sea_level_predictor.py

import pandas as pd
import matplotlib.pyplot as plt
from scipy.stats import linregress

def draw_plot():
    # Read data from file
    df = pd.read_csv("epa-sea-level.csv")

    # Create scatter plot
    plt.figure(figsize=(10, 6))
    plt.scatter(df['Year'], df['CSIRO Adjusted Sea Level'], label='Data', color='b')

    # Create first line of best fit using all available data
    slope1, intercept1, r_value1, p_value1, std_err1 = linregress(df['Year'], df['CSIRO Adjusted Sea Level'])
    years_extended = pd.Series([i for i in range(1880, 2051)])
    plt.plot(years_extended, intercept1 + slope1 * years_extended, label='Best Fit Line 1880-2050', color='r')

    # Create second line of best fit using data from 2000 onwards
    df_recent = df[df['Year'] >= 2000]
    slope2, intercept2, r_value2, p_value2, std_err2 = linregress(df_recent['Year'], df_recent['CSIRO Adjusted Sea Level'])
    years_recent_extended = pd.Series([i for i in range(2000, 2051)])
    plt.plot(years_recent_extended, intercept2 + slope2 * years_recent_extended, label='Best Fit Line 2000-2050', color='g')

    # Add labels and title
    plt.xlabel('Year')
    plt.ylabel('Sea Level (inches)')
    plt.title('Rise in Sea Level')
    plt.legend()

    # Save plot and return data for testing (DO NOT MODIFY)
    plt.savefig('sea_level_plot.png')
    return plt.gca()