mlextend 0.1.0__tar.gz

mlextend-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 The mlextend contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

mlextend-0.1.0/PKG-INFO

@@ -0,0 +1,107 @@
+Metadata-Version: 2.5
+Name: mlextend
+Version: 0.1.0
+Summary: Ready-to-copy source code of 10 machine learning practicals (EDA, regression, KNN, decision tree, K-Means, PCA, Apriori, Q-Learning).
+License-Expression: MIT
+License-File: LICENSE
+Keywords: education,lab,machine learning,practicals,scikit-learn,source code
+Classifier: Intended Audience :: Education
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Education
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+
+# mlextend
+
+Ready-to-copy source code for 10 machine learning practicals.
+
+`mlextend` does **not** run anything. Each experiment only gives you its complete
+Python code as plain text. Copy it into Jupyter Notebook, VS Code or any other
+Python environment and run it there.
+
+## Installation
+
+```bash
+pip install mlextend
+```
+
+The package itself has no dependencies. Each practical lists the libraries it needs
+in its first comment lines, for example:
+
+```bash
+pip install numpy pandas matplotlib seaborn scikit-learn statsmodels mlxtend
+```
+
+## Usage
+
+```python
+import mlextend
+
+mlextend.list_experiments()   # list all experiments
+
+mlextend.exp1.print()         # print the complete code of Experiment 1
+```
+
+Or import single experiments:
+
+```python
+from mlextend import exp3, exp7
+
+exp3.print()
+```
+
+| Call | What it does |
+|---|---|
+| `exp1.print()` | Prints the complete code as plain text, ready to copy |
+| `exp1.code` | Returns the complete code as a Python string |
+| `exp1.show()` | Shows syntax-highlighted code in Jupyter (plain text elsewhere) |
+| `exp1.save("exp1.py")` | Saves the code to a `.py` file (default name: `exp1.py`) |
+
+`save()` will not replace an existing file unless you pass `overwrite=True`:
+
+```python
+mlextend.exp1.save("exp1.py", overwrite=True)
+```
+
+None of these calls execute, import or compile the practical code.
+
+## Using your own dataset
+
+Where a practical reads a file, the line just above it is marked:
+
+```python
+# CHANGE THIS PATH TO YOUR DATASET
+data = pd.read_csv("heart_disease.csv")
+```
+
+Replace the file name with the path to your own CSV, and make sure the column names
+match the ones used in the code. No datasets are bundled with this package.
+
+| Experiment | File needed | Required columns |
+|---|---|---|
+| exp4 | `heart_disease.csv` | `Age, Resting_Blood_Pressure, Cholesterol, Maximum_Heart_Rate, Exercise_Induced_Angina, Heart_Disease` |
+| exp7 | `Mall_Customers.csv` | `Age, Annual Income (k$), Spending Score (1-100)` |
+
+All other experiments generate their own data or use a dataset built into scikit-learn.
+exp1 and exp2 also show where to plug in your own CSV.
+
+## Experiments
+
+| Name | Topic | Libraries |
+|---|---|---|
+| `exp1` | Data Pre-processing and Exploratory Data Analysis (EDA) | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp2` | Simple Linear Regression | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp3` | Multiple Linear Regression (House Price Prediction) | numpy, pandas, matplotlib, seaborn, scikit-learn, statsmodels |
+| `exp4` | Logistic Regression for Heart Disease Prediction | pandas, matplotlib, scikit-learn |
+| `exp5` | K-Nearest Neighbors (KNN) Classifier for Credit Risk Rating | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp6` | Decision Tree Classifier for Multi-Class Credit Risk Assessment | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp7` | K-Means Clustering for Customer Profiling | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp8` | Dimensionality Reduction using PCA | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp9` | Apriori Algorithm for Association Rule Mining | pandas, mlxtend |
+| `exp10` | Q-Learning Algorithm for Grid World Environment | numpy, pandas |
+
+## License
+
+MIT

