Added n_samples and n_features as slider options

app.py

@@ -31,24 +31,53 @@ X = iris.data
 y = iris.target
 target_names = iris.target_names
 
-# fit PCA
-pca = PCA(n_components=2)
-X_r = pca.fit(X).transform(X)
-
-# fit LDA
-lda = LinearDiscriminantAnalysis(n_components=2)
-X_r2 = lda.fit(X, y).transform(X)
-
-# Percentage of variance explained for each components
-print(
-    "explained variance ratio (first two components): %s"
-    % str(pca.explained_variance_ratio_)
-)
-
-# save models using skop
-
+def plot_lda_pca(n_samples = 100,
+                 n_components=2,
+                 n_features=4):
+    
+    '''
+    Function to plot LDA and PCA clustering.
+    
+    Parameters
+    ----------
+    n_components : int, default=2
+        Number of components to keep.
 
-def plot_lda_pca():
+    n_features : int, default=5
+        Number of features to generate.
+    
+    Returns
+    -------
+    fig : matplotlib.pyplot.figure
+        Figure object.
+    '''
+    
+    
+    
+    # take sample of data
+    X = X[:n_samples, :n_features]
+    y = y[:n_samples]
+    
+    # fit PCA
+    pca = PCA(n_components=n_components)
+    X_r = pca.fit(X).transform(X)
+    print(f"shape of X_r: {X_r.shape}")
+    # fit LDA
+    lda = LinearDiscriminantAnalysis(n_components=n_components)
+    X_r2 = lda.fit(X, y).transform(X)
+    print(f"shape of X_r2: {X_r2.shape}")
+    # take first two components
+    X_r = X_r[:, :2]
+    X_r2 = X_r2[:, :2]
+    
+    print(f"shape of X_r after: {X_r.shape}")
+    print(f"shape of X_r2 after: {X_r2.shape}")
+    
+    # Percentage of variance explained for each components
+    print(
+        "explained variance ratio (first two components): %s"
+        % str(pca.explained_variance_ratio_)
+    )
 
     # fig = plt.figure(1, facecolor="w", figsize=(5,5))
     fig, axes = plt.subplots(2,1, sharey= False, sharex=False, figsize = (8,6))
@@ -77,27 +106,28 @@ def plot_lda_pca():
 title = "2-D projection of Iris dataset using LDA and PCA"
 with gr.Blocks(title=title) as demo:
     gr.Markdown(f"# {title}")
-    gr.Markdown(" This example shows how one can use Prinicipal Components Analysis (PCA) and Linear Discriminant Analysis (LDA) to cluster the Iris dataset based on provided features. <br>"
-    " PCA applied to this data identifies the combination of attributes (principal components, or directions in the feature space) that account for the most variance in the data. Here we plot the different samples on the 2 first principal components.  <br>"
-    "   <br>"
-
+    gr.Markdown(" This example shows how one can use Prinicipal Components Analysis (PCA) and Factor Analysis (FA) for model selection by observing the likelihood of a held-out dataset with added noise <br>"
+    " The number of samples (n_samples) will determine the number of data points to produce.  <br>"
+    " The number of components (n_components) will determine the number of components each method will fit to, and will affect the likelihood of the held-out set.  <br>"
+    " The number of features (n_components) determine the number of features the toy dataset X variable will have.  <br>"
     " For further details please see the sklearn docs:"    
     )
 
     gr.Markdown(" **[Demo is based on sklearn docs found here](https://scikit-learn.org/stable/auto_examples/decomposition/plot_pca_vs_lda.html#sphx-glr-auto-examples-decomposition-plot-pca-vs-lda-py)** <br>")
 
-    gr.Markdown(" **Dataset** : The Iris dataset represents 3 kind of Iris flowers (Setosa, Versicolour and Virginica) with 4 attributes: sepal length, sepal width, petal length and petal width. . <br>")
-
-    # with gr.Row():
-    #     n_samples = gr.Slider(value=100, minimum=10, maximum=1000, step=10, label="n_samples")
-    #     n_components = gr.Slider(value=2, minimum=1, maximum=20, step=1, label="n_components")
-    #     n_features = gr.Slider(value=5, minimum=5, maximum=25, step=1, label="n_features")
-        
-    
-      # options for n_components
+    gr.Markdown(" **Dataset** : A toy dataset with corrupted with homoscedastic noise (noise variance is the same for each feature) or heteroscedastic noise (noise variance is the different for each feature) . <br>")
+    gr.Markdown(" Different number of features and number of components affect how well the low rank space is recovered. <br>"
+                "  Larger Depth trying to overfit and learn even the finner details of the data.<br>"
+               )
+    # set max samples
+    max_samples = len(iris.data)
+    with gr.Row():        
+        n_samples = gr.Slider(value=100, minimum=2, maximum=max_samples, step=1, label="n_samples")
+        n_features = gr.Slider(value=4, minimum=2, maximum=4, step=1, label="n_features")
         
+
     btn = gr.Button(value="Run")
-    btn.click(plot_lda_pca, outputs= gr.Plot(label='PCA vs LDA clustering') ) # 
+    btn.click(plot_lda_pca,inputs= [n_samples, n_features], outputs= gr.Plot(label='PCA vs LDA clustering') ) # 
     
 
 demo.launch()