Skip to content

Commit

Permalink
Merge branch 'develop' into feature/floris_tuning
Browse files Browse the repository at this point in the history
  • Loading branch information
@paulf81
paulf81 committed Sep 12, 2023
2 parents 8adae25 + 7c08af9 commit c5dd9bb
Show file tree
Hide file tree
Showing 6 changed files with 427 additions and 113 deletions.
32 changes: 7 additions & 25 deletions examples_artificial_data/03_energy_ratio/05_wake_steering_example.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,20 +10,16 @@
# License for the specific language governing permissions and limitations under
# the License.

import numpy as np

import matplotlib.pyplot as plt
import os
import numpy as np
import pandas as pd
import seaborn as sns

from floris import tools as wfct
from floris.utilities import wrap_360

from flasc.energy_ratio import energy_ratio as er
from flasc.energy_ratio.energy_ratio_input import EnergyRatioInput
# from flasc import floris_tools as fsatools
from flasc.visualization import plot_layout_with_waking_directions, plot_binned_mean_and_ci
from flasc.utilities_examples import load_floris_artificial as load_floris
from flasc.visualization import plot_binned_mean_and_ci, plot_layout_with_waking_directions


if __name__ == "__main__":
Expand Down Expand Up @@ -129,21 +125,13 @@

# Make a color palette that visually links the nominal and noisy data sets together
color_palette = sns.color_palette("Paired",4)[::-1]
# color_palette = ['r','g','b','k']

# Initialize the energy ratio suite object and add each dataframe
# separately.

# Initialize the energy ratio input object
er_in = EnergyRatioInput(
[df_baseline, df_wakesteering, df_baseline_noisy, df_wakesteering_noisy],
["Baseline", "WakeSteering", "Baseline (Noisy)", "WakeSteering (Noisy)"]
)

# fsc.add_df(df_baseline, 'Baseline', color_palette[0])
# fsc.add_df(df_wakesteering, 'WakeSteering', color_palette[1])
# fsc.add_df(df_baseline_noisy, 'Baseline (Noisy)', color_palette[2])
# fsc.add_df(df_wakesteering_noisy, 'WakeSteering (Noisy)', color_palette[3])

# Calculate and plot the energy ratio for the downstream turbine [2]
# With respect to reference turbine [0]
# datasets with uncertainty quantification using 50 bootstrap samples
Expand All @@ -159,16 +147,10 @@
percentiles=[5., 95.],
uplift_pairs=[("Baseline", "WakeSteering"),
("Baseline (Noisy)", "WakeSteering (Noisy)")],
uplift_names=["Clean", "Noisy"]
uplift_names=["Clean", "Noisy"],
weight_by='min'
)
# fsc.get_energy_ratios(
# test_turbines=[2],
# wd_step=2.0,
# ws_step=1.0,
# N=10,
# percentiles=[5., 95.],
# verbose=False
# )

er_out.plot_energy_ratios(
color_dict={"Baseline":"blue",
"WakeSteering":"green",
Expand Down
153 changes: 88 additions & 65 deletions flasc/energy_ratio/energy_ratio.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,17 @@

from flasc.energy_ratio.energy_ratio_output import EnergyRatioOutput
from flasc.energy_ratio.energy_ratio_input import EnergyRatioInput
from flasc.energy_ratio.energy_ratio_utilities import add_ws_bin, add_wd, add_wd_bin, add_power_ref, add_power_test, add_reflected_rows
from flasc.energy_ratio.energy_ratio_utilities import (
add_ws_bin,
add_wd,
add_wd_bin,
add_power_ref,
add_power_test,
add_reflected_rows,
check_compute_energy_ratio_inputs,
filter_all_nulls,
filter_any_nulls
)


# Internal version, returns a polars dataframe
Expand All @@ -29,9 +39,11 @@ def _compute_energy_ratio_single(df_,
ws_min = 0.0,
ws_max = 50.0,
bin_cols_in = ['wd_bin','ws_bin'],
weight_by = 'min', #min, sum
wd_bin_overlap_radius = 0.,
uplift_pairs = [],
uplift_names = []
uplift_names = [],
remove_all_nulls = False
):

