length	RFS	RFS_code	PCR	RCB
SUBJECTID
1001	38.73	Yes	Yes	No	Yes	No	No	88.0	78.0	30.0	14.0	No	1264	751	1	No	2.0
1002	37.79	Yes	Yes	Yes	Yes	No	Yes	29.0	26.0	66.0	16.0	No	1155	1043	1	No	3.0