🏠🌸 ML Internship Tasks — Month 2 (Task 3 & Task 4)

This repository contains two Machine Learning projects completed as part of Month 2 of the ML Internship.

---

📋 Table of Contents

• Task 3 — Housing Price Prediction
• Task 4 — Iris Flower Classification
• Libraries Used
• How to Run
• Project Structure

---

Task 3 — Housing Price Prediction

📌 Overview

Using the California Housing Dataset, a Linear Regression model is built to predict median house prices based on location, number of rooms, income, and population.

---

📂 Dataset

• File: housing.csv
• Target Variable: median_house_value
• Key Features:

Feature	Description
median_income	Median income of the area
ocean_proximity	Location category (one-hot encoded)
total_rooms	Total rooms in the block
housing_median_age	Age of the houses
households	Number of households
population	Population of the area

---

⚙️ Data Preprocessing

• Filled missing total_bedrooms values with median
• Applied One-Hot Encoding on ocean_proximity column
• Applied StandardScaler for feature scaling
• 80/20 Train-Test Split

---

📈 Feature Importance (Top Correlations)

Feature	Correlation
median_income	0.688
ocean_proximity_NEAR BAY	0.160
ocean_proximity_NEAR OCEAN	0.142
total_rooms	0.134
housing_median_age	0.106

---

🤖 Model Used

• Linear Regression

📊 Results

Metric	Value
MSE	4,908,476,721
R² Score	0.6254

📌 R² of 0.625 means the model explains ~62.5% of the variance in house prices.

---

📉 Visualizations

• Scatter Plot: Actual vs Predicted house values
• Bar Chart: Top 10 features affecting house price (by correlation)

---

---

Task 4 — Iris Flower Classification

📌 Overview

Using the Iris Dataset, two classification models are built to classify iris flowers into 3 species — Setosa, Versicolor, and Virginica — based on petal and sepal measurements.

---

📂 Dataset

• File: iris.csv
• Target Variable: Species (3 classes)
• Features Used:

Feature	Description
sepal_length	Length of the sepal
sepal_width	Width of the sepal
petal_length	Length of the petal
petal_width	Width of the petal

---

⚙️ Data Preprocessing

• Applied LabelEncoder on target (species names → numbers)
• Applied StandardScaler for feature scaling
• 80/20 Train-Test Split

---

🤖 Models Used

1. Random Forest Classifier

• random_state = 42
• Default parameters

2. Logistic Regression

• max_iter = 200

---

📊 Results

Model	Accuracy
Random Forest	100%
Logistic Regression	100%

✅ Both models achieved perfect accuracy on the Iris dataset — a well-balanced, clean dataset ideal for classification benchmarking.

---

📉 Visualizations

• Confusion Matrix: Random Forest predictions heatmap
• Bar Chart: Accuracy comparison between both models

---

---

🛠️ Libraries Used

numpy
pandas
matplotlib
seaborn
scikit-learn

---

🚀 How to Run

1. Clone the repository:

git clone https://github.com/hamza93-ai/ML-Internship-Month-2.git

2. Open the notebook in Google Colab or Jupyter:

jupyter notebook ML_Internship_Month2_Tasks.ipynb

3. Upload the required CSV file (housing.csv or iris.csv) when prompted and run all cells.

---

📁 Project Structure

ML-Internship-Month-2/
│
├── ML_Internship_Month2_Tasks.ipynb   # Main notebook (Task 3 + Task 4)
├── ML_Internship_Month2_Report.pdf    # Project report
└── README.md                          # Project documentation

---

👤 Author

Hamza Asif ML Internship — Month 2 | Task 3 & Task 4