def test_load_peyton_manning_ts():
dl = DataLoaderTS()
ts = dl.load_peyton_manning_ts()
assert ts.original_time_col == TIME_COL
assert ts.original_value_col == VALUE_COL
assert ts.freq == "1D"
assert_equal(ts.df[VALUE_COL], ts.y)
def test_load_hourly_bikesharing_ts():
dl = DataLoaderTS()
ts = dl.load_bikesharing_ts()
assert ts.original_time_col == "ts"
assert ts.original_value_col == "count"
assert ts.freq == "H"
assert ts.regressor_cols == ["tmin", "tmax", "pn"]
assert_equal(ts.df[VALUE_COL], ts.y)
def test_plot():
"""Checks plot function"""
# Plots with `color`
ts = UnivariateTimeSeries()
df = pd.DataFrame({
TIME_COL: [
dt(2018, 1, 1, 3, 0, 0),
dt(2018, 1, 1, 4, 0, 0),
dt(2018, 1, 1, 5, 0, 0)
],
VALUE_COL: [1, 2, 3]
})
ts.load_data(df, TIME_COL, VALUE_COL)
fig = ts.plot(color="green")
assert len(fig.data) == 1
assert fig.data[0].line.color == "green"
with pytest.raises(
ValueError,
match=
"There is no `anomaly_info` to show. `show_anomaly_adjustment` must be False."
):
ts.plot(show_anomaly_adjustment=True)
# Plots with `show_anomaly_adjustment`
dl = DataLoaderTS()
df = dl.load_beijing_pm()
value_col = "pm"
# Masks up to 2011-02-04-03, and adds 100.0 to the rest
anomaly_df = pd.DataFrame({
START_DATE_COL: ["2010-01-01-00", "2011-02-04-03"],
END_DATE_COL: ["2011-02-04-03", "2014-12-31-23"],
ADJUSTMENT_DELTA_COL: [np.nan, 100.0],
METRIC_COL: [value_col, value_col]
})
anomaly_info = {
"value_col": value_col,
"anomaly_df": anomaly_df,
"start_date_col": START_DATE_COL,
"end_date_col": END_DATE_COL,
"adjustment_delta_col": ADJUSTMENT_DELTA_COL,
"filter_by_dict": {
METRIC_COL: value_col
},
"adjustment_method": "add"
}
ts = UnivariateTimeSeries()
ts.load_data(df=df, value_col="pm", anomaly_info=anomaly_info)
fig = ts.plot(show_anomaly_adjustment=True)
assert len(fig.data) == 2
assert fig.data[0].name == value_col
assert fig.data[1].name == f"{value_col}_unadjusted"
assert fig.layout.xaxis.title.text == ts.original_time_col
assert fig.layout.yaxis.title.text == ts.original_value_col
assert fig.data[0].y.shape[0] == df.shape[0]
assert fig.data[1].y.shape[0] == df.shape[0]
# adjusted data has more NaNs, since anomalies are replaced with NaN
assert sum(np.isnan(fig.data[0].y)) == 10906
assert sum(np.isnan(fig.data[1].y)) == 2067
def test_load_hourly_beijing_pm_ts():
dl = DataLoaderTS()
ts = dl.load_beijing_pm_ts()
assert ts.original_time_col == TIME_COL
assert ts.original_value_col == "pm"
assert ts.freq == "H"
assert ts.regressor_cols == [
"dewp", "temp", "pres", "cbwd", "iws", "is", "ir"
]
assert_equal(ts.df[VALUE_COL], ts.y)
def test_load_hourly_parking_ts():
dl = DataLoaderTS()
ts = dl.load_parking_ts(system_code_number=None)
assert ts.original_time_col == "LastUpdated"
assert ts.original_value_col == "OccupancyRatio"
assert ts.freq == "30min"
assert ts.df.shape == (3666, 4)
ts = dl.load_parking_ts(system_code_number="NIA South")
assert ts.original_time_col == "LastUpdated"
assert ts.original_value_col == "OccupancyRatio"
assert ts.freq == "30min"
assert ts.df.shape == (3522, 5)
def test_load_data_anomaly():
"""Checks anomaly_info parameter"""
dl = DataLoaderTS()
df = dl.load_beijing_pm()
value_col = "pm"
# no anomaly adjustment
ts = UnivariateTimeSeries()
ts.load_data(df=df, value_col=value_col)
assert ts.df_before_adjustment is None
# adjusts two columns
dim_one = "one"
dim_two = "two"
anomaly_df = pd.DataFrame({
START_DATE_COL: ["2011-04-04-10", "2011-10-10-00", "2012-12-20-10"],
