WIP add linear combination to tree_stats pairplot

matsengrp · Jul 22, 2024 · cf5e4b8 · cf5e4b8
1 parent be3946c
commit cf5e4b8
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 9 deletions.
diff --git a/gctree/branching_processes.py b/gctree/branching_processes.py
@@ -1575,10 +1575,14 @@ def print_stats(
             # To clear _dp_data fields of their large cargo
             dag.optimal_weight_annotate(edge_weight_func=lambda n1, n2: 0)
             num_ranking_filters = len(dag_filters)
+            col_names = combined_observer_filter.weight_funcs.names
+
             if not lexicographic:
+                col_names += (ranking_strategy.replace(' ', ''),)
+                dag_ls = [tup + (linear_combinator(tup),) for tup in dag_ls]
 
                 def minfunckey(tup):
-                    return linear_combinator(tup[:num_ranking_filters])
+                    return tup[-1]
 
             else:
                 _tuple_coeffs = [
@@ -1590,14 +1594,15 @@ def minfunckey(tup):
 
             dag_ls.sort(key=minfunckey)
 
+
             df = pd.DataFrame(
-                dag_ls, columns=combined_observer_filter.weight_funcs.names
+                dag_ls, columns=col_names
             ).drop(columns=[""])
             df.to_csv(outbase + ".tree_stats.csv")
             df["set"] = ["all_trees"] * len(df)
             bestdf = pd.DataFrame(
                 [first_tree_weighttuple],
-                columns=combined_observer_filter.weight_funcs.names,
+                columns=col_names,
             )
             bestdf["set"] = ["best_tree"]
             toplot_df = pd.concat([df, bestdf], ignore_index=True)

diff --git a/tests/smalltest.sh b/tests/smalltest.sh
@@ -6,12 +6,11 @@ export XDG_RUNTIME_DIR=/tmp/runtime-runner
 export MPLBACKEND=agg
 mkdir -p tests/smalltest_output
 
-# mutabilities=HS5F_Mutability.csv
-# substitutions=HS5F_Substitution.csv
-mutabilities=random_s5_mutabilities.csv
-substitutions=random_s5_substitution.csv
-# wget -O HS5F_Mutability.csv https://bitbucket.org/kleinstein/shazam/raw/ba4b30fc6791e2cfd5712e9024803c53b136e664/data-raw/HS5F_Mutability.csv
-# wget -O HS5F_Substitution.csv https://bitbucket.org/kleinstein/shazam/raw/ba4b30fc6791e2cfd5712e9024803c53b136e664/data-raw/HS5F_Substitution.csv
+mutabilities=HS5F_Mutability.csv
+substitutions=HS5F_Substitution.csv
+
+wget -O $mutabilities https://bitbucket.org/kleinstein/shazam/raw/ba4b30fc6791e2cfd5712e9024803c53b136e664/data-raw/HS5F_Mutability.csv
+wget -O $substitutions https://bitbucket.org/kleinstein/shazam/raw/ba4b30fc6791e2cfd5712e9024803c53b136e664/data-raw/HS5F_Substitution.csv
 
 gctree infer tests/small_outfile tests/abundances.csv --outbase tests/smalltest_output/gctree.infer1  --root GL --frame 1 --verbose --idlabel