-
Notifications
You must be signed in to change notification settings - Fork 0
/
plotlyWidget.py
165 lines (150 loc) · 6.13 KB
/
plotlyWidget.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
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Aug 7 19:36:27 2019
@author: tefirman
"""
import dash
from dash import dcc
from dash import html
import pandas as pd
import plotly.graph_objs as go
external_stylesheets = ['https://codepen.io/chriddyp/pen/bWLwgP.css']
app = dash.Dash(__name__, external_stylesheets=external_stylesheets)
server = app.server
df = pd.read_csv('Presidential_Vocabs.csv')
for col in df.columns:
df[col] = df[col].fillna(0.0)
del col
byParty = df.groupby(['Party','Word']).Count.sum().reset_index()
totCount = df.groupby('Party').Count.sum().reset_index().rename(index=str,columns={'Count':'Total'})
byParty = pd.merge(left=byParty,right=totCount,how='inner',on='Party')
byParty['Frequency'] = byParty.Count/byParty.Total
del byParty['Total'], totCount
allPresidents = (df.groupby('Word').Count.sum()/df.Count.sum())\
.reset_index().rename(index=str,columns={'Count':'Frequency'})
allPresidents['Name'] = 'All Presidents'
#ngrams = df.groupby('Word').Probability.mean().fillna(0.0).reset_index().rename(index=str,columns={'Probability':'Frequency'})
#ngrams['Name'] = 'Google N-grams (2000)'
#allPresidents = allPresidents.append(ngrams,ignore_index=True)
#del ngrams
available_indicators = df['Word'].unique()
app.layout = html.Div([
html.Div([
html.Div([
dcc.Dropdown(
id='crossfilter-yaxis-column',
options=[{'label': i, 'value': i} for i in available_indicators],
value=['america','americans'],
multi=True
),
dcc.RadioItems(
id='crossfilter-xaxis-type',
options=[{'label': i, 'value': i} for i in ['By President','By Party','Overall']],
value='By President',
labelStyle={'display': 'inline-block'}
)
],
style={'width': '96%', 'display': 'inline-block'})
], style={
'borderBottom': 'thin lightgrey solid',
'backgroundColor': 'rgb(250, 250, 250)',
'padding': '10px 5px'
}),
html.Div([
dcc.Graph(
id='crossfilter-indicator-scatter',
hoverData={'points': [{'customdata': 'Barack Obama'}]}
)
], style={'width': '96%', 'display': 'inline-block', 'padding': '0 20'})
])
@app.callback(
dash.dependencies.Output('crossfilter-indicator-scatter', 'figure'),
[dash.dependencies.Input('crossfilter-yaxis-column', 'value'),
dash.dependencies.Input('crossfilter-xaxis-type', 'value')])
def update_graph(yaxis_column_name,xaxis_type):
if xaxis_type == 'Overall':
dff = allPresidents.loc[allPresidents['Word'].isin(yaxis_column_name)]
dff = dff.sort_values(by=['Word','Name'])
return {
'data': [go.Bar(
x=dff.loc[dff.Word == word,'Name'],
y=100*dff.loc[dff.Word == word,'Frequency'],
name=word,
hovertext=dff.loc[dff.Word == word,'Name'] + '<br>' + \
dff.loc[dff.Word == word,'Word'] + ': ' + \
round(100*dff.loc[dff.Word == word,'Frequency'],4).astype(str) + '%',
hoverinfo="text"
) for word in yaxis_column_name],
'layout': go.Layout(
yaxis={
'title': '% of words',
'type': 'linear'
},
margin={'l': 60, 'b': 80, 't': 10, 'r': 50},
height=450,
barmode='group',
hovermode='closest'
)
}
elif xaxis_type == 'By Party':
dff = byParty.loc[byParty['Word'].isin(yaxis_column_name)]
for word in dff.Word.unique():
for party in df.Party.unique():
if party not in dff.Party.unique():
dff = dff.append({'Word':word,'Party':party,'Frequency':0.0},ignore_index=True)
dff = dff.sort_values(by=['Word','Party'])
return {
'data': [go.Bar(
x=dff.loc[dff.Word == word,'Party'],
y=100*dff.loc[dff.Word == word,'Frequency'],
name=word,
hovertext=dff.loc[dff.Word == word,'Party'] + '<br>' + \
dff.loc[dff.Word == word,'Word'] + ': ' + \
round(100*dff.loc[dff.Word == word,'Frequency'],4).astype(str) + '%',
hoverinfo="text"
) for word in yaxis_column_name],
'layout': go.Layout(
yaxis={
'title': '% of words',
'type': 'linear'
},
margin={'l': 60, 'b': 80, 't': 10, 'r': 50},
height=450,
barmode='group',
hovermode='closest'
)
}
elif xaxis_type == 'By President':
dff = df.loc[df['Word'].isin(yaxis_column_name)]
for word in dff.Word.unique():
for president in df.President.unique():
if president not in dff.President.unique():
dff = dff.append({'Word':word,'President':president,\
'Actual_Year':df.loc[df.President == president,'Actual_Year'].values[0],\
'Ngram_Year':df.loc[df.President == president,'Ngram_Year'].values[0],\
'Frequency':0.0},ignore_index=True)
dff = dff.sort_values(by=['Word','Actual_Year'])
return {
'data': [go.Bar(
x=dff.loc[dff.Word == word,'President'],
y=100*dff.loc[dff.Word == word,'Frequency'],
name=word,
hovertext=dff.loc[dff.Word == word,'President'] + '<br>' + \
dff.loc[dff.Word == word,'Word'] + ': ' + \
round(100*dff.loc[dff.Word == word,'Frequency'],4).astype(str) + '%',
hoverinfo="text"
) for word in yaxis_column_name],
'layout': go.Layout(
yaxis={
'title': '% of words',
'type': 'linear'
},
margin={'l': 60, 'b': 80, 't': 10, 'r': 50},
height=450,
barmode='group',
hovermode='closest'
)
}
if __name__ == '__main__':
app.run_server()