mlextend-0.1.0/README.md

@@ -0,0 +1,92 @@
+# mlextend
+
+Ready-to-copy source code for 10 machine learning practicals.
+
+`mlextend` does **not** run anything. Each experiment only gives you its complete
+Python code as plain text. Copy it into Jupyter Notebook, VS Code or any other
+Python environment and run it there.
+
+## Installation
+
+```bash
+pip install mlextend
+```
+
+The package itself has no dependencies. Each practical lists the libraries it needs
+in its first comment lines, for example:
+
+```bash
+pip install numpy pandas matplotlib seaborn scikit-learn statsmodels mlxtend
+```
+
+## Usage
+
+```python
+import mlextend
+
+mlextend.list_experiments()   # list all experiments
+
+mlextend.exp1.print()         # print the complete code of Experiment 1
+```
+
+Or import single experiments:
+
+```python
+from mlextend import exp3, exp7
+
+exp3.print()
+```
+
+| Call | What it does |
+|---|---|
+| `exp1.print()` | Prints the complete code as plain text, ready to copy |
+| `exp1.code` | Returns the complete code as a Python string |
+| `exp1.show()` | Shows syntax-highlighted code in Jupyter (plain text elsewhere) |
+| `exp1.save("exp1.py")` | Saves the code to a `.py` file (default name: `exp1.py`) |
+
+`save()` will not replace an existing file unless you pass `overwrite=True`:
+
+```python
+mlextend.exp1.save("exp1.py", overwrite=True)
+```
+
+None of these calls execute, import or compile the practical code.
+
+## Using your own dataset
+
+Where a practical reads a file, the line just above it is marked:
+
+```python
+# CHANGE THIS PATH TO YOUR DATASET
+data = pd.read_csv("heart_disease.csv")
+```
+
+Replace the file name with the path to your own CSV, and make sure the column names
+match the ones used in the code. No datasets are bundled with this package.
+
+| Experiment | File needed | Required columns |
+|---|---|---|
+| exp4 | `heart_disease.csv` | `Age, Resting_Blood_Pressure, Cholesterol, Maximum_Heart_Rate, Exercise_Induced_Angina, Heart_Disease` |
+| exp7 | `Mall_Customers.csv` | `Age, Annual Income (k$), Spending Score (1-100)` |
+
+All other experiments generate their own data or use a dataset built into scikit-learn.
+exp1 and exp2 also show where to plug in your own CSV.
+
+## Experiments
+
+| Name | Topic | Libraries |
+|---|---|---|
+| `exp1` | Data Pre-processing and Exploratory Data Analysis (EDA) | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp2` | Simple Linear Regression | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp3` | Multiple Linear Regression (House Price Prediction) | numpy, pandas, matplotlib, seaborn, scikit-learn, statsmodels |
+| `exp4` | Logistic Regression for Heart Disease Prediction | pandas, matplotlib, scikit-learn |
+| `exp5` | K-Nearest Neighbors (KNN) Classifier for Credit Risk Rating | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp6` | Decision Tree Classifier for Multi-Class Credit Risk Assessment | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp7` | K-Means Clustering for Customer Profiling | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp8` | Dimensionality Reduction using PCA | numpy, pandas, matplotlib, seaborn, scikit-learn |
+| `exp9` | Apriori Algorithm for Association Rule Mining | pandas, mlxtend |
+| `exp10` | Q-Learning Algorithm for Grid World Environment | numpy, pandas |
+
+## License
+
+MIT

mlextend-0.1.0/pyproject.toml

@@ -0,0 +1,30 @@
+[build-system]
+requires = ["hatchling>=1.24"]
+build-backend = "hatchling.build"
+
+[project]
+name = "mlextend"
+version = "0.1.0"
+description = "Ready-to-copy source code of 10 machine learning practicals (EDA, regression, KNN, decision tree, K-Means, PCA, Apriori, Q-Learning)."
+readme = "README.md"
+license = "MIT"
+license-files = ["LICENSE"]
+requires-python = ">=3.9"
+dependencies = []
+keywords = ["machine learning", "practicals", "lab", "education", "scikit-learn", "source code"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+    "Intended Audience :: Education",
+    "Topic :: Education",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/mlextend"]
+
+[tool.hatch.build.targets.sdist]
+include = ["src/mlextend", "tests", "README.md", "LICENSE", "pyproject.toml"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

