Initial Commit

app.py

@@ -0,0 +1,113 @@
+"""
+Demo is based on https://scikit-learn.org/stable/auto_examples/feature_selection/plot_rfe_with_cross_validation.html
+"""
+from sklearn.svm import SVC
+from sklearn.datasets import load_digits
+from sklearn.feature_selection import RFE
+import matplotlib.pyplot as plt
+
+from sklearn.datasets import make_classification
+import matplotlib.pyplot as plt
+from sklearn.feature_selection import RFECV
+from sklearn.model_selection import StratifiedKFold
+from sklearn.linear_model import LogisticRegression
+
+import gradio as gr
+
+
+def create_classification_data(informative, redundant):
+    X, y = make_classification(
+        n_samples=500,
+        n_features=15,
+        n_informative=informative,
+        n_redundant=redundant,
+        n_repeated=0,
+        n_classes=8,
+        n_clusters_per_class=1,
+        class_sep=0.8,
+        random_state=0,
+    )
+    return X, y
+
+
+def run_rfecv(informative, redundant):
+    X, y = create_classification_data(informative, redundant)
+    min_features_to_select = 1  # Minimum number of features to consider
+    clf = LogisticRegression()
+    cv = StratifiedKFold(5)
+    rfecv = RFECV(
+        estimator=clf,
+        step=1,
+        cv=cv,
+        scoring="accuracy",
+        min_features_to_select=min_features_to_select,
+        n_jobs=2,
+    )
+    rfecv.fit(X, y)
+
+    print(f"Optimal number of features: {rfecv.n_features_}")
+    n_scores = len(rfecv.cv_results_["mean_test_score"])
+    fig = plt.figure()
+    plt.xlabel("Number of features selected")
+    plt.ylabel("Mean test accuracy")
+    plt.errorbar(
+        range(min_features_to_select, n_scores + min_features_to_select),
+        rfecv.cv_results_["mean_test_score"],
+        yerr=rfecv.cv_results_["std_test_score"],
+    )
+    plt.title("\n Recursive Feature Elimination \nwith correlated features")
+    return plt
+
+
+title = " Recursive feature elimination with cross-validation "
+
+with gr.Blocks(title=title) as demo:
+    gr.Markdown(f"# {title}")
+    gr.Markdown(
+        " This example the feature importnace when features have both redundant and useless features using  Recursive feature elimination <br>"
+        " Dataset: A classification set of 500 data points and 15 features in total  <br>"
+        " **Features** <br> <br> **Informative features** : Number of features that actually having the signal to differentiate between classes. <br>"
+        " **Redundant features** : Number of feature which are just some random linear combinations of informative features.<br>"
+    )
+
+    gr.Markdown(
+        " **Note** Total features - (informative features + redundant features) are Useless features. <br>"
+    )
+    gr.Markdown(
+        " Logistic Regression classifier is used as estimator to rank features. <br>"
+    )
+
+    gr.Markdown(
+        " **[Demo is based on sklearn docs](https://scikit-learn.org/stable/auto_examples/feature_selection/plot_rfe_with_cross_validation.html)**"
+    )
+    with gr.Row():
+        informative = gr.Slider(
+            minimum=0,
+            maximum=10,
+            step=1,
+            value=3,
+            label="Number of Informative features in data",
+        )
+        redundant = gr.Slider(
+            minimum=0,
+            maximum=5,
+            step=1,
+            value=2,
+            label="Number of Redundant features in data",
+        )
+
+    btn = gr.Button(value="Submit")
+    btn.click(
+        run_rfecv,
+        inputs=[informative, redundant],
+        outputs=gr.Plot(label="RFE with cross validation"),
+    )
+
+    gr.Markdown(
+        " Plot demonstrate mean test accuracy for the corresponding feature selected . <br>"
+    )
+    gr.Markdown(
+        " Number of features selected with highest test accuracy will be  nearly ~ equal to informative features . <br>"
+    )
+
+demo.launch()

requirements.txt

@@ -0,0 +1 @@
+scikit-learn==1.2.1