Skip to content

Update detect_clearsky( ) #1708

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 32 commits into
base: main
Choose a base branch
from
Open

Update detect_clearsky( ) #1708

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
32 commits
Select commit Hold shift + click to select a range
89034a1
''
eccoope Mar 7, 2023
403c798
''
eccoope Mar 7, 2023
a657310
''
eccoope Mar 16, 2023
a9fdfcd
''
eccoope Mar 22, 2023
f3db8d3
'Supporting_missing_timesteps_in_detect_clearsky()'
eccoope Mar 24, 2023
7121215
Merge branch 'main' of https://github.com/eccoope/pvlib-python-forked…
eccoope Mar 24, 2023
fd0f0c0
Merge branch 'main' of https://github.com/eccoope/pvlib-python-forked…
eccoope Mar 24, 2023
3e2ea1f
stickler changes
eccoope Mar 24, 2023
664bfae
stickler
eccoope Mar 24, 2023
2acfd40
stickler changes
eccoope Mar 24, 2023
d29c7de
'Fixed_unit_test'
eccoope Mar 24, 2023
97e53d0
Apply suggestions from code review
eccoope Mar 29, 2023
e8e5faa
'modified_to_preserve_nans'
eccoope Apr 17, 2023
386b260
Merge branch 'pvlib:main' into cs_branch
eccoope Apr 17, 2023
2110d67
Merge branch 'main' of https://github.com/eccoope/pvlib-python-forked…
eccoope Apr 17, 2023
d4d1187
'modified_to_preserve_nans'
eccoope Apr 17, 2023
92cb84b
'added_tests_for_data_with_nans_for_detect_clearsk'y
eccoope Apr 18, 2023
bd33436
fixed relative import statements
eccoope Apr 18, 2023
710c056
updated whatsnew file and included data for test_clearsky.py
eccoope Apr 20, 2023
dea6d00
Merge branch 'cs_branch' of https://github.com/eccoope/pvlib-python-f…
eccoope Apr 20, 2023
868e45b
Stickler corrections
eccoope Apr 27, 2023
f5e1fbc
Stickler
eccoope Apr 27, 2023
9385702
Added tests for if/else clause in detect_clearsky()
eccoope Jun 21, 2023
9d5d0cb
Update clearsky.py
eccoope Jun 21, 2023
61490bf
Merge branch 'main' into cs_branch
eccoope Jun 21, 2023
cc36315
Delete v0.9.6.rst
eccoope Jul 10, 2023
f4ff62b
Merge branch 'main' into cs_branch
eccoope Jul 10, 2023
3c29c99
Update tools.py
eccoope Jul 24, 2023
806e46a
Merge branch 'pvlib:main' into cs_branch
eccoope Jul 24, 2023
0021e1d
Update tools.py
eccoope Jul 24, 2023
ecf2bbf
Update test_tools.py
eccoope Jul 24, 2023
ae0b2c7
Merge branch 'pvlib:main' into cs_branch
eccoope Nov 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
137 changes: 109 additions & 28 deletions pvlib/clearsky.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -579,9 +579,10 @@ def _calc_stats(data, samples_per_window, sample_interval, H):
"""

data_mean = data.values[H].mean(axis=0)
data_mean = _to_centered_series(data_mean, data.index, samples_per_window)
data_mean = _to_centered_series(data_mean, data.index, samples_per_window,
H)
data_max = data.values[H].max(axis=0)
data_max = _to_centered_series(data_max, data.index, samples_per_window)
data_max = _to_centered_series(data_max, data.index, samples_per_window, H)
# shift to get forward difference, .diff() is backward difference instead
data_diff = data.diff().shift(-1)
data_slope = data_diff / sample_interval
Expand All @@ -594,30 +595,48 @@ def _slope_nstd_windowed(slopes, data, H, samples_per_window, sample_interval):
with np.errstate(divide='ignore', invalid='ignore'):
nstd = slopes[H[:-1, ]].std(ddof=1, axis=0) \
/ data.values[H].mean(axis=0)
return _to_centered_series(nstd, data.index, samples_per_window)
return _to_centered_series(nstd, data.index, samples_per_window, H)


