Basic

[PrasenjeetSaha]

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

Load data using Pandas

data = pd.read_csv('your_data.csv')

Data exploration with Pandas and NumPy

print("Data info:") print(data.info()) print("Statistical summary:") print(data.describe())

Data visualization with Seaborn and Matplotlib

sns.pairplot(data) plt.title('Pairplot of the Data') plt.show()

Data manipulation with Pandas and NumPy

X = data[['feature_1', 'feature_2']] # Features y = data['target'] # Target variable

Split data into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

Linear regression with Scikit-learn

model = LinearRegression() model.fit(X_train, y_train)

Model evaluation

print("Model R^2 score on test data:", model.score(X_test, y_test))