def expander_general_stats()

in utils/gradio_utils.py [0:0]

• 31 lines of code
• 2 McCabe index (conditional complexity)

def expander_general_stats(dstats, column_id=""):
    with gr.Accordion(f"General Text Statistics{column_id}"):
        st.caption(
            "Use this widget to check whether the terms you see most "
            "represented in the dataset make sense for the goals of the dataset."
        )
        st.markdown("There are {0} total words".format(str(dstats.total_words)))
        st.markdown(
            "There are {0} words after removing closed "
            "class words".format(str(dstats.total_open_words))
        )
        st.markdown(
            "The most common "
            "[open class words](https://dictionary.apa.org/open-class-words) "
            "and their counts are: "
        )
        st.dataframe(dstats.sorted_top_vocab_df)
        st.markdown(
            "There are {0} missing values in the dataset.".format(
                str(dstats.text_nan_count)
            )
        )
        if dstats.dups_frac > 0:
            st.markdown(
                "The dataset is {0}% duplicates. "
                "For more information about the duplicates, "
                "click the 'Duplicates' tab below.".format(
                    str(round(dstats.dups_frac * 100, 2)))
            )
        else:
            st.markdown("There are 0 duplicate items in the dataset. ")