Aim:- To Implement Linear Regression .
# importing the dataset
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
# Load dataset
dataset = pd.read_csv('Salary_Data.csv')
dataset.head()
# Data preprocessing
X = dataset.iloc[:, :-1].values # independent variable array
y = dataset.iloc[:, 1].values # dependent variable vector
# Splitting the dataset
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=1/3, random_state=0)
# Fitting the regression model
regressor = LinearRegression()
regressor.fit(X_train, y_train) # Fit the model
# Predicting the test set results
y_pred = regressor.predict(X_test)
# Model Evaluation Metrics
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)
print(f"Mean Squared Error (MSE): {mse:.2f}")
print(f"R² Score: {r2:.4f}")
# Visualizing the results
# Plot for the TRAIN set
plt.scatter(X_train, y_train, color='red')
plt.plot(X_train, regressor.predict(X_train), color='blue')
plt.title("Salary vs Experience (Training set)")
plt.xlabel("Years of experience")
plt.ylabel("Salaries")
plt.show()
# Plot for the TEST set
plt.scatter(X_test, y_test, color='red')
plt.plot(X_train, regressor.predict(X_train), color='blue')
plt.title("Salary vs Experience (Testing set)")
plt.xlabel("Years of experience")
plt.ylabel("Salaries")
plt.show()
Aim:- To Implement Multiple Linear Regression .
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from sklearn.compose import ColumnTransformer
# Load dataset
dataset = pd.read_csv('50_Startups.csv')
dataset.head()
x = dataset.iloc[:, :-1].values # independent variable array
y = dataset.iloc[:, 1].values
#Catgorical data
labelencoder_x= LabelEncoder()
x[:, 3] = labelencoder_x.fit_transform(x[:,3])
# onehotencoder= OneHotEncoder(categorical_features= [3])
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(drop='first'), [3])],
remainder='passthrough')
# x= onehotencoder.fit_transform(x).toarray()
x = x[:, 1:]
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state=0)
#Fitting the MLR model to the training set:
regressor= LinearRegression()
regressor.fit(x_train, y_train)
y_train_pred = regressor.predict(x_train)
y_test_pred = regressor.predict(x_test)
print("Train Score:",regressor.score(x_train,y_train))
print("Test Score:",regressor.score(x_test,y_test))
