pages/1_Language_Statistics.py

import streamlit as st
import pandas as pd
from filter_dataframe import filter_dataframe


@st.cache_data
def get_language_stats_df():
    return pd.read_parquet("data/language_stats.parquet")



st.set_page_config(page_title="Language Statistics", page_icon="📈")

st.markdown("# Language Statistics")
st.write("""\
The table below shows the per-language statistics of the MMS corpus.  
You can use the **'Add filters'** checkbox to filter the table by any of the columns.  

Column descriptions:
- **Language**: Language name,
- **Datasets**: Number of datasets in the MMS corpus for the given language,
- **News**: Number of datasets from news domain,
- **Reviews**: Number of datasets from reviews domain,
- **Social media**: Number of datasets from social media domain,
- **Other**: Number of datasets from other domains,
- **Negative**: Number of examples with negative sentiment,
- **Neutral**: Number of examples with neutral sentiment,
- **Positive**: Number of examples with positive sentiment,
- **Words**: The average number of words in a single example,
- **Characters**: The average number of characters in a single example,""")

df = get_language_stats_df()

st.dataframe(filter_dataframe(df, numeric_as_categorical=False))