modules/multimatch_result_table.py

import streamlit as st
import pandas as pd

"""
Result table of the Multi Project Matching
"""

def show_multi_table(p1_df, p2_df):
    """
    p1_df & p2_df from functions/multi_project_matching
    """

    st.write("------------------")

    p1_df = p1_df.reset_index(drop=True)
    p2_df = p2_df.reset_index(drop=True)
    # Convert orga_abbreviation to uppercase for the selected project
    p2_df['orga_abbreviation'] = p2_df['orga_abbreviation'].str.upper()
    p1_df['orga_abbreviation'] = p1_df['orga_abbreviation'].str.upper()

    actual_ind = 0

    # Loop to display every matching pair from p1 and p2 dfs
    for i in range(0, len(p1_df), 2): # stepsize 2 to not display duplicates
        actual_ind += 1
        match_df = pd.DataFrame()
        row_from_p1 = p1_df.iloc[[i]]
        row_from_p2 = p2_df.iloc[[i]]

        # INTEGRATE IN PREPROCESSING !!!
        # transform strings to list
        """
        Add this to preprocessing
        - flag url
        - crs code lists
        """

        try:
            row_from_p1["crs_3_code_list"] = [row_from_p1['crs_3_name'].item().split(";")[:-1]]
            row_from_p2["crs_3_code_list"] = [row_from_p2['crs_3_name'].item().split(";")[:-1]]
        except:
            row_from_p1["crs_3_code_list"] = [""]
            row_from_p2["crs_3_code_list"] = [""]

        try:
            row_from_p1["crs_5_code_list"] = [row_from_p1['crs_5_name'].item().split(";")[:-1]]
            row_from_p2["crs_5_code_list"] = [row_from_p2['crs_5_name'].item().split(";")[:-1]]
        except:
            row_from_p1["crs_5_code_list"] = [""]
            row_from_p2["crs_5_code_list"] = [""]

        row_from_p1["sdg_list"] = [row_from_p1['sgd_pred_code'].item()]
        row_from_p2["sdg_list"] = [row_from_p2['sgd_pred_code'].item()]

        # Check for missing country and set flag URL accordingly
        def get_flag_url(country):
            if pd.isna(country) or country.strip() == "":
                return ""
            return f"https://flagicons.lipis.dev/flags/4x3/{country[:2].lower()}.svg"

        row_from_p1["flag"] = get_flag_url(row_from_p1['country'].item())
        row_from_p2["flag"] = get_flag_url(row_from_p2['country'].item())

        # concat p1_df and p2_df rows 
        match_df = pd.concat([row_from_p1, row_from_p2], ignore_index=True)
        
        col1, col2 = st.columns([1, 12])

        # MATCHING INFOS
        with col1:
            
            # remove arrow from standard st.metric()
            st.write(
                """
                <style>
                [data-testid="stMetricDelta"] svg {
                    display: none;
                }
                </style>
                """,
                unsafe_allow_html=True,
            )

            st.metric(label="Match", value=f"{actual_ind}", delta=f"~ {str(round(row_from_p1['similarity'].item(), 5) * 100)[:4]} %")

        # MATCHING Project Informations as table
        with col2:
            st.write("    ")
            st.dataframe(
                match_df[["iati_id", "title_main", "orga_abbreviation", "description_main", "country_name", "flag", "sdg_list", "crs_3_code_list", "crs_5_code_list", "Project Link"]],
                use_container_width=True,
                height=35 + 35 * len(match_df),
                column_config={
                    "iati_id": st.column_config.TextColumn(
                        "IATI ID",
                        help="IATI Project ID",
                        disabled=True,
                        width="small"
                    ),
                    "orga_abbreviation": st.column_config.TextColumn(
                        "Organization",
                        help="If description not in English, description in other language provided",
                        disabled=True,
                        width="small"
                    ),
                    "title_main": st.column_config.TextColumn(
                        "Title",
                        help="If title not in English, title in other language provided",
                        disabled=True,
                        width="large"
                    ),
                    "description_main": st.column_config.TextColumn(
                        "Description",
                        help="If description not in English, description in other language provided",
                        disabled=True,
                        width="large"
                    ),
                    "country_name": st.column_config.TextColumn(
                        "Country",
                        help="Country of project",
                        disabled=True,
                        width="small"
                    ),
                    "flag": st.column_config.ImageColumn(
                        "Flag",
                        help="country flag",
                        width="small"
                    ),
                    "sdg_list": st.column_config.ListColumn(
                        "SDG Prediction",
                        help="Prediction of SDG's",
                        width="small"
                    ),
                    "crs_3_code_list": st.column_config.ListColumn(
                        "CRS 3",
                        help="CRS 3 code given by organization",
                        width="medium"
                    ),
                    "crs_5_code_list": st.column_config.ListColumn(
                        "CRS 5",
                        help="CRS 5 code given by organization",
                        width="medium"
                    ),
                    "Project Link": st.column_config.TextColumn(
                        "Project Link",
                        help="Link to the project",
                        disabled=True,
                        width="small"
                    ),                
                },
                hide_index=True,
            )

        st.write("------------------")