initial commit

README.md

@@ -1,10 +1,10 @@
 ---
-title: Model Based And Sequential Feature Selection
+title: Model-based And Sequential Feature Selection
 emoji: 🔥
 colorFrom: blue
 colorTo: gray
 sdk: gradio
-sdk_version: 3.24.1
+sdk_version: 3.27.0
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -0,0 +1,57 @@
+import gradio as gr
+import numpy as np
+from sklearn.datasets import load_diabetes
+from sklearn.linear_model import RidgeCV
+from sklearn.feature_selection import SelectFromModel
+from time import time
+from sklearn.feature_selection import SequentialFeatureSelector
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+
+def select_features(method,num_features):
+    diabetes = load_diabetes()
+    X, y = diabetes.data, diabetes.target
+    ridge = RidgeCV(alphas=np.logspace(-6, 6, num=5)).fit(X, y)
+    feature_names = np.array(diabetes.feature_names)
+    if method == 'model':
+        importance = np.abs(ridge.coef_)
+        threshold = np.sort(importance)[-3] + 0.01
+        tic = time()
+        sfm = SelectFromModel(ridge, threshold=threshold).fit(X, y)
+        toc = time()
+        selected_features = feature_names[sfm.get_support()]
+        if int(num_features) < len(selected_features):
+            selected_features = selected_features[:int(num_features)]
+        execution_time = toc - tic
+    elif method == 'sfs-forward':
+        tic_fwd = time()
+        sfs_forward = SequentialFeatureSelector(
+            ridge, n_features_to_select=int(num_features), direction="forward"
+        ).fit(X, y)
+        toc_fwd = time()
+        selected_features = feature_names[sfs_forward.get_support()]
+        execution_time = toc_fwd - tic_fwd
+    elif method == 'sfs-backward':
+        tic_bwd = time()
+        sfs_backward = SequentialFeatureSelector(
+            ridge, n_features_to_select=int(num_features), direction="backward"
+        ).fit(X, y)
+        toc_bwd = time()
+        selected_features = feature_names[sfs_backward.get_support()]
+        execution_time = toc_bwd - tic_bwd
+    return f"Selected the following features: {selected_features} in {execution_time:.3f} seconds"
+
+title = "Selecting features with Sequential Feature Selection"
+with gr.Blocks(title=title) as demo:
+    gr.Markdown(f"## {title}")
+    gr.Markdown("This app demonstrates feature selection techniques using model based selection and sequential feature selection. The app uses the diabetes dataset from sklearn")
+
+    method = gr.Radio(["model", "sfs-forward", "sfs-backward"], label="Method")
+    num_features = gr.Textbox(label="Number of features")
+    output = gr.Textbox(label="Output Box")
+    select_btn = gr.Button("Select")
+    select_btn.click(fn=select_features, inputs=[method,num_features], outputs=output)
+
+demo.launch()
+

requirements.txt

@@ -0,0 +1,2 @@
+scikit-learn==1.2.2
+matplotlib==3.7.1