"""
Expand All @@ -51,14 +63,20 @@ def _compute_energy_ratio_single(df_,
ws_min (float): The minimum wind speed to use.
ws_max (float): The maximum wind speed to use.
bin_cols_in (list[str]): A list of column names to use for the wind speed and wind direction bins.
weight_by (str): How to weight the energy ratio, options are 'min', or 'sum'. 'min' means
the minimum count across the dataframes is used to weight the energy ratio. 'sum' means the sum of the counts
across the dataframes is used to weight the energy ratio. Defaults to 'min'.
wd_bin_overlap_radius (float): The distance in degrees one wd bin overlaps into the next, must be
less or equal to half the value of wd_step
uplift_pairs: (list[tuple]): List of pairs of df_names to compute uplifts for. Each element
of the list should be a tuple (or list) of length 2, where the first element will be the
base case in the uplift calculation and the second element will be the test case in the
uplift calculation. If None, no uplifts are computed.
uplift_names: (list[str]): Names for the uplift columns, following the order of the
pairs specified in uplift_pairs. If None, will default to "uplift_df_name1_df_name2"
pairs specified in uplift_pairs. If None, will default to "uplift_df_name1_df_name2",
remove_all_nulls: (bool): Construct reference and test by strictly requiring all data to be
available. If False, a minimum one data point from ref_cols, test_cols, wd_cols, and ws_cols
must be available to compute the bin. Defaults to False.
Returns:
pl.DataFrame: A dataframe containing the energy ratio for each wind direction bin
Expand All @@ -67,23 +85,25 @@ def _compute_energy_ratio_single(df_,
# Identify the number of dataframes
num_df = len(df_names)

# Filter df_ that all the columns are not null
print(ref_cols + test_cols + ws_cols + wd_cols)
df_ = df_.filter(pl.all_horizontal(pl.col(ref_cols + test_cols + ws_cols + wd_cols).is_not_null()))
# Filter df_ to remove null values
null_filter = filter_all_nulls if remove_all_nulls else filter_any_nulls
df_ = null_filter(df_, ref_cols, test_cols, ws_cols, wd_cols)
if len(df_) == 0:
raise RuntimeError("After removing nulls, no data remains for computation.")

# If wd_bin_overlap_radius is not zero, add reflected rows
if wd_bin_overlap_radius > 0.:

# Need to obtain the wd column now rather than during binning
df_ = add_wd(df_, wd_cols)
df_ = add_wd(df_, wd_cols, remove_all_nulls)

# Add reflected rows
edges = np.arange(wd_min, wd_max + wd_step, wd_step)
df_ = add_reflected_rows(df_, edges, wd_bin_overlap_radius)

# Assign the wd/ws bins
df_ = add_ws_bin(df_, ws_cols, ws_step, ws_min, ws_max)
df_ = add_wd_bin(df_, wd_cols, wd_step, wd_min, wd_max)
df_ = add_ws_bin(df_, ws_cols, ws_step, ws_min, ws_max, remove_all_nulls=remove_all_nulls)
df_ = add_wd_bin(df_, wd_cols, wd_step, wd_min, wd_max, remove_all_nulls=remove_all_nulls)



Expand All @@ -102,13 +122,15 @@ def _compute_energy_ratio_single(df_,
.agg([pl.mean("pow_ref"), pl.mean("pow_test"),pl.count()])
.with_columns(
[
pl.col('count').min().over(bin_cols_without_df_name).alias('count_min')#, # Find the min across df_name
# Get the weighting by counts
pl.col('count').min().over(bin_cols_without_df_name).alias('count_weight') if weight_by == 'min' else
pl.col('count').sum().over(bin_cols_without_df_name).alias('count_weight')
]
)
.with_columns(
[
pl.col('pow_ref').mul(pl.col('count_min')).alias('ref_energy'), # Compute the reference energy
pl.col('pow_test').mul(pl.col('count_min')).alias('test_energy'), # Compute the test energy
pl.col('pow_ref').mul(pl.col('count_weight')).alias('ref_energy'), # Compute the reference energy
pl.col('pow_test').mul(pl.col('count_weight')).alias('test_energy'), # Compute the test energy
]
)
.groupby(['wd_bin','df_name'], maintain_order=True)
Expand Down Expand Up @@ -146,11 +168,13 @@ def _compute_energy_ratio_bootstrap(er_in,
ws_min = 0.0,
ws_max = 50.0,
bin_cols_in = ['wd_bin','ws_bin'],
weight_by = 'min', #min, sum
wd_bin_overlap_radius = 0.,
uplift_pairs = [],
uplift_names = [],
N = 1,
percentiles=[5., 95.]
percentiles=[5., 95.],
remove_all_nulls=False,
):

