Added Decision Tree model and Streamlit page

models/decision_tree.py

@@ -0,0 +1,37 @@
+from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
+from sklearn.metrics import accuracy_score, mean_squared_error
+import pandas as pd
+import numpy as np
+
+class DecisionTreeModel:
+    """
+    Decision Tree model wrapper supporting both classification and regression.
+    """
+
+    def __init__(self, task_type="classification", max_depth=None, random_state=42):
+        self.task_type = task_type
+        self.max_depth = max_depth
+        self.random_state = random_state
+
+        if task_type == "classification":
+            self.model = DecisionTreeClassifier(max_depth=max_depth, random_state=random_state)
+        elif task_type == "regression":
+            self.model = DecisionTreeRegressor(max_depth=max_depth, random_state=random_state)
+        else:
+            raise ValueError("Invalid task_type. Use 'classification' or 'regression'.")
+
+    def train(self, X, y):
+        self.model.fit(X, y)
+
+    def predict(self, X):
+        return self.model.predict(X)
+
+    def evaluate(self, X, y):
+        preds = self.predict(X)
+        if self.task_type == "classification":
+            return {"accuracy": accuracy_score(y, preds)}
+        else:
+            return {"mse": mean_squared_error(y, preds)}
+
+    def get_model(self):
+        return self.model

pages/Decision_Tree.py

@@ -0,0 +1,52 @@
+import streamlit as st
+import pandas as pd
+from models.decision_tree import DecisionTreeModel
+from utils.data_helpers import generate_sample_regression_data  # For regression data
+from sklearn.datasets import make_classification
+import matplotlib.pyplot as plt
+from sklearn.tree import plot_tree
+
+st.title("🌳 Decision Tree Model Playground")
+
+task_type = st.radio("Select Task Type", ["classification", "regression"])
+
+# Sidebar parameters
+st.sidebar.header("Model Parameters")
+max_depth = st.sidebar.slider("Max Depth", 1, 10, 3)
+n_samples = st.sidebar.slider("Number of Samples", 50, 500, 100)
+n_features = st.sidebar.slider("Number of Features", 1, 5, 2)
+noise = st.sidebar.slider("Noise (for regression)", 0.0, 10.0, 1.0)
+
+st.write("### Generated Dataset Preview")
+
+# Generate dataset
+if task_type == "classification":
+    X, y = make_classification(
+        n_samples=n_samples, n_features=n_features, n_informative=n_features,
+        n_redundant=0, random_state=42
+    )
+    df = pd.DataFrame(X, columns=[f"X{i+1}" for i in range(n_features)])
+    df["y"] = y
+else:
+    df = generate_sample_regression_data(n_samples, n_features, noise)
+
+st.dataframe(df.head())
+
+# Train model
+st.write("### Train Model")
+model = DecisionTreeModel(task_type=task_type, max_depth=max_depth)
+X = df.iloc[:, :-1]
+y = df.iloc[:, -1]
+model.train(X, y)
+
+# Evaluate
+metrics = model.evaluate(X, y)
+st.write("### Evaluation Metrics")
+st.json(metrics)
+
+# Visualization
+st.write("### Decision Tree Visualization")
+
+fig, ax = plt.subplots(figsize=(10, 6))
+plot_tree(model.get_model(), filled=True, feature_names=X.columns)
+st.pyplot(fig)