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 def plot_figure(N, u1, std1, u2, std2, 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. points_class1 = [stats.norm.rvs(loc=u1, scale = std1) for x in range(N)] points_class2 = [stats.norm.rvs(loc=u2, scale = std2) for x in range(N)] pd_class1 = pd.DataFrame({'Feature 1 (X)': points_class1, 'Label (Y)': np.repeat(0,len(points_class1))}) pd_class2 = pd.DataFrame({'Feature 1 (X)': points_class2, 'Label (Y)': np.repeat(1,len(points_class2))}) pd_all = pd.concat([pd_class1, pd_class2]).reset_index(drop=True) import numpy as np X_data= pd_all['Feature 1 (X)'].to_numpy().reshape((len(pd_all),1)) y_labels= pd_all['Label (Y)'] # define x, y limits x_min, x_max = X_data[:, 0].min() - 1, X_data[:, 0].max() + 1 y_min, y_max = 0-1, 1 + 1 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 = False , labelbottom = True, bottom = False) #reference = [stats.uniform.rvs(loc=1, scale = 1) for x in range(N)] pp.plot(points_class1, np.zeros_like(points_class1) + val, 'x', label = 'Class 1', markersize = 10) pp.plot(points_class2, np.zeros_like(points_class2) + val, 'o', label = 'Class 2', markersize = 10) if show_dist: x = np.arange(x_min, x_max, 0.01, dtype=np.float) # define range of x x, y, u, s = gaussian(x, 10000, np.mean(points_class1), np.std(points_class1) ) pp.plot(x, y) #pp.plot(x, y, label=r'$Gaussian (\mu=%.2f,\ \sigma=%.2f)$' % (u, s)) x = np.arange(x_min, x_max, 0.01, dtype=np.float) # define range of x x, y, u, s = gaussian(x, 10000, np.mean(points_class2), np.std(points_class2) ) pp.plot(x, y) #pp.plot(x, y, label=r'$Gaussian (\mu=%.2f,\ \sigma=%.2f)$' % (u, s)) ### 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']) xx, yy = np.meshgrid(np.linspace(x_min, x_max, 100), np.linspace(y_min, y_max, 100)) if classifier == 'LDA': from sklearn.discriminant_analysis import LinearDiscriminantAnalysis model_sk = LinearDiscriminantAnalysis() model_sk.fit(X_data,y_labels) zz = model_sk.predict(np.c_[xx.ravel()]) #Predictions for each point on meshgrid #zz = np.array( [model_sk.predict( [[xx,yy]])[0] for xx, yy in zip(np.ravel(X), np.ravel(Y)) ] ) #Reshaping the predicted class into the meshgrid shape Z = zz.reshape(xx.shape) pp.pcolormesh(xx, yy, Z, cmap=cmap_light, alpha=0.2) elif classifier == 'QDA': from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis model_sk = QuadraticDiscriminantAnalysis() model_sk.fit(X_data,y_labels) model_sk.fit(X_data,y_labels) zz = model_sk.predict(np.c_[xx.ravel()]) #Predictions for each point on meshgrid #zz = np.array( [model_sk.predict( [[xx,yy]])[0] for xx, yy in zip(np.ravel(X), np.ravel(Y)) ] ) #Reshaping the predicted class into the meshgrid shape Z = zz.reshape(xx.shape) print("Z: ",Z) pp.pcolormesh(xx, yy, 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) Z = model_sk.predict(np.c_[xx.ravel()]) Z = Z.reshape(xx.shape) pp.pcolormesh(xx, yy, Z, cmap=cmap_light, alpha=0.2) pp.xlim([x_min, x_max]) pp.ylim([y_min, y_max]) pp.xlabel("Feature 1 (X1)", size=20) pp.xticks(fontsize=20) pp.ylabel("Feature 2 (X2)") pp.legend(loc='upper right', borderpad=0, handletextpad=0, fontsize = 20) pp.savefig('plot.png') return 'plot.png', pd_all set_mean_class1 = gr.inputs.Slider(-20, 20, step=0.5, default=1, label = 'Mean (Class 1)') set_std_class1 = gr.inputs.Slider(0, 10, step=0.5, default=1.5, label = 'Standard Deviation (Class 1)') # 2. define mean and standard deviation for class 2 set_mean_class2 = gr.inputs.Slider(-20, 20, step=0.5, default=10, label = 'Mean (Class 2)') set_std_class2 = gr.inputs.Slider(0, 10, step=0.5, default=1.5, label = 'Standard Deviation (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') ### configure gradio, detailed can be found at https://www.gradio.app/docs/#i_slider interface = gr.Interface(fn=plot_figure, inputs=[set_number_points,set_mean_class1,set_std_class1,set_mean_class2,set_std_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 (Single feature)", description= "Click examples below for a quick demo", theme = 'huggingface', layout = 'vertical', live=True ) interface.launch(debug=True)