mlextend-0.1.0/src/mlextend/__init__.py

@@ -0,0 +1,51 @@
+"""mlextend - ready-to-copy source code of 10 machine learning practicals.
+
+    import mlextend
+    mlextend.list_experiments()
+    mlextend.exp1.print()      # print the full code
+    mlextend.exp1.code         # the code as a string
+    mlextend.exp1.show()       # syntax-highlighted in Jupyter
+    mlextend.exp1.save()       # write exp1.py
+
+Retrieving code never executes it.
+"""
+
+from ._experiment import Experiment
+
+__version__ = "0.1.0"
+
+_TITLES = {
+    1: "Data Pre-processing and Exploratory Data Analysis (EDA)",
+    2: "Simple Linear Regression",
+    3: "Multiple Linear Regression (House Price Prediction)",
+    4: "Logistic Regression for Heart Disease Prediction",
+    5: "K-Nearest Neighbors (KNN) Classifier for Credit Risk Rating",
+    6: "Decision Tree Classifier for Multi-Class Credit Risk Assessment",
+    7: "K-Means Clustering for Customer Profiling",
+    8: "Dimensionality Reduction using PCA",
+    9: "Apriori Algorithm for Association Rule Mining",
+    10: "Q-Learning Algorithm for Grid World Environment",
+}
+
+EXPERIMENTS = {f"exp{n}": Experiment(n, t) for n, t in _TITLES.items()}
+
+exp1 = EXPERIMENTS["exp1"]
+exp2 = EXPERIMENTS["exp2"]
+exp3 = EXPERIMENTS["exp3"]
+exp4 = EXPERIMENTS["exp4"]
+exp5 = EXPERIMENTS["exp5"]
+exp6 = EXPERIMENTS["exp6"]
+exp7 = EXPERIMENTS["exp7"]
+exp8 = EXPERIMENTS["exp8"]
+exp9 = EXPERIMENTS["exp9"]
+exp10 = EXPERIMENTS["exp10"]
+
+
+def list_experiments():
+    """Print all available experiments and return their names."""
+    for name, exp in EXPERIMENTS.items():
+        print(f"{name:<6} {exp.title}")
+    return list(EXPERIMENTS)
+
+
+__all__ = ["Experiment", "EXPERIMENTS", "list_experiments", *EXPERIMENTS]

mlextend-0.1.0/src/mlextend/_experiment.py

@@ -0,0 +1,70 @@
+"""The Experiment class: read-only access to a practical's source code.
+
+Nothing in this module ever executes, imports or compiles the practical code.
+The code is stored as plain text files inside the package and only read.
+"""
+
+from __future__ import annotations
+
+import builtins
+import os
+from importlib.resources import files
+
+_CODES = "codes"
+
+
+class Experiment:
+    """One practical. Use ``.print()``, ``.code``, ``.show()`` and ``.save()``."""
+
+    def __init__(self, number: int, title: str) -> None:
+        self.number = number
+        self.name = f"exp{number}"
+        self.title = title
+        self._resource = f"exp{number:02d}.txt"
+        self._code: str | None = None
+
+    @property
+    def code(self) -> str:
+        """The complete source code of the practical, as a string."""
+        if self._code is None:
+            path = files(__package__).joinpath(_CODES).joinpath(self._resource)
+            self._code = path.read_text(encoding="utf-8")
+        return self._code
+
+    def print(self) -> None:
+        """Print the complete source code as plain text, ready to copy."""
+        builtins.print(self.code, end="")
+
+    def show(self) -> None:
+        """Display the code in a readable format.
+
+        In Jupyter / IPython the code is rendered with syntax highlighting;
+        anywhere else it is printed as plain text.
+        """
+        try:
+            from IPython import get_ipython
+            from IPython.display import Markdown, display
+
+            shell = get_ipython()
+            if shell is not None and shell.__class__.__name__ == "ZMQInteractiveShell":
+                display(Markdown(f"```python\n{self.code}```"))
+                return
+        except ImportError:
+            pass
+        self.print()
+
+    def save(self, path: str | os.PathLike | None = None, overwrite: bool = False) -> str:
+        """Save the code to a ``.py`` file and return its path.
+
+        Defaults to ``exp<N>.py`` in the current directory. An existing file is
+        not replaced unless ``overwrite=True``.
+        """
+        path = os.fspath(path) if path is not None else f"{self.name}.py"
+        if os.path.exists(path) and not overwrite:
+            raise FileExistsError(f"{path} already exists; pass overwrite=True to replace it")
+        with open(path, "w", encoding="utf-8", newline="\n") as fh:
+            fh.write(self.code)
+        return path
+
+    def __repr__(self) -> str:
+        return f"<{self.name}: {self.title}>"

