def show_num_bins(slider_value):
""" Display the number of bins. """
df = get_tweet_data()
total_tweets = len(df)
return "Total number of tweets streamed during last 3 hours: " + str(
int(total_tweets))
def update_graph_bar(interval):
# query tweets from the database
df = get_tweet_data()
print(df)
# get the counter for all the tokens
word_counter = bag_of_words(df.text)
# get the most common n tokens
# n is specified by the slider
top_n = word_counter.most_common(10)[::-1]
# get the x and y values
X = [cnt for word, cnt in top_n]
Y = [word for word, cnt in top_n]
# plot the bar chart
bar_chart = go.Bar(
x=X, y=Y,
name='Word Counts',
orientation='h',
marker=dict(color=chart_colors[::-1])
)
# specify the layout
layout = go.Layout(
xaxis={
'type': 'log',
'autorange': True,
'title': 'Number of Words'
},
height=300,
plot_bgcolor=app_color["graph_bg"],
paper_bgcolor=app_color["graph_bg"],
font={"color": app_color["graph_font"]},
autosize=True,
margin=go.layout.Margin(
l=100,
r=25,
b=75,
t=25,
pad=4
),
)
return go.Figure(
data=[bar_chart], layout=layout
)
def update_graph_sentiment(interval):
# query tweets from the database
df = get_tweet_data()
# get the number of tweets for each keyword
cnt = bag_of_words(df['text'])
# get top-N words
top_N = cnt.most_common(num_tags_scatter)
top_N_words = [keyword for keyword, cnt in top_N]
# preprocess the text column
df['text'] = df.text.apply(preprocess_nltk)
sentiments = {keyword: [] for keyword in top_N_words}
for row in df['text']:
# print(row)
for keyword in top_N_words:
# print(keyword)
if keyword.lower() in row.lower():
# print(sid.polarity_scores(row)['compound'])
sentiments[keyword].append(
sid.polarity_scores(row)['compound'])
# print(sentiments)
avg_sentiments = {}
for keyword, score_list in sentiments.items():
avg_sentiments[keyword] = [np.mean(score_list), np.std(score_list)]
# get the current time for x-axis
time = datetime.datetime.now().strftime('%D, %H:%M:%S')
X_universal.append(time)
to_pop = []
for keyword, score_queue in sentiment_dict.items():
if score_queue:
while score_queue and (score_queue[0][1] <= X_universal[0]):
score_queue.popleft()
else:
to_pop.append(keyword)
for keyword in to_pop:
sentiment_dict.pop(keyword)
for keyword, score in avg_sentiments.items():
if keyword not in sentiment_dict:
sentiment_dict[keyword] = deque(maxlen=30)
sentiment_dict[keyword].append([score, time])
else:
sentiment_dict[keyword].append([score, time])
new_colors = chart_colors[:len(sentiment_dict)]
# plot the scatter plot
data = [
go.Scatter(x=[time for score, time in score_queue],
y=[score[0] for score, time in score_queue],
error_y={
"type": "data",
"array": [score[1] / 30 for score, time in score_queue],
"thickness": 1.5,
"width": 1,
"color": "#000",
},
name=keyword,
mode='markers',
opacity=0.7,
marker=dict(color=color))
for color, (
keyword,
score_queue) in list(zip(new_colors, sentiment_dict.items()))
]
# specify the layout
layout = go.Layout(
xaxis={
'automargin': False,
'range': [min(X_universal), max(X_universal)],
'title': 'Current Time (GMT)',
'nticks': 2,
},
yaxis={
'autorange': True,
'title': 'Sentiment Score'
},
height=400,
plot_bgcolor=app_color["graph_bg"],
paper_bgcolor=app_color["graph_bg"],
font={"color": app_color["graph_font"]},
autosize=False,
legend={
'orientation': 'v',
# 'xanchor': 'right',
# 'yanchor': 'middle',
# 'x': 0.5,
# 'y': 1.025
},
margin=go.layout.Margin(l=75, r=25, b=70, t=25, pad=4),
)
return go.Figure(
data=data,
layout=layout,
)
def update_graph_scatter(n):
# query tweets from the database
df = get_tweet_data()
# get the number of tweets for each keyword
cnt = bag_of_words(df['text'])
# get the current time for x-axis
time = datetime.datetime.now().strftime('%D, %H:%M:%S')
X_universal.append(time)
to_pop = []
for keyword, cnt_queue in scatter_dict.items():
if cnt_queue:
while cnt_queue and (cnt_queue[0][1] < X_universal[0]):
cnt_queue.popleft()
else:
to_pop.append(keyword)
for keyword in to_pop:
scatter_dict.pop(keyword)
top_N = cnt.most_common(num_tags_scatter)
for keyword, cnt in top_N:
if keyword not in scatter_dict:
scatter_dict[keyword] = deque(maxlen=30)
scatter_dict[keyword].append([cnt, time])
else:
scatter_dict[keyword].append([cnt, time])
new_colors = chart_colors[:len(scatter_dict)]
# plot the scatter plot
data = [
go.Scatter(
x=[time for cnt, time in cnt_queue],
y=[cnt for cnt, time in cnt_queue],
name=keyword,
mode='lines+markers',
opacity=0.5,
marker=dict(
size=10,
color=color,
),
line=dict(
width=6,
# dash='dash',
color=color,
))
for color, (keyword,
cnt_queue) in list(zip(new_colors, scatter_dict.items()))
]
# specify the layout
layout = go.Layout(
xaxis={
'automargin': False,
'range': [min(X_universal), max(X_universal)],
'title': 'Current Time (GMT)',
'nticks': 6
},
yaxis={
'type': 'log',
'autorange': True,
'title': 'Number of Tweets'
},
height=700,
plot_bgcolor=app_color["graph_bg"],
paper_bgcolor=app_color["graph_bg"],
font={"color": app_color["graph_font"]},
autosize=False,
legend={
'orientation': 'h',
'xanchor': 'center',
'yanchor': 'top',
'x': 0.5,
'y': 1.025
},
margin=go.layout.Margin(l=75, r=25, b=45, t=25, pad=4),
)
return go.Figure(
data=data,
layout=layout,
)
'#00BDFF', '#A5E82C', '#FFBD42', '#FFCA30'
]
# the number of most frequently mentioned tags
num_tags_scatter = 5
# initalize a dictionary to store the number of tweets for each game
scatter_dict = {}
sentiment_dict = {}
# initialize x and y coordinates for scatter plot
# use duque here to store the changing trend of number of tweets
# X is the x-axis with time stamps
X_universal = deque(maxlen=30)
df = get_tweet_data()
# add layout to the app
app.layout = html.Div(
[
# header
html.Div(
[
html.Div(
[
html.A(html.H4(
"Mosquito-borne disease TWITTER STREAMING", ),
href='https://geu.ac.in',
target='_blank',
className="app__header__title"),
html.P(