1efinal.py

import matplotlib
matplotlib.use('Agg')  # Use the Agg backend
import dask.dataframe as dd
import matplotlib.pyplot as plt



# Read data using Dask
df_data = dd.read_csv('Trips_Full_Data.csv', dtype = {'Trips 1-25 Miles': 'float64',
                                                          'Trips 1-3 Miles': 'float64',
                                                          'Trips 10-25 Miles': 'float64',
                                                          'Trips 100-250 Miles': 'float64',
                                                          'Trips 25-50 Miles': 'float64',
                                                          'Trips 250-500 Miles': 'float64',
                                                          'Trips 3-5 Miles': 'float64',
                                                          'Trips 5-10 Miles': 'float64',
                                                          'Trips 50-100 Miles': 'float64',
                                                          'Trips <1 Mile': 'float64',
                                                          'Trips >=500 Miles': 'float64',
                                                          'Population Not Staying at Home': 'float64',
                                                          'Population Staying at Home': 'float64',
                                                          'Week': 'float64'
                                                      })


Trips = [ 
    'Trips 1-25 Miles',
    'Trips 1-3 Miles',
    'Trips 10-25 Miles',
    'Trips 100-250 Miles',
    'Trips 100+ Miles',
    'Trips 25-100 Miles',
    'Trips 25-50 Miles',
    'Trips 250-500 Miles',
    'Trips 3-5 Miles',
    'Trips 5-10 Miles',
    'Trips 50-100 Miles',
    'Trips 500+ Miles'
]
# Group and sum
df_merge = df_data[Trips].sum().compute()
print(df_merge)

# Plot
plt.figure(figsize=(10, 6))
df_merge.plot(kind='bar', color='orange')
plt.title('Number of Participants of Travelers by Distance Trips')
plt.xlabel('Number of Trips by Distance')
plt.ylabel('Population Not Staying at Home')
plt.xticks(rotation=45)   
plt.tight_layout()
plt.savefig('bar_plot11data.png')