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

added distinct lin count for each mutation

Browse source
This commit is contained in:
Tanushree Tunstall 2022-04-07 18:47:53 +01:00
parent 67d9e6160a
commit 28d0d68413
1 changed files with 13 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

16
test_data/processing.py
View file

@ -175,6 +175,15 @@ data2.drop(['mutation'], axis=1, inplace=True)
#%% Process lineage info
# add how many different lineages a sample is represented in?
# https://stackoverflow.com/questions/37189878/pandas-add-column-to-groupby-dataframe
# https://stackoverflow.com/questions/43847520/how-to-get-the-distinct-count-of-values-in-a-python-pandas-dataframe
data2.groupby('mutationinformation')['lineage'].size() # sample count
data2.groupby('mutationinformation')['sample'].size()
data2.groupby('mutationinformation')['lineage'].value_counts()
data2.groupby('mutationinformation')['lineage'].nunique()
data2['lin_count'] = data2['mutationinformation'].map(data2.groupby('mutationinformation')['lineage'].nunique())
#%% subset: equivalent of merged_df3?
# https://stackoverflow.com/questions/39900061/sort-lists-in-a-pandas-dataframe-column
@ -185,6 +194,7 @@ data2.drop(['mutation'], axis=1, inplace=True)
# data2['dst_multimode'].value_counts()
# data2.sort_values(['dst_multimode'], ascending=False)
data_df3 = data2.drop_duplicates(['mutationinformation'])
data_df3_v2 = data2.drop_duplicates(['mutationinformation'])
all(data_df3 == data_df3_v2)
#data_df3 = data2.drop_duplicates(['mutationinformation'])
#data_df3_v2 = data2.drop_duplicates(['mutationinformation'])
#all(data_df3 == data_df3_v2)
#%%