initial commit

README.md

@@ -4,7 +4,7 @@ emoji: 🏃
 colorFrom: gray
 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 +1,123 @@
+import gradio as gr
+import numpy as np
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+from sklearn.datasets import fetch_openml
+from sklearn.utils import shuffle
+from sklearn.ensemble import StackingRegressor
+from sklearn.linear_model import RidgeCV
+from skops.hub_utils import download
+import joblib
+import shutil
+
+# load dataset
+def load_ames_housing():
+    df = fetch_openml(name="house_prices", as_frame=True, parser="pandas")
+    X = df.data
+    y = df.target
+
+    features = [
+        "YrSold",
+        "HeatingQC",
+        "Street",
+        "YearRemodAdd",
+        "Heating",
+        "MasVnrType",
+        "BsmtUnfSF",
+        "Foundation",
+        "MasVnrArea",
+        "MSSubClass",
+        "ExterQual",
+        "Condition2",
+        "GarageCars",
+        "GarageType",
+        "OverallQual",
+        "TotalBsmtSF",
+        "BsmtFinSF1",
+        "HouseStyle",
+        "MiscFeature",
+        "MoSold",
+    ]
+
+    X = X.loc[:, features]
+    X, y = shuffle(X, y, random_state=0)
+
+    X = X.iloc[:600]
+    y = y.iloc[:600]
+    return X, np.log(y)
+
+def stacked_model(model1,model2,model3):
+    X, y = load_ames_housing()
+    estimators = []
+    for model in [model1,model2,model3]:
+        download(repo_id="haizad/ames-housing-lasso-predictor", dst='temp_dir')
+        pipeline = joblib.load( "temp_dir/model.pkl")
+        estimators.append((model.split('/')[-1], pipeline))
+        shutil.rmtree("temp_dir")
+
+    stacking_regressor = StackingRegressor(estimators=estimators, final_estimator=RidgeCV())
+
+    # plot and compare the performance of the single models and the stacked model
+    import time
+    import matplotlib.pyplot as plt
+    from sklearn.metrics import PredictionErrorDisplay
+    from sklearn.model_selection import cross_validate, cross_val_predict
+
+    fig, axs = plt.subplots(2, 2, figsize=(9, 7))
+    axs = np.ravel(axs)
+
+    for ax, (name, est) in zip(
+        axs, estimators + [("Stacking Regressor", stacking_regressor)]
+    ):
+        scorers = {"R2": "r2", "MAE": "neg_mean_absolute_error"}
+
+        start_time = time.time()
+        scores = cross_validate(
+            est, X, y, scoring=list(scorers.values()), n_jobs=-1, verbose=0
+        )
+
+        elapsed_time = time.time() - start_time
+
+        y_pred = cross_val_predict(est, X, y, n_jobs=-1, verbose=0)
+        scores = {
+            key: (
+                f"{np.abs(np.mean(scores[f'test_{value}'])):.2f} +- "
+                f"{np.std(scores[f'test_{value}']):.2f}"
+            )
+            for key, value in scorers.items()
+        }
+
+        display = PredictionErrorDisplay.from_predictions(
+            y_true=y,
+            y_pred=y_pred,
+            kind="actual_vs_predicted",
+            ax=ax,
+            scatter_kwargs={"alpha": 0.2, "color": "tab:blue"},
+            line_kwargs={"color": "tab:red"},
+        )
+        ax.set_title(f"{name}\nEvaluation in {elapsed_time:.2f} seconds")
+
+        for name, score in scores.items():
+            ax.plot([], [], " ", label=f"{name}: {score}")
+        ax.legend(loc="upper left")
+
+    fig.suptitle("Single predictors versus stacked predictors")
+    fig.tight_layout()
+    fig.subplots_adjust(top=0.9)
+    return fig
+
+title = "Multi-class AdaBoosted Decision Trees"
+with gr.Blocks(title=title) as demo:
+    gr.Markdown(f"## {title}")
+    gr.Markdown("This app demonstrates the Multi-class AdaBoosted Decision Trees")
+
+    model1 = gr.Textbox(label="Repo id of first model")
+    model2 = gr.Textbox(label="Repo id of second model")
+    model3 = gr.Textbox(label="Repo id of third model")
+    plot = gr.Plot()
+    stack_btn = gr.Button("Stack")
+    stack_btn.click(fn=stacked_model, inputs=[model1,model2,model3], outputs=[plot])
+
+demo.launch()
+

requirements.txt

@@ -0,0 +1,3 @@
+scikit-learn==1.2.2
+matplotlib==3.7.1
+skops==0.6.0