END_DATE_COL: ["2011-04-05-20", "2011-10-11-23", "2012-12-20-13"],
ADJUSTMENT_DELTA_COL: [np.nan, 100.0, -100.0],
METRIC_COL: [dim_one, dim_one, dim_two]
})
anomaly_info = [{
"value_col": value_col,
"anomaly_df": anomaly_df,
"start_date_col": START_DATE_COL,
"end_date_col": END_DATE_COL,
"adjustment_delta_col": ADJUSTMENT_DELTA_COL,
"filter_by_dict": {
METRIC_COL: dim_one
},
"adjustment_method": "add"
}, {
"value_col": "pres",
"anomaly_df": anomaly_df,
"start_date_col": START_DATE_COL,
"end_date_col": END_DATE_COL,
"adjustment_delta_col": ADJUSTMENT_DELTA_COL,
"filter_by_dict": {
METRIC_COL: dim_two
},
"adjustment_method": "subtract"
}]
ts = UnivariateTimeSeries()
ts.load_data(df=df, value_col=value_col, anomaly_info=anomaly_info)
canonical_data_dict = get_canonical_data(df=df,
value_col=value_col,
anomaly_info=anomaly_info)
assert_equal(ts.df, canonical_data_dict["df"])
assert_equal(ts.df_before_adjustment,
canonical_data_dict["df_before_adjustment"])
def test_load_data_ts():
dl = DataLoaderTS()
ts = dl.load_data_ts(data_name="daily_peyton_manning")
expected_ts = dl.load_peyton_manning_ts()
assert_equal(ts.df, expected_ts.df)
ts = dl.load_data_ts(data_name="hourly_parking",
system_code_number="Shopping")
expected_ts = dl.load_parking_ts(system_code_number="Shopping")
assert_equal(ts.df, expected_ts.df)
# Error due to unavailable data name
data_name = "dummy"
data_inventory = dl.get_data_inventory()
with pytest.raises(
ValueError,
match=fr"Input data name '{data_name}' is not recognized. "
fr"Must be one of \{data_inventory}\."):
dl.load_data_ts(data_name=data_name)
from greykite.algo.forecast.silverkite.constants.silverkite_seasonality import SilverkiteSeasonalityEnum from greykite.algo.forecast.silverkite.forecast_simple_silverkite_helper import cols_interact from greykite.common import constants as cst from greykite.common.features.timeseries_features import build_time_features_df from greykite.common.features.timeseries_features import convert_date_to_continuous_time from greykite.framework.benchmark.data_loader_ts import DataLoaderTS from greykite.framework.templates.autogen.forecast_config import EvaluationPeriodParam from greykite.framework.templates.autogen.forecast_config import ForecastConfig from greykite.framework.templates.autogen.forecast_config import MetadataParam from greykite.framework.templates.autogen.forecast_config import ModelComponentsParam from greykite.framework.templates.forecaster import Forecaster from greykite.framework.templates.model_templates import ModelTemplateEnum from greykite.framework.utils.result_summary import summarize_grid_search_results # Loads dataset into UnivariateTimeSeries dl = DataLoaderTS() ts = dl.load_peyton_manning_ts() df = ts.df # cleaned pandas.DataFrame # %% # Exploratory data analysis (EDA) # -------------------------------- # After reading in a time series, we could first do some exploratory data analysis. # The `~greykite.framework.input.univariate_time_series.UnivariateTimeSeries` class is # used to store a timeseries and perform EDA. # describe print(ts.describe_time_col()) print(ts.describe_value_col()) # %%
def test_init():
dl = DataLoaderTS()
assert dl.available_datasets == dl.get_data_inventory()
def test_get_quantiles_and_overlays():
"""Tests get_quantiles_and_overlays"""
dl = DataLoaderTS()
peyton_manning_ts = dl.load_peyton_manning_ts()
# no columns are requested
with pytest.raises(
ValueError,
match=
"Must enable at least one of: show_mean, show_quantiles, show_overlays."
