Added files

.gitignore

@@ -0,0 +1 @@
+.venv/

app.py

@@ -0,0 +1,156 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# Import sklearn tools
+from sklearn.datasets import load_breast_cancer
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.linear_model import LogisticRegression
+from sklearn.svm import SVC
+from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.neural_network import MLPClassifier
+from sklearn.metrics import confusion_matrix, classification_report
+
+# Set up page configuration and title
+st.set_page_config(page_title="Breast Cancer Classification App", layout="wide")
+st.title("Breast Cancer Classification Analysis")
+
+# Display a header image (ensure you have this image file)
+# st.image("breast_cancer_banner.jpg", caption="Breast Cancer Analysis", use_column_width=True)
+
+# About the app
+with st.expander("About this App"):
+    st.markdown("""
+    **Overview:** This application demonstrates classification of the Breast Cancer dataset using several machine learning models.
+    
+    **Models included:**
+    - Logistic Regression
+    - Support Vector Machine (SVM)
+    - Random Forest
+    - Gradient Boosting
+    - K-Nearest Neighbors (KNN)
+    - MLP Neural Network
+
+    **Features:**
+    - Data preprocessing and scaling
+    - Visualization of confusion matrices, performance reports, and detailed result discussions
+    - Interactive model selection and performance comparison
+    """)
+
+# Load the Breast Cancer dataset
+data = load_breast_cancer()
+df = pd.DataFrame(data.data, columns=data.feature_names)
+df['target'] = data.target
+
+# Display the raw dataset
+st.subheader("Dataset Overview")
+st.write(df.head())
+
+# Split data and preprocess
+X = df.drop("target", axis=1)
+y = df["target"]
+
+# Scale features
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+
+# Sidebar: Allow the user to select test set size
+test_size = st.sidebar.slider("Test Set Size", 0.1, 0.5, 0.2, step=0.05)
+X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=test_size, random_state=42)
+
+# Dictionary of models
+models = {
+    "Logistic Regression": LogisticRegression(max_iter=10000),
+    "SVM": SVC(kernel='linear'),
+    "Random Forest": RandomForestClassifier(n_estimators=100),
+    "Gradient Boosting": GradientBoostingClassifier(),
+    "KNN": KNeighborsClassifier(),
+    "MLP Neural Network": MLPClassifier(max_iter=500)
+}
+
+# Sidebar: Model selection
+model_choice = st.sidebar.selectbox("Choose a model", list(models.keys()))
+selected_model = models[model_choice]
+
+# Train the selected model
+with st.spinner("Training model..."):
+    selected_model.fit(X_train, y_train)
+    y_pred = selected_model.predict(X_test)
+
+# Mapping labels for readability
+label_mapping = {0: "malignant", 1: "benign"}
+y_test_labels = [label_mapping[label] for label in y_test]
+y_pred_labels = [label_mapping[label] for label in y_pred]
+
+# Evaluate model performance
+cm = confusion_matrix(y_test_labels, y_pred_labels, labels=["malignant", "benign"])
+cr = classification_report(y_test_labels, y_pred_labels, output_dict=True)
+# Display the confusion matrix with a smaller figure size
+st.subheader(f"Confusion Matrix: {model_choice}")
+fig, ax = plt.subplots(figsize=(4, 3))  # Further reduced size
+sns.heatmap(cm, annot=True, fmt="d", cmap="Blues", ax=ax, 
+            xticklabels=["malignant", "benign"], yticklabels=["malignant", "benign"])
+ax.set_xlabel("Predicted")
+ax.set_ylabel("True")
+plt.tight_layout()  # Adjusts the layout to fit within the figure area
+st.pyplot(fig)
+
+
+# Display classification report
+st.subheader(f"Classification Report: {model_choice}")
+cr_df = pd.DataFrame(cr).transpose()
+st.dataframe(cr_df)
+
+# Result and Discussion section
+st.subheader("Result and Discussion")
+if model_choice == "Logistic Regression":
+    st.markdown("""
+    **Logistic Regression Discussion:**
+    - **Performance:** The model shows robust performance with clear separation between classes.
+    - **Strengths:** It is fast, interpretable, and performs well on linearly separable data.
+    - **Weaknesses:** May underperform on non-linear boundaries and could be sensitive to outliers.
+    """)
+elif model_choice == "SVM":
+    st.markdown("""
+    **SVM Discussion:**
+    - **Performance:** The linear SVM performs well for this dataset, handling high-dimensional data efficiently.
+    - **Strengths:** Effective in cases where the number of features is greater than the number of samples.
+    - **Weaknesses:** Tuning parameters (like the kernel) is crucial and can be computationally expensive.
+    """)
+elif model_choice == "Random Forest":
+    st.markdown("""
+    **Random Forest Discussion:**
+    - **Performance:** Typically provides high accuracy and robust results due to ensemble learning.
+    - **Strengths:** Handles non-linearity well and provides insights via feature importance.
+    - **Weaknesses:** Can be less interpretable and may overfit if the trees are not properly tuned.
+    """)
+elif model_choice == "Gradient Boosting":
+    st.markdown("""
+    **Gradient Boosting Discussion:**
+    - **Performance:** Demonstrates strong performance by sequentially improving on previous errors.
+    - **Strengths:** Excellent for handling complex data patterns.
+    - **Weaknesses:** Sensitive to overfitting if hyperparameters are not carefully optimized.
+    """)
+elif model_choice == "KNN":
+    st.markdown("""
+    **KNN Discussion:**
+    - **Performance:** Simple yet effective for this dataset, though performance depends on the choice of 'k'.
+    - **Strengths:** Easy to implement and understand.
+    - **Weaknesses:** Computationally expensive for large datasets and sensitive to feature scaling.
+    """)
+elif model_choice == "MLP Neural Network":
+    st.markdown("""
+    **MLP Neural Network Discussion:**
+    - **Performance:** Provides competitive accuracy with a flexible model that can capture non-linear relationships.
+    - **Strengths:** Can learn complex patterns with enough training data.
+    - **Weaknesses:** Requires careful tuning of hyperparameters and more computational resources compared to simpler models.
+    """)
+else:
+    st.markdown("No discussion available for the selected model.")
+
+# Optionally, provide a download button for the classification report
+st.download_button("Download Classification Report as CSV", cr_df.to_csv().encode('utf-8'), "classification_report.csv", "text/csv")

requirements.txt

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