task-3

import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# Load the Iris dataset as an example
iris = load_iris()
data = pd.DataFrame(data= np.c_[iris['data'], iris['target']], columns= iris['feature_names'] + ['target'])

# Display the first few rows of the dataset
print("Original Dataset:")
print(data.head())

# Separate features (X) and target (y)
X = data.drop('target', axis=1)
y = data['target']

# Split the data into training and testing sets (e.g., 80% training, 20% testing)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Data Preprocessing:
# 1. Standardize the features (mean=0, std=1)
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Feature Engineering (for demonstration purposes, we'll create a new feature)
# 2. Create a new feature, 'sepal_length + petal_length'
X_train['sepal_petal_length'] = X_train['sepal length (cm)'] + X_train['petal length (cm)']
X_test['sepal_petal_length'] = X_test['sepal length (cm)'] + X_test['petal length (cm)']

# Display the preprocessed and engineered dataset
print("\nPreprocessed and Engineered Dataset:")
print(X_train.head())

# Now, you can use X_train and y_train to train your machine learning model,
# and X_test and y_test for testing.

# Example: Train a simple model (e.g., Logistic Regression)
from sklearn.linear_model import LogisticRegression

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

# Evaluate the model
accuracy = model.score(X_test, y_test)
print(f"\nModel Accuracy: {accuracy:.2f}")