Cleaning up

app.py

@@ -36,9 +36,22 @@ target_names = iris.target_names
 
 
 def plot_lda_pca(n_samples = 50, n_features = 4):
+
+    '''
+    Function to plot LDA and PCA of Iris dataset
+    
+    Parameters
+    ----------
+    n_samples : int, optional
+        Number of samples to use from the dataset. The default is 50.
+    n_features : int, optional
+        Number of features to use from dataset. The default is 4.
+    
+    '''
     
     # print(f"all X is: {all_X}")
     
+    
     idx = np.random.randint(0, len(iris.data), n_samples)
     # sub-sample
     X = all_X[idx, :n_features]
@@ -85,25 +98,26 @@ def plot_lda_pca(n_samples = 50, n_features = 4):
 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 Factor Analysis (FA) for model selection by observing the likelihood of a held-out dataset with added noise <br>"
+    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>"
+    " LDA is a supervised method that tries to identify attributes that account for the most variance between classes using the known class labels.  <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>"
+    " The number of components is fixed to 2 for this 2-D visualisation and LDA requires the number of components to be the number of classes -1, which in this case is (3-1) = 2"
+    " The number of features (n_features) determine the number of features from the IRIS dataset to use for the model fitting.  <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** : 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>"
-               )
+    gr.Markdown(" **Dataset** : The Iris dataset represents 3 kind of Iris flowers (Setosa, Versicolour and Virginica) with 4 attributes or features: sepal length, sepal width, petal length and petal width. . <br>")
 
+    # get max possible samples and features
     max_samples = len(iris.data)
+    max_features = iris.data.shape[1]
     with gr.Row():
         n_samples = gr.Slider(value=100, minimum=10, maximum=max_samples, step=10, label="n_samples")
 
-        n_features = gr.Slider(value=2, minimum=2, maximum=4, step=1, label="n_features")
+        n_features = gr.Slider(value=2, minimum=2, maximum=max_features, step=1, label="n_features")
         
     btn = gr.Button(value="Run")
     btn.click(plot_lda_pca, inputs = [n_samples, n_features], outputs= gr.Plot(label='PCA vs LDA clustering') ) #