Duplicate from NTaylor/pca_vs_lda

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Pca Vs Lda
+emoji: 🐨
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+sdk_version: 3.27.0
+app_file: app.py
+pinned: false
+duplicated_from: NTaylor/pca_vs_lda
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,103 @@
+"""
+=======================================================
+Comparison of LDA and PCA 2D projection of Iris 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.
+
+Principal Component Analysis (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.
+
+Linear Discriminant Analysis (LDA) tries to identify attributes that
+account for the most variance *between classes*. In particular,
+LDA, in contrast to PCA, is a supervised method, using known class labels.
+
+"""
+
+import matplotlib.pyplot as plt
+import gradio as gr
+from sklearn import datasets
+from sklearn.decomposition import PCA
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
+
+# load data
+iris = datasets.load_iris()
+
+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():
+
+    # fig = plt.figure(1, facecolor="w", figsize=(5,5))
+    fig, axes = plt.subplots(2,1, sharey= False, sharex=False, figsize = (8,6))
+    colors = ["navy", "turquoise", "darkorange"]
+    lw = 2
+
+    for color, i, target_name in zip(colors, [0, 1, 2], target_names):
+        axes[0].scatter(
+            X_r[y == i, 0], X_r[y == i, 1], color=color, alpha=0.8, lw=lw, label=target_name
+        )
+    axes[0].legend(loc="lower right")
+    axes[0].set_title("PCA of IRIS dataset")    
+    for color, i, target_name in zip(colors, [0, 1, 2], target_names):
+        axes[1].scatter(
+            X_r2[y == i, 0], X_r2[y == i, 1], alpha=0.8, color=color, label=target_name
+        )
+    plt.legend(loc="best", shadow=False, scatterpoints=1)
+    axes[1].legend(loc="lower right")
+    axes[1].set_title("LDA of IRIS dataset")
+    plt.tight_layout()   
+
+
+    return fig
+
+
+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>"
+
+    " 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
+        
+    btn = gr.Button(value="Run")
+    btn.click(plot_lda_pca, outputs= gr.Plot(label='PCA vs LDA clustering') ) # 
+    
+
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+scikit-learn==1.2.2
+matplotlib==3.5.1
+numpy==1.21.6