Update app.py

app.py

@@ -0,0 +1,237 @@
+import gradio as gr
+import numpy as np
+import pandas as pd
+from matplotlib import pyplot as plt
+import matplotlib.colors as colors
+import itertools
+from scipy.stats import norm
+from scipy import stats
+from sklearn.naive_bayes import GaussianNB
+
+
+
+def gaussian(x, n, u, s):
+    #u = x.mean()
+    #s = x.std()
+
+    # divide [x.min(), x.max()] by n
+    x = np.linspace(x.min(), x.max(), n)
+
+    a = ((x - u) ** 2) / (2 * (s ** 2))
+    y = 1 / (s * np.sqrt(2 * np.pi)) * np.exp(-a)
+
+    return x, y, u, s
+    
+  import gradio as gr
+# 1. define mean and standard deviation for class 1
+
+set_fea1_mean_class1 = gr.inputs.Slider(0, 20, step=0.5, default=1, label = 'Feature_1 Mean (Class 1)')
+set_fea1_var_class1 = gr.inputs.Slider(0, 10, step=0.5, default=1.5, label = 'Feature_1 Variance (Class 1)')
+
+set_fea2_mean_class1 = gr.inputs.Slider(0, 20, step=0.5, default=2, label = 'Feature_2 Mean (Class 1)')
+set_fea2_var_class1 = gr.inputs.Slider(0, 10, step=0.5, default=1.5, label = 'Feature_2 Variance (Class 1)')
+
+set_fea_covariance_class1 = gr.inputs.Slider(0, 10, step=0.5, default=1.5, label = 'Feature_1_2 Co-Variance (Class 1)')
+
+# 2. define mean and standard deviation for class 2
+
+set_fea1_mean_class2 = gr.inputs.Slider(0, 20, step=0.5, default=5, label = 'Feature_1 Mean (Class 2)')
+set_fea1_var_class2 = gr.inputs.Slider(0, 10, step=0.5, default=1.5, label = 'Feature_1 Variance (Class 2)')
+
+set_fea2_mean_class2 = gr.inputs.Slider(0, 20, step=0.5, default=6, label = 'Feature_2 Mean (Class 2)')
+set_fea2_var_class2 = gr.inputs.Slider(0, 10, step=0.5, default=1.5, label = 'Feature_2 Variance (Class 2)')
+
+set_fea_covariance_class2 = gr.inputs.Slider(0, 10, step=0.5, default=1.5, label = 'Feature_1_2 Co-Variance (Class 2)')
+
+# 3. Define the number of data points 
+set_number_points = gr.inputs.Slider(10, 100, step=5, default=20, label = 'Number of samples in each class')
+
+# 4. show distribution or not
+set_show_dist = gr.inputs.Checkbox(label="Show data distribution")
+
+# 5. set classifier type
+set_classifier = gr.inputs.Dropdown(["None", "LDA", "QDA", "NaiveBayes"])
+
+# 6. define output imagem model
+set_out_plot_images = gr.outputs.Image(label="Data visualization")
+
+set_out_plot_table = gr.outputs.Dataframe(type='pandas', label ='Simulated Dataset')
+
+
+
+def plot_figure_twofeature(N, fea1_u1, fea1_var1, fea2_u1, fea2_var1, covariance1, fea1_u2, fea1_var2, fea2_u2, fea2_var2, covariance2, show_dist, classifier=None):
+  
+  
+  #N = 100
+  import numpy as np
+  import matplotlib.pyplot as pp
+  pp.style.use('default')
+  val = 0. # this is the value where you want the data to appear on the y-axis.