def _max_diff_windowed(data, H, samples_per_window):
raw = np.diff(data)
raw = np.abs(raw[H[:-1, ]]).max(axis=0)
return _to_centered_series(raw, data.index, samples_per_window)
return _to_centered_series(raw, data.index, samples_per_window, H)


def _line_length_windowed(data, H, samples_per_window,
sample_interval):
raw = np.sqrt(np.diff(data)**2. + sample_interval**2.)
raw = np.sum(raw[H[:-1, ]], axis=0)
return _to_centered_series(raw, data.index, samples_per_window)
return _to_centered_series(raw, data.index, samples_per_window, H)


def _to_centered_series(vals, idx, samples_per_window):
vals = np.pad(vals, ((0, len(idx) - len(vals)),), mode='constant',
constant_values=np.nan)
shift = samples_per_window // 2 # align = 'center' only
return pd.Series(index=idx, data=vals).shift(shift)
def _to_centered_series(vals, idx, samples_per_window, H):
# Get center of interval using zero-indexing, round down to nearest
# index if there are an even number of rows
if samples_per_window % 2 == 0:
center_row = samples_per_window//2 - 1
else:
center_row = samples_per_window//2

try:
# Maintain tz that is stripped when idx is put in H
if idx.tz is not None:
c = pd.DatetimeIndex(idx.values[H][center_row, :],
tz='UTC').tz_convert(idx.tz)
else:
c = idx.values[H][center_row, :]
# If the index is a range
except AttributeError:
c = idx.values[H][center_row, :]

def _clear_sample_index(clear_windows, samples_per_window, align, H):
# Assign summary values for each interval to the indices of the center row
centered = pd.Series(index=idx, dtype='object')
centered.loc[c] = vals
return centered


def _clear_sample_index(clear_windows, samples_per_window, gaps, H, align):
"""
Returns indices of clear samples in clear windows
"""
Expand All @@ -635,12 +654,22 @@ def _clear_sample_index(clear_windows, samples_per_window, align, H):
# shift = - (samples_per_window // 2)
# else:
# shift = 0
shift = -(samples_per_window // 2)
idx = clear_windows.shift(shift)

# Account for the row # on which the interval is centered not actually
# being in row samples_per_window // 2 if samples_per_window is even
if samples_per_window % 2 == 0:
shift = -(samples_per_window // 2 - 1)
else:
shift = -(samples_per_window // 2)
clear_cols = clear_windows.shift(shift)
# drop rows at the end corresponding to windows past the end of data
idx = idx.drop(clear_windows.index[1 - samples_per_window:])
idx = idx.astype(bool) # shift changed type to object
clear_samples = np.unique(H[:, idx])
clear_cols = clear_cols.drop(clear_windows.index[1 - samples_per_window:])
clear_cols = clear_cols.astype(bool) # shift changed type to object
# Boolean mask for column indices of intervals with temporal gaps
gap_cols = [True if c not in gaps else False for c in range(0,
len(clear_windows) - (samples_per_window - 1))]
mask = np.logical_and(clear_cols, gap_cols)
clear_samples = np.unique(H[:, mask])
return clear_samples


Expand Down Expand Up @@ -756,8 +785,6 @@ def detect_clearsky(measured, clearsky, times=None, infer_limits=False,
------
ValueError
If measured is not a Series and times is not provided
NotImplementedError
If timestamps are not equally spaced

References
----------
Expand All @@ -784,6 +811,11 @@ def detect_clearsky(measured, clearsky, times=None, infer_limits=False,
* option to return individual test components and clearsky scaling
parameter
* uses centered windows (Matlab function uses left-aligned windows)

2023-03-24 - This algorithm does accept data with skipped or missing
timestamps. The DatetimeIndex (either times or index of measured)
provided still must be regular, i.e. the length of intervals between
points are equal except in the case that data is missing.
"""

if times is None:
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I feel like this if and try should move down and use ispandas, optional cleanup.

