Plots#

[1]:

# Import to be able to import python package from src
import sys
sys.path.insert(0, '../src')

[2]:

import pandas as pd
import ontime as on
from darts.datasets import EnergyDataset

The `LightGBM` module could not be imported. To enable LightGBM support in Darts, follow the detailed instructions in the installation guide: https://github.com/unit8co/darts/blob/master/INSTALL.md
The `Prophet` module could not be imported. To enable Prophet support in Darts, follow the detailed instructions in the installation guide: https://github.com/unit8co/darts/blob/master/INSTALL.md

Load data#

[3]:

ts = EnergyDataset().load()

Complete TimeSeries

[4]:

df = ts.pd_dataframe()
df = df.interpolate()
cols = ['generation biomass', 'generation solar', 'generation nuclear']
df = df[cols]

[5]:

ts = on.TimeSeries.from_dataframe(df)

Prepare data

[6]:

ts_uni = ts['generation solar'].slice(pd.Timestamp('2015'), pd.Timestamp('2016'))
ts_multi = ts.slice(pd.Timestamp('2015'), pd.Timestamp('2016'))

Primitive Plots#

Line(s)#

With univariate TimeSeries

[7]:

on.Plot(ts_uni.head(400))\
    .add(on.marks.line)\
    .properties(width=600)\
    .show()

[7]:

with multivariate TimeSeries

[8]:

on.Plot(ts_multi.head(400))\
    .add(on.marks.line)\
    .properties(width=600)\
    .show()

[8]:

Dots#

With univariate TimeSeries

[9]:

on.Plot(ts_uni.head(400))\
    .add(on.marks.dots)\
    .properties(width=600)\
    .show()

[9]:

with multivariate TimeSeries

[10]:

on.Plot(ts_multi.head(400))\
    .add(on.marks.dots)\
    .properties(width=600)\
    .show()

[10]:

Areas#

With a single time series

[11]:

on.Plot(ts_uni.head(400))\
    .add(on.marks.area)\
    .properties(width=600)\
    .show()

[11]:

With a multivariate time series it works with exactly two

[12]:

from darts import concatenate

[13]:

# First we create the series with two components
ts_ci = concatenate([
    ts_multi.univariate_component(0),
    ts_multi.univariate_component(1)
], axis=1)
ts_ci = on.TimeSeries.from_darts(ts_ci)

[14]:

# Then we plot it
on.Plot(ts_ci.head(200))\
    .add(on.marks.area, title='Diff. between solar and biomass generation')\
    .properties(width=600, height=200)\
    .show()

[14]:

Heatmaps#

with univariate TimeSeries

[15]:

on.Plot(ts_uni.head(1000))\
    .add(on.marks.heatmap)\
    .properties(width=600, height=50)\
    .show()

[15]:

with multivariate Heatmap

[23]:

on.Plot(ts_multi.head(1000))\
    .add(on.marks.heatmap)\
    .properties(width=600, height=150)\
    .show()

[23]:

Combined Plots#

Most of the plots in onTime can be combined as they are based on Altair layered charts. For instance, you can do the following to have a dots on a line.

[24]:

on.Plot()\
    .add(on.marks.dots, ts_multi.univariate_component(1).head(400))\
    .add(on.marks.line, ts_multi.univariate_component(0).head(400))\
    .properties(width=600, height=200)\
    .show()

[24]:

Thematic Plots#

Forecasts#

[25]:

ts_train, ts_test = ts_uni.split_before(0.9)

[26]:

from ontime.context import common

[27]:

model = common.GenericPredictor()
model.fit(ts_train)

[27]:

<ontime.context.common.generic_predictor.GenericPredictor at 0x1759654b0>

[28]:

ts_pred = model.predict(24 * 3)

[29]:

ts_train = ts_train.rename({'generation solar':'Training set'})
ts_test = ts_test.rename({'generation solar':'Test set'})
ts_pred = ts_pred.rename({'generation solar':'Forecast'})