"""
Expand All @@ -169,6 +193,9 @@ def _compute_energy_ratio_bootstrap(er_in,
ws_min (float): The minimum wind speed to use.
ws_max (float): The maximum wind speed to use.
bin_cols_in (list[str]): A list of column names to use for the wind speed and wind direction bins.
weight_by (str): How to weight the energy ratio, options are 'min', or 'sum'. 'min' means
the minimum count across the dataframes is used to weight the energy ratio. 'sum' means the sum of the counts
across the dataframes is used to weight the energy ratio.
wd_bin_overlap_radius (float): The distance in degrees one wd bin overlaps into the next, must be
less or equal to half the value of wd_step
uplift_pairs: (list[tuple]): List of pairs of df_names to compute uplifts for. Each element
Expand All @@ -178,6 +205,12 @@ def _compute_energy_ratio_bootstrap(er_in,
uplift_names: (list[str]): Names for the uplift columns, following the order of the
pairs specified in uplift_pairs. If None, will default to "uplift_df_name1_df_name2"
N (int): The number of bootstrap samples to use.
percentiles: (list or None): percentiles to use when returning energy ratio bounds.
If specified as None with N > 1 (bootstrapping), defaults to [5, 95].
remove_all_nulls: (bool): Construct reference and test by strictly requiring all data to be
available. If False, a minimum one data point from ref_cols, test_cols, wd_cols, and ws_cols
must be available to compute the bin. Defaults to False.
Returns:
pl.DataFrame: A dataframe containing the energy ratio between the two sets of turbines.
Expand All @@ -199,9 +232,11 @@ def _compute_energy_ratio_bootstrap(er_in,
ws_min,
ws_max,
bin_cols_in,
weight_by,
wd_bin_overlap_radius,
uplift_pairs,
uplift_names
uplift_names,
remove_all_nulls
) for i in range(N)])

bound_names = er_in.df_names + uplift_names
Expand Down Expand Up @@ -231,11 +266,13 @@ def compute_energy_ratio(er_in: EnergyRatioInput,
ws_min = 0.0,
ws_max = 50.0,
bin_cols_in = ['wd_bin','ws_bin'],
weight_by = 'min', #min or sum
wd_bin_overlap_radius = 0.,
uplift_pairs = None,
uplift_names = None,
N = 1,
percentiles = None
percentiles = None,
remove_all_nulls = False
)-> EnergyRatioOutput:

"""
Expand All @@ -257,6 +294,9 @@ def compute_energy_ratio(er_in: EnergyRatioInput,
ws_min (float): The minimum wind speed to use.
ws_max (float): The maximum wind speed to use.
bin_cols_in (list[str]): A list of column names to use for the wind speed and wind direction bins.
weight_by (str): How to weight the energy ratio, options are 'min', , or 'sum'. 'min' means
the minimum count across the dataframes is used to weight the energy ratio. 'sum' means the sum of the counts
across the dataframes is used to weight the energy ratio.
wd_bin_overlap_radius (float): The distance in degrees one wd bin overlaps into the next, must be
less or equal to half the value of wd_step
uplift_pairs: (list[tuple]): List of pairs of df_names to compute uplifts for. Each element
Expand All @@ -268,6 +308,9 @@ def compute_energy_ratio(er_in: EnergyRatioInput,
N (int): The number of bootstrap samples to use.
percentiles: (list or None): percentiles to use when returning energy ratio bounds.
If specified as None with N > 1 (bootstrapping), defaults to [5, 95].
remove_all_nulls: (bool): Construct reference and test by strictly requiring all data to be
available. If False, a minimum one data point from ref_cols, test_cols, wd_cols, and ws_cols
must be available to compute the bin. Defaults to False.
Returns:
EnergyRatioOutput: An EnergyRatioOutput object containing the energy ratio between the two sets of turbines.
Expand All @@ -277,55 +320,31 @@ def compute_energy_ratio(er_in: EnergyRatioInput,
# Get the polars dataframe from within the er_in
df_ = er_in.get_df()

