import streamlit as st

from matplotlib import pyplot as plt
from wordcloud import WordCloud, STOPWORDS 
import numpy as np

from app import AnalysisData


df = AnalysisData.ds.to_pandas(batched=False)
disaster_types = df['disaster_type'].unique()

text_data = {
    disaster: ' '.join(df[df['disaster_type'] == disaster]['tweet_text'])
     for disaster in disaster_types
}

for disaster in disaster_types:
    st.subheader(disaster + ' ' + 'Word Cloud')
    wordcloud = WordCloud(width=800, height=400).generate(text_data[disaster])
    fig, ax = plt.subplots(figsize=(10, 5))
    ax.imshow(wordcloud, interpolation='bilinear')
    ax.axis('off')

    st.pyplot(fig)


# DataSet links
st.subheader("DataSet links")
st.markdown("- [Humaid Dataset](https://crisisnlp.qcri.org/humaid_dataset?fbclid=IwAR2rpSdcVhcXvQagxAG5VA2dvwAUOJOCVwTKxqtDiz7soIhVMUtp_N0BfSo)")