PyCafe - Dash - debug

app.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
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
import dash
import dash_mantine_components as dmc
import pandas as pd
import dash_ag_grid as dag
from dash import _dash_renderer, callback, Input, Output, Dash
from dash import dcc, html


_dash_renderer._set_react_version("18.2.0")
app = Dash(
    external_stylesheets=dmc.styles.ALL)


def load_data():
    df = pd.read_csv('https://raw.githubusercontent.com/SmartDvi/Air_Pollution/main/air-pollution.csv')
    df1 = pd.read_csv('https://raw.githubusercontent.com/SmartDvi/Air_Pollution/main/air-poplution-extraction-data.csv')
    
    df_melted = df.melt(id_vars=['Year'], var_name='City', value_name='PM2.5')
    df_melted[['City', 'Country']] = df_melted['City'].str.split(', ', expand=True, n=1)
    df_melted['Country'] = df_melted['Country'].fillna('Singapore')
    
    # Categorize PM2.5 values
    df_melted['AQI_Level'] = df_melted['PM2.5'].apply(categorize_pm25)

    # Merge the two datasets
    merged_df = pd.merge(df_melted, df1, on='City', how='left')

    # Calculate yearly averages and anomalies
    yearly_avg = merged_df.groupby('Year')['PM2.5'].mean().reset_index()
    yearly_avg.columns = ['Year', 'Yearly_Avg_PM2.5']
    merged_df = merged_df.merge(yearly_avg, on='Year', how='left')
    merged_df['PM2.5_Anomaly'] = merged_df['PM2.5'] - merged_df['Yearly_Avg_PM2.5']
    
    # Calculate percentage change in PM2.5
    merged_df.sort_values(by=['City', 'Year'], inplace=True)
    merged_df['PM2.5_Pct_Change'] = merged_df.groupby('City')['PM2.5'].pct_change() * 100

    # Convert Year to string for dropdown use
    merged_df['Year'] = merged_df['Year'].astype(str)

    return merged_df

def categorize_pm25(value):
    if value <= 9.0:
        return "Good"
    elif 9.1 <= value <= 35.4:
        return "Moderate"
    elif 35.5 <= value <= 55.4:
        return "Unhealthy for Sensitive Groups"
    elif 55.5 <= value <= 150.4:
        return "Unhealthy"
    elif 150.5 <= value <= 225.4:
        return "Very Unhealthy"
    else:
        return "Hazardous"

def group_aqi_level(aqi_level, specific_level):
    """
    Function to group AQI levels into specific categories or 'Others'
    """
    if aqi_level == specific_level:
        return specific_level
    else:
        return 'Others'

def prepare_aqi_data(merged_df):
    """
    Grouping the AQI level data for a donuts chart
    """
    aqi_levels = ['Good', 'Moderate', 'Unhealthy', 'Unhealthy for Sensitive Groups', 'Hazardous']
    aqi_data = {}

    for level in aqi_levels:
        merged_df['group_AQI'] = merged_df['AQI_Level'].apply(lambda x: group_aqi_level(x, level))
        group_data = merged_df.groupby('group_AQI')['PM2.5'].sum().reset_index()

        # Fetch the value for the specific AQI level and 'Others'
        specific_value = group_data.loc[group_data['group_AQI'] == level, 'PM2.5'].values
        others_value = group_data.loc[group_data['group_AQI'] == 'Others', 'PM2.5'].sum()

        aqi_data[level] = {
            'value': specific_value[0] if len(specific_value) > 0 else 0,
            'others': others_value
        }

    return aqi_data

# Load the data and prepare AQI data
merged_df = load_data()
aqi_data = prepare_aqi_data(merged_df)

# Output a summary of AQI data (for debugging)
aqi_data

columnDefs=[
    {'field': 'City', 'headerName': 'City'},
    {'field': 'Country', 'headerName': 'Country'},
    {
        'field': 'PM2.5', 
        'headerName': 'PM2.5',
        'valueFormatter': {"function": "d3.format('.2f')(params.value)"}, 
        'type': 'rightAligned'
    },
    {
        'field': 'PM2.5_Anomaly',
        'headerName': 'PM2.5 Anomaly',
        'valueFormatter': {"function": "d3.format('.2f')(params.value)"},  # Format to two decimal places
        'type': 'rightAligned'
    },
    {
        'field': 'PM2.5_Pct_Change',
        'headerName': 'PM2.5 % Change',
        'valueFormatter': {"function": "d3.format('.1f')(params.value) + '%'"},
        'type': 'rightAligned'
    },
    {
        'field': 'Yearly_Avg_PM2.5',
        'headerName': 'Yearly_Avg_PM2.5',
        'valueFormatter': {"function": "d3.format('.2f')(params.value)"},  # Format to two decimal places
        'type': 'rightAligned'
    }
]

grid = html.Div([
    html.H1('Grid Page'),
    dag.AgGrid(
        id='grid_id',
        columnDefs=columnDefs,
        columnSize="autoSize",
        rowData=merged_df.to_dict('records'),
        
        defaultColDef={'editable': True, "filter": True, "floatingFilter": True},
        dashGridOptions = {"suppressFieldDotNotation": True},
        className="ag-theme-alpine-dark",

    ),

])


 
print(merged_df)
# developing app layout
app.layout = html.Div([
    grid
]

)



if __name__ == "__main__":
    app.run(debug=True, port=6084)
    
merged_df
print(columnDefs)
Py.Cafe

debug_project
