sf_crime_6.py

sf_crime_6.py

# finalize the log road probability feature
pd_counts = pd.Series(counts)
log_probas = np.log(pd_counts / pd_counts.sum())

# have a look at the distribution of log road probabilities in the data
plt.figure(figsize=(10, 10))
sns.displot(log_probas.values)
plt.xlabel('ln(P(road))')
plt.ylabel('P(x)')
_ = plt.title("Distribution of Log Probas for Street Occurrence", fontdict={'fontsize': 16})