Teager Target Release

Announcements
2

Target heatmap

heatmap
heatmap1920×1920 493 KB

Target clustermap

cluster
cluster3590×3590 302 KB 

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

targets = ['target_nomi_v4_20', 'target_nomi_v4_60', 'target_tyler_v4_20', 'target_tyler_v4_60', 'target_victor_v4_20', 'target_victor_v4_60', 'target_ralph_v4_20', 'target_ralph_v4_60', 'target_waldo_v4_20', 'target_waldo_v4_60', 'target_jerome_v4_20', 'target_jerome_v4_60', 'target_janet_v4_20', 'target_janet_v4_60', 'target_ben_v4_20', 'target_ben_v4_60', 'target_alan_v4_20', 'target_alan_v4_60', 'target_paul_v4_20', 'target_paul_v4_60', 'target_george_v4_20', 'target_george_v4_60', 'target_william_v4_20', 'target_william_v4_60', 'target_arthur_v4_20', 'target_arthur_v4_60', 'target_thomas_v4_20', 'target_thomas_v4_60', 'target_cyrus_v4_20', 'target_cyrus_v4_60', 'target_caroline_v4_20', 'target_caroline_v4_60', 'target_sam_v4_20', 'target_sam_v4_60', 'target_xerxes_v4_20', 'target_xerxes_v4_60', 'target_alpha_v4_20', 'target_alpha_v4_60', 'target_bravo_v4_20', 'target_bravo_v4_60', 'target_charlie_v4_20', 'target_charlie_v4_60', 'target_delta_v4_20', 'target_delta_v4_60', 'target_echo_v4_20', 'target_echo_v4_60', 'target_jeremy_v4_20', 'target_jeremy_v4_60', 'target_teager_v4_20', 'target_teager_v4_60', 'target_agnes_v4_20', 'target_agnes_v4_60', 'target_claudia_v4_20', 'target_claudia_v4_60', 'target_rowan_v4_20', 'target_rowan_v4_60']

# analyse the validation data, but we could do the same on the training data
df = pd.read_parquet('v4.2/validation_int8.parquet', columns=targets + ['era'])

# compute the mean of the era correlation of every target with any other target
corr = df.groupby('era').corr(method='spearman').mean(axis=0, level=1)

# arrange the order of the columns and rows (for visualization) so that they
# are sorted by correlation with the target 'target_cyrus_v4_20' 
corr = corr.sort_values(
    'target_cyrus_v4_20',
    axis=0,
    ascending=False).sort_values(
        'target_cyrus_v4_20',
        axis=1,
    ascending=False)


plt.rcParams["figure.figsize"] = [24,24] # default is [6.4, 4.8]

ax = sns.heatmap(corr, annot=True)
ax.get_figure().savefig('heatmap.png')

sns.clustermap(corr, figsize=(36,36)).savefig('cluster.png')
5 Likes