File size: 3,734 Bytes
80556c2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
import streamlit as st
import pandas as pd
import numpy as np
import plotly.express as px
from wordcloud import WordCloud, STOPWORDS
import matplotlib.pyplot as plt
st.set_option('deprecation.showPyplotGlobalUse', False)
DATA_ = pd.read_csv("Tweets.csv")
st.title("Sentiment Analysis of Tweets about US Airlines")
st.sidebar.title("Sentiment Analysis of Tweets about US Airlines")
st.markdown("This application is a streamlit dashboard to analyze the sentiment of Tweets")
st.sidebar.markdown("This application is a streamlit dashboard to analyze the sentiment of Tweets")
def run():
@st.cache(persist=True)
def load_data():
DATA_['tweet_created'] = pd.to_datetime(DATA_['tweet_created'])
return DATA_
data = load_data()
st.sidebar.subheader("Show random tweet")
random_tweet = st.sidebar.radio('Sentiment', ('positive', 'neutral', 'negative'))
st.sidebar.markdown(data.query('airline_sentiment == @random_tweet')[["text"]].sample(n=1).iat[0,0])
st.sidebar.markdown("### Number of tweets by sentiment")
select = st.sidebar.selectbox('Visualization type', ['Histogram', 'Pie chart'])
sentiment_count = data['airline_sentiment'].value_counts()
sentiment_count = pd.DataFrame({'Sentiment':sentiment_count.index, 'Tweets':sentiment_count.values})
if not st.sidebar.checkbox("Hide", True):
st.markdown("### Number of tweets by sentiment")
if select == "Histogram":
fig = px.bar(sentiment_count, x='Sentiment', y='Tweets', color='Tweets', height=500)
st.plotly_chart(fig)
else:
fig = px.pie(sentiment_count, values='Tweets', names='Sentiment')
st.plotly_chart(fig)
st.sidebar.subheader("When and Where are users tweeting from?")
hour = st.sidebar.slider("Hour of day", 0,23)
modified_data = data[data['tweet_created'].dt.hour == hour]
if not st.sidebar.checkbox("Close", True, key='1'):
st.markdown("### Tweets locations based on the time of date")
st.markdown("%i tweets between %i:00 and %i:00" % (len(modified_data), hour, (hour+1)%24))
st.map(modified_data)
if st.sidebar.checkbox("Show Raw Data", False):
st.write(modified_data)
st.sidebar.subheader("Breakdown airline tweets by sentiment")
choice = st.sidebar.multiselect('Pick airline', ('US Airways', 'United', 'American', 'Southwest', 'Delta', 'Virgin America'), key='0')
if len(choice) > 0:
choice_data = data[data.airline.isin(choice)]
fig_choice = px.histogram(choice_data, x='airline',
y='airline_sentiment',
histfunc = 'count', color = 'airline_sentiment',
facet_col='airline_sentiment',
labels={'airline_sentiment':'tweets'}, height=600, width=800)
st.plotly_chart(fig_choice)
st.sidebar.header("Word Cloud")
word_sentiment = st.sidebar.radio('Display word cloud for what sentiment?',('positive', 'neutral','negative'))
if not st.sidebar.checkbox("Close", True, key='3'):
st.header('Word cloud for %s sentiment' % (word_sentiment))
df = data[data['airline_sentiment']==word_sentiment]
words = ' '.join(df['text'])
processed_words = ' '.join([word for word in words.split() if 'http' not in word and not word.startswith('@') and word !='RT'])
wordcloud = WordCloud(stopwords=STOPWORDS,
background_color='white', height=640, width=800).generate(processed_words)
plt.imshow(wordcloud)
plt.xticks([])
plt.yticks([])
st.pyplot()
if __name__ == '__main__':
run()
|