):
peyton_manning_ts.get_quantiles_and_overlays(
groupby_time_feature="doy")
# show_mean only
grouped_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_time_feature="dow",
show_mean=True,
mean_col_name="custom_name")
assert_equal(
grouped_df.columns,
pd.MultiIndex.from_arrays([[MEAN_COL_GROUP], ["custom_name"]],
names=["category", "name"]))
assert grouped_df.index.name == "dow"
assert grouped_df.shape == (7, 1)
assert grouped_df.index[0] == 1
# show_quantiles only (bool)
grouped_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_sliding_window_size=180, show_quantiles=True)
assert_equal(
grouped_df.columns,
pd.MultiIndex.from_arrays(
[[QUANTILE_COL_GROUP, QUANTILE_COL_GROUP], ["Q0.1", "Q0.9"]],
names=["category", "name"]))
assert grouped_df.index.name == "ts_downsample"
assert grouped_df.shape == (17, 2)
assert grouped_df.index[0] == pd.Timestamp(2007, 12, 10)
# show_quantiles only (list)
custom_col = pd.Series(
np.random.choice(list("abcd"), size=peyton_manning_ts.df.shape[0]))
grouped_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_custom_column=custom_col,
show_quantiles=[0, 0.25, 0.5, 0.75, 1],
quantile_col_prefix="prefix")
assert_equal(
grouped_df.columns,
pd.MultiIndex.from_arrays(
[[QUANTILE_COL_GROUP] * 5,
["prefix0", "prefix0.25", "prefix0.5", "prefix0.75", "prefix1"]],
names=["category", "name"]))
assert grouped_df.index.name == "groups"
assert grouped_df.shape == (4, 5)
assert grouped_df.index[0] == "a"
# checks quantile computation
df = peyton_manning_ts.df.copy()
df["custom_col"] = custom_col.values
quantile_df = df.groupby("custom_col")[VALUE_COL].agg(
[np.nanmin, np.nanmedian, np.nanmax])
assert_equal(grouped_df["quantile"]["prefix0"],
quantile_df["nanmin"],
check_names=False)
assert_equal(grouped_df["quantile"]["prefix0.5"],
quantile_df["nanmedian"],
check_names=False)
assert_equal(grouped_df["quantile"]["prefix1"],
quantile_df["nanmax"],
check_names=False)
# show_overlays only (bool), no overlay label
grouped_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_time_feature="doy", show_overlays=True)
assert_equal(
grouped_df.columns,
pd.MultiIndex.from_arrays(
[[OVERLAY_COL_GROUP] * 9, [f"overlay{i}" for i in range(9)]],
names=["category", "name"]))
assert grouped_df.index.name == "doy"
assert grouped_df.shape == (366, 9)
assert grouped_df.index[0] == 1
# show_overlays only (int below the available number), time feature overlay label
np.random.seed(123)
grouped_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_time_feature="doy",
show_overlays=4,
overlay_label_time_feature="year")
assert_equal(
grouped_df.columns,
pd.MultiIndex.from_arrays(
[[OVERLAY_COL_GROUP] * 4, ["2007", "2011", "2012", "2014"]],
names=["category", "name"]))
