-
Notifications
You must be signed in to change notification settings - Fork 1
/
plot.py
150 lines (137 loc) · 6.43 KB
/
plot.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
import dash
from dash import dcc, html, Input, Output, ctx, dash_table
import plotly.express as px
from sklearn.metrics import mean_squared_error, mean_absolute_error
import pandas as pd
import numpy as np
import os
# Load the data
file_path = '/Users/wexu/Downloads/CODE/data_forecast.csv'
data = pd.read_csv(file_path)
data['Year'] = pd.to_datetime(data['Year']).dt.year
data = data.sort_values('Year')
data['Is_Forecast'] = data['Is_Forecast'] == "Yes"
# Initialize the app
app = dash.Dash(__name__, suppress_callback_exceptions=True)
app.layout = html.Div([
dcc.Tabs(id="tabs", value='tab-1', children=[
dcc.Tab(label='Data Visualization', value='tab-1'),
dcc.Tab(label='Statistical Summary', value='tab-2'),
dcc.Tab(label='Error Metrics', value='tab-3'), # New tab for error metrics
]),
html.Div(id='tabs-content')
])
@app.callback(Output('tabs-content', 'children'),
Input('tabs', 'value'))
def render_content(tab):
if tab == 'tab-1':
return html.Div([
html.Div([
dcc.Dropdown(
id='country-dropdown',
options=[{'label': country, 'value': country} for country in data['Country'].unique()],
value=['United States'],
multi=True
),
dcc.Dropdown(
id='category-dropdown',
options=[{'label': col, 'value': col} for col in data.columns if col not in ['Year', 'Is_Forecast', 'Country']],
value='Economic Quality'
),
], style={'width': '100%', 'display': 'inline-block'}),
dcc.Graph(id='time-series-chart'),
dcc.RangeSlider(
id='year-slider',
min=data['Year'].min(),
max=data['Year'].max(),
value=[data['Year'].min(), data['Year'].max()],
marks={str(year): str(year) for year in data['Year'].unique()},
step=None
),
html.Button("Download CSV", id="btn_csv"),
dcc.Download(id="download-dataframe-csv")
])
elif tab == 'tab-2':
return html.Div([
html.H4('Statistical Summary'),
dcc.Dropdown(
id='country-summary-dropdown',
options=[{'label': country, 'value': country} for country in data['Country'].unique()],
value='United States',
clearable=False
),
dash_table.DataTable(id='summary-table', style_table={'overflowY': 'auto'})
])
elif tab == 'tab-3': # Content for the new Error Metrics tab
return html.Div([
html.H4('Error Metrics'),
dcc.Dropdown(
id='country-error-dropdown',
options=[{'label': country, 'value': country} for country in data['Country'].unique()],
value='United States', # Default to 'United States'
clearable=False
),
dcc.Dropdown(
id='category-error-dropdown',
options=[{'label': col, 'value': col} for col in data.columns if col not in ['Year', 'Is_Forecast', 'Country']],
value='Economic Quality' # Default to 'Economic Quality'
),
dash_table.DataTable(id='error-metrics-table', style_table={'overflowY': 'auto'})
])
@app.callback(
Output('time-series-chart', 'figure'),
[Input('country-dropdown', 'value'),
Input('category-dropdown', 'value'),
Input('year-slider', 'value')]
)
def update_graph(selected_countries, selected_category, year_range):
dff = data[(data['Year'] >= year_range[0]) & (data['Year'] <= year_range[1])]
actual_data = dff[dff['Is_Forecast'] == False]
forecast_data = dff[dff['Is_Forecast'] == True]
fig = px.line(actual_data[actual_data['Country'].isin(selected_countries)],
x='Year', y=selected_category, color='Country', markers=True,
labels={selected_category: f'{selected_category} Ranking'},
title=f'Time Series of {selected_category}')
for country in selected_countries:
country_forecast_data = forecast_data[forecast_data['Country'] == country]
if not country_forecast_data.empty:
fig.add_scatter(x=country_forecast_data['Year'], y=country_forecast_data[selected_category],
mode='lines+markers', name=f'{country} (Forecast)', line=dict(dash='dot'),
hoverinfo='name+y+x')
fig.update_layout(hovermode='x unified')
return fig
@app.callback(
[Output('error-metrics-table', 'data'), Output('error-metrics-table', 'columns')],
[Input('country-error-dropdown', 'value'), Input('category-error-dropdown', 'value')]
)
def update_error_metrics(selected_country, selected_category):
actual_data = data[(data['Country'] == selected_country) & (data['Is_Forecast'] == False)]
forecast_data = data[(data['Country'] == selected_country) & (data['Is_Forecast'] == True)]
if not actual_data.empty and not forecast_data.empty:
merged_data = pd.merge(
actual_data[['Year', selected_category]],
forecast_data[['Year', selected_category]],
on='Year',
suffixes=('_actual', '_forecast')
)
if not merged_data.empty:
mse = mean_squared_error(merged_data[selected_category + '_actual'], merged_data[selected_category + '_forecast'])
rmse = np.sqrt(mse)
mae = mean_absolute_error(merged_data[selected_category + '_actual'], merged_data[selected_category + '_forecast'])
error_metrics = pd.DataFrame({
"Metric": ["MSE", "RMSE", "MAE"],
"Value": [mse, rmse, mae]
})
return error_metrics.to_dict('records'), [{"name": i, "id": i} for i in error_metrics.columns]
return [], [{"name": "Metric", "id": "Metric"}, {"name": "Value", "id": "Value"}]
@app.callback(
[Output('summary-table', 'data'), Output('summary-table', 'columns')],
[Input('country-summary-dropdown', 'value')]
)
def update_statistical_summary(selected_country):
filtered_data = data[data['Country'] == selected_country].select_dtypes(include=[np.number])
description = filtered_data.describe().reset_index()
description = description.round(2)
return description.to_dict('records'), [{"name": i, "id": i} for i in description.columns]
if __name__ == '__main__':
app.run_server(debug=True)