from regression_utils import generate_nonlinear_synthetic_data_regression, generate_nonlinear_synthetic_sine_data_regression, generate_linear_synthetic_data_regression, \ plot_model_2d_regression, plot_model_3d_regression, plot_data_2d_regression, plot_data_3d_regression, \ grid_search_plot_models_regression, plot_coefficients_regression, \ plot_target_and_transformed_target_regression, rmse, regression_performance from feature_reduction_utils import feature_reduction_linear_pca, feature_reduction_kernel_pca, \ feature_reduction_tsne, feature_reduction_isomap from kernel_utils import GaussianFeatures, KernelTransformer from sklearn.model_selection import train_test_split from sklearn import metrics, decomposition, manifold from sklearn import tree, covariance, linear_model, ensemble, neighbors, svm, model_selection, feature_selection import pandas as pd import numpy as np import matplotlib.pyplot as plt X, y = generate_linear_synthetic_data_classification(n_samples=1000, n_features=3, n_redundant=0, n_classes=3, weights=[.3,.3,.4]) plot_data_3d(X) X_lpca = feature_reduction_linear_pca(X, 2) plot_data_2d(X_lpca, new_window=True) X_kpca = feature_reduction_kernel_pca(X, 2) plot_data_2d(X_kpca, new_window=True) X_tsne = feature_reduction_tsne(X, 2) plot_data_2d(X_tsne, new_window=True) X_isomap = feature_reduction_isomap(X, 2) plot_data_2d(X_isomap, new_window=True) X, y = generate_nonlinear_synthetic_data_classification2(n_samples=1000) plot_data_2d(X) X_lpca = feature_reduction_linear_pca(X, 2) plot_data_2d(X_lpca, new_window=True) X_kpca = feature_reduction_kernel_pca(X, 2, 'rbf', 15) plot_data_2d(X_kpca, new_window=True)
import sys path = 'J:/utils' sys.path.append(path) import common_utils as utils import tsne_utils as tutils import classification_utils as cutils import clustering_utils as cl_utils import pandas as pd #tsne effect on non-linearly related data X, y = cutils.generate_nonlinear_synthetic_data_classification2(n_samples=1000) X = pd.DataFrame(X, columns=['X1', 'X2']) utils.plot_data_2d(X) tutils.plot_tsne_result(X, y, 2) #tsne effect on clustered data X, y = cl_utils.generate_synthetic_data_3d_clusters(1000, 7, 0.01) X = pd.DataFrame(X, columns=['X1', 'X2', 'X3']) utils.plot_data_3d(X) tutils.plot_tsne_result(X, y, 2) #tsne effect on linearly related data(2 redundant featues) X, y = cutils.generate_linear_synthetic_data_classification(n_samples=1000, n_features=3, n_redundant=2, n_classes=2, weights=[.5,.5]) X = pd.DataFrame(X, columns=['X1', 'X2', 'X3']) utils.plot_data_3d(X) tutils.plot_tsne_result(X, y, 2)