def evaluate(p_t, p_yt_co_occur):
p_yt = norm(p_yt_co_occur)
p_tx = membership_probability(p_t, p_yt, beta, p_x, p_yx)
fe = get_free_energy(bp_x.value, p_tx, p_yx, p_t, p_yt, beta)
free_energy.append(fe)
assigns = join_assigns(hardcluster(p_tx), assigns)
entropy.append(compute_entropy(assigns))
def split_entropy(init_beta, converge_dist, split_dist, numOfX, \
p_x, p_yx, p_yx_co_occur, trials = 10):
entropy = []
traces = ['' for k in range(numOfX)]
loop = 0
while loop < trials:
loop = loop + 1
log.info("Loop %d" % loop)
init_p_tx, assignments = hartigan_twoCentroids(p_x, p_yx, numOfX)
beta, p_tx = search_beta(init_p_tx, init_beta, converge_dist, split_dist, p_x, p_yx, p_yx_co_occur)
for k, c in zip(range(numOfX), np.argmax(p_tx, axis=1)):
traces[k] = traces[k] + "(%d)" % c
entropy.append(compute_entropy(traces))
return traces, entropy
y = df_results["Best model ROC"]
y = y.sample(frac=1)
entropies = []
#Compute Shanon's entropy
for i in range(len(y)): #0,1,...,201
pd_series = pd.Series(y[:i + 1])
count = pd_series.value_counts()
probabilities = count / (i + 1)
entropy = []
for prob in probabilities:
entropy.append(prob * log2(prob))
entropies.append(-sum(entropy))
# Plot the entropy vs. the number of training datasets
training_datasets = list(range(1, 203))
plt.figure(dpi=1200)
plt.xlabel('Number of training datasets', fontsize=16)
plt.ylabel("Shannon's entropy [bits]", fontsize=16)
plt.yticks([0, 1, 2, 3, 4], [0, 1, 2, 3, 4], fontsize=14)
plt.ylim(0, 3.5)
plt.xticks(fontsize=14)
plt.title("Entropy vs. Number of training datasets",
fontsize=16,
fontweight='bold')