Upload streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,67 @@
-import altair as alt
-import numpy as np
-import pandas as pd
+# To run this app, use: streamlit run test.py
 import streamlit as st
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
+# Application title and description
+st.title("Machine Learning Model Visualization")
+st.write("This application demonstrates random forest classification on the iris dataset")
 
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
+# Data acquisition and preparation
+@st.cache_data
+def load_data():
+    from sklearn.datasets import load_iris
+    iris = load_iris()
+    df = pd.DataFrame(iris.data, columns=iris.feature_names)
+    df['target'] = iris.target
+    return df, iris.target_names
 
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
+data, target_names = load_data()
 
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
+# Interactive data exploration
+st.subheader("Dataset Exploration")
+if st.checkbox("Display dataset"):
+    st.dataframe(data)
 
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
+# Feature selection interface
+st.subheader("Feature Selection")
+features = st.multiselect(
+    "Select features for model training",
+    options=data.columns[:-1],
+    default=data.columns[0]
+)
 
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+if len(features) > 0:
+    # Model parameters adjustment
+    st.subheader("Model Parameters")
+    n_estimators = st.slider("Number of trees", 1, 100, 10)
+    max_depth = st.slider("Maximum tree depth", 1, 20, 5)
+    
+    # Model training
+    if st.button("Train Model"):
+        X = data[features]
+        y = data['target']
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+        
+        model = RandomForestClassifier(n_estimators=n_estimators, max_depth=max_depth, random_state=42)
+        model.fit(X_train, y_train)
+        
+        # Performance evaluation
+        y_pred = model.predict(X_test)
+        accuracy = accuracy_score(y_test, y_pred)
+        
+        st.success(f"Model accuracy: {accuracy:.4f}")
+        
+        # Visualization of feature importance
+        if len(features) > 1:
+            st.subheader("Feature Importance")
+            fig, ax = plt.subplots()
+            ax.bar(features, model.feature_importances_)
+            plt.xticks(rotation=45)
+            st.pyplot(fig)
+else:
+    st.warning("Please select at least one feature for model training")