def pcoords(X, y, outpath, **kwargs):
# Create a new figure and axes
_, ax = plt.subplots()
# Create the visualizer
visualizer = ParallelCoordinates(ax=ax, **kwargs)
visualizer.fit_transform(X, y)
# Save to disk
visualizer.poof(outpath=outpath)
def pcoords(X, y, outpath, **kwargs):
# Create a new figure and axes
_, ax = plt.subplots()
# Create the visualizer
visualizer = ParallelCoordinates(ax=ax, **kwargs)
visualizer.fit_transform(X, y)
# Save to disk
visualizer.poof(outpath=outpath)
def pcoords_time(X, y, fast=True):
_, ax = plt.subplots()
oz = ParallelCoordinates(fast=fast, ax=ax)
start = time.time()
oz.fit_transform(X, y)
delta = time.time() - start
plt.cla() # clear current axis
plt.clf() # clear current figure
plt.close("all") # close all existing plots
return delta
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 pcoords_time(X, y, fast=True):
_, ax = plt.subplots()
oz = ParallelCoordinates(fast=fast, ax=ax)
start = time.time()
oz.fit_transform(X, y)
delta = time.time() - start
plt.cla() # clear current axis
plt.clf() # clear current figure
plt.close("all") # close all existing plots
return delta
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")
X, y = tf.create_X_y()
mask = IsolationForest(contamination=0.15).fit_predict(X[column].to_frame(),
y) == 1
new_X = X[mask]
new_y = y[mask]
X_scaled = StandardScaler().fit_transform(new_X)
target_names = ['f', 's']
visualizer = ParallelCoordinates(classes=target_names,
features=list(X.columns),
sample=0.5,
shuffle=True)
visualizer.fit_transform(X_scaled, new_y)
visualizer.show()
# %%
from sklearn.manifold import TSNE
from sklearn.decomposition import PCA
X, y = tf.cats_to_one_hot(columns=[]).create_X_y()
X_scaled = StandardScaler().fit_transform(X)
X = X.values
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X_scaled)
def pcoords():
X, y = load_occupancy()
oz = ParallelCoordinates(sample=0.05, shuffle=True, ax=newfig())
oz.fit_transform(X, y)
savefig(oz, "parallel_coordinates")
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_)
sns.set(style="ticks")
grid = sns.pairplot(df, hue="cluster", vars=feature_names)
plt.subplots_adjust(top=0.96)
grid.fig.suptitle(label + ": K-means k=" + str(best_k))
plt.savefig(path.join(PLOT_DIR, abbrev + "_em_scatter.png"),
bbox_inches='tight')
plt.show()
plt.close()
# parallel coordinates plot
print("# Parallel Coordinates Plot for " + label)
visualizer = ParallelCoordinates(features=feature_names,
sample=0.1,
shuffle=True,
fast=True)
visualizer.fit_transform(X, y_pred)
visualizer.ax.set_xticklabels(visualizer.ax.get_xticklabels(),
rotation=45,
horizontalalignment='right')
visualizer.finalize()
plt.savefig(path.join(PLOT_DIR, abbrev + "_em_parallel.png"),
bbox_inches='tight')
visualizer.show()
plt.close()
# compare with ground truth (classes)
print(label + ": Homogeneity Score = " +
str(metrics.homogeneity_score(y, y_pred)))
print(label + ": V Measure Score = " +
str(metrics.v_measure_score(y, y_pred)))
print(label + ": Mutual Info Score = " +