import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import seaborn as sns
import clusters
import plot
data = clusters.get_data()
num_clusters = 4
pipe = clusters.get_pipeline_kmeans(num_clusters)
pipe.fit(data)
_, _, data_pca = clusters.get_pca_data_kmeans(num_clusters)
data_with_clusters = data
data_with_clusters['predicted_cluster'] = pipe.predict(data)
mean_vals = data_with_clusters.groupby('predicted_cluster',
as_index=False).mean()
max_vals = data_with_clusters.groupby('predicted_cluster',
as_index=False).max()
min_vals = data_with_clusters.groupby('predicted_cluster',
as_index=False).min()
std_dev_vals = data_with_clusters.groupby('predicted_cluster',
as_index=False).std()
# print(min_vals.to_markdown())
# Finally we plot all of our data and make it look a bit pretty
plt.style.use("fivethirtyeight")
plt.figure(figsize=(8, 8))
color = cm.nipy_spectral(float(i) / n_clusters)
ax1.fill_betweenx(np.arange(y_lower, y_upper),
0,
ith_cluster_silhouette_values,
facecolor=color,
edgecolor=color,
alpha=0.7)
# Label the silhouette plots with their cluster numbers at the middle
ax1.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))
# Compute the new y_lower for next plot
y_lower = y_upper + 10 # 10 for the 0 samples
ax1.set_title("The silhouette plot for the various clusters.")
ax1.set_xlabel("The silhouette coefficient values")
ax1.set_ylabel("Cluster label")
# The vertical line for average silhouette score of all the values
ax1.axvline(x=silhouette_avg, color="red", linestyle="--")
ax1.set_yticks([]) # Clear the yaxis labels / ticks
ax1.set_xticks([-1, -0.8, -.6, -.4, -.2, 0, 0.2, 0.4, 0.6, 0.8, 1])
plt.show()
data = get_data()
plot_average_silhouette(data, 8)
plot_average_silhouette(data, 8, usePCA=False)