def predict(self, predictor, columns, data_dict, time_steps_back, lines_reservations=None):
"""
Prepares feature vector for prediction algorithms an generates prediction
:param predictor: sklearn predictor or other with simmilar interface
:param columns: List with names of columns that must be in feature vector
:param data_dict: Dictionary with time data containing columns names and default vaules
:param time_steps_back: Number of time steps for one input to prediction algorithm
:param lines_reservations: List with line reservations for predicted day generated by get_lines_usage_for_day method
:return: Vector with prediction for the day (288 items)
"""
lines_reserved_id = -1
org_ids = dict()
for org_id, column in enumerate(columns):
if column.startswith('reserved_'):
org_ids[column] = org_id
if column == 'lines_reserved':
lines_reserved_id = org_id
if lines_reservations is None:
lines_reservations = ['']*64
data = list()
for i in range(self.prediction_steps):
data.append([0]*len(columns))
for j, column in enumerate(columns):
if column in data_dict:
data[i][j] = data_dict[column]
slot_id = (data_dict['minute_of_day']-360)//15
if slot_id >= 0 and slot_id < 64:
org_list = lines_reservations[slot_id].split(',')[:-1]
for name in org_list:
feature_name = 'reserved_' + name
if feature_name in columns:
data[i][org_ids[feature_name]] += 1
elif 'reserved_other' in columns:
data[i][org_ids['reserved_other']] += 1
if lines_reserved_id >= 0:
data[i][lines_reserved_id] += 1
data_dict['minute'] += 5
data_dict['minute_of_day'] += 5
if data_dict['minute'] == 60:
data_dict['minute'] = 0
data_dict['hour'] += 1
df = pd.DataFrame(data, columns=columns)
day = Day('ts')
day.data = df
x, y = self.dh.get_feature_vectors_from_days([day], [], time_steps_back, 1, True)
return self.dh.predict_day_from_features(x, predictor, time_steps_back)
def prepare_days_data(self):
"""
Loads pickle with all Days
"""
if os.path.isfile(self.days_data_path):
with open(self.days_data_path, 'rb') as input_file:
self.days_train, self.days_test, self.days_valid = pickle.load(
input_file)
self.columns = self.days_train[0].data.columns
else:
if os.path.isfile(self.csv_path):
days_stats = [0, 0, 0, 0, 0, 0, 0]
print('Preparing days.pickle')
days_list = []
last_date = 'start'
day_start_id = 0
day_stop_id = 0
n_bad_days = 0
data_frame = pd.read_csv(self.csv_path)
for index, row in data_frame.iterrows():
if row['minute_of_day'] > 1320:
data_frame['pool'].iloc[index] = 0
new_date = data_frame['time'].iloc[index][:10]
if not last_date == new_date:
day_stop_id = index
if index > 0:
new_day = Day(last_date)
new_day.data = data_frame.iloc[
day_start_id:day_stop_id]
if day_stop_id - day_start_id == 288:
days_list.append(new_day)
days_stats[
data_frame['day_of_week'].iloc[index]] += 1
else:
if abs(day_stop_id - day_start_id - 288) < 15:
expected = 0
n_bad_days += 1
print(
'Error in day %s, length of day is %d'
% (last_date,
day_stop_id - day_start_id))
for value in list(
data_frame['minute_of_day'].
iloc[day_start_id:day_stop_id]):
if not value == expected:
print('Should be %d is %d' %
(expected, value))
expected = value
expected += 5
print('\n\n')
# TODO: Most of them have less than 10 missing values.
# If the missinga values are out of openning hours - fill with zeros and use
# Many other missing values can be filled in
# Also change of time from summer to winter makes 1 hour gap or duplicate hour
# Move this function to data preprocessing
last_date = data_frame['time'].iloc[index][:10]
day_start_id = index
Random(RANDOM_SEED).shuffle(days_list)
train_portion = 0.4
validation_portion = 0.2
n_days = len(days_list)
print('Generated %d days. (%d days removed)' %
(n_days, n_bad_days))
print('Number of days from Monday to Sunday', days_stats)
n_train_days = int(n_days * train_portion)
n_validation_days = int(n_days * validation_portion)
train_days = days_list[:n_train_days]
validation_days = days_list[n_train_days:n_train_days +
n_validation_days]
test_days = days_list[n_train_days + n_validation_days:]
with open(self.days_data_path, 'wb') as input_file:
pickle.dump([train_days, test_days, validation_days],
input_file)
else:
raise Exception(
'Missing days.pickle and dataset.csv.\nGenerate dataset.csv in preprocess_data.py first.'
)
