Update app.py

app.py

@@ -3,19 +3,41 @@ import matplotlib as mpl
 import matplotlib.pyplot as plt
 import pandas as pd
 import numpy as np
-import time
-#mport tensorflow as tf
-#from sklearn.metrics import accuracy_score
-#from sklearn.neighbors import KNeighborsClassifier
+import gradio as gr
+import tensorflow as tf
+from sklearn.metrics import accuracy_score
+from sklearn.neighbors import KNeighborsClassifier
 
 #step 1
-#(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
+(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
 
-input_module1 = gr.inputs.Image(label = "test_image")
+input_module1 = gr.inputs.Image(label = "test_image", image_mode='L', shape = (28,28))
 
 input_module2 = gr.inputs.Slider(1, 10, step=1, label = "k")
 
-output_module1 = gr.outputs.Label(label = "Predicted Digit")
+output_module1 = gr.outputs.Textbox(label = "Predicted Digit")
 
 output_module2 = gr.outputs.Image(label = "Predicted Probability per class")
 
+def image_classification(input1, input2):
+    print(input1.shape)
+    print(input2)
+
+    image = input1.reshape(1, 28 *28)
+    X_train = x_train.reshape(60000, 28*28)
+    X_test = x_test.reshape(10000, 28*28)
+   
+    kNN_classifier = KNeighborsClassifier(n_neighbors=input2)
+    kNN_classifier.fit(X_train, y_train)
+    
+    y_test_predicted_label = kNN_classifier.predict(image)
+
+    output1 = y_test_predicted_label# text output example
+    output2 = np.random.rand(2,2) # image-like array output example
+    return output1,output2
+
+# Step 6.4: Put all three component together into the gradio's interface function 
+gr.Interface(fn=image_classification, 
+             inputs=[input_module1, input_module2], 
+             outputs=[output_module1, output_module2]
+            ).launch(debug = True)