def test_load_beliefs(csv_file):
"""Test loading BeliefsDataFrame to csv.
The saved file does not contain the sensor information, and the sources are saved by their name.
Therefore, we test the following functionality:
- The user should specify the sensor upon loading
- The user should be warned that the loaded sources are not of type BeliefSource.
- The user should have the possibility to look up the saved source names by passing a list of sources.
"""
# Load beliefs with tb.read_csv
df = pd.read_csv("test.csv")
with pytest.warns(UserWarning, match="type other than BeliefSource"):
df = tb.BeliefsDataFrame(df, sensor=tb.Sensor("Sensor Y"))
assert df.sensor.name == "Sensor Y"
# No lookup should issue warning
with pytest.warns(UserWarning, match="type other than BeliefSource"):
df = tb.read_csv("test.csv", sensor=tb.Sensor("Sensor Y"))
assert all(
c != tb.BeliefSource for c in df.index.get_level_values("source").map(type)
)
# This lookup should fail
with pytest.raises(ValueError, match="not in list"):
tb.read_csv(
"test.csv",
sensor=tb.Sensor("Sensor Y"),
look_up_sources=[tb.BeliefSource(name="Source X")],
)
# This lookup should succeed
source_a, source_b = tb.BeliefSource("Source A"), tb.BeliefSource("Source B")
df = tb.read_csv(
"test.csv", sensor=tb.Sensor("Sensor Y"), look_up_sources=[source_a, source_b]
)
assert df.sensor.name == "Sensor Y"
assert source_a in df.index.get_level_values("source")
assert source_b in df.index.get_level_values("source")
assert isinstance(df.index.get_level_values("event_start")[0], datetime)
assert isinstance(df.index.get_level_values("belief_time")[0], datetime)
def csv_as_belief(csv_in,tz_hour_difference,n_events = None):
sensor_descriptions = (
("Temperature", "°C"),
)
# Create source and sensors
source_a = tb.BeliefSource(name="KNMI")
sensors = (tb.Sensor(name=descr[0], unit=descr[1], event_resolution=timedelta(minutes=15)) for descr in sensor_descriptions)
# Create BeliefsDataFrame
for sensor in sensors:
blfs = read_beliefs_from_csv(sensor,csv_in, source=source_a, tz_hour_difference=tz_hour_difference, n_events=n_events)
df = tb.BeliefsDataFrame(sensor=sensor, beliefs=blfs).sort_index()
#df['2015-05-16 09:14:01+00
return df
def make_df(n_events = 100, n_horizons = 169, tz_hour_difference=-9, event_resolution=timedelta(hours=1)):
"""
Returns DataFrame in which n events and n horizons are stored
@param n_events: int,number of events in DataFrame
@param n_horizons: int,number of horizons in DataFrame
@param tz_hour_difference: float,time difference
@param event_resolution: timedelta object,event resolution
"""
sensor_descriptions = (("Temperature", "°C"),)
source = tb.BeliefSource(name="Random forest")
sensors = (tb.Sensor(name=descr[0], unit=descr[1], event_resolution=event_resolution) for descr in sensor_descriptions)
blfs=[]
for sensor in sensors:
blfs += read_beliefs_from_csv(sensor, source=source, cp=0.05, event_resolution=event_resolution, tz_hour_difference=tz_hour_difference)
blfs += read_beliefs_from_csv(sensor, source=source, cp=0.5, event_resolution=event_resolution, tz_hour_difference=tz_hour_difference)
blfs += read_beliefs_from_csv(sensor, source=source, cp=0.95, event_resolution=event_resolution, tz_hour_difference=tz_hour_difference)
bdf = tb.BeliefsDataFrame(sensor=sensor, beliefs=blfs).sort_index()
return bdf
def csv_as_belief(csv_in, tz_hour_difference, n_events=None):
# Uncomment desired forecasting data one at a time
sensor_descriptions = (
# ("Solar irradiation", "kW/m²"),
# ("Solar power", "kW"),
# ("Wind speed", "m/s"),
# ("Wind power", "MW"),
("Temperature", "°C"), )
# Create source and sensors
source_a = tb.BeliefSource(name="KNMI")
sensors = (tb.Sensor(name=descr[0],
unit=descr[1],
event_resolution=timedelta(minutes=15))
for descr in sensor_descriptions)
# Create BeliefsDataFrame
for sensor in sensors:
blfs = read_beliefs_from_csv(sensor,
csv_in,
source=source_a,
tz_hour_difference=tz_hour_difference,
n_events=n_events)
df = tb.BeliefsDataFrame(sensor=sensor, beliefs=blfs).sort_index()
return df
assert beliefs.index.tzinfo == pytz.utc
# Construct the BeliefsDataFrame by looping over the belief horizons
blfs = load_time_series(
beliefs[sensor.name.replace(' ', '_').lower()],
sensor=sensor,
source=source,
belief_horizon=timedelta(hours=0),
cumulative_probability=0.5) # load the observations (keep cp=0.5)
return blfs
# Create source and sensors
source_a = tb.BeliefSource(name="KNMI")
sensors = (tb.Sensor(name=descr[0],
unit=descr[1],
event_resolution=timedelta(minutes=15))
for descr in sensor_descriptions)
# Create BeliefsDataFrame
for sensor in sensors:
blfs = read_beliefs_from_csv(sensor,
source=source_a,
tz_hour_difference=tz_hour_difference,
n_events=n_events)
df = tb.BeliefsDataFrame(sensor=sensor, beliefs=blfs).sort_index()
#print(df)
df.keys()
#df['2015-05-16 09:14:01+00:00']
import os
from datetime import timedelta
from timely_beliefs.examples.beliefs_data_frames import sixteen_probabilistic_beliefs
import timely_beliefs as tb
example_df = sixteen_probabilistic_beliefs()
temperature_df = tb.read_csv(
os.path.dirname(os.path.abspath(__file__)) + "/temperature.csv",
sensor=tb.Sensor("Thermometer A",
unit="°C",
event_resolution=timedelta(hours=1)),
source=tb.BeliefSource("Source X"),
)
blfs += load_time_series(
beliefs[h].head(n_events),
sensor=sensor,
source=source,
belief_horizon=(isodate.parse_duration("%s" % h)) +
event_resolution,
cumulative_probability=cp) # load the forecasts
return blfs
source_a = tb.BeliefSource(name="Linear regression")
source_b = tb.BeliefSource(name="XGBoost")
source_c = tb.BeliefSource(name="Random forest")
sensors = (tb.Sensor(name=descr[0],
unit=descr[1],
event_resolution=event_resolution)
for descr in sensor_descriptions)
for sensor in sensors:
blfs = read_beliefs_from_csv(sensor,
source=source_a,
cp=0.5,
event_resolution=event_resolution,
tz_hour_difference=tz_hour_difference)
blfs += read_beliefs_from_csv(sensor,
source=source_b,
cp=0.5,
event_resolution=event_resolution,
tz_hour_difference=tz_hour_difference)
blfs += read_beliefs_from_csv(sensor,
