Upload 2 files

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+import pandas as pd
+import os
+from itertools import islice
+import tempfile
+
+
+def guarantee_multiindex_rows(df):
+   if not isinstance(df.index, pd.MultiIndex):
+      path = df.index[0]
+      try:
+         sep = "/" if "/" in path else "\\"
+         splits = tuple(df.index.str.split(sep))
+         df.index = pd.MultiIndex.from_tuples(splits)
+      except TypeError:
+         pass
+
+   try:
+      df.index = df.index.set_levels(df.index.levels[1].astype(str), level=1)
+   except AttributeError:
+      pass
+
+
+def convertcsv2h5(csv_name):
+   csv_name = csv_name.name
+   csv_path = os.path.splitext(csv_name)[0]
+   scorer = csv_path.split('_')[1]
+   with open(csv_name) as datafile:
+      head = list(islice(datafile, 0, 5))
+      if "individuals" in head[1]:
+         header = list(range(4))
+      else:
+         header = list(range(3))
+      if head[-1].split(",")[0] == "labeled-data":
+         index_col = [0, 1, 2]
+      else:
+         index_col = 0
+      data = pd.read_csv(csv_name, index_col=index_col, header=header)
+      data.columns = data.columns.set_levels([scorer], level="scorer")
+      guarantee_multiindex_rows(data)
+
+      with tempfile.NamedTemporaryFile(suffix=".h5", delete=False) as temp_file:
+         temp_file_path = csv_name.replace(".csv", ".h5")
+         data.to_hdf(temp_file_path, key="df_with_missing", mode="w")
+
+   return temp_file_path
+
+
+iface = gr.Interface(fn=convertcsv2h5, inputs="file", outputs="file")
+iface.launch()

requirements.txt

@@ -0,0 +1 @@
+pandas