assert grouped_df.index.name == "doy"
assert grouped_df.shape == (366, 4)
assert grouped_df.index[0] == 1
# show_overlays only (int above the available number), custom overlay label
grouped_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_time_feature="dom",
show_overlays=200,
overlay_label_custom_column=custom_col)
assert_equal(
grouped_df.columns,
pd.MultiIndex.from_arrays(
[[OVERLAY_COL_GROUP] * 4, ["a", "b", "c", "d"]],
names=["category", "name"]))
assert grouped_df.index.name == "dom"
assert grouped_df.shape == (31, 4)
assert grouped_df.index[0] == 1
# show_overlays only (list of indices), sliding window overlay label
grouped_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_time_feature="dom",
show_overlays=[0, 4],
overlay_label_sliding_window_size=365 * 2)
assert_equal(
grouped_df.columns,
pd.MultiIndex.from_arrays(
[[OVERLAY_COL_GROUP] * 2,
["2007-12-10 00:00:00", "2015-12-08 00:00:00"]],
names=["category", "name"]))
assert grouped_df.index.name == "dom"
assert grouped_df.shape == (31, 2)
assert grouped_df.index[0] == 1
# show_overlays only (np.ndarray), sliding window overlay label
grouped_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_time_feature="dom",
show_overlays=np.arange(0, 6, 2),
overlay_label_sliding_window_size=365 * 2)
assert_equal(
grouped_df.columns,
pd.MultiIndex.from_arrays(
[[OVERLAY_COL_GROUP] * 3,
[
"2007-12-10 00:00:00", "2011-12-09 00:00:00",
"2015-12-08 00:00:00"
]],
names=["category", "name"]))
assert grouped_df.index.name == "dom"
assert grouped_df.shape == (31, 3)
assert grouped_df.index[0] == 1
# show_overlays only (list of column names), sliding window overlay label
grouped_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_time_feature="dom",
show_overlays=["2007-12-10 00:00:00", "2015-12-08 00:00:00"],
overlay_label_sliding_window_size=365 * 2)
assert_equal(
grouped_df.columns,
pd.MultiIndex.from_arrays(
[[OVERLAY_COL_GROUP] * 2,
["2007-12-10 00:00:00", "2015-12-08 00:00:00"]],
names=["category", "name"]))
assert grouped_df.index.name == "dom"
assert grouped_df.shape == (31, 2)
assert grouped_df.index[0] == 1
# Show all 3 (no overlay label)
grouped_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_sliding_window_size=50, # 50 per group (50 overlays)
show_mean=True,
show_quantiles=[0.05, 0.5, 0.95], # 3 quantiles
show_overlays=True)
assert_equal(
grouped_df.columns,
pd.MultiIndex.from_arrays(
[[MEAN_COL_GROUP] + [QUANTILE_COL_GROUP] * 3 +
[OVERLAY_COL_GROUP] * 50, ["mean", "Q0.05", "Q0.5", "Q0.95"] +
[f"overlay{i}" for i in range(50)]],
names=["category", "name"]))
assert grouped_df.index.name == "ts_downsample"
assert grouped_df.shape == (60, 54)
assert grouped_df.index[-1] == pd.Timestamp(2016, 1, 7)
