def predict_values(model, type, date, training_data_length=14, days_to_predict=25, window=24):
training_data_length, days_to_predict = int(training_data_length), int(days_to_predict)
modelclass = get_model(model)
cc = CrashCounts(type, window)
x, original = cc.crash_counts()
date = datetime.strptime(date, "%Y%m%d")
bucket = int(buckify(window, date))
date = x.index(bucket)
x = []
predicted_values = []
actual_values = []
residuals = []
for i in xrange(1, days_to_predict):
counts = original[date-training_data_length-i:date-i]
model = modelclass(counts)
predicted = model.predict_next()
predicted_values.append(predicted)
actual_values.append(original[-i])
x.append(len(original) - i)
residuals.append(abs((predicted - original[-i]) / original[-i] * 100))
plt.plot(x, actual_values)
plt.plot(x, predicted_values)
plt.legend(("Actual", "Predicted"))
plt.ylim(0, 1.2 * np.max(predicted_values + actual_values))
elementary_stats(residuals)
plt.show()
def crashes_time_series(type="global", start="", end="", hours=24, *args):
start, end = parse_start_end(start, end)
hours = int(hours)
cc = CrashCounts(type, hours)
t, counts = cc.crash_counts(start, end)
elementary_stats(counts)
plt.title("{} crashes from {} to {} (bin={} hours)".format(type, start, end, hours))
plt.xlabel("Time")
plt.ylabel("Crashes")
plt.xlim(min(t), max(t))
plt.ylim(0, max(counts) * 1.2)
plt.grid(True)
plt.plot(t, counts)
plt.show()