number1b.py

import pandas as pd
import matplotlib.pyplot as plt

# Step 1: Load Data
data = pd.read_csv("trips_by_distance.csv")

# Step 2: Data Filtering
# Filter data for > 10,000,000 people conducting 10-25 trips
filtered_data_10_25 = data[(data['Number of Trips 10-25'] > 0) & (data['Number of Trips 10-25'] < 100) & (data['Population Not Staying at Home'] > 10000000)]

# Filter data for > 10,000,000 people conducting 50-100 trips
filtered_data_50_100 = data[(data['Number of Trips 50-100'] > 0) & (data['Number of Trips 50-100'] < 100) & (data['Population Not Staying at Home'] > 10000000)]

# Step 3: Extract Dates
# Get dates where > 10,000,000 people conducted 10-25 trips
dates_10_25 = filtered_data_10_25['Date'].unique()

# Get dates where > 10,000,000 people conducted 50-100 trips
dates_50_100 = filtered_data_50_100['Date'].unique()

# Step 4: Comparison
# Print dates for > 10,000,000 people conducted 10-25 trips
print("Dates where > 10,000,000 people conducted 10-25 trips:")
print(dates_10_25)

# Print dates for > 10,000,000 people conducted 50-100 trips
print("Dates where > 10,000,000 people conducted 50-100 trips:")
print(dates_50_100)

# Step 5: Visualization
plt.figure(figsize=(10, 6))

# Plot total population (assuming it's represented by Population Not Staying at Home)
plt.plot(data['Date'], data['Population Not Staying at Home'], label='Total Population Not Staying at Home')

# Plot > 10,000,000 people conducting 10-25 trips
plt.scatter(filtered_data_10_25['Date'], filtered_data_10_25['Population Not Staying at Home'], color='red', label='> 10,000,000 people (10-25 trips)')

# Plot > 10,000,000 people conducting 50-100 trips
plt.scatter(filtered_data_50_100['Date'], filtered_data_50_100['Population Not Staying at Home'], color='green', label='> 10,000,000 people (50-100 trips)')

# Add labels and legend
plt.xlabel('Date')
plt.ylabel('Population Not Staying at Home')
plt.title('Population Not Staying at Home vs. Date')
plt.legend()
plt.xticks(rotation=45)
plt.tight_layout()

# Show plot
plt.show()