app.py

import streamlit as st
from PIL import Image
import os
import pandas as pd
import tomli


pd.options.mode.chained_assignment = None


st.set_page_config(layout="wide")


st.markdown(
    "<div style='background-color: lightblue; text-align: center; padding: 10px;'><h1 style='font-size: 70px;'>Our History in Data</h1></div>",
    unsafe_allow_html=True,
)


@st.cache_data
def load_data():
    df_ind = pd.read_csv("data/df_individuals_score.csv", index_col=[0])
    df_ind["productive_year"] = df_ind["productive_year"].astype(int)
    df_ind["individual_wikidata_id"] = "https://www.wikidata.org/wiki/" + df_ind[
        "individual_wikidata_id"
    ].astype(str)

    df_ind = df_ind[df_ind["productive_year"] <= 1800]
    return df_ind


df_ind = load_data()


def load_region_descriptions():
    with open("regions.toml", "rb") as toml_file:
        data = tomli.load(toml_file)
    return data


# Function to get description based on selected region
def get_region_description(region_data, selected_region):
    return region_data[selected_region]["description"]


region_data = load_region_descriptions()


# page = st.sidebar.selectbox("Navigate to:", ["Home", "Methodology", "Team"])
page = st.sidebar.radio(
    "Menu",
    ["Home", "Methodology", "Team", "About"],
    key="navigation_radio",
)


st.sidebar.success(
    "This project is led by Charles de Dampierre, Folgert Karsdorp, Mike Kestemont, Valentin Thouzeau and Nicolas Baumard"
)


# Test change
if page == "Home":

    # Set the global index path
    global_index_path = "data/immaterial_index/figures_trends_R/results"
    global_index_path_per_capita = (
        "data/immaterial_index/figures_trends_R/results_capita"
    )
    unseen_index_path = "data/immaterial_index/figures_trends_R/results_unseen"
    unseen_capita_index_path = (
        "data/immaterial_index/figures_trends_R/results_unseen_capita"
    )

    complexity_index_path = "data/immaterial_index/figures_trends_R/results_complexity"
    occupations_index_path = (
        "data/immaterial_index/figures_trends_R/results_occupations"
    )
    population_path = "data/population"
    gdp_per_capita_path = "data/gdp_per_capita"
    maps_path = "data/map_figures"

    from region_list import region_list

    region_filtered = list(region_list.keys())

    index_paths = {}

    for region_key in region_list:
        # Create the index paths for the current region
        index_paths[region_key] = {
            "map": f"{maps_path}/map_{region_key}.png",
            "global_index": f"{global_index_path}/{region_key}.png",
            "global_index_per_capita": f"{global_index_path_per_capita}/{region_key}.png",
            "unseen_index": f"{unseen_index_path}/{region_key}.png",
            "unseen_index_capita": f"{unseen_capita_index_path}/{region_key}.png",
            "complexity_index": f"{complexity_index_path}/{region_key}.png",
            "occupations_index": f"{occupations_index_path}/{region_key}.png",
            "gdp_per_capita_index": f"{gdp_per_capita_path}/{region_key}.png",
            "population_index": f"{population_path}/{region_key}.png",
        }

    # Get the region names (keys) from the index_paths dictionary
    regions = list(index_paths.keys())

    # Allow the user to select a region
    selected_region = st.sidebar.selectbox(
        "Region:", regions, index=regions.index("Japan")
    )

    # Display the selected region's images vertically
    if selected_region in index_paths:
        st.markdown(
            f"<h1 style='text-align: left; font-size: 50px;'>{selected_region}</h1>",
            unsafe_allow_html=True,
        )

        try:
            st.image(
                f"image/{selected_region}.jpeg",
                caption="Japan",
                use_column_width=False,
                width=1000,
            )
        except:
            pass

        col1, col2, col3 = st.columns([8, 1, 8])

        # Display the data in the left column
        with col1:
            for key, path in index_paths[selected_region].items():
                if os.path.exists(path):

                    if key == "global_index":
                        st.subheader("Cultural Index")
                        st.image(
                            Image.open(path),
                            caption=key.capitalize(),
                            use_column_width=True,
                        )
                    elif key == "global_index_per_capita":
                        st.subheader("Cultural Index per capita")
                        st.image(
                            Image.open(path),
                            caption=key.capitalize(),
                            use_column_width=True,
                        )
                    elif key == "unseen_index":
                        st.subheader(
                            "Cultural Index corrected by the unseen-species model"
                        )
                        st.image(
                            Image.open(path),
                            caption=key.capitalize(),
                            use_column_width=True,
                        )
                    elif key == "unseen_index_capita":
                        st.subheader(
                            "Cultural Index per capita corrected by the unseen-species model"
                        )
                        st.image(
                            Image.open(path),
                            caption=key.capitalize(),
                            use_column_width=True,
                        )

                    # elif key == "complexity_index":
                    #     st.subheader("Complexity Index")
                    #     st.image(
                    #         Image.open(path),
                    #         caption=key.capitalize(),
                    #         use_column_width=True,
                    #     )

                    elif key == "occupations_index":
                        st.subheader("Occupation Index")
                        st.image(
                            Image.open(path),
                            caption=key.capitalize(),
                            use_column_width=True,
                        )

                    elif key == "gdp_per_capita_index":
                        st.subheader("GDP per capita")
                        st.image(
                            Image.open(path),
                            caption=key.capitalize(),
                            use_column_width=True,
                        )

                else:
                    st.write(f"File for {key.capitalize()} does not exist.")

            with col3:
                try:
                    st.image(
                        Image.open(f"data/map_figures/map_{selected_region}.png"),
                        use_column_width=True,
                        width=1000,
                    )
                except:
                    pass

                st.subheader("Analysis")
                try:
                    region_description = get_region_description(
                        region_data, selected_region
                    )
                    st.write(f"{region_description}")
                except:
                    st.write("Analysis not ready yet")

                st.subheader("Cultural Producers in Wikidata")
                df = df_ind[df_ind["region_name"] == selected_region]
                df = df.drop(["region_name", "decade"], axis=1)
                df = df[
                    [
                        "individual_name",
                        "productive_year",
                        "score",
                        "individual_wikidata_id" "",
                    ]
                ]
                df = df.sort_values("score", ascending=False)
                df = df.rename(columns={"score": "Number of Catalogs"})

                min_date = region_list[selected_region]["time_range"][0]
                max_date = region_list[selected_region]["time_range"][1]
                df = df[df["productive_year"] >= min_date]
                df = df[df["productive_year"] <= max_date]
                # df["productive_year"] = df["productive_year"] * 1000
                df["productive_year"] = round(df["productive_year"], 0).astype(str)

                # df["productive_year"] = round(df["productive_year"], 0).astype(int)
                df = df.reset_index(drop=True)
                st.dataframe(df)
                st.write(f"Number of Cultural producers active before 1800: {len(df)}")

                try:
                    st.subheader("Population")
                    st.image(
                        Image.open(path),
                        caption=key.capitalize(),
                        use_column_width=True,
                    )
                except:
                    pass


elif page == "Methodology":

    # Read the content of the file methodolog.md
    with open("docs/methodology.md", "r") as file:
        methodology_content = file.read()

    # Display the content in the Streamlit app
    st.write(methodology_content)