sync with remote

app.py

@@ -0,0 +1,71 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.model_selection import train_test_split
+from sklearn.svm import SVC
+from sklearn.metrics import confusion_matrix, classification_report
+
+# Load the dataset
+st.title("SVM Kernel Performance Comparison")
+
+uploaded_file = 'data\overlapped.csv'
+if uploaded_file:
+    df = pd.read_csv(uploaded_file)
+    st.write("### Data Preview")
+    st.dataframe(df)
+    
+    # Assuming the last column is the target
+    X = df.iloc[:, :-1]
+    y = df.iloc[:, -1]
+    
+    # Splitting dataset
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+    
+    # Plot overlapped clusters
+    st.write("### Cluster Visualization")
+    fig, ax = plt.subplots()
+    scatter = sns.scatterplot(x=X.iloc[:, 0], y=X.iloc[:, 1], hue=y, palette='coolwarm', alpha=0.6)
+    plt.xlabel("Feature 1")
+    plt.ylabel("Feature 2")
+    plt.title("Overlapped Clusters")
+    st.pyplot(fig)
+    
+    # Function to train SVM and get performance metrics
+    def evaluate_svm(kernel_type):
+        model = SVC(kernel=kernel_type)
+        model.fit(X_train, y_train)
+        y_pred = model.predict(X_test)
+        cm = confusion_matrix(y_test, y_pred)
+        cr = classification_report(y_test, y_pred, output_dict=True)
+        return cm, cr
+    
+    # Streamlit tabs
+    tab1, tab2, tab3 = st.tabs(["Linear Kernel", "Polynomial Kernel", "RBF Kernel"])
+    
+    for tab, kernel in zip([tab1, tab2, tab3], ["linear", "poly", "rbf"]):
+        with tab:
+            st.write(f"## SVM with {kernel.capitalize()} Kernel")
+            cm, cr = evaluate_svm(kernel)
+            
+            # Confusion matrix
+            st.write("### Confusion Matrix")
+            fig, ax = plt.subplots()
+            sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')
+            plt.xlabel("Predicted")
+            plt.ylabel("Actual")
+            plt.title("Confusion Matrix")
+            st.pyplot(fig)
+            
+            # Classification report
+            st.write("### Classification Report")
+            st.dataframe(pd.DataFrame(cr).transpose())
+            
+            # Explanation
+            explanation = {
+                "linear": "The linear kernel performs well when the data is linearly separable.",
+                "poly": "The polynomial kernel captures more complex relationships but may overfit with high-degree polynomials.",
+                "rbf": "The RBF kernel is effective in capturing non-linear relationships in the data but requires careful tuning of parameters."
+            }
+            st.markdown(f"**Performance Analysis:** {explanation[kernel]}")

