PyCafe - Dash - Global Air Quality Analysis with Plotly

pages/
air-pollution.csv
air-poplution-extraction-data.csv
app.py
requirements.txt
utils.py
utils.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
import pandas as pd


def load_data():
    #df = pd.read_csv('C:\\Users\\Moritus Peters\\Downloads\\air-pollution.csv')
    #df1 = pd.read_csv('C:\\Users\\Moritus Peters\\Downloads\\air-poplution-extraction-data.csv')
    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 <= 12.0:
        return "Good"
    elif 12.1 <= value <= 35.4:
        return "Moderate"
    elif 35.5 <= value <= 55:
        return "Unhealthy for Sensitive Groups"
    elif 55.1 <= value <= 75:
        return "Unhealthy"
    elif 75.1 <= value <= 90:
        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', 'Very Unhealthy', '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

def standardize_country_names(df, country_column='Country'):
    country_mapping = {
        "Côte d'Ivoire": "Ivory Coast",
        "UK": "United Kingdom",
        "USA": "United States",
        "D.C., USA": "United States",
        "Taiwan": "Republic of China (Taiwan)",
        "South Korea": "Republic of Korea",
        "North Korea": "Democratic People's Republic of Korea",
        "Burkina Faso": "Upper Volta",
        "DRC": "Democratic Republic of the Congo",
        "CAR": "Central African Republic",
        "UAE": "United Arab Emirates",
        "Vietnam": "Socialist Republic of Vietnam"
    }

    # Standardize country names using the mapping
    df[country_column] = df[country_column].replace(country_mapping)

    return df
merged_df = standardize_country_names(merged_df)


print(f'{merged_df['AQI_Level'].value_counts()}')
Py.Cafe

plotly-global-air-quality

Global Air Quality Analysis with Plotly
