import numpy as np
from scipy.stats import pearsonr
import matplotlib.pyplot as plt
import seaborn as sns

# Generating data points
np.random.seed(42)  # For reproducibility
hours_studied = np.random.randint(8, 25, size=50)
exam_scores = 60 + 2 * hours_studied + np.random.normal(0, 5, size=50)

# Calculate Pearson correlation coefficient
pearson_corr, _ = pearsonr(hours_studied, exam_scores)

# Calculate Pearson correlation line coefficients
m, b = np.polyfit(hours_studied, exam_scores, 1)  # Fit a linear regression line

# Scatter plot
fig, ax = plt.subplots()
ax.scatter(hours_studied, exam_scores, color=sns.color_palette("hls",24)[14], alpha=.9, label='Data points')
plt.plot(hours_studied, m * np.array(hours_studied) + b, color='red', alpha=.6, label='Pearson Correlation Line')
plt.title("Hours Studied vs. Exam Scores")
plt.xlabel("Hours Studied")
plt.ylabel("Exam Scores")
plt.legend(loc='lower right')
ax.spines['top'].set_visible(False)
ax.spines['bottom'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
ax.xaxis.set_ticks_position('none') 
ax.yaxis.set_ticks_position('none')