#data_2 = bm.read_data(SECOND_FILE)
#data_2['Scaled_2'], sc = bm.scale_data(data_2, sc)
#data_2.drop(['Speed'], axis = 'columns', inplace = True)
#data_3 = bm.read_data(THIRD_FILE)
#data_3['Scaled_3'], sc = bm.scale_data(data_3, sc)
#data_3.drop(['Speed'], axis = 'columns', inplace = True)
#data_2 = bm.merge_two_data(data_2, data_3)
#data = bm.merge_two_data(data_2, data)
#adding more prev data
data_prev = data.shift(7 * 24 * 12 - int(TIME_DIFFERENCE / SAMPLE_FREQUENCY))
#data_prev_2 = data.shift(2*7*24*12)
#data_prev = bm.merge_two_data(data_prev_2, data_prev)
data = bm.merge_two_data(data_prev, data)
#channge missing values 0 to NaN
data.replace(0, np.nan, inplace=True)
#add one hots to data
data = bm.join_weekday_one_hot(data)
data = bm.join_daypart_one_hot(data)
#data = bm.join_minute_one_hot(data)
#Prepare the sets
features = len(data.columns)
x_features = features * TIME_STEP
reframed = bm.series_to_supervised(data, TIME_INTERVAL, TIME_DIFFERENCE,
SAMPLE_FREQUENCY)
#data = pd.concat([bm.read_data("preprocessed_471_2016.csv"), data])
data['Scaled'], sc = bm.scale_data(data)
#drop the speed column which includes real speed values (scaled values will be used instead)
data.drop(['Speed'], axis='columns', inplace=True)
#Nerging another sensor data to main one
#data_2 = bm.read_data("preprocessed_470.csv")
#data_2['Scaled_2'], sc = bm.scale_data(data_2, sc)
#data_2.drop(['Speed'], axis = 'columns', inplace = True)
#data = bm.merge_two_data(data_2, data)
#adding more prev data
data_prev = data.shift(7 * 24 * 12)
data_prev_2 = data.shift(2 * 7 * 24 * 12)
data_prev = bm.merge_two_data(data_prev_2, data_prev)
data = bm.merge_two_data(data_prev, data)
#channge missing values 0 to NaN
data.replace(0, np.nan, inplace=True)
#add one hots to data
data = bm.join_weekday_one_hot(data)
data = bm.join_daypart_one_hot(data)
#data = bm.join_minute_one_hot(data)
#Prepare the sets
features = len(data.columns)
x_features = features * TIME_STEP
reframed = bm.series_to_supervised(data, TIME_INTERVAL, TIME_DIFFERENCE,
data = bm.read_data(FILE_NAME)
#pd.concat([bm.read_data("preprocessed_471_2016.csv"), data])
data['Scaled'], sc = bm.scale_data(data)
#drop the speed column which includes real speed values (scaled values will be used instead)
data.drop(['Speed'], axis='columns', inplace=True)
#Nerging another sensor data to main one
data_2 = bm.read_data(SECOND_FILE)
data_2['Scaled_2'], sc = bm.scale_data(data_2, sc)
data_2.drop(['Speed'], axis = 'columns', inplace = True)
data_3 = bm.read_data(THIRD_FILE)
data_3['Scaled_3'], sc = bm.scale_data(data_3, sc)
data_3.drop(['Speed'], axis = 'columns', inplace = True)
data_2 = bm.merge_two_data(data_2, data_3)
data = bm.merge_two_data(data_2, data)
#adding more prev data
data_prev = data.shift(7*24*12)
#data_prev_2 = data.shift(2*7*24*12)
#data_prev = bm.merge_two_data(data_prev_2, data_prev)
data = bm.merge_two_data(data_prev, data)
#channge missing values 0 to NaN
data.replace(0, np.nan, inplace = True)
#add one hots to data
data = bm.join_weekday_one_hot(data)
data = bm.join_daypart_one_hot(data)
est = np.mean(reframed.values[:, :-1], axis=1)
result = reframed.values[:, -1]
mape = bm.mean_absolute_percentage_error(result, est)
mapes[file_name] = mape
mapes_20 = pd.DataFrame.from_dict(data=mapes,
orient='index',
columns=['mape_20'])
mapes = {}
for file_name in FILES.keys():
time_interval = 30
data = bm.read_data(FILES[file_name])
data['Scaled'], sc = bm.scale_data(data)
data.drop(['Speed'], axis='columns', inplace=True)
data.replace(0, np.nan, inplace=True)
reframed = bm.series_to_supervised(data, time_interval, 7 * 24 * 60, 5)
reframed = reframed[reframed.index.month == 5]
est = np.mean(reframed.values[:, :-1], axis=1)
result = reframed.values[:, -1]
mape = bm.mean_absolute_percentage_error(result, est)
mapes[file_name] = mape
mapes_30 = pd.DataFrame.from_dict(data=mapes,
orient='index',
columns=['mape_30'])
mapes = bm.merge_two_data(mapes_20, mapes_30)
mapes.to_csv("mapes.csv")
