def draw_origin_paths():
rows = return_data_rows()
for data in rows:
one_taxi_polyline = data.polyline
points_list = []
for point in one_taxi_polyline:
points_list.append([point.lat, point.long])
plt.plot(*zip(*points_list), linewidth=0.5)
plt.title("Raw-paths")
# and finally save it with high resolution
plt.savefig(Config.assets_path + 'origin-paths.png', dpi=500)
def do_apriori(min_support):
transactions = []
result = return_data_rows()
for row in result:
one_trip_locations = []
for location in row.polyline:
x = str(location.lat)[:8] + "," + str(location.long)[:8]
one_trip_locations.append(x)
transactions.append(one_trip_locations)
start_time = datetime.now()
item_sets = list(
apriori(transactions, min_support=min_support / 10, min_confidence=1))
end_time = datetime.now()
diff = (end_time - start_time)
print(item_sets)
print("apriori longs : ", diff.total_seconds(), "seconds")
def do_eclat(min_support):
transactions = []
result = return_data_rows()
for row in result:
one_trip_locations = []
for location in row.polyline:
x = str(location.lat)[:8] + "," + str(location.long)[:8]
one_trip_locations.append(x)
numbers_tuple = tuple(one_trip_locations)
transactions.append(numbers_tuple)
start_time = datetime.now()
rules = eclat(transactions, supp=min_support * 10)
rules.sort(key=lambda x: x[1], reverse=True)
end_time = datetime.now()
print(rules)
diff = (end_time - start_time)
print("eclat longs : ", diff.total_seconds(), "seconds")
def do_fp_growth(min_support):
transactions = []
result = return_data_rows()
for row in result:
one_trip_locations = []
for location in row.polyline:
x = str(location.lat)[:8] + "," + str(location.long)[:8]
one_trip_locations.append(x)
numbers_tuple = tuple(one_trip_locations)
transactions.append(numbers_tuple)
min_support = min_support * len(transactions)
start_time = datetime.now()
itemset = find_frequent_itemsets(transactions, minimum_support=min_support)
end_time = datetime.now()
for item in itemset:
print(item)
diff = (end_time - start_time)
print("fp_growth longs : ", diff.total_seconds(), "seconds")
def check_jump_data():
result = return_data_rows()
miss_data = []
long_trip_dict = {}
all_distance = []
for row in result:
polyline_locations = row.polyline
for i in range(len(polyline_locations) - 1):
distance = calculate_distance(polyline_locations[i],
polyline_locations[i + 1])
distance = distance * 1000
all_distance.append(distance)
if distance > 417:
miss_data.append((row.trip_id, distance))
if row.trip_id in long_trip_dict:
long_trip_dict[
row.trip_id] = long_trip_dict[row.trip_id] + 1
else:
long_trip_dict[row.trip_id] = 1
sorted_long_trip_dict = sorted(long_trip_dict.items(),
key=operator.itemgetter(1))
from pylab import rcParams
rcParams['figure.figsize'] = 20, 5
key_list = []
value_list = []
for i in sorted_long_trip_dict:
key_list.append(i[0])
value_list.append(i[1])
objects = tuple(key_list)
y_pos = np.arange(len(objects))
performance = value_list
plt.bar(y_pos, performance, align='center', alpha=0.5, linewidth=0.5)
plt.xticks(y_pos)
plt.ylabel('Count of long distance')
plt.xlabel('Trip ID')
plt.title('long Distance between two locations')
plt.savefig('long_distance.png', dpi=500)
plt.show()
def main():
result = return_data_rows()
distance_list = []
hour_and_min = []
for row in result:
polyline_locations = row.polyline
for i in range(len(polyline_locations) - 1):
distance = calculate_distance(polyline_locations[i],
polyline_locations[i + 1])
distance = distance * 1000
distance_list.append(distance)
trip_datetime = datetime.fromtimestamp(row.timestamp)
hour_and_min.append(
int(str(trip_datetime.hour) + str(trip_datetime.minute)))
x = hour_and_min
print(hour_and_min)
y = distance_list
r = Regression
sum_x = r.find_sum(x, 1)
sum_y = r.find_sum(y, 1)
sum_x2 = r.find_sum(x, 2)
sum_xy = r.find_mul_sum(x, y)
res = []
res = r.solve_equ(sum_x, sum_x2, sum_y, sum_xy)
y_pred = r.predict(x, res)
plt.scatter(x, y, color='red')
plt.plot(x, y_pred, color='blue')
plt.title('Distance per day time Regression')
plt.xlabel('Time (from 00:00 to 24:00)')
plt.ylabel('Distance')
plt.show()