def plot_fast_vs_slow():
data = load_iris()
_, axes = plt.subplots(nrows=2, figsize=(9,9))
for idx, fast in enumerate((False, True)):
title = "Fast Parallel Coordinates" if fast else "Standard Parallel Coordinates"
oz = ParallelCoordinates(ax=axes[idx], fast=fast, title=title)
oz.fit_transform(data.data, data.target)
oz.finalize()
plt.tight_layout()
plt.savefig("images/fast_vs_slow_parallel_coordinates.png")
def plot_fast_vs_slow():
data = load_iris()
_, axes = plt.subplots(nrows=2, figsize=(9,9))
for idx, fast in enumerate((False, True)):
title = "Fast Parallel Coordinates" if fast else "Standard Parallel Coordinates"
oz = ParallelCoordinates(ax=axes[idx], fast=fast, title=title)
oz.fit_transform(data.data, data.target)
oz.finalize()
plt.tight_layout()
plt.savefig("images/fast_vs_slow_parallel_coordinates.png")
plt.xlabel('number of components')
plt.ylabel('variance (%)')
plt.title(label + ": Explained Variance by Number of Components")
plt.savefig(path.join(PLOT_DIR, abbrev + "_pca_variance.png"), bbox_inches='tight')
plt.show()
plt.close()
# save as new set of features
pca = PCA(n_components=n_components, svd_solver='full', random_state=SEED)
start_time = time.perf_counter()
df = pd.DataFrame(pca.fit_transform(X))
run_time = time.perf_counter() - start_time
print(label + ": run time = " + str(run_time))
df.to_pickle(path.join(PKL_DIR, abbrev + "_pca.pickle"))
# parallel coordinates plot
visualizer = ParallelCoordinates(sample=0.2, shuffle=True, fast=True)
visualizer.fit_transform(df, y)
visualizer.ax.set_xticklabels(visualizer.ax.get_xticklabels(), rotation=45, horizontalalignment='right')
visualizer.finalize()
plt.savefig(path.join(PLOT_DIR, abbrev + "_pca_parallel.png"), bbox_inches='tight')
visualizer.show()
plt.close()
# output reconstruction error
recon_err = get_reconstruction_error_invertable(X, df, pca)
print(label + ": reconstruction error = " + str(recon_err))
# distribution of eigenvalues
print(label + ": eigenvalues?", pca.components_)