+
+  np.random.seed(seed = 3)
+
+  mu1 = [fea1_u1, fea2_u1]
+  sigma1 = [[np.sqrt(fea1_var1), np.sqrt(covariance1)], [np.sqrt(covariance1), np.sqrt(fea2_var1)]]
+  points_class1_fea1, points_class1_fea2 = np.random.multivariate_normal(mu1, sigma1, N).T
+
+  mu2 = [fea1_u2, fea2_u2]
+  sigma2 = [[np.sqrt(fea1_var2), np.sqrt(covariance2)], [np.sqrt(covariance2), np.sqrt(fea2_var2)]]
+  points_class2_fea1, points_class2_fea2 = np.random.multivariate_normal(mu2, sigma2, N).T
+
+  mu_list = [mu1,mu2]
+  sigma_list = [sigma1,sigma2]
+  color_list = ['darkblue','darkgreen']
+
+
+  pd_class1 = pd.DataFrame({'Feature 1 (X)': points_class1_fea1,'Feature 2 (X)': points_class1_fea2, 'Label (Y)': np.repeat(0,len(points_class1_fea1))})
+  pd_class2 = pd.DataFrame({'Feature 1 (X)': points_class2_fea1,'Feature 2 (X)': points_class2_fea2, 'Label (Y)': np.repeat(1,len(points_class2_fea1))})
+
+
+  pd_all = pd.concat([pd_class1, pd_class2]).reset_index(drop=True)
+
+  import numpy as np
+  #X_data= pd_all['Feature 1 (X)','Feature 2 (X)'].to_numpy().reshape((len(pd_all),2))
+  #y_labels= pd_all['Label (Y)']
+
+
+  #Setup X and y data
+  X_data = np.asarray(np.vstack((np.hstack((points_class1_fea1, points_class1_fea2)),np.hstack((points_class2_fea1, points_class2_fea2)))).T)
+  y_labels = np.hstack((np.zeros(N),np.ones(N)))
+
+  print("X_data: ",X_data.shape)
+
+  fig = pp.figure(figsize=(8, 6)) # figure size in inches
+  fig.subplots_adjust(left=0, right=1, bottom=0, top=1, hspace=0.3, wspace=0.05) 
+
+
+  #pp.tick_params(left = False, right = False , labelleft = True ,
+  #                labelbottom = True, bottom = False)
+
+  #reference = [stats.uniform.rvs(loc=1, scale = 1) for x in range(N)]
+  pp.plot(points_class1_fea1, points_class1_fea2 + val, 'x', label = 'Class 1', markersize = 10)
+  pp.plot(points_class2_fea1, points_class2_fea2 + val, 'o', label = 'Class 2', markersize = 10)
+
+
+
+  
+  # define x, y limits
+  #x_min, x_max = X_data[:, 0].min() - 1, X_data[:, 0].max() + 1
+  #y_min, y_max = X_data[:, 1].min() - 1, X_data[:, 1].max() + 1
+
+  x_min, x_max = -5, 15
+  y_min, y_max = -5, 15
+  X_grid, Y_grid = np.meshgrid(np.linspace(x_min, x_max, 100),
+                          np.linspace(y_min, y_max, 100))
+  
+
+  if show_dist:
+  
+      #%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%#
+
+      #Plotting the contours of the Gaussians on left hand side plot
+      for i in range(2):
+          zz = np.array(  [stats.multivariate_normal.pdf(np.array([xx,yy]), mean=mu_list[i], cov=sigma_list[i]) 
+                          for xx, yy in zip(np.ravel(X_grid), np.ravel(Y_grid)) ] )
+
+      #Reshaping the predicted class into the meshgrid shape
+          Z = zz.reshape(X_grid.shape[0])
+
+      #Plot the  contours
+          pp.contour( X_grid, Y_grid, Z, 5, alpha = .3, colors = color_list[i])
+
+
+  ### draw decision boundary on knn 
+
+  import numpy as np
+  from matplotlib import pyplot as plt
+  from sklearn import neighbors, datasets
+  from matplotlib.colors import ListedColormap
+
+  # Create color maps for 3-class classification problem, as with iris
+  cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA'])
+  cmap_bold = ListedColormap(['#FF0000', '#00FF00'])
+
+  # plt.scatter(x1, y1, marker='x', alpha = .7, label = 'Class 1', s = 50)
+  # plt.scatter(x2, y2, marker='o', alpha = .7, label = 'Class 2', s = 50)