mlextend-0.1.0/src/mlextend/codes/exp01.txt

@@ -0,0 +1,110 @@
+# Experiment 1: Data Pre-processing and Exploratory Data Analysis (EDA)
+# Requirements: pip install numpy pandas matplotlib seaborn scikit-learn
+
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.preprocessing import LabelEncoder, MinMaxScaler
+
+# ==========================================
+# STEP 1: Loading the Dataset
+# ==========================================
+# Raw retail customer dataset (from the problem statement).
+# To use your own data instead, uncomment the next line:
+# CHANGE THIS PATH TO YOUR DATASET
+# df = pd.read_csv("your_dataset.csv")
+df = pd.DataFrame({
+    'CustomerID': [101, 102, 103, 104, 105, 106, 107],
+    'Age': [23, 45, np.nan, 31, 22, 54, 38],
+    'Annual_Income_k': [50, 85, 62, np.nan, 45, 120, 350],
+    'City': ['New York', 'Paris', 'New York', 'London', np.nan, 'London', 'Paris']
+})
+
+print("--- Raw Dataset ---")
+print(df)
+
+# ==========================================
+# STEP 2: Data Inspection & Handling Missing Values
+# ==========================================
+print("\n--- Dataset Info ---")
+df.info()
+
+print("\n--- Missing Values per Column ---")
+print(df.isnull().sum())
+
+# Numerical columns -> Median imputation (robust to outliers)
+for col in ['Age', 'Annual_Income_k']:
+    df[col] = df[col].fillna(df[col].median())
+
+# Categorical column -> Mode imputation
+df['City'] = df['City'].fillna(df['City'].mode()[0])
+
+print("\n--- Dataset after Imputation ---")
+print(df)
+
+# ==========================================
+# STEP 3: Outlier Detection & Treatment (IQR Capping)
+# ==========================================
+Q1 = df['Annual_Income_k'].quantile(0.25)
+Q3 = df['Annual_Income_k'].quantile(0.75)
+IQR = Q3 - Q1
+lower_bound = Q1 - 1.5 * IQR
+upper_bound = Q3 + 1.5 * IQR
+
+print(f"\nIQR Bounds for Annual_Income_k: [{lower_bound:.2f}, {upper_bound:.2f}]")
+outliers = df[(df['Annual_Income_k'] < lower_bound) | (df['Annual_Income_k'] > upper_bound)]
+print("Detected Outliers:")
+print(outliers)
+
+# Boxplot before capping
+plt.figure(figsize=(6, 4))
+sns.boxplot(x=df['Annual_Income_k'])
+plt.title('Annual Income (Before Outlier Capping)')
+plt.show()
+
+# Cap values outside the IQR bounds
+df['Annual_Income_k'] = df['Annual_Income_k'].clip(lower=lower_bound, upper=upper_bound)
+
+print("\n--- Dataset after Outlier Capping ---")
+print(df)
+
+# ==========================================
+# STEP 4: Categorical Encoding & Feature Scaling
+# ==========================================
+# Encode City names into integer identifiers
+le = LabelEncoder()
+df['City_Encoded'] = le.fit_transform(df['City'])
+print("\nCity Encoding:", dict(zip(le.classes_, le.transform(le.classes_))))
+
+# Normalize Age and Income to the range [0, 1]
+scaler = MinMaxScaler()
+df[['Age_Scaled', 'Income_Scaled']] = scaler.fit_transform(df[['Age', 'Annual_Income_k']])
+
+print("\n--- Final Pre-processed Dataset ---")
+print(df)
+
+# ==========================================
+# STEP 5: Exploratory Data Analysis (EDA) - Heatmaps & Histograms
+# ==========================================
+# Histograms: distribution of Age and Income
+fig, axes = plt.subplots(1, 2, figsize=(12, 4))
+sns.histplot(df['Age'], bins=5, kde=True, ax=axes[0], color='skyblue')
+axes[0].set_title('Age Distribution')
+sns.histplot(df['Annual_Income_k'], bins=5, kde=True, ax=axes[1], color='salmon')
+axes[1].set_title('Annual Income Distribution (k)')
+plt.tight_layout()
+plt.show()
+
+# Scatter plot: demographic clusters by City
+plt.figure(figsize=(6, 4))
+sns.scatterplot(data=df, x='Age', y='Annual_Income_k', hue='City', s=100)
+plt.title('Age vs Annual Income by City')
+plt.show()
+
+# Correlation heatmap
+numeric_cols = ['Age', 'Annual_Income_k', 'City_Encoded']
+plt.figure(figsize=(6, 5))
+sns.heatmap(df[numeric_cols].corr(), annot=True, cmap='coolwarm', fmt='.2f')
+plt.title('Feature Correlation Heatmap')
+plt.show()

