Sample classification dataset

models/linear_regressuin.py

@@ -1,23 +1,14 @@
-# Contributing Guide
-
-We ❤️ contributions! This project is part of **Hacktoberfest**.
-
-## Steps to Contribute
-1. Fork the repo
-2. Create a new branch (`git checkout -b feature-model`)
-3. Add your model/page under `/pages`
-4. Use helper functions from `/utils`
-5. Commit and push (`git push origin feature-model`)
-6. Open a Pull Request (PR)
-
-## What You Can Work On
-- Add a new ML model (e.g., Decision Tree, KNN, SVM, etc.)
-- Improve plotting helpers
-- Add more datasets to `data_helpers`
-- Enhance UI/UX in Streamlit
-
-## Labels
-- `good first issue` → beginner-friendly
-- `feature` → add a new model
-- `bug` → fix something broken
-- `documentation` → improve docs
+# models/linear_regression_model.py
+from sklearn.linear_model import LinearRegression
+import numpy as np
+
+# Train a simple model for demonstration
+model = LinearRegression()
+X = np.array([[1], [2], [3], [4], [5]])
+y = np.array([2, 4, 6, 8, 10])
+model.fit(X, y)
+
+def predict(features):
+    arr = np.array(features).reshape(1, -1)
+    prediction = model.predict(arr)
+    return prediction.tolist()

pages/Linear_Regression.md

@@ -0,0 +1,24 @@
+# Linear Regression Model
+
+## 🏃‍♂️ How to Run
+1. Open the simulator and select **Linear Regression** from the model list.
+2. Upload your dataset or use the default sample dataset.
+3. Adjust parameters if available, then click **Run Simulation**.
+
+## ⚙️ Parameters
+| Parameter | Description | Default |
+|------------|-------------|----------|
+| `fit_intercept` | Whether to calculate the intercept term | True |
+| `normalize` | Normalize input features before training | False |
+| `test_size` | Proportion of data for testing | 0.2 |
+
+## 📈 Output Plots
+- **Scatter Plot:** Shows actual vs. predicted values.
+- **Regression Line:** Displays the best-fit line learned by the model.
+- **Error Distribution:** Optional plot showing residuals.
+
+![Linear Regression Output](../assets/linear_regression_output.png)
+
+## 🧩 Notes
+- Works well for linearly related data.
+- Avoid using with categorical or highly nonlinear datasets.

utils/data_helpers.py

@@ -1,30 +1,47 @@
 # utils/data_helpers.py
-
-from sklearn.datasets import make_regression
+from sklearn.datasets import make_classification
 import pandas as pd
 
-def generate_sample_regression(n_samples=100, n_features=1, noise=0.0, random_state=None):
+def generate_classification_dataset(
+    n_samples: int = 100,
+    n_features: int = 10,
+    n_informative: int = 5,
+    n_classes: int = 2,
+    random_state: int = 42
+):
     """
-    Generate a sample regression dataset.
+    Generate a synthetic classification dataset.
 
-    Parameters:
-        n_samples (int): Number of data points.
-        n_features (int): Number of features.
-        noise (float): Standard deviation of Gaussian noise added to the output.
-        random_state (int or None): Random seed for reproducibility.
+    Parameters
+    ----------
+    n_samples : int, optional
+        Number of samples to generate (default=100).
+    n_features : int, optional
+        Total number of features (default=10).
+    n_informative : int, optional
+        Number of informative features (default=5).
+    n_classes : int, optional
+        Number of target classes (default=2).
+    random_state : int, optional
+        Random seed for reproducibility (default=42).
 
-    Returns:
-        X (pd.DataFrame): Feature dataframe of shape (n_samples, n_features)
-        y (pd.Series): Target variable of shape (n_samples,)
+    Returns
+    -------
+    data : pandas.DataFrame
+        A DataFrame containing the generated features and target column ('target').
     """
-    X, y = make_regression(
+
+    X, y = make_classification(
         n_samples=n_samples,
         n_features=n_features,
-        noise=noise,
+        n_informative=n_informative,
+        n_redundant=0,
+        n_classes=n_classes,
         random_state=random_state
     )
-    # Convert to pandas for convenience
-    X_df = pd.DataFrame(X, columns=[f'feature_{i+1}' for i in range(n_features)])
-    y_series = pd.Series(y, name='target')
-
-    return X_df, y_series
+
+    feature_names = [f"feature_{i}" for i in range(n_features)]
+    data = pd.DataFrame(X, columns=feature_names)
+    data["target"] = y
+
+    return data