Expand All @@ -803,6 +835,13 @@ def detect_clearsky(measured, clearsky, times=None, infer_limits=False,

if not isinstance(clearsky, pd.Series):
clear = pd.Series(clearsky, index=times)
# This clause is designed to address cases where measured has missing time
# steps - if this is the case, clear should be set to have the same
# missing time intervals as measured. Not doing this may cause issues with
# arrays of different lengths when evaluating comparison criteria and
# when indexing the Hankel matrix to construct clear_samples
elif len(clearsky.index) != len(times):
clear = pd.Series(clearsky, index=times)
else:
clear = clearsky

Expand All @@ -828,6 +867,19 @@ def detect_clearsky(measured, clearsky, times=None, infer_limits=False,
H = hankel(np.arange(samples_per_window),
np.arange(samples_per_window-1, len(times)))

# Identify intervals with missing indices
time_h = times.values[H]
# Get maximum time step (in minutes) between consecutive Timestamps
# for each column
time_h_diff_max = np.max(np.diff(time_h, axis=0) /
np.timedelta64(1, '60s'), axis=0)
# Get column indices where max time step > sample_interval
gaps = np.ravel(np.argwhere(time_h_diff_max > sample_interval))
# Get column indices where at least one of the values is a NaN
gaps = set().union(*[
gaps, np.ravel(np.argwhere(np.isnan(meas\
.values[H].mean(axis=0))))])

# calculate measurement statistics
meas_mean, meas_max, meas_slope_nstd, meas_slope = _calc_stats(
meas, samples_per_window, sample_interval, H)
Expand All @@ -853,26 +905,55 @@ def detect_clearsky(measured, clearsky, times=None, infer_limits=False,
line_diff = meas_line_length - clear_line_length
slope_max_diff = _max_diff_windowed(
meas - scaled_clear, H, samples_per_window)

# evaluate comparison criteria
c1 = np.abs(meas_mean - alpha*clear_mean) < mean_diff
c2 = np.abs(meas_max - alpha*clear_max) < max_diff
c3 = (line_diff > lower_line_length) & (line_diff < upper_line_length)
# Condition 1
c1 = np.abs(meas_mean - alpha*clear_mean)
c1_where_nan = c1[c1.isna()].index
c1 = c1 < mean_diff
# Condition 2
c2 = np.abs(meas_max - alpha*clear_max)
c2_where_nan = c2[c2.isna()].index
c2 = c2 < max_diff
# Condition 3a & 3b
c3_where_nan = line_diff[line_diff.isna()].index
c3a = line_diff > lower_line_length
c3b = line_diff < upper_line_length
c3 = np.logical_and(c3a, c3b)
# Condition 4
c4_where_nan = meas_slope_nstd[meas_slope_nstd.isna()].index
c4 = meas_slope_nstd < var_diff
# Condition 5
c5_where_nan = slope_max_diff[slope_max_diff.isna()].index
c5 = slope_max_diff < slope_dev
c6 = (clear_mean != 0) & ~np.isnan(clear_mean)
clear_windows = c1 & c2 & c3 & c4 & c5 & c6
# Condition 6
c6 = clear_mean != 0
c6_where_nan = clear_mean[clear_mean.isna()].index

# np.logical_and() maintains NaNs
clear_windows = pd.Series(
index=times, data=np.logical_and.reduce([c1, c2, c3, c4, c5, c6]))
windows_where_nan = pd.DatetimeIndex(set().union(*[
c1_where_nan,c2_where_nan, c3_where_nan, c4_where_nan, c5_where_nan,
c6_where_nan]))
clear_windows[windows_where_nan] = np.nan

# create array to return
clear_samples = np.full_like(meas, False, dtype='bool')
# dtype='bool' removed because it typecast NaNs to False values
clear_samples = np.full_like(meas, False)
# find the samