fix bugs

- anova metabolite boxplot index
- heatmap key error

Author: axelwalter

src/clustering.py

@@ -36,24 +36,17 @@ def get_heatmap(data):
     # Create dataframe with sorted features
     ord_ft = ord_samp.T.reset_index()
     ord_ft = ord_ft.reindex(cluster_ft["leaves"])
-    ord_ft.rename(columns={"index": "metabolite"}, inplace=True)
 
-    # ord_ft.set_index("metabolite", inplace=True)
+    ord_ft.drop(columns=["row ID"], inplace=True)
+    # Append string prefix to numeric indeces
+    ord_ft.index = pd.Index(["m_"+x if x.isnumeric() else x for x in ord_ft.index.astype(str)])
 
-    # if we have numerical values convert them to strings to have even spacing
-    # try: 
-    #     float(ord_ft.index[0])
-    #     y_ticks = ["m_"+str(m) for m in ord_ft.index]
-    # except ValueError:
-    #     y_ticks = list(ord_ft.index)
-    ord_ft["metabolite"] = ord_ft["metabolite"].astype(str).apply(lambda x: "m_"+x if x.isnumeric() else x)
-    ord_ft.set_index("metabolite", inplace=True)
-
-    y_ticks = ord_ft.index.tolist()
+    st.dataframe(ord_ft)
+    
     # Heatmap
     fig = px.imshow(
         ord_ft,
-        y=y_ticks,
+        y=ord_ft.index.tolist(),
         x=list(ord_ft.columns),
         text_auto=False,
         aspect="auto",

src/fileselection.py

@@ -75,7 +75,7 @@ def load_from_gnps(task_id, cmn=False):
             an_url = f"https://proteomics2.ucsd.edu/ProteoSAFe/DownloadResultFile?task={task_id}&file=DB_result/&block=main"
             an = pd.read_csv(an_url, sep = "\t")[["#Scan#", "Compound_Name"]].set_index("#Scan#")
     if cmn:
-        ft.index = ft["row ID"]
+        ft.index = ft["row ID"].astype(str)
         ft = ft.drop(columns=["row m/z", "row retention time", "row ID"])
     else:
         index_with_mz_RT = pd.Index(ft.apply(lambda x: f'{x["row ID"]}_{round(x["row m/z"], 4)}_{round(x["row retention time"], 2)}', axis=1))