Update app.py

app.py

@@ -14,7 +14,7 @@ def cal_mse(X,y,b,w):
   mse = np.mean((y_predict-y)**2)
   return mse
 
-def gradient_descent(n_samples=100, intercept=4, slope=3, intercept_random=4, slope_random=3, gradient_descent='False', gradient_descent_type = 'Batch GradientDescent' , learning_rate= 0.01, iteration=100):
+def gradient_descent(n_samples=100, intercept=4, slope=3, intercept_random=4, slope_random=3, gradient_descent='False', gradient_descent_type = 'Batch GradientDescent' , learning_rate= 0.01, iteration=100, mini_batchsize = 32):
   ### (1) generate simulated data points
   X = 2 * np.random.rand(n_samples, 1)
   y = intercept + slope * X + np.random.randn(n_samples, 1)
@@ -105,7 +105,7 @@ def gradient_descent(n_samples=100, intercept=4, slope=3, intercept_random=4, sl
 
           train_mse = []
           # Iterations
-          minibatch_size = 32
+          minibatch_size = mini_batchsize
           for i in range(iteration):
               # shuffle dataset
               shuffled_indices = np.random.permutation(len(X))
@@ -227,8 +227,11 @@ input_gradients = gr.inputs.Checkbox(label="Apply Gradient Descent")
 #input_gradients_type = gr.inputs.CheckboxGroup(['Batch GradientDescient', 'Stochastic GradientDescent', 'Mini-Batch GradientDescent'],label="Type of Gradient Descent")
 input_gradients_type = gr.inputs.Dropdown(['Batch GradientDescent', 'Stochastic GradientDescent', 'Mini-Batch GradientDescent'],label="Type of Gradient Descent")
 
+
+input_batchsize = gr.inputs.Slider(1, 64, step=1, default=100, label='Batch size for Mini-BatchGD')
+
 input_learningrate = gr.inputs.Slider(0,2, step=0.0001, default=0.001, label='Learning Rate')
-input_interation = gr.inputs.Slider(1, 1000, step=2, default=100, label='Iteration')
+input_iteration = gr.inputs.Slider(1, 1000, step=2, default=100, label='Iteration')
 
 
 #### Define output component
@@ -237,7 +240,7 @@ output_plot1 = gr.outputs.Image(label="Regression plot")
 
 ### configure gradio, detailed can be found at https://www.gradio.app/docs/#i_slider
 interface = gr.Interface(fn=gradient_descent, 
-                         inputs=[input_sample, input_intercept, input_slope, input_intercept_random, input_slope_random, input_gradients, input_gradients_type, input_learningrate, input_interation], 
+                         inputs=[input_sample, input_intercept, input_slope, input_intercept_random, input_slope_random, input_gradients, input_gradients_type, input_learningrate, input_iteration, input_batchsize], 
                          outputs=[output_plot1],
                          examples_per_page = 2,
                          #examples = [[4, 3, -7, -5, True, 0.0001, 100], [1, 2, -7, -8, False, 0.0001, 100]],