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

saving work with sections reflecting activities

Browse source
This commit is contained in:
Tanushree Tunstall 2022-04-14 19:43:14 +01:00
parent e99c169b35
commit 95a73efdd2
1 changed files with 12 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

24
scripts/data_extraction_v2.py
View file

@ -1602,14 +1602,6 @@ gene_LF3.head()
gene_LF3['drtype_max'] = gene_LF3.groupby(['mutationinformation'])['drtype_numeric'].max() gene_LF3['drtype_max'] = gene_LF3.groupby(['mutationinformation'])['drtype_numeric'].max()
gene_LF3.head() gene_LF3.head()
#%% Reset index: original indices
#gene_LF3 = gene_LF3.reset_index()
gene_LF3.index
gene_LF3['mutationinformation'] = gene_LF3.index
gene_LF3 = gene_LF3.set_index(['index_orig'])
gene_LF3[['mutationinformation']]
gene_LF3.index
#%% Revised counts #%% Revised counts
gene_LF3['dst_mode'].value_counts() gene_LF3['dst_mode'].value_counts()
gene_LF3[drug].value_counts() gene_LF3[drug].value_counts()
@ -1688,7 +1680,6 @@ foo2['lineage_corrupt_ucount']
foo2.index foo2.index
foo2 = foo2.set_index(['mutationinformation']) foo2 = foo2.set_index(['mutationinformation'])
# now merge # now merge
foo.index foo.index
foo.index.nunique() foo.index.nunique()
@ -1699,6 +1690,7 @@ foo_copy['lineage_ucount'] = foo_copy['lineage']
foo_copy.loc[foo2.index, 'lineage_ucount'] = foo2['lineage_corrupt_ucount'] foo_copy.loc[foo2.index, 'lineage_ucount'] = foo2['lineage_corrupt_ucount']
#%%FIXME: do regex for lineage for meta data else the ; messes it up #%%FIXME: do regex for lineage for meta data else the ; messes it up
# MOVE THIS TO THE RELEVANT section
#-------------------------- #--------------------------
# lineage multimode mode # lineage multimode mode
#-------------------------- #--------------------------
@ -1741,8 +1733,7 @@ c2 = foo2[foo2.loc[:, 'MUT'].isin(['A102P'])]
c2['lineage_numeric'].value_counts() c2['lineage_numeric'].value_counts()
#%% Lineage counts (including the ones containing multiple entries)[[<<< INCOMPLETE, TB finished]]
#%% Lineage counts (including the ones containing multiple entries)
# Get information about how many distinct lineages each mutation comes from # Get information about how many distinct lineages each mutation comes from
gene_LF3['lineage'].value_counts() gene_LF3['lineage'].value_counts()
@ -1781,4 +1772,13 @@ check1 = gene_LF3[['mutationinformation', 'lineage', 'lineage_ucount']]
check2 = check1[check1.loc[:, 'mutationinformation'].isin(['H57D'])] check2 = check1[check1.loc[:, 'mutationinformation'].isin(['H57D'])]
check2.value_counts() check2.value_counts()
#%% #%% Reset index: original indices [WAS above section Revised counts]
#gene_LF3 = gene_LF3.reset_index()
gene_LF3.index
gene_LF3['mutationinformation'] = gene_LF3.index
gene_LF3 = gene_LF3.set_index(['index_orig'])
gene_LF3[['mutationinformation']]
gene_LF3.index
#%% ADD summary results
#%% final output file with selected columns