Add application file

app.py

@@ -0,0 +1,150 @@
+import pandas as pd
+import numpy as np
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+import gradio as gr
+
+def load_dataset(n=100, w = 0.4, b=5., x_range = [0, 50]):
+    np.random.seed(42)
+    def s(x):
+        g = (x - x_range[0]) / (x_range[1] - x_range[0])
+        return 5 * (0.25 + g**2.)
+
+    x = (x_range[1] - x_range[0]) * np.random.rand(n) + x_range[0]
+    eps = np.random.randn(n) * s(x)
+    y = (w * x * (1. + np.sin(x)/5) + b) + eps
+    y = (y - y.mean()) / y.std()
+    idx = np.argsort(x)
+    return pd.DataFrame({"x": x[idx], "y": y[idx]})
+
+def check_sanitize_data(inp):
+    try:
+        inp=inp.astype(float)
+    except:
+        return None, [("Data points not numeric", "Error")]
+    x,y = inp["x"].to_numpy(), inp["y"].to_numpy()
+    if(len(x)<2):
+        return None, [("Data points not provided", "Error")]
+    return (x,y), [("", "OK")]
+
+def plot_data(inp, m=None, b=None):
+    xy, status = check_sanitize_data(inp)
+    if xy is None:
+        return None, status
+    x, y = xy
+    fig,ax = plt.subplots()
+    ax.set(aspect=np.std(x).item()/3, ylabel="Y-axis")
+    ax.plot(x, y, "o", label="Original data", markersize=2)
+    # center text
+    # fig.text(.5, .05, "OLS", ha="center")
+    if(m):
+        y_hat = m * x + b
+        rss = np.sum((y-y_hat)**2)
+        ax.set(xlabel = f"RSS:{rss:.4f}")
+        ax.xaxis.label.set(color="red")
+        ax.plot(x, m * x + b, "r", label="Fitted line")
+    ax.legend()
+    ax.grid()
+    fig.tight_layout()
+    return fig, [("Data check", "OK")]
+
+def linear_regression_from_scratch(X,y):
+    XT_X = np.matmul(X.T, X)
+    XT_y = np.matmul(X.T, y)
+    m,b = np.matmul(np.linalg.inv(XT_X), XT_y)
+    return m,b
+
+def linear_regression_linalg_lstsq(X,y):
+    (m,b),*_ = np.linalg.lstsq(X, y, rcond=None)
+    return m,b
+
+def linear_regression_plot(method, inp):
+    xy, status = check_sanitize_data(inp)
+    if xy is None:
+        return None, status
+    x,y = xy
+    X = np.column_stack((x, np.ones(len(x))))
+    if method == "numpy from scratch":
+        m, b = linear_regression_from_scratch(X, y)
+    elif method == "numpy.linalg.lstsq":
+        m, b = linear_regression_linalg_lstsq(X, y)
+    else:
+        return None, [("Method not selected", "Error")]
+    fig, _ = plot_data(inp, m, b)
+    return fig, [("Regression", "OK")]
+
+data = load_dataset()
+block_params = {
+    "title": "Ordinary Least Squares",
+    "css": """
+            #XY {max-height: 350px; overflow-y: scroll}
+            #images img {width:auto; height:auto}
+            #images .flex {display:none; height:auto}
+            #accord > div > span {font-weight: bold}
+            """
+}
+plot_data(data)
+
+with gr.Blocks(**block_params) as demo:
+    with gr.Row():
+        with gr.Column(scale=1):
+
+            data_frm = gr.Dataframe(headers=data.columns.tolist(),
+                                datatype=["number", "number"],
+                                col_count=(2, "fixed"), elem_id="XY",
+                                    values=np.zeros((150, 2)).tolist()
+                                )
+            plot_btn = gr.Button("Check&Plot")
+            gr.Examples([[data.values.tolist()]], inputs=data_frm)
+            gr.Markdown("""
+                        #### How to use?
+                        1.Fill the x-y table below (or use the example data provided)  
+                        2.**Check&Plot**  
+                        3.Select an implementation   
+                        4.**Regression&Plot**
+                        """)
+        with gr.Column(scale=1):
+            status_hlt = gr.HighlightedText(
+                label="Status",
+                combine_adjacent=True,
+            ).style(color_map={"Error": "red", "OK": "green"})
+            data_plt = gr.Plot(label="Plot")
+            method_dd = gr.Dropdown(label="Select an implementation",choices=["numpy from scratch", "numpy.linalg.lstsq"],)
+            regression_btn = gr.Button("Regression&Plot")
+            # gr.Examples(label="Proofs", examples=[["img.png"]],inputs=img)
+
+    with gr.Accordion("Motivation", open=False, elem_id="accord"):
+        gr.Markdown("""
+                    In this space, I tried to get most out of Gradio an HF. So that this combination can be
+                    used not only for advanced ML models but also to demonstrate the topics regarding
+                    mathematical background of ML. The first topic is Linear Regression optimized with OLS 
+                    """)
+    with gr.Accordion("Model Card", open=False, elem_id="accord"):
+        gr.Markdown("""
+                    | Name | Objective | Metric | Solution |
+                    | -------- | ------- | -------- | -------- |
+                    | Linear regression | Ord. least squares (OLS) | Residual sum-of-squares (RSS) | Analytical |
+                    """)
+    with gr.Accordion("Math Background", open=False, elem_id="accord"):
+        with gr.Row():
+            with gr.Column(scale=1):
+                gr.Markdown("""
+                            We have a linear regression model in (1).  
+                            We want to minimize RSS (2).  
+                            We need the derivative of RSS(β) with respect to β to and set it zero.
+                            The resulting formula is given (3).  
+                            An example matrix represenation of the model y = Xβ is given (4).    
+                            """)
+            with gr.Column(scale=1):
+                img = gr.Image(label="Proof", value="img.png", elem_id="images")
+    with gr.Accordion("References", open=False, elem_id="accord"):
+        links = ("statproofbook.github.io/P/mlr-ols",
+                 "statproofbook.github.io/P/mlr-ols2",
+                 "towardsdatascience.com/building-linear-regression-least-squares-with-linear-algebra-2adf071dd5dd")
+        gr.Markdown("\n".join(f"{i}.[https://{l}](https://{l})  " for i, l in enumerate(links,1)))
+
+    plot_btn.click(fn=plot_data, inputs=data_frm, outputs=[data_plt,status_hlt])
+    regression_btn.click(fn=linear_regression_plot, inputs=[method_dd,data_frm], outputs=[data_plt,status_hlt])
+
+demo.launch()