Bugfix data-explorer images

data_explorer/app/data.py

@@ -1,7 +1,7 @@
 """This file contains data loading logic"""
 import json
 import logging
-from typing import List, Tuple
+from typing import List
 from urllib.parse import urlparse
 
 import dask.dataframe as dd

data_explorer/app/main.py

@@ -1,13 +1,16 @@
 """Main file of the data explorer interface"""
 import logging
 
+import dask
 import streamlit as st
 from data import load_dataframe
 from table import get_image_fields, get_numeric_fields
 from widgets import (build_explorer_table, build_image_explorer,
                      build_numeric_analysis_plots,
                      build_numeric_analysis_table, build_sidebar)
 
+dask.config.set({"dataframe.convert-string": False})
+
 LOGGER = logging.getLogger(__name__)
 # streamlit wide
 st.set_page_config(layout="wide")
@@ -31,7 +34,6 @@
         # extract image and numeric columns
         image_fields = get_image_fields(fields)
         numeric_fields = get_numeric_fields(fields)
-
         # build tabs
         tab_explorer, tab_numeric, tab_images = st.tabs(
             ["Data explorer", "Numerical analysis", "Image explorer"]

data_explorer/app/table.py

@@ -45,7 +45,7 @@ def get_image_fields(fields: Dict[str, str]) -> List[str]:
     # check which of the columns contain byte data
     image_fields = []
     for k, v in fields.items():
-        if v == "object":
+        if v == "binary":
             image_fields.append(k)
     return image_fields
 

data_explorer/app/widgets.py

@@ -78,7 +78,7 @@ def build_sidebar() -> Tuple[Optional[str], Optional[str], Optional[Dict]]:
 
 
 def build_explorer_table(
-    dataframe: Union[dd.DataFrame, pd.DataFrame], image_fields: List[str]
+        dataframe: Union[dd.DataFrame, pd.DataFrame], image_fields: List[str]
 ) -> None:
     """Build the dataframe explorer table.
 
@@ -129,7 +129,7 @@ def build_explorer_table(
 
 
 def build_numeric_analysis_table(
-    dataframe: Union[dd.DataFrame, pd.DataFrame], numeric_fields: List[str]
+        dataframe: Union[dd.DataFrame, pd.DataFrame], numeric_fields: List[str]
 ) -> None:
     """Build the numeric analysis table.
 
@@ -138,7 +138,9 @@ def build_numeric_analysis_table(
         numeric_fields (List[str]): list of numeric fields
     """
     # check if there are numeric fields
-    if len(numeric_fields) > 0:
+    if len(numeric_fields) == 0:
+        st.warning("There are no numeric fields in this subset")
+    else:
         st.write("## Numerical statistics")
 
         # make numeric statistics table
@@ -159,25 +161,29 @@ def build_numeric_analysis_table(
 
 
 def build_numeric_analysis_plots(
-    dataframe: Union[dd.DataFrame, pd.DataFrame], numeric_fields: List[str]
+        dataframe: Union[dd.DataFrame, pd.DataFrame], numeric_fields: List[str]
 ) -> None:
     """Build the numeric analysis plots.
 
     Args:
         dataframe (Union[dd.DataFrame, pd.DataFrame]): dataframe to explore
         numeric_fields (List[str]): list of numeric fields
     """
-    st.write("## Show numeric distributions")
+    # check if there are numeric fields
+    if len(numeric_fields) == 0:
+        st.warning("There are no numeric fields in this subset")
+    else:
+        st.write("## Show numeric distributions")
 
-    # choose a numeric field in dropdown
-    cols = st.columns(2)
-    with cols[0]:
-        numeric_field = st.selectbox("Field", numeric_fields)
-    with cols[1]:
-        plot_type = st.selectbox("Plot type",
-                                 ["histogram", "violin", "density", "categorical"])
+        # choose a numeric field in dropdown
+        cols = st.columns(2)
+        with cols[0]:
+            numeric_field = st.selectbox("Field", numeric_fields)
+        with cols[1]:
+            plot_type = st.selectbox("Plot type",
+                                     ["histogram", "violin", "density", "categorical"])
 
-    make_numeric_plot(dataframe, numeric_field, plot_type)
+        make_numeric_plot(dataframe, numeric_field, plot_type)
 
 
 def build_image_explorer(dataframe: dd.DataFrame, image_fields: List[str]):
@@ -188,12 +194,13 @@ def build_image_explorer(dataframe: dd.DataFrame, image_fields: List[str]):
         dataframe (dd.DataFrame): dataframe to explore
         image_fields (List[str]): list of image fields
     """
-    st.write("## Image explorer")
-    st.write("In this table, you can explore the images")
 
     if len(image_fields) == 0:
         st.warning("There are no image fields in this subset")
     else:
+        st.write("## Image explorer")
+        st.write("In this table, you can explore the images")
+
         image_field = st.selectbox("Image field", image_fields)
 
         images = dataframe[image_field].compute()