1e.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_distance = dd.read_csv('Trips_by_Distance.csv', dtype={'County Name': 'object',
                                                           'Number of Trips': 'float64',
                                                           'Number of Trips 1-3': 'float64',
                                                           'Number of Trips 10-25': 'float64',
                                                           'Number of Trips 100-250': 'float64',
                                                           'Number of Trips 25-50': 'float64',
                                                           'Number of Trips 250-500': 'float64',
                                                           'Number of Trips 3-5': 'float64',
                                                           'Number of Trips 5-10': 'float64',
                                                           'Number of Trips 50-100': 'float64',
                                                           'Number of Trips <1': 'float64',
                                                           'Number of Trips >=500': 'float64',
                                                           'Population Not Staying at Home': 'float64',
                                                           'Population Staying at Home': 'float64',
                                                           'Week': 'float64'})

# Group and sum
# For Dask DataFrame
df_merge = df_distance.groupby('Week')['Population Not Staying at Home'].sum().compute()

df_merge = df_merge.astype('int64')
print(df_merge)

# Barplot
plt.figure(figsize=(10, 6))
df_merge.plot(kind='bar', color='orange')
plt.title('Number of Participants of Travelers by Distance Trips')
plt.xlabel('Week')
plt.ylabel('Population Not Staying at Home')
plt.xticks(rotation=45)   
plt.tight_layout()
plt.savefig('bar_plot6.png')