# Check that the inputs are valid
# If use_predefined_ref is True, df_ must have a column named 'pow_ref'
if use_predefined_ref:
if 'pow_ref' not in df_.columns:
raise ValueError('df_ must have a column named pow_ref when use_predefined_ref is True')
# If ref_turbines supplied, warn user that it will be ignored
if ref_turbines is not None:
warnings.warn('ref_turbines will be ignored when use_predefined_ref is True')
else:
# ref_turbine must be supplied
if ref_turbines is None:
raise ValueError('ref_turbines must be supplied when use_predefined_ref is False')

# If use_predefined_ws is True, df_ must have a column named 'ws'
if use_predefined_ws:
if 'ws' not in df_.columns:
raise ValueError('df_ must have a column named ws when use_predefined_ws is True')
# If ws_turbines supplied, warn user that it will be ignored
if ws_turbines is not None:
warnings.warn('ws_turbines will be ignored when use_predefined_ws is True')
else:
# ws_turbine must be supplied
if ws_turbines is None:
raise ValueError('ws_turbines must be supplied when use_predefined_ws is False')

# If use_predefined_wd is True, df_ must have a column named 'wd'
if use_predefined_wd:
if 'wd' not in df_.columns:
raise ValueError('df_ must have a column named wd when use_predefined_wd is True')
# If wd_turbines supplied, warn user that it will be ignored
if wd_turbines is not None:
warnings.warn('wd_turbines will be ignored when use_predefined_wd is True')
else:
# wd_turbine must be supplied
if wd_turbines is None:
raise ValueError('wd_turbines must be supplied when use_predefined_wd is False')


# Confirm that test_turbines is a list of ints or a numpy array of ints
if not isinstance(test_turbines, list) and not isinstance(test_turbines, np.ndarray):
raise ValueError('test_turbines must be a list or numpy array of ints')

# Confirm that test_turbines is not empty
if len(test_turbines) == 0:
raise ValueError('test_turbines cannot be empty')

# Confirm that wd_bin_overlap_radius is less than or equal to wd_step/2
if wd_bin_overlap_radius > wd_step/2:
raise ValueError('wd_bin_overlap_radius must be less than or equal to wd_step/2')
# Check that inputs are valid
check_compute_energy_ratio_inputs(
df_,
ref_turbines,
test_turbines,
wd_turbines,
ws_turbines,
use_predefined_ref,
use_predefined_wd,
use_predefined_ws,
wd_step,
wd_min,
wd_max,
ws_step,
ws_min,
ws_max,
bin_cols_in,
weight_by,
wd_bin_overlap_radius,
uplift_pairs,
uplift_names,
N,
percentiles,
remove_all_nulls
)

# Set up the column names for the reference and test power
if not use_predefined_ref:
Expand Down Expand Up @@ -380,9 +399,11 @@ def compute_energy_ratio(er_in: EnergyRatioInput,
ws_min,
ws_max,
bin_cols_in,
weight_by,
wd_bin_overlap_radius,
uplift_pairs,
uplift_names
uplift_names,
remove_all_nulls
)
else:
if percentiles is None:
Expand All @@ -403,6 +424,7 @@ def compute_energy_ratio(er_in: EnergyRatioInput,
ws_min,
ws_max,
bin_cols_in,
weight_by,
wd_bin_overlap_radius,
uplift_pairs,
uplift_names,
Expand All @@ -427,6 +449,7 @@ def compute_energy_ratio(er_in: EnergyRatioInput,
ws_min,
ws_max,
bin_cols_in,
weight_by,
wd_bin_overlap_radius,
N)

Expand Down
1 change: 0 additions & 1 deletion flasc/energy_ratio/energy_ratio_input.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,6 @@

from typing import Optional, Dict, List, Any, Tuple, Union

from flasc.energy_ratio.energy_ratio_utilities import add_ws_bin, add_wd_bin
from flasc.dataframe_operations.dataframe_manipulations import df_reduce_precision


Expand Down
Loading

0 comments on commit c5dd9bb

Please sign in to comment.