Plot a prediction

[30]:

(
on.Plot()
    .add(on.marks.line, ts_test.head(24 * 3), type='dashed')
    .add(on.marks.line, ts_train.tail(24 * 4))
    .add(on.marks.line, ts_pred)
    .properties(width=600, height=200)
    .show()
)

[30]:

Anomalies#

Create the mock data

[56]:

td_point = on.detectors.quantile(high_quantile=0.99)
td_collective = on.detectors.threshold(low_threshold=-30)
td_contextual = on.detectors.quantile(high_quantile=0.98)

Add anomalies

[57]:

import numpy as np
import random

def add_point_anomalies(ts, n, value):
    df = ts.pd_dataframe()
    random_indices = np.random.choice(df.index, size=n, replace=False)
    df.loc[random_indices] = value
    return on.TimeSeries.from_dataframe(df)

def add_collective_anomalies(ts, n, min_duration=10, max_duration=20):
    df = ts.pd_dataframe()
    for i in range(n+1):
        block_duration = random.randint(min_duration, max_duration)
        start_index = np.random.choice(df.index[:-block_duration])
        end_index = start_index + pd.Timedelta(days=block_duration - 1)
        df.loc[start_index:end_index] = -40
    return on.TimeSeries.from_dataframe(df)

Select univariate component

[58]:

ts = ts.univariate_component(0)

[59]:

ts = add_point_anomalies(ts, 10, 30)
ts = add_collective_anomalies(ts, 4)

Create binary time series

[60]:

td_point.fit(ts)
td_contextual.fit(ts)

ts_ano_point = td_point.detect(ts)
ts_ano_collective = td_collective.detect(ts)
ts_ano_contextual = td_contextual.detect(ts)

[61]:

ts_ano_point = ts_ano_point.rename({'0': 'Ponctual anomalies'})
ts_ano_collective = ts_ano_collective.rename({'0': 'Collective anomalies'})
ts_ano_contextual = ts_ano_contextual.rename({'0': 'Contextual anomalies'})

Plot the time series with marked anomalies

[64]:

# Define windows for plotting
start = 24 * 7 * 4 * 9
duration = 24 * 7 * 10
end = start + duration

[67]:

# Actually plot
(
on.Plot(ts[start:end])
    .add(on.marks.mark, data=ts_ano_contextual[start:end], type='highlight')
    .add(on.marks.mark, data=ts_ano_collective[start:end], type='background')
    .add(on.marks.line)
    .add(on.marks.mark, data=ts_ano_point[start:end], type='dot')
    .properties(width=800, height=200)
    .show()
)

[67]:

Confidence Intervals#

[91]:

# Generate two time series
ts1 = on.generators.random_walk().generate(start=pd.Timestamp('2022-01-01'), end=pd.Timestamp('2022-12-31'))
ts2 = on.generators.random_walk().generate(start=pd.Timestamp('2022-01-01'), end=pd.Timestamp('2022-12-31'))

[92]:

# First we create the series with two components
ts1_abs = ts1.map(np.abs)
ts2_abs = ts2.map(np.abs)
ts_ci = concatenate([ts1_abs, ts2_abs], axis=1)
ts_ci = on.TimeSeries.from_darts(ts_ci)
ts_ci = ts_ci.rename({'random_walk': 'CI Upper bound', 'random_walk_1': 'CI Lower bound'})

# Then the hypothetical measurement
ts_mid = (ts1_abs + ts2_abs) / 2
ts_mid = ts_mid.rename({'random_walk': 'Measurement'})

[93]:

# Then we plot it
(
on.Plot() # main line
    .add(on.marks.area, ts_ci.head(200), title='Confidence interval')
    .add(on.marks.line, ts_mid.head(200))
    .properties(width=600, height=200)
    .show()
)

[93]:

[ ]:
On this page
Show Source