Py.Cafe
Interactive Word and Bigram Analysis Dashboard - Plotly & Dash
- app.py
- helper.py
- requirements.txt
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
# Figure Friday 2024 - week 43
# https://community.plotly.com/t/figure-friday-2024-week-43/88243
import dash
from dash import Dash, dcc, html, Input, Output, callback
import dash_bootstrap_components as dbc
from helper import *
# Download the file from github
df = pd.read_csv("https://raw.githubusercontent.com/plotly/Figure-Friday/refs/heads/main/2024/week-43/OpenRepair_Data_RepairCafeInt_202407.csv", low_memory=False)
df.dropna(subset='problem', inplace=True)
# Apply the function to each row
df['words'] = df['problem'].apply(lambda x: ' '.join(extract_ngrams(x)[0])) # -> string
df['bigrams'] = df['problem'].apply(lambda x: extract_ngrams(x)[1]) # -> list[tuple]
all_words = ' '.join(df['words'])
unique_words = len(set(all_words.split()))
wc_chart = create_word_cloud(all_words)
bar_top_20 = create_bar_top_20_words_and_bigrams(df[['words', 'bigrams']])
# Define dropdown for categories---------------------------------------------------
category_dropdown = dcc.Dropdown(
id="dropdown",
options= sorted(['All'] + df['product_category'].unique().tolist()) ,
value='Vacuum',
clearable=False,
searchable=True,
style={'background-color':'#F6F8FA', 'margin-top':'20px', 'margin-bottom':'20px'})
# Create app---------------------------------------------------------------
app = Dash(__name__, external_stylesheets=[dbc.themes.SPACELAB])
# Define the app layout----------------------------------------------------
app.layout = dbc.Container([
dbc.Row([
dbc.Col(html.H4('Select Category', style= {'color' :'#1F77B4'}),
width=2, class_name='text-center'),
dbc.Col(category_dropdown, width=4),
dbc.Col(html.H4(['Number of Unique Words = ',
html.Span(id='unique-words', children=f'{unique_words:,.0f}')], style= {'color' :'#1F77B4'}),
width=6, class_name='text-center',)
], style={'align-items': 'center', 'border': 'solid #2980B9 1px', 'background-color': 'powderblue'}
),
dbc.Row([
dbc.Col(dcc.Graph(id='word-cloud', figure=wc_chart, config={'staticPlot': True}),
width=6,
style={'border': 'solid lightgrey', 'padding-top':'15px', 'padding-bottom':'15px',
'border-width': '1px', 'background-color': '#F6F8FA', 'justify-items': 'center'} ),
dbc.Col(dcc.Graph(id='bar-chart', figure=bar_top_20, config={'displayModeBar': False}),
width=6,
style={'border': 'solid lightgrey', 'border-width': '1px',
'background-color': '#F6F8FA', 'justify-items': 'center'} ),
]),
],
fluid=False, # don't expand to full width
)
# Define the callback and update function
@app.callback(
Output('word-cloud', 'figure'),
Output('bar-chart', 'figure'),
Output('unique-words', 'children'),
Input('dropdown', 'value')
)
def update_word_cloud(category):
if category == 'All':
return wc_chart, bar_top_20 , f'{unique_words:,.0f}'
else:
filtered_df = df[df['product_category'] == category][['words', 'bigrams']]
category_text = ' '.join(filtered_df['words'])
num_unique_words = len(set(category_text.split()))
bar_top_20_updated = create_bar_top_20_words_and_bigrams(filtered_df)
if category == 'Vacuum':
wc_vacuum = create_word_cloud(category_text, mask=vacuum_mask)
return wc_vacuum , bar_top_20_updated, f'{num_unique_words:,.0f}'
else:
wc_updated = create_word_cloud(category_text)
return wc_updated , bar_top_20_updated, f'{num_unique_words:,.0f}'
if __name__ == "__main__":
app.run_server(debug=False) # debug=True --> auto-reload