Create app.py

app.py

@@ -0,0 +1,102 @@
+import gradio as gr
+import numpy as np
+import time
+import matplotlib.pyplot as plt
+
+from sklearn.datasets import load_iris
+from sklearn.decomposition import PCA, IncrementalPCA
+
+
+theme = gr.themes.Monochrome(
+    primary_hue="indigo",
+    secondary_hue="blue",
+    neutral_hue="slate",
+)
+model_card = f"""
+## Description
+
+**Incremental principal component analysis (IPCA)** is a suitable alternative to **Principal component analysis (PCA)** when the dataset to be analyzed is too large to fit in memory. 
+**IPCA** generates a low-rank representation of the input data utilizing a fixed amount of memory that is not reliant on the number of input data samples. 
+
+In this demo, you can play around with different ``number of components`` and ``number of samples`` to explore the performance of IPCA and PCA, including a comparison of their respective outputs and running times.
+**Note**: Incremental PCA is comparatively slower to regular PCA, as it processes partial data sets sequentially.
+
+
+## Dataset
+
+Iris dataset
+"""
+iris = load_iris()
+X = iris.data
+y = iris.target
+
+def plot_pca(n_components, batch_size):
+    # Create linkage matrix and then plot the dendrogram
+    colors = ["navy", "turquoise", "darkorange"]
+
+    ipca = IncrementalPCA(n_components=n_components, batch_size=batch_size)
+    t1 = time.time()
+    X_ipca = ipca.fit_transform(X)
+    ipca_time = time.time() - t1
+
+    pca = PCA(n_components=n_components)
+    t2 = time.time()
+    X_pca = pca.fit_transform(X)
+    pca_time = time.time() - t2
+    
+    fig1, axes1 = plt.subplots()
+    for color, i, target_name in zip(colors, [0, 1, 2], iris.target_names):
+        axes1.scatter(
+            X_ipca[y == i, 0],
+            X_ipca[y == i, 1],
+            color=color,
+            lw=2,
+            label=target_name,
+            )
+    err = np.abs(np.abs(X_pca) - np.abs(X_ipca)).mean()
+    axes1.set_title(f"Incremental PCA of iris dataset")
+    axes1.axis([-4, 4, -1.5, 1.5])
+    axes1.legend(loc="best", shadow=False, scatterpoints=1)
+
+    fig2, axes2 = plt.subplots()
+    for color, i, target_name in zip(colors, [0, 1, 2], iris.target_names):
+        axes2.scatter(
+            X_pca[y == i, 0],
+            X_pca[y == i, 1],
+            color=color,
+            lw=2,
+            label=target_name,
+            )
+    axes2.set_title("PCA of iris dataset")
+    axes2.axis([-4, 4, -1.5, 1.5])
+    axes2.legend(loc="best", shadow=False, scatterpoints=1)
+
+    text = f"PCA runing time : {pca_time:.6f} seconds. Incremental PCA runing time : {ipca_time:.6f} seconds. Mean absolute unsigned error {err*100:.6f}%"
+        
+    return fig1, fig2, text
+
+
+
+with gr.Blocks(theme=theme) as demo:
+    gr.Markdown('''
+            <div>
+            <h1 style='text-align: center'>Incremental PCA</h1>
+            </div>
+        ''')
+    gr.Markdown(model_card)
+    gr.Markdown("Author: <a href=\"https://huggingface.co/vumichien\">Vu Minh Chien</a>. Based on the example from <a href=\"https://scikit-learn.org/stable/auto_examples/decomposition/plot_incremental_pca.html#sphx-glr-auto-examples-decomposition-plot-incremental-pca-py\">scikit-learn</a>")
+    n_components = gr.Slider(minimum=2, maximum=4, step=1, value=2, label="Number of components to keep")
+    batch_size = gr.Slider(minimum=10, maximum=50, step=10, value=10, label="The number of samples to use for each batch")
+
+    with gr.Row():
+        with gr.Column():
+            plot_1 = gr.Plot(label="Incremental PCA")
+        with gr.Column():
+            plot_2 = gr.Plot(label="PCA")
+    with gr.Row():
+        resutls = gr.Textbox(label="Results")
+
+    n_components.change(fn=plot_pca, inputs=[n_components, batch_size], outputs=[plot_1, plot_2, resutls])
+    batch_size.change(fn=plot_pca, inputs=[n_components, batch_size], outputs=[plot_1, plot_2, resutls])
+
+demo.launch()