Plot_DEF_Clearances

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
# from sklearn.linear_model import LinearRegression
import pandas as pd

# Sample data
np.random.seed(0)
# X = np.random.rand(100, 1) * 10  # Independent variable
# y = 2.5 * X + np.random.randn(100, 1) * 2  # Dependent variable with some noise
df = pd.read_csv("modified_df_DEF.csv")

# Convert 'Rating' and 'Fifa Ability Overall' columns to numeric, ignoring errors
df['Clearances per game'] = pd.to_numeric(df['Clearances per game'], errors='coerce')
df['Fifa Ability Overall'] = pd.to_numeric(df['Fifa Ability Overall'], errors='coerce')

y = df['Clearances per game']
X = df['Fifa Ability Overall']

# Create a scatter plot
plt.figure(figsize=(10, 6))
plt.scatter(X, y, color='black', label='number of clearances')

# Fit a linear regression model
# model = LinearRegression()
# model.fit(X, y)
# y_pred = model.predict(X)

# Plot the linear regression line
# plt.plot(X, y_pred, color='red', linewidth=2, label='Linear regression line')

# Add labels and legend
plt.xlabel('FIFA Ability Overall')
plt.ylabel('Clearances per game')
plt.title('Scatter Plot with Linear Regression Line')
plt.legend()

# Show the plot
plt.show()