polynomial_regression.py

# import libraries

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# import machine learning libraries
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures

# import the dataset
dataset = pd.read_csv("Position_Salaries.csv")
X = dataset.iloc[:, 1:-1].values
y = dataset.iloc[:, -1].values

print(dataset)

# Training the Linear Regression model on the whole dataset
lin_reg = LinearRegression()
lin_reg.fit(X, y)

# Training the Polynomial Regression model on the whole dataset
poly_reg = PolynomialFeatures(degree=4)
poly_reg.fit_transform(X)
X_poly = poly_reg.fit_transform(X)
lin_reg_2 = LinearRegression()
lin_reg_2.fit(X_poly, y)

# Visualizing the Linear Regression results
plt.scatter(X, y, color="red")
plt.plot(X, lin_reg.predict(X), color="blue")
plt.title("Truth or Bluff (Linear Regression)")
plt.xlabel("Position Level")
plt.ylabel("Salary")
plt.show()

# Visualizing the Polynomial Regression Results
plt.scatter(X, y, color="red")
plt.plot(X, lin_reg_2.predict(X_poly), color="blue")
plt.title("Truth or Bluff (Polynomial Regression)")
plt.xlabel("Position Level")
plt.ylabel("Salary")
plt.show()

# Visualizing Polynomial Regression Results (higher resolution and smoother curve)
X_grid = np.arange(min(X), max(X), 0.1)
X_grid = X_grid.reshape(len(X_grid), 1)
plt.scatter(X, y, color="red")
plt.plot(X_grid, lin_reg_2.predict(poly_reg.fit_transform(X_grid)), color="blue")
plt.title("Truth or Bluff (Polynomial Regression)")
plt.xlabel("Position Level")
plt.ylabel("Salary")
plt.show()

# Predicting new result with Linear Regression
salary1 = round(lin_reg.predict([[6.5]])[0], 2)
print(salary1)

# Predicting a new salary with Polynomial Regression
salary2 = round(lin_reg_2.predict(poly_reg.fit_transform([[6.5]]))[0], 2)
print(salary2)