+  # plt.xlabel("Feature 1 (X1)", size=20)
+  # plt.xticks(fontsize=20)
+  # plt.ylabel("Feature 2 (X2)", size=20)
+  # plt.yticks(fontsize=20)
+
+  if classifier == 'LDA':
+    from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
+    model_sk = LinearDiscriminantAnalysis()
+    model_sk.fit(X_data,y_labels)
+
+    X_grid, Y_grid = np.meshgrid(np.linspace(x_min, x_max, N),
+                          np.linspace(y_min, y_max, N))
+    #Predictions for each point on meshgrid
+    zz = np.array(  [model_sk.predict( [[xx,yy]])[0] for xx, yy in zip(np.ravel(X_grid), np.ravel(Y_grid)) ] )
+
+    Z = zz.reshape(X_grid.shape)
+
+    pp.pcolormesh(X_grid, Y_grid, Z, cmap=cmap_light, alpha=0.2)
+    #pp.contour( X_grid, Y_grid, Z, 1, alpha = .3, colors = ('red'))
+
+  elif classifier == 'QDA':
+    from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
+    model_sk = QuadraticDiscriminantAnalysis()
+    model_sk.fit(X_data,y_labels)
+
+    X_grid, Y_grid = np.meshgrid(np.linspace(x_min, x_max, N),
+                          np.linspace(y_min, y_max, N))
+    #Predictions for each point on meshgrid
+    zz = np.array(  [model_sk.predict( [[xx,yy]])[0] for xx, yy in zip(np.ravel(X_grid), np.ravel(Y_grid)) ] )
+
+    Z = zz.reshape(X_grid.shape)
+
+    pp.pcolormesh(X_grid, Y_grid, Z, cmap=cmap_light, alpha=0.2)
+
+  elif classifier == 'NaiveBayes':
+    from sklearn.naive_bayes import GaussianNB
+    model_sk = GaussianNB(priors = None)
+    model_sk.fit(X_data,y_labels)
+
+    X_grid, Y_grid = np.meshgrid(np.linspace(x_min, x_max, N),
+                          np.linspace(y_min, y_max, N))
+    #Predictions for each point on meshgrid
+    zz = np.array(  [model_sk.predict( [[xx,yy]])[0] for xx, yy in zip(np.ravel(X_grid), np.ravel(Y_grid)) ] )
+
+    Z = zz.reshape(X_grid.shape)
+
+    pp.pcolormesh(X_grid, Y_grid, Z, cmap=cmap_light, alpha=0.2)
+
+
+  #Reshaping the predicted class into the meshgrid shape
+
+  #Plot the  contours
+  
+
+
+  print(x_min, x_max)
+  print(y_min, y_max)
+  #pp.xlim([x_min-0.8*x_max, x_max+0.8*x_max])
+  #pp.ylim([y_min-0.8*y_max, y_max+0.8*y_max])
+  pp.xlim([x_min, x_max])
+  pp.ylim([y_min, y_max])
+  pp.xlabel("Feature 1 (X)", size=20)
+  pp.xticks(fontsize=20)
+  pp.yticks(fontsize=20)
+  pp.ylabel("Feature 2 (X)", size=20)
+  pp.legend(loc='upper right', borderpad=0, handletextpad=0, fontsize = 20)
+  pp.savefig('plot.png')
+
+  return 'plot.png', pd_all
+
+
+### configure gradio, detailed can be found at https://www.gradio.app/docs/#i_slider
+interface = gr.Interface(fn=plot_figure_twofeature, inputs=[set_number_points,set_fea1_mean_class1,set_fea1_var_class1,set_fea2_mean_class1,set_fea2_var_class1,set_fea_covariance_class1,set_fea1_mean_class2,set_fea1_var_class2,set_fea2_mean_class2,set_fea2_var_class2,set_fea_covariance_class2, set_show_dist, set_classifier], 
+                         outputs=[set_out_plot_images,set_out_plot_table],
+                         examples_per_page = 2,
+                         #examples = get_sample_data(10), 
+                         title="CSCI4750/5750 Demo: Web Application for Probabilistic Classifier (Two feature)", 
+                         description= "Click examples below for a quick demo",
+                         theme = 'huggingface',
+                         layout = 'vertical', live=True
+                         )
+interface.launch(debug=True)