diff --git a/test_data/processing.py b/test_data/processing.py
index f75afee..135c174 100644
--- a/test_data/processing.py
+++ b/test_data/processing.py
@@ -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)
\ No newline at end of file
+#data_df3 = data2.drop_duplicates(['mutationinformation'])
+#data_df3_v2 = data2.drop_duplicates(['mutationinformation'])
+#all(data_df3 == data_df3_v2)
+#%%
\ No newline at end of file