mlextend-0.1.0/src/mlextend/codes/exp02.txt

@@ -0,0 +1,89 @@
+# Experiment 2: Simple Linear Regression
+# Requirements: pip install numpy pandas matplotlib seaborn scikit-learn
+
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error, r2_score
+
+# ==========================================
+# STEP 1: Generate the Data
+# ==========================================
+# Synthetic data: Years of Experience vs Salary, with random noise.
+np.random.seed(42)
+n_samples = 100
+
+experience = np.random.uniform(0, 15, n_samples)
+noise = np.random.normal(0, 5000, n_samples)
+salary = 30000 + 4500 * experience + noise
+
+data = pd.DataFrame({'YearsExperience': experience, 'Salary': salary})
+data.to_csv('simple_linear_regression_data.csv', index=False)
+
+# Load the saved CSV
+# CHANGE THIS PATH TO YOUR DATASET (and the column names below)
+df = pd.read_csv('simple_linear_regression_data.csv')
+print("--- Dataset Head ---")
+print(df.head())
+
+X = df[['YearsExperience']]   # Feature matrix (2D)
+y = df['Salary']              # Target vector
+
+# ==========================================
+# STEP 2: Splitting Data into Training and Testing Sets (80/20)
+# ==========================================
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size=0.2, random_state=42
+)
+print(f"\nTraining Set Shape: {X_train.shape}")
+print(f"Testing Set Shape:  {X_test.shape}")
+
+# ==========================================
+# STEP 3: Training the Simple Linear Regression Model
+# ==========================================
+model = LinearRegression()
+model.fit(X_train, y_train)
+
+print(f"\nIntercept (beta_0): {model.intercept_:.2f}")
+print(f"Slope     (beta_1): {model.coef_[0]:.2f}")
+
+# ==========================================
+# STEP 4: Making Predictions & Model Evaluation
+# ==========================================
+y_pred = model.predict(X_test)
+
+mse = mean_squared_error(y_test, y_pred)
+rmse = np.sqrt(mse)
+r2 = r2_score(y_test, y_pred)
+
+print("\n--- MODEL PERFORMANCE METRICS ---")
+print(f"Mean Squared Error (MSE)       : {mse:.2f}")
+print(f"Root Mean Squared Error (RMSE) : {rmse:.2f}")
+print(f"R^2 Score                      : {r2:.4f}")
+
+# ==========================================
+# STEP 5: Visualizing Results
+# ==========================================
+fig, axes = plt.subplots(1, 2, figsize=(12, 5))
+
+# Training set
+sns.scatterplot(x=X_train['YearsExperience'], y=y_train, ax=axes[0], color='blue', label='Actual')
+axes[0].plot(X_train['YearsExperience'], model.predict(X_train), color='red', label='Regression Line')
+axes[0].set_title('Training Set: Salary vs Experience')
+axes[0].set_xlabel('Years of Experience')
+axes[0].set_ylabel('Salary')
+axes[0].legend()
+
+# Testing set
+sns.scatterplot(x=X_test['YearsExperience'], y=y_test, ax=axes[1], color='green', label='Actual')
+axes[1].plot(X_train['YearsExperience'], model.predict(X_train), color='red', label='Regression Line')
+axes[1].set_title('Testing Set: Salary vs Experience')
+axes[1].set_xlabel('Years of Experience')
+axes[1].set_ylabel('Salary')
+axes[1].legend()
+
+plt.tight_layout()
+plt.show()

