sf_crime_5.py

sf_crime_5.py

train['IsOnBlock'] = train['Address'].str.contains('block', case=False)
train['IsAtIntersection'] = train['Address'].str.contains('/', case=False)

def clean_road(text):
    return re.sub(r"[0-9]+ [bB]lock of ", "", text)

def make_counts(values):
    counts = Counter()
    for value in values:
        cur_counts = list(map(clean_road, value.split(" / ")))
        counts.update(cur_counts)
    return counts

# compute road counts, in preparation of the log road probability feature
counts = make_counts(train["Address"])
common_roads = pd.Series(dict(counts.most_common(20)))

# have a look at the most common roads in the data
plt.figure(figsize=(10, 10))
with sns.axes_style("whitegrid"):
    ax = sns.barplot(
        (common_roads / common_roads.sum()) * 100,
        common_roads.index,
        orient='h',
        palette="Blues_r")

plt.title('Most Common Roads', fontdict={'fontsize': 16})
plt.xlabel('P(x)')

plt.show()