data/overlapped.csv

@@ -0,0 +1,360 @@
+4.86,4.87,0
+4.69,5.37,0
+3.82,5.71,0
+2.58,9.88,1
+8.3,5.36,1
+3.41,1.46,1
+4.4,5.77,0
+5.35,5.02,0
+4.77,5.03,0
+2.18,8.08,1
+7.41,5.87,1
+2.6,1.7,1
+6.39,6.26,0
+4.83,3.62,0
+5.82,4.95,0
+1.88,7.33,1
+7.93,6.52,1
+3.1,3.05,1
+4.44,5.09,0
+5.69,5.35,0
+5.11,5.76,0
+2.02,8.78,1
+8.9,4.67,1
+2.53,2.63,1
+5.56,4.9,0
+3.79,5.27,0
+5.45,4.65,0
+3.54,7.7,1
+6.44,4.94,1
+3.34,2.62,1
+5.24,6.22,0
+4.28,4.92,0
+4.75,5.88,0
+2.35,7.94,1
+7.86,4.65,1
+4.47,1.69,1
+4.19,5.53,0
+4.58,4.97,0
+4.81,4.95,0
+2.88,7.87,1
+7.21,5.37,1
+2.46,2.61,1
+5.77,5.61,0
+5.13,4.87,0
+5.9,2.26,0
+2.11,8.14,1
+8.68,5.61,1
+3.19,2.19,1
+4.73,6.74,0
+5.27,5.62,0
+4.62,5.77,0
+1.59,8.38,1
+6.98,4.72,1
+2.9,3.02,1
+4.81,5.5,0
+4.16,4.88,0
+4.34,3.7,0
+1.08,7.69,1
+8.13,5.58,1
+3.13,1.68,1
+5.42,4.57,0
+4.67,5.04,0
+4.49,5.13,0
+2.85,6.91,1
+8.68,5.95,1
+3.69,1.27,1
+5.07,5.19,0
+3.96,4.93,0
+4.27,4.45,0
+2.46,8.31,1
+7.81,4.54,1
+2.8,1.32,1
+6.03,5.69,0
+4.08,4.96,0
+5.67,5.57,0
+2.18,8.42,1
+8.22,5.77,1
+4.04,1.1,1
+5.48,4.92,0
+4.39,3.83,0
+4.75,4.6,0
+2.53,7.92,1
+7.31,5.45,1
+3.35,2.18,1
+4.55,4.87,0
+5.44,6.27,0
+5.4,3.88,0
+1.94,8.62,1
+7.15,6.57,1
+2.95,1.22,1
+4.55,5.29,0
+4.52,6.22,0
+5.03,4.13,0
+3.38,7.45,1
+8.86,4.62,1
+1.54,1.67,1
+5.25,5.05,0
+4.52,5.58,0
+4.59,4.85,0
+2.12,8.41,1
+7.14,4.97,1
+4.6,1.57,1
+4.95,4.45,0
+5.1,5.59,0
+5.21,6.03,0
+1.87,8.12,1
+8.17,4.38,1
+2.86,1.48,1
+4.57,4.99,0
+6.21,5.75,0
+4.47,4.39,0
+0.75,8.36,1
+8.45,5.37,1
+4.27,1.52,1
+5.21,6.52,0
+3.5,5.0,0
+4.17,5.17,0
+3.6,8.2,1
+8.3,5.82,1
+2.4,2.25,1
+4.38,5.05,0
+6.15,5.32,0
+4.53,5.54,0
+1.23,7.82,1
+7.08,5.55,1
+3.5,1.59,1
+6.21,4.02,0
+5.5,4.18,0
+6.29,4.73,0
+2.89,8.32,1
+8.81,6.08,1
+2.48,2.35,1
+5.51,3.91,0
+5.02,5.5,0
+4.02,4.76,0
+3.58,7.91,1
+9.32,4.43,1
+4.27,3.07,1
+3.64,5.24,0
+4.76,3.91,0
+4.69,5.08,0
+2.96,7.92,1
+8.17,5.8,1
+2.76,1.11,1
+5.34,5.59,0
+4.84,5.3,0
+5.63,5.81,0
+2.98,7.88,1
+8.27,4.42,1
+2.93,1.1,1
+4.62,4.89,0
+6.09,4.83,0
+6.26,4.67,0
+1.52,8.73,1
+7.78,5.37,1
+3.77,1.01,1
+5.21,6.67,0
+4.67,4.63,0
+5.81,4.44,0
+1.51,7.27,1
+8.27,4.91,1
+1.97,0.35,1
+4.4,5.18,0
+4.38,3.88,0
+3.96,5.07,0
+3.46,9.07,1
+10.18,5.05,1
+3.15,2.59,1
+6.66,4.82,0
+4.99,5.24,0
+4.34,4.83,0
+3.21,7.98,1
+7.64,4.45,1
+2.94,2.61,1
+5.25,5.1,0
+5.49,4.73,0
+4.93,5.29,0
+1.57,8.23,1
+8.27,5.66,1
+2.11,2.06,1
+4.47,4.81,0
+5.33,6.31,0
