app.py

from collections import Counter
import streamlit as st
import json
from itertools import islice
from typing import Generator
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import httpx
from plotly import express as px


def chunks(data: dict, size=13) -> Generator:
    it = iter(data)
    for i in range(0, len(data), size):
        yield {k: data[k] for k in islice(it, size)}


def get_tree_map_data(
    data: dict,
    countings_parents: dict,
    countings_labels: dict,
    root: str = " ",
) -> tuple:
    names: list = [""]
    parents: list = [root]
    values: list = ["0"]

    for group, labels in data.items():
        names.append(group)
        parents.append(root)
        if group in countings_parents:
            values.append(str(countings_parents[group]))
        else:
            values.append("0")
        for label in labels:
            if "-" in label:
                label = label.split("-")
                label = label[0] + "<br> -" + label[1]
            names.append(label)
            parents.append(group)
            if label in countings_labels:
                values.append(str(countings_labels[label]))
            else:
                values.append("0")
            # if "-" in label:
            #     names.append(label.split("-")[0])
            #     parents.append(label)
            #     names.append(label.split("-")[1])
            #     parents.append(label)
    return parents, names, values


# Load Data
with open("taxonomy_processed_v3.json", "r") as fp:
    taxonomy = json.load(fp)

re = httpx.get(
    "https://www.bertelsmann-stiftung.de/fileadmin/files/musterdatenkatalog/Musterdatenkatalog_4.0_042023.json"
)

data = re.json()

theme_counts = dict(Counter([el["THEMA"] for el in data]))
labels_counts = dict(Counter([el["BEZEICHNUNG"] for el in data]))


taxonomy = taxonomy

names = [""]
parents = ["Musterdatenkatalog"]

taxonomy_group_label_mapper: dict = {el["group"]: [] for el in taxonomy}

for el in taxonomy:
    if el["group"] != "Sonstiges":
        taxonomy_group_label_mapper[el["group"]].append(el["label"])
    else:
        taxonomy_group_label_mapper[el["group"]].append("Sonstiges ")

parents, name, values = get_tree_map_data(
    data=taxonomy_group_label_mapper,
    countings_parents=theme_counts,
    countings_labels=labels_counts,
    root="Musterdatenkatalog",
)


# fig = go.Figure(
#     go.Treemap(
#         labels=name,
#         parents=parents,
#         root_color="white",
#         values=values,
#         # textinfo="label+value",
#     ),
# )

fig = px.treemap(
    names=name,
    parents=parents,
)

fig.update_layout(
    margin=dict(t=50, l=25, r=25, b=25),
    height=1000,
    width=1000,
    template="plotly",
)


st.title("    Musterdatenkatalog")

st.plotly_chart(fig)