-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathapp.py
126 lines (108 loc) · 5.73 KB
/
app.py
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
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
import streamlit as st
import pandas as pd
import numpy as np
import plotly.express as px
from plotly.subplots import make_subplots
import plotly.graph_objects as go
import matplotlib.pyplot as plt
from wordcloud import WordCloud, STOPWORDS
st.title("Sentiment Analysis of Tweets about US Airlines ✈️")
st.sidebar.title("Sentiment Analysis of Tweets 🤖")
st.markdown("**This dashboard is used to analyze sentiments of tweets** 📊 ")
@st.cache(persist=True)
def load_data():
data = pd.read_csv('Tweets.csv')
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', ['Bar plot', 'Pie chart'], key='1')
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 == 'Bar plot':
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 to look at", 0, 23)
modified_data = data[data['tweet_created'].dt.hour == hour]
if not st.sidebar.checkbox("Close", True, key='1'):
st.markdown("### Tweet locations based on time of day")
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("Total number of tweets for each airline")
each_airline = st.sidebar.selectbox('Visualization type', ['Bar plot', 'Pie chart'], key='2')
airline_sentiment_count = data.groupby('airline')['airline_sentiment'].count().sort_values(ascending=False)
airline_sentiment_count = pd.DataFrame({'Airline':airline_sentiment_count.index, 'Tweets':airline_sentiment_count.values.flatten()})
if not st.sidebar.checkbox("Close", True, key='2'):
if each_airline == 'Bar plot':
st.subheader("Total number of tweets for each airline")
fig_1 = px.bar(airline_sentiment_count, x='Airline', y='Tweets', color='Tweets', height=500)
st.plotly_chart(fig_1)
if each_airline == 'Pie chart':
st.subheader("Total number of tweets for each airline")
fig_2 = px.pie(airline_sentiment_count, values='Tweets', names='Airline')
st.plotly_chart(fig_2)
@st.cache(persist=True)
def plot_sentiment(airline):
df = data[data['airline']==airline]
count = df['airline_sentiment'].value_counts()
count = pd.DataFrame({'Sentiment':count.index, 'Tweets':count.values.flatten()})
return count
st.sidebar.subheader("Breakdown airline by sentiment")
choice = st.sidebar.multiselect('Pick airlines', ('US Airways','United','American','Southwest','Delta','Virgin America'))
if len(choice) > 0:
st.subheader("Breakdown airline by sentiment")
breakdown_type = st.sidebar.selectbox('Visualization type', ['Pie chart', 'Bar plot', ], key='3')
fig_3 = make_subplots(rows=1, cols=len(choice), subplot_titles=choice)
if breakdown_type == 'Bar plot':
for i in range(1):
for j in range(len(choice)):
fig_3.add_trace(
go.Bar(x=plot_sentiment(choice[j]).Sentiment, y=plot_sentiment(choice[j]).Tweets, showlegend=False),
row=i+1, col=j+1
)
fig_3.update_layout(height=600, width=800)
st.plotly_chart(fig_3)
else:
fig_3 = make_subplots(rows=1, cols=len(choice), specs=[[{'type':'domain'}]*len(choice)], subplot_titles=choice)
for i in range(1):
for j in range(len(choice)):
fig_3.add_trace(
go.Pie(labels=plot_sentiment(choice[j]).Sentiment, values=plot_sentiment(choice[j]).Tweets, showlegend=True),
i+1, j+1
)
fig_3.update_layout(height=600, width=800)
st.plotly_chart(fig_3)
st.sidebar.subheader("Breakdown airline by sentiment")
choice = st.sidebar.multiselect('Pick airlines', ('US Airways','United','American','Southwest','Delta','Virgin America'), key=0)
if len(choice) > 0:
choice_data = data[data.airline.isin(choice)]
fig_0 = 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_0)
st.sidebar.header("Word Cloud")
word_sentiment = st.sidebar.radio('Display word cloud for what sentiment?', ('positive', 'neutral', 'negative'))
st.set_option('deprecation.showPyplotGlobalUse', False)
if not st.sidebar.checkbox("Close", True, key='3'):
st.subheader('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', width=800, height=640).generate(processed_words)
plt.imshow(wordcloud)
plt.xticks([])
plt.yticks([])
st.pyplot()