dtaset11.4.py

import dask.dataframe as dd
import dask
import pandas as pd
import matplotlib.pyplot as plt
import time  # import libraries needed

def staying_home():
    dataset1 = dd.read_csv('dataset11.csv', dtype={'Population Staying at Home': 'float64'})  
    home_pop = dataset1.groupby('Week')['Population Staying at Home'].mean().compute()
    print(home_pop)

def avg_dist_travelled():
    dataset2 = dd.read_csv('dataset22.csv')
    trip_columns = ['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']
    average_trip_per_week = {}
    for column in trip_columns:
        average_trip_per_week[column] = dataset2.groupby('Week of Date')[column].mean().compute()
    for column, average in average_trip_per_week.items():
        print(f"Average distance traveled for {column}:")
        print(average)

def identify_dates():
    
    dataset2 = dd.read_csv('dataset22.csv')
    trips_10_25_over_10M = dataset2[dataset2['Trips 10-25 Miles'] > 10000000]
    dates_10_25_over_10M = trips_10_25_over_10M['Date']
    trips_50_100_over_10M = dataset2[dataset2['Trips 50-100 Miles'] > 10000000]
    dates_50_100_over_10M = trips_50_100_over_10M['Date']
    print("Dates for 10-25 trips with more than 10,000,000 people:")
    print(dates_10_25_over_10M.compute())
    print("Dates for 50-100 trips with more than 10,000,000 people:")
    print(dates_50_100_over_10M.compute())

def processor():
    n_processors = [1, 2, 3, 4, 5, 6, 7, 7, 8, 9, 10,15, 20]
    n_processors_time = {}      
    for processor_count in n_processors:
        start_time = time.time()
        with dask.config.set(num_workers=processor_count):
            
            avd_dt = avg_dist_travelled() 
            
        dask_time = time.time() - start_time
        n_processors_time[processor_count] = dask_time
    print(n_processors_time)

def plot():
    data = {
        'Trips 1-25 Miles': [934957837, 996863262, 1014614495, 1084498325, 984193010, 1052793819, 1040967509],
        'Trips 1-3 Miles': [346577279, 358008909, 366533991, 401474049, 347857770, 378936486, 386948113],
        'Trips 10-25 Miles': [200922270, 228809869, 235621127, 249988663, 226055368, 245571995, 230580285],
        'Trips 100-250 Miles': [8595827, 6535920, 5993704, 5379881, 6259735, 7635743, 7550100],
        'Trips 100+ Miles': [15338786, 12563068, 11104823, 8528574, 12892348, 12256537, 12173176],
        'Trips 25-100 Miles': [79429125, 86004297, 87599579, 92200386, 84193587, 95005653, 91829556],
        'Trips 25-50 Miles': [59517188, 68184743, 70149166, 74381367, 66724543, 74512584, 70644329],
        'Trips 250-500 Miles': [2273613, 1941260, 1741994, 1272248, 1957888, 1823661, 1794030],
        'Trips 3-5 Miles': [171336406, 178996059, 179210645, 189163336, 179346163, 186257669, 186580557],
        'Trips 5-10 Miles': [216121882, 231048425, 233248732, 243872277, 230933709, 242027669, 236858554],
        'Trips 50-100 Miles': [19911937, 17819554, 17450413, 17819019, 17469044, 20493069, 21185227],
        'Trips 500+ Miles': [4469346, 4085888, 3369125, 1876445, 4674725, 2797133, 2829046]
    }

    avg_values = [sum(vals) / len(vals) for vals in data.values()]
    labels = list(data.keys())

    plt.figure(figsize=(12, 6))
    plt.bar(labels, avg_values, color='skyblue')
    plt.title('Average Number of Participants by Distance-Trips')
    plt.xlabel('Distance-Trips')
    plt.ylabel('Average Number of Participants')
    plt.xticks(rotation=50)
    plt.grid(axis='y', linestyle='--', alpha=0.7)
    plt.show()


if __name__ == "__main__":
    identify_dates()