def analyse(path, filter_fn, field_name, print_csv=False):
data = load_data(path, filter_fn)
occurrences = data['days']
day_of_cycle = data['day_of_cycle']
weekdays = data['weekdays']
day_of_cycle_total = sum([day_of_cycle[x] for x in day_of_cycle])
if len(occurrences) == 0:
print "No tags found. Are you sure '%s' is the correct tag?" % tag
return
deltas = []
for d in xrange(len(occurrences)-1):
delta = occurrences[d+1] - occurrences[d]
if delta.days > 2:
deltas.append(delta.days)
if print_csv:
print "date,%s" % field_name
for d in date_range(occurrences[0], occurrences[len(occurrences)-1]):
if d in occurrences:
print str(d) + ",1"
else:
print str(d) + ",0"
return
print "==============="
print "Day of cycle distribution"
previous = None
for k in sorted(day_of_cycle.keys()):
if previous:
if k - previous > 1:
print ".\n."
previous = k
print ("Day %s:" % k).ljust(10), str(day_of_cycle[k]).ljust(4), round(day_of_cycle[k] / float(day_of_cycle_total), 2)
print "==============="
print "Weekday distribution"
for k in sorted(weekdays.keys()):
print weekday_from_int(k).ljust(5), weekdays[k]
print "==============="
print "Total amount of days with %s: " % field_name, len(occurrences)
print "Average amount of days between %s: " % field_name, average(deltas)
print "Std dev: ", std_dev(deltas)
print "Last day with %s: " % field_name, occurrences[len(occurrences)-1]
print "Days between today and last day with %s: " % field_name, (datetime.datetime.today().date() - occurrences[len(occurrences)-1].date()).days
print "==============="
if __name__ == "__main__":
filename = sys.argv[1]
num_trees = int(sys.argv[2])
data, attributes, target_attr = get_data(filename)
n = len(data)
accs = []
for i in range(5):
valid_data = data[int(float(n) / 5 * i):int(float(n) / 5 *
(i + 1))] #validation data
train_data = [d for d in data if not d in valid_data] #training data
labels = [d[target_attr] for d in valid_data]
trees = create_forest(data, attributes, target_attr, num_trees)
#classify
classes = []
for tree in trees:
classification = classify_decision_tree(tree, valid_data,
vote(labels))
classes.append(classification)
classification = [vote(c) for c in zip(*classes)]
count = 0
for x, y in zip(classification, labels):
if x == y:
count += 1
acc = float(count) / len(classification)
accs.append(acc)
print("accuracy: " + str(100 * acc) + "%")
print("standard deviation: " + str(std_dev(accs)))