peter2000's picture
Update apps/sdg_pd.py
afa2c48
import plotly.express as px
import streamlit as st
from sentence_transformers import SentenceTransformer
import umap.umap_ as umap
import pandas as pd
import os
def app():
st.title("SDG Embedding Visualisation")
with st.expander("ℹ️ - About this app", expanded=True):
st.write(
"""
Information cartography - Get your word/phrase/sentence/paragraph embedded and visualized.
The (English) sentence-transformers model "all-MiniLM-L6-v2" maps sentences & paragraphs to a 384 dimensional dense vector space This is normally used for tasks like clustering or semantic search, but in this case, we use it to place your text to a 3D map. Before plotting, the dimension needs to be reduced to three so we can actually plot it, but preserve as much information as possible. For this, we use a technology called umap.
On this page, you find thousands of text excerpts that were labelled by the community volunteers with respect to Sustainable Development Goals, a project by OSDG.ai, embedded as described. Ready to explore.
""")
with st.spinner("πŸ‘‘ load data"):
df_osdg = pd.read_csv("sdg_umap.csv", sep = "|")
#labels = [_lab_dict[lab] for lab in df_osdg['label'] ]
keys = list(df_osdg['keys'])
#docs = list(df_osdg['text'])
agree = st.checkbox('add labels')
if agree:
with st.spinner("πŸ‘‘ create visualisation"):
fig = px.scatter_3d(
df_osdg, x='coord_x', y='coord_y', z='coord_z',
color='labels',
opacity = .5, hover_data=[keys])
fig.update_scenes(xaxis_visible=False, yaxis_visible=False,zaxis_visible=False )
fig.update_traces(marker_size=4)
st.plotly_chart(fig)
else:
with st.spinner("πŸ‘‘ create visualisation"):
fig = px.scatter_3d(
df_osdg, x='coord_x', y='coord_y', z='coord_z',
opacity = .5, hover_data=[keys])
fig.update_scenes(xaxis_visible=False, yaxis_visible=False,zaxis_visible=False )
fig.update_traces(marker_size=4)
st.plotly_chart(fig)