'''
lecture16_linear_regression.py
Demo of using Numpy to compute linear regression, R^2, and p-value of slope test vs. slope = 0
Using diamond dataset
Oliver W. Layton
CS251: Data Analysis and Visualization
Spring 2019
'''

import numpy as np
from scipy import stats
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style("darkgrid")

# Load diamond data CSV file (included in seaborn module)

# Randomly sample 500 points

# Do the linear regression using
#   x: 'carat'
#   y: 'price'

# Plot data sample

# superimpose linear regression line

# Plot styling stuff
plt.title(f'y = {m:.1f}x+{b:.1f}')
plt.xlabel('Diamond carat')
plt.ylabel('Price ($)')
plt.text(1, 15, f'$R^2$ = {r**2:.2f}', fontsize=15)
plt.text(2, 15, f'$p$ = {p:.2}', fontsize=15)

# Show us the plot in a pop-up window
plt.show()