+5.69,4.62,0
+3.16,7.96,1
+9.3,6.11,1
+1.79,3.3,1
+6.04,5.69,0
+4.47,4.45,0
+4.06,5.61,0
+1.79,7.8,1
+7.58,5.98,1
+2.5,3.0,1
+5.42,5.03,0
+5.62,4.48,0
+4.99,5.25,0
+1.75,8.06,1
+8.1,5.6,1
+3.18,1.51,1
+4.64,5.15,0
+4.74,4.2,0
+3.53,6.52,0
+2.34,8.02,1
+8.5,4.71,1
+3.33,2.34,1
+5.64,5.4,0
+5.25,4.39,0
+4.54,4.31,0
+2.43,7.84,1
+8.06,5.49,1
+2.89,0.89,1
+5.81,5.18,0
+5.23,4.78,0
+5.49,5.27,0
+1.56,8.29,1
+6.87,5.5,1
+3.67,1.78,1
+5.7,4.76,0
+4.41,4.77,0
+4.63,6.21,0
+1.86,8.58,1
+8.29,6.11,1
+1.71,1.34,1
+5.24,5.23,0
+6.06,5.09,0
+5.42,5.45,0
+2.99,8.51,1
+8.89,4.74,1
+1.97,2.54,1
+5.32,5.03,0
+5.43,6.42,0
+6.34,5.9,0
+2.15,8.08,1
+9.23,5.55,1
+2.5,2.24,1
+5.6,5.12,0
+5.17,4.43,0
+5.17,6.01,0
+3.77,6.38,1
+7.69,4.22,1
+3.47,1.37,1
+5.3,4.83,0
+5.69,5.2,0
+5.09,5.34,0
+2.11,8.13,1
+7.92,6.32,1
+3.39,1.44,1
+5.52,4.62,0
+4.37,5.36,0
+4.49,4.4,0
+2.79,9.68,1
+8.96,5.35,1
+3.43,2.07,1
+5.01,5.71,0
+4.76,4.58,0
+5.94,4.77,0
+2.5,7.6,1
+6.49,4.83,1
+4.09,2.58,1
+5.83,6.57,0
+3.75,4.82,0
+4.78,5.36,0
+1.5,9.46,1
+8.33,5.42,1
+3.07,2.51,1
+4.23,5.78,0
+4.7,4.86,0
+6.1,5.83,0
+2.76,8.45,1
+8.38,6.21,1
+3.15,2.1,1
+4.7,5.61,0
+4.77,4.82,0
+5.39,6.2,0
+2.42,8.57,1
+7.59,5.78,1
+3.78,1.37,1
+5.25,5.49,0
+3.74,3.51,0
+3.9,5.09,0
+1.98,8.97,1
+7.07,6.61,1
+3.71,1.88,1
+4.9,3.93,0
+4.64,5.2,0
+4.54,4.63,0
+2.52,8.14,1
+8.54,5.15,1
+2.7,0.43,1
+4.68,5.76,0
+5.84,4.63,0
+6.2,4.75,0
+2.52,7.32,1
+7.9,5.05,1
+2.98,1.86,1
+5.11,6.02,0
+5.33,5.64,0
+5.37,5.79,0
+1.6,8.85,1
+9.08,5.46,1
+3.85,3.76,1
+6.15,5.31,0
+5.36,4.23,0
+5.81,5.36,0
+3.49,7.84,1
+8.95,5.95,1
+2.99,1.77,1
+5.31,4.85,0
+5.49,4.99,0
+4.31,5.01,0
+3.71,8.84,1
+8.25,4.83,1
+2.91,2.53,1
+5.83,7.03,0
+3.32,5.09,0
+4.66,5.09,0
+3.02,7.22,1
+7.24,4.67,1
+3.09,2.43,1
+4.75,5.27,0
+5.18,4.2,0
+5.01,4.47,0
+2.02,7.92,1
+8.05,6.65,1
+2.55,2.65,1
+5.51,5.19,0
+4.28,3.82,0
+5.71,5.9,0
+1.89,9.15,1
+7.14,5.64,1
+3.42,1.41,1
+5.14,6.11,0
+4.54,6.96,0
+4.29,5.76,0
+2.24,7.66,1
+7.78,5.83,1
+2.65,1.09,1
+5.29,5.68,0
+3.46,4.89,0
+4.4,5.91,0
+2.71,8.98,1
+7.02,6.16,1
+3.48,1.63,1
+6.11,5.97,0
+4.78,4.69,0
+5.35,5.65,0
+1.78,8.26,1
+8.04,5.83,1
+3.24,1.55,1
+6.99,4.63,0
+4.26,5.47,0
+4.75,5.97,0
+2.49,8.73,1
+7.55,5.34,1
+2.18,2.04,1
+4.89,5.2,0
+4.11,4.8,0
+5.13,3.6,0
+5.58,7.17,1
+8.62,6.02,1
+3.05,2.11,1

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+pandas
+numpy
+matplotlib
+seaborn
+scikit-learn