# Show all 3 (with overlay label).
# Pass overlay_pivot_table_kwargs.
grouped_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_sliding_window_size=180,
show_mean=True,
show_quantiles=[0.05, 0.5, 0.95], # 3 quantiles
show_overlays=True,
overlay_label_time_feature="dow", # 7 possible values
aggfunc="median")
assert_equal(
grouped_df.columns,
pd.MultiIndex.from_arrays(
[[MEAN_COL_GROUP] + [QUANTILE_COL_GROUP] * 3 +
[OVERLAY_COL_GROUP] * 7,
[
"mean", "Q0.05", "Q0.5", "Q0.95", "1", "2", "3", "4", "5",
"6", "7"
]],
names=["category", "name"]))
assert grouped_df.index.name == "ts_downsample"
assert grouped_df.shape == (17, 11)
assert grouped_df.index[-1] == pd.Timestamp(2015, 10, 29)
assert np.linalg.norm(
grouped_df[OVERLAY_COL_GROUP].mean()) > 1.0 # not centered
with pytest.raises(
TypeError,
match="pivot_table\\(\\) got an unexpected keyword argument 'aggfc'"
):
peyton_manning_ts.get_quantiles_and_overlays(
groupby_sliding_window_size=180,
show_mean=True,
show_quantiles=[0.05, 0.5, 0.95],
show_overlays=True,
overlay_label_time_feature="dow",
aggfc=np.nanmedian) # unrecognized parameter
# center_values with show_mean=True
centered_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_sliding_window_size=180,
show_mean=True,
show_quantiles=[0.05, 0.5, 0.95],
show_overlays=True,
overlay_label_time_feature="dow",
aggfunc="median",
center_values=True)
assert np.linalg.norm(centered_df[[MEAN_COL_GROUP, OVERLAY_COL_GROUP
]].mean()) < 1e-8 # centered at 0
assert_equal(
centered_df[QUANTILE_COL_GROUP],
grouped_df[QUANTILE_COL_GROUP] - grouped_df[MEAN_COL_GROUP].mean()[0])
# center_values with show_mean=False
centered_df = peyton_manning_ts.get_quantiles_and_overlays(
groupby_sliding_window_size=180,
show_mean=False,
show_quantiles=[0.05, 0.5, 0.95],
show_overlays=True,
overlay_label_time_feature="dow",
aggfunc="median",
center_values=True)
assert np.linalg.norm(centered_df[[OVERLAY_COL_GROUP
]].mean()) < 1e-8 # centered at 0
overall_mean = peyton_manning_ts.df[VALUE_COL].mean()
assert_equal(centered_df[QUANTILE_COL_GROUP],
grouped_df[QUANTILE_COL_GROUP] - overall_mean)
# new value_col
df = generate_df_with_reg_for_tests(freq="D", periods=700)["df"]
ts = UnivariateTimeSeries()
ts.load_data(df=df)
grouped_df = ts.get_quantiles_and_overlays(
groupby_time_feature="dow",
show_mean=True,
show_quantiles=True,
show_overlays=True,
overlay_label_time_feature="woy",
value_col="regressor1")
df_dow = add_groupby_column(df=ts.df,
time_col=TIME_COL,
groupby_time_feature="dow")
dow_mean = df_dow["df"].groupby("dow").agg(
mean=pd.NamedAgg(column="regressor1", aggfunc=np.nanmean))
assert_equal(grouped_df["mean"], dow_mean, check_names=False)
def test_plot_quantiles_and_overlays():
"""Tests plot_quantiles_and_overlays"""
dl = DataLoaderTS()
peyton_manning_ts = dl.load_peyton_manning_ts()
# plots one at a time, with different axis options
fig = peyton_manning_ts.plot_quantiles_and_overlays(
groupby_time_feature="doy", show_mean=True)
assert fig.layout.showlegend
assert fig.layout.title.text == "y vs doy"
assert fig.layout.xaxis.title.text == "doy"
assert fig.layout.yaxis.title.text == "y"
assert len(fig.data) == 1
assert fig.data[0].mode == "lines"
assert fig.data[0].legendgroup == MEAN_COL_GROUP
assert fig.data[0].line.color == "#595959"
assert fig.data[0].line.width == 2
assert fig.data[0].name == "mean"
fig = peyton_manning_ts.plot_quantiles_and_overlays(
groupby_time_feature="doy",
show_quantiles=True,
ylabel="log(pageviews)",
xlabel="day of year")
assert fig.layout.showlegend
assert fig.layout.title.text == "log(pageviews) vs day of year"
assert fig.layout.xaxis.title.text == "day of year"