mlextend-0.1.0/src/mlextend/codes/exp03.txt

@@ -0,0 +1,110 @@
+# Experiment 3: Multiple Linear Regression (House Price Prediction)
+# Requirements: pip install numpy pandas matplotlib seaborn scikit-learn statsmodels
+
+# Step 1: Environment Setup & Synthetic Data Generation
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
+from statsmodels.stats.outliers_influence import variance_inflation_factor
+import statsmodels.api as sm
+
+# Set random seed for reproducibility
+np.random.seed(42)
+n_samples = 500
+
+# Generate synthetic features
+sqft = np.random.normal(2100, 500, n_samples).clip(800, 4500)
+bedrooms = np.random.choice([1, 2, 3, 4, 5], size=n_samples, p=[0.1, 0.25, 0.4, 0.2, 0.05])
+dist_transit = np.random.exponential(scale=4.0, size=n_samples).clip(0.5, 20.0)
+age = np.random.uniform(1, 40, n_samples)
+school_rating = np.random.uniform(3.0, 9.8, n_samples)
+
+# True linear relationship + Gaussian noise
+noise = np.random.normal(0, 25000, n_samples)
+price = (150 * sqft) + (12000 * bedrooms) - (8500 * dist_transit) - (1500 * age) + (9000 * school_rating) + 50000 + noise
+
+# Construct DataFrame
+df = pd.DataFrame({
+    'Square_Footage': sqft,
+    'Number_of_Bedrooms': bedrooms,
+    'Distance_to_Transit_km': dist_transit,
+    'Age_of_Property': age,
+    'School_Rating': school_rating,
+    'House_Price': price
+})
+
+print("Dataset Head:")
+print(df.head())
+
+# Step 2: Train-Test Split (80:20)
+# Define Independent Features (X) and Target Variable (Y)
+X = df[['Square_Footage', 'Number_of_Bedrooms', 'Distance_to_Transit_km', 'Age_of_Property', 'School_Rating']]
+Y = df['House_Price']
+
+# Split data into 80% training and 20% testing sets
+X_train, X_test, Y_train, Y_test = train_test_split(
+    X, Y, test_size=0.20, random_state=42
+)
+
+print(f"Training Set Shape: {X_train.shape}")
+print(f"Testing Set Shape:  {X_test.shape}")
+
+# Step 3: Model Fitting & Parameter Estimation
+# Instantiate and fit Linear Regression model
+model = LinearRegression()
+model.fit(X_train, Y_train)
+
+# Extract intercept and slope coefficients
+intercept = model.intercept_
+coefficients = pd.DataFrame({
+    'Feature': X.columns,
+    'Coefficient (Beta)': model.coef_
+})
+
+print(f"Intercept (Beta_0): ${intercept:,.2f}\n")
+print("Learned Feature Coefficients:")
+print(coefficients.to_string(index=False))
+
+# Step 4: Predictions & Quantitative Performance Evaluation
+# Model Predictions on Test Data
+Y_pred = model.predict(X_test)
+
+# Calculate Evaluation Metrics
+mae = mean_absolute_error(Y_test, Y_pred)
+mse = mean_squared_error(Y_test, Y_pred)
+rmse = np.sqrt(mse)
+r2 = r2_score(Y_test, Y_pred)
+
+# Adjusted R-Squared
+n = len(Y_test)
+p = X_test.shape[1]
+adj_r2 = 1 - (1 - r2) * (n - 1) / (n - p - 1)
+
+print("--- MODEL PERFORMANCE METRICS ---")
+print(f"Mean Absolute Error (MAE)      : ${mae:,.2f}")
+print(f"Mean Squared Error (MSE)        : ${mse:,.2f}")
+print(f"Root Mean Squared Error (RMSE)  : ${rmse:,.2f}")
+print(f"R-squared Score (R²)            : {r2:.4f}")
+print(f"Adjusted R-squared Score       : {adj_r2:.4f}")
+
+# Step 5: Residual Diagnostics & VIF Check
+# Calculate Residuals
+residuals = Y_test - Y_pred
+
+# Calculate Variance Inflation Factor (VIF) for Multicollinearity
+vif_data = pd.DataFrame()
+vif_data["Feature"] = X.columns
+vif_data["VIF"] = [variance_inflation_factor(X.values, i) for i in range(X.shape[1])]
+
+print("--- VARIANCE INFLATION FACTOR (VIF) ---")
+print(vif_data.to_string(index=False))
+
+# Statsmodels OLS detailed summary
+X_train_sm = sm.add_constant(X_train)
+ols_model = sm.OLS(Y_train, X_train_sm).fit()
+print(ols_model.summary())