Create app.py

app.py

@@ -0,0 +1,73 @@
+import streamlit as st
+
+st.set_page_config(page_title="ML Performance Metrics", layout="wide")
+
+# Title
+st.title("📊 Machine Learning Performance Metrics")
+st.markdown("Understand key metrics used to evaluate ML models — for both **classification** and **regression** problems.")
+
+st.markdown("---")
+
+# Tabs for Classification and Regression
+tab1, tab2 = st.tabs(["🧠 Classification Metrics", "📈 Regression Metrics"])
+
+# ======================== CLASSIFICATION ========================
+with tab1:
+    st.header("🧠 Classification Metrics")
+    st.markdown("These metrics evaluate how well a model classifies input data into distinct categories.")
+
+    with st.expander("🎯 Accuracy"):
+        st.latex(r"Accuracy = \frac{TP + TN}{TP + TN + FP + FN}")
+        st.markdown("Proportion of correct predictions out of all predictions.")
+        st.info("✔️ Best used when classes are balanced.")
+
+    with st.expander("🎯 Precision"):
+        st.latex(r"Precision = \frac{TP}{TP + FP}")
+        st.markdown("How many predicted positives are actually correct?")
+        st.info("✔️ Important when False Positives are costly (e.g., spam detection).")
+
+    with st.expander("🎯 Recall (Sensitivity)"):
+        st.latex(r"Recall = \frac{TP}{TP + FN}")
+        st.markdown("How many actual positives did we correctly predict?")
+        st.info("✔️ Critical when False Negatives are costly (e.g., disease detection).")
+
+    with st.expander("🎯 F1 Score"):
+        st.latex(r"F1 = 2 \cdot \frac{Precision \cdot Recall}{Precision + Recall}")
+        st.markdown("Harmonic mean of precision and recall.")
+        st.info("✔️ Good balance when you need both precision and recall.")
+
+    with st.expander("🎯 ROC-AUC Score"):
+        st.markdown("Area under the ROC curve — plots **True Positive Rate** vs **False Positive Rate**.")
+        st.image("https://upload.wikimedia.org/wikipedia/commons/6/6b/Roccurves.png", caption="ROC Curves Example", use_column_width=True)
+        st.info("✔️ Best when evaluating probabilistic classifiers.")
+
+    st.markdown("---")
+    st.success("📌 Tip: Always use multiple metrics for a complete performance picture.")
+
+# ======================== REGRESSION ========================
+with tab2:
+    st.header("📈 Regression Metrics")
+    st.markdown("These metrics evaluate how well a model predicts continuous numerical values.")
+
+    with st.expander("🎯 Mean Absolute Error (MAE)"):
+        st.latex(r"MAE = \frac{1}{n} \sum_{i=1}^{n} |y_i - \hat{y}_i|")
+        st.markdown("Average of absolute differences between actual and predicted values.")
+        st.info("✔️ Less sensitive to outliers.")
+
+    with st.expander("🎯 Mean Squared Error (MSE)"):
+        st.latex(r"MSE = \frac{1}{n} \sum_{i=1}^{n} (y_i - \hat{y}_i)^2")
+        st.markdown("Average of squared differences. Penalizes larger errors more.")
+        st.info("✔️ Good for highlighting large deviations.")
+
+    with st.expander("🎯 Root Mean Squared Error (RMSE)"):
+        st.latex(r"RMSE = \sqrt{MSE}")
+        st.markdown("Square root of MSE. Same units as target variable.")
+        st.info("✔️ Interpretable on the same scale as the original data.")
+
+    with st.expander("🎯 R² Score (Coefficient of Determination)"):
+        st.latex(r"R^2 = 1 - \frac{\sum (y_i - \hat{y}_i)^2}{\sum (y_i - \bar{y})^2}")
+        st.markdown("Measures proportion of variance explained by the model.")
+        st.info("✔️ Ranges from 0 to 1. Closer to 1 means better model.")
+
+    st.markdown("---")
+    st.success("📌 Tip: Use MAE when you care about average error, and RMSE when you want to penalize large errors.")