assert fig.layout.yaxis.title.text == "log(pageviews)"
assert len(fig.data) == 2
assert fig.data[0].mode == "lines"
assert fig.data[0].legendgroup == QUANTILE_COL_GROUP
assert fig.data[0].line.color == "#1F9AFF"
assert fig.data[0].line.width == 2
assert fig.data[0].fill is None # no fill from first line
assert fig.data[1].fill == "tonexty"
assert fig.data[0].name == "Q0.1"
assert fig.data[1].name == "Q0.9"
fig = peyton_manning_ts.plot_quantiles_and_overlays(
groupby_time_feature="doy",
show_overlays=True,
overlay_label_time_feature="year",
ylabel="log(pageviews)",
xlabel="day of year",
title="Yearly seasonality patterns",
showlegend=False)
assert not fig.layout.showlegend
assert fig.layout.title.text == "Yearly seasonality patterns"
assert fig.layout.xaxis.title.text == "day of year"
assert fig.layout.yaxis.title.text == "log(pageviews)"
assert len(fig.data) == 10
assert fig.data[0].mode == "lines"
assert fig.data[0].legendgroup == OVERLAY_COL_GROUP
assert fig.data[0].line.color == "#B3B3B3"
assert fig.data[0].line.width == 1
assert fig.data[0].line.dash == "solid"
assert fig.data[0].name == "2007"
assert fig.data[-1].name == "2016"
# plots all at once
fig = peyton_manning_ts.plot_quantiles_and_overlays(
groupby_time_feature="doy",
show_mean=True,
show_quantiles=True,
show_overlays=True,
overlay_label_time_feature="year",
ylabel="log(pageviews)",
xlabel="day of year",
title="Yearly seasonality patterns",
showlegend=True)
assert fig.layout.showlegend
assert fig.layout.title.text == "Yearly seasonality patterns"
assert fig.layout.xaxis.title.text == "day of year"
assert fig.layout.yaxis.title.text == "log(pageviews)"
assert len(fig.data) == 13 # 1 (mean) + 2 (quantiles) + 10 (one per year)
assert fig.data[0].mode == "lines"
assert fig.data[0].legendgroup == OVERLAY_COL_GROUP
assert fig.data[0].line.color == "#B3B3B3"
assert fig.data[0].line.width == 1
assert fig.data[0].line.dash == "solid"
assert fig.data[0].opacity == 0.5
assert fig.data[0].name == "2007"
assert fig.data[9].name == "2016"
assert fig.data[10].name == "Q0.1"
assert fig.data[11].name == "Q0.9"
assert fig.data[12].name == "mean"
# plots all with custom style
beijing_pm_ts = dl.load_beijing_pm_ts()
mean_style = {
"line": dict(width=2, color="#757575"), # gray
"legendgroup": MEAN_COL_GROUP
}
quantile_style = {
"line": dict(width=2, color="#A3A3A3"), # light gray
"legendgroup": QUANTILE_COL_GROUP,
"fill": "tonexty"
}
overlay_style = { # Different color for each line (unspecified)
"line":
dict( # No legendgroup to allow individual toggling of lines.
width=1,
dash="dot")
}
fig = beijing_pm_ts.plot_quantiles_and_overlays(
groupby_time_feature="hour",
show_mean=True,
show_quantiles=[0.2, 0.8],
show_overlays=True,
overlay_label_time_feature="month",
center_values=True,
mean_col_name="avg",
mean_style=mean_style,
quantile_style=quantile_style,
overlay_style=overlay_style,
xlabel="hour of day",
value_col="pres",
title="Daily seasonality pattern: pres")
assert fig.layout.showlegend
assert fig.layout.title.text == "Daily seasonality pattern: pres"
assert fig.layout.xaxis.title.text == "hour of day"
assert fig.layout.yaxis.title.text == "pres"
assert len(fig.data) == 15
# The first timeseries is the 12 overlays (one per month), then Q0.1, Q0.9, then the mean
assert fig.data[0].name == "1"
assert fig.data[11].name == "12"
assert fig.data[12].name == "Q0.2"
assert fig.data[13].name == "Q0.8"
assert fig.data[14].name == "avg"
assert fig.data[0].mode == "lines"
assert fig.data[0].legendgroup is None
assert fig.data[0].line.color is None
assert fig.data[12].line.color == "#A3A3A3"
assert fig.data[14].line.color == "#757575"