from datasets import load_dataset
import streamlit as st
import pandas as pd
import re
import nltk
from wordcloud import WordCloud, STOPWORDS
from nltk.corpus import stopwords
nltk.download("stopwords")
stop = stopwords.words('english')

dataset = load_dataset("huggingartists/gorillaz")
df = pd.DataFrame.from_dict(dataset["train"])

st.dataframe(df)
st.write("Removed special characters")

def standardize(text, remove_digits=True):
    text=re.sub('[^a-zA-Z\d\s]', '',text)
    text = text.lower()

    return text

df.text = df.text.apply(lambda x: ' '.join([word for word in x.split() if word not in (stop)]))
df.text=df.text.apply(standardize)
st.dataframe(df)

words = df.text.str.split(expand=True).unstack().value_counts()
st.bar_chart(words[20:40])
st.set_option('deprecation.showPyplotGlobalUse', False)

import matplotlib.pyplot as plt
def word_cloud(content, title):
    wc = WordCloud(background_color='white', max_words=200,
                  stopwords=STOPWORDS, max_font_size=50)
    wc.generate(" ".join(content.index.values))
    fig = plt.figure(figsize=(16, 13))
    plt.title(title, fontsize=20)
    plt.imshow(wc.recolor(colormap='Pastel2', random_state=42), alpha=0.98)
    plt.axis('off')
    st.pyplot()

word_cloud(words, "Word Cloud")