utils/filterable_dataframe.py

import streamlit as st
import re



def filterable_dataframe(df):
    # 多選框選擇需要篩選的列
    selected_columns = st.multiselect('Select columns to filter', options=df.columns)

    filters = {}

    # 動態生成篩選條件
    for column in selected_columns:
        with st.expander(f'Filter by {column}', expanded=True):
            if df[column].dtype == 'object':
                unique_values = df[column].unique()
                multiselect_value = st.multiselect(f'Select values for {column}', options=list(unique_values))
                re_pattern = st.text_input(f'Search re pattern {column}')
                
                final_selected_values = []
                if multiselect_value:
                    final_selected_values.extend(multiselect_value)


                if re_pattern:
                    re_pattern = re.compile(re_pattern)
                    match_value = [value for value in unique_values if re_pattern.search(value)]
                    if match_value:
                        final_selected_values.extend(match_value)
                        # st.write('Match value:', match_value)
                    else:
                        st.write('No match value')
                        final_selected_values.append('')

                if final_selected_values:
                    filters[column] = final_selected_values

            else:
                min_value, max_value = df[column].min(), df[column].max()
                selected_range = st.slider(f'Select range for {column}', min_value, max_value, (min_value, max_value))
                if selected_range != (min_value, max_value):
                    filters[column] = selected_range

    # 根據篩選條件過濾數據框
    filtered_df = df
    for column, value in filters.items():
        if isinstance(value, list):
            filtered_df = filtered_df[filtered_df[column].isin(value)]
        elif isinstance(value, tuple):
            filtered_df = filtered_df[(filtered_df[column] >= value[0]) & (filtered_df[column] <= value[1])]

    return filtered_df