tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

saving work for yesterday where uq runs were repeated

Browse source
This commit is contained in:
Tanushree Tunstall 2022-06-20 14:57:11 +01:00
parent efeaf52cde
commit 4ab99dcbd2
11 changed files with 10993 additions and 10660 deletions
Download patch file Download diff file Expand all files Collapse all files

8
scripts/ml/ml_data_rt.py
View file

@ -552,18 +552,18 @@ def setvars(gene,drug):
#=================================================
# Training and BLIND test set: imputed vs actual
# BUT in REVERSE i.e
# BUT in REVERSE i.e.
# dst with actual values : blind test
# dst with imputed values : training set
#==================================================
my_df_ml[drug].isna().sum() #'na' ones are now training set
blind_test_df = my_df_ml[my_df_ml[drug].notna()]
blind_test_df.shape
training_df = my_df_ml[my_df_ml[drug].isna()]
training_df.shape
blind_test_df = my_df_ml[my_df_ml[drug].notna()]
blind_test_df.shape
# Target 1: dst_mode
training_df[drug].value_counts()
training_df['dst_mode'].value_counts()