number1.py

import pandas as pd

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

# Step 2: Data Cleaning
data = data.dropna(axis=1, how='all')
# Handle Missing Values (if any)
# Remove Duplicates (if any)
data = data.dropna(axis=1, how='all')

# Step 3: Data Categorization
# Assuming the "Date" column needs to be converted to datetime format
data['Date'] = pd.to_datetime(data['Date'])

# Step 4: Data Aggregation
# Count People at Home per Week
people_at_home_per_week = data.groupby(pd.Grouper(key='Date', freq='W'))['Population Staying at Home'].sum()

# Step 5: Calculate Average
average_people_at_home_per_week = people_at_home_per_week.mean()

# Display the Result
print("Average number of people staying at home per week:", average_people_at_home_per_week)