add dataset sizes to treemap and description

app.py

@@ -1,21 +1,16 @@
 from collections import Counter
+import pandas as pd
 import streamlit as st
 import json
-from itertools import islice
-from typing import Generator
 from plotly import express as px
 from safetensors import safe_open
 from semantic_search import predict
 from sentence_transformers import SentenceTransformer
 import os
+import plotly.graph_objects as go
 
 HF_TOKEN = os.environ.get("HF_TOKEN")
 
-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,
@@ -28,27 +23,72 @@ def get_tree_map_data(
     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]))
+            group_name_with_count = (
+                group
+                + "<br>"
+                + "Anzahl Datensätze:"
+                + " "
+                + str(countings_parents[group])
+            )
+            names.append(group_name_with_count)
         else:
             values.append("0")
+            group_name_with_count = group + "<br>" + "Anzahl Datensätze:" + " " + "0"
+            names.append(group_name_with_count)
         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:
+                label_name_with_count = (
+                    label
+                    + "<br>"
+                    + "<br>"
+                    + "Anzahl Datensätze:"
+                    + "<br>"
+                    + ""
+                    + str(countings_labels[label])
+                )
+                names.append(label_name_with_count)
+                parents.append(group_name_with_count)
                 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)
+            if label not in countings_labels:
+                if "<br>" in label:
+                    if (
+                        label.split("<br>")[0].strip() + label.split("<br>")[-1]
+                        in countings_labels
+                    ):
+                        label_name_with_count = (
+                            label
+                            + "<br>"
+                            + "<br>"
+                            + "Anzahl Datensätze:"
+                            + "<br>"
+                            + ""
+                            + str(
+                                countings_labels[
+                                    label.split("<br>")[0].strip()
+                                    + label.split("<br>")[-1]
+                                ]
+                            )
+                        )
+                else:
+                    print(label)
+                    label_name_with_count = (
+                        label
+                        + "<br>"
+                        + "<br>"
+                        + "Anzahl Datensätze:"
+                        + "<br>"
+                        + ""
+                        + "0"
+                    )
+                    names.append(label_name_with_count)
+                    parents.append(group_name_with_count)
+                    values.append("0")
     return parents, names, values
 
 
@@ -76,24 +116,28 @@ for el in taxonomy:
     else:
         taxonomy_group_label_mapper[el["group"]].append("Sonstiges ")
 
-parents, name, values = get_tree_map_data(
+del taxonomy_group_label_mapper["Sonstiges"]
+
+parents, names, values = get_tree_map_data(
     data=taxonomy_group_label_mapper,
     countings_parents=theme_counts,
     countings_labels=labels_counts,
     root="Musterdatenkatalog",
 )
 
-fig = px.treemap(
-    names=name,
-    parents=parents,
-)
+df = pd.DataFrame(data={"thema": parents, "bezeichnung": names, "value": values})
+df["value"] = df["value"].astype(str)
+df["bezeichnung"] = df["bezeichnung"]
 
-fig.update_layout(
-    margin=dict(t=50, l=25, r=25, b=25),
-    height=1000,
-    width=1000,
-    template="plotly",
+fig = go.Figure(
+    go.Treemap(
+        labels=df["bezeichnung"],
+        parents=df["thema"],
+        textinfo="label",
+    )
 )
+fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
+fig.update_layout(height=1000, width=1000, template="plotly")
 
 
 tensors = {}
@@ -112,6 +156,29 @@ st.set_page_config(layout="wide")
 
 st.title("Musterdatenkatalog")
 
+st.markdown(
+    """
+<style>
+.font {
+    font-size:20px !important;
+}
+</style>
+""",
+    unsafe_allow_html=True,
+)
+
+st.markdown(
+    '<p class="font">This demo showcases the algorithm of Musterdatenkatalog (MDK) of the Bertelsmann Stiftung. The MDK is a taxonomy of Open Data in municipalities in Germany. It is intended to help municipalities in Germany, as well as data analysts and journalists, to get an overview of the topics and the extent to which cities have already published data sets.</p>',
+    unsafe_allow_html=True,
+)
+
+
+st.markdown(
+    '<p class="font"> For more details checkout the <a href=https://www.bertelsmann-stiftung.de/de/unsere-projekte/smart-country/musterdatenkatalog> Musterdatenkatalog.</p>',
+    unsafe_allow_html=True,
+)
+
+
 col1, col2, col3 = st.columns(3)
 col1.metric("Datensätze", len(data))
 col2.metric("Themen", len(theme_counts))
@@ -123,23 +190,6 @@ st.plotly_chart(fig)
 
 st.title("Predict a Dataset")
 
-# create two columns and make left column wider
-
-# st.markdown(
-#     """
-# <style>
-#     div[data-testid="stVerticalBlock"] div[style*="flex-direction: column;"] div[data-testid="stVerticalBlock"] {
-#         border-radius: 15px;
-#         background-color: white;
-#         box-shadow: 0 0 10px #eee;
-#         border: 1px solid #ddd;
-#         padding: 1rem;;
-#     }
-# </style>
-# """,
-#     unsafe_allow_html=True,
-# )
-
 st.markdown(
     """
 <style>
@@ -170,7 +220,7 @@ col1, col2 = st.columns([1.2, 1])
 
 
 with col2:
-    st.subheader("Example Datasets")
+    st.subheader("Example Input Dataset Names")
     examples = [
         "Spielplätze",
         "Berliner Weihnachtsmärkte 2022",

pyproject.toml

@@ -0,0 +1,25 @@
+[tool.poetry]
+name = "musterdatenkatalog-space-app"
+version = "0.1.0"
+description = ""
+authors = ["Rahkakavee Baskaran <rahkakavee.baskaran@cause-effect.io>"]
+readme = "README.md"
+packages = [{include = "musterdatenkatalog_space_app"}]
+
+[tool.poetry.dependencies]
+python = "^3.11"
+streamlit = "^1.22.0"
+plotly-express = "^0.4.1"
+plotly = "^5.14.1"
+httpx = "^0.24.0"
+sentence-transformers = "^2.2.2"
+safetensors = "^0.3.1"
+
+
+[tool.poetry.group.dev.dependencies]
+black = "^23.3.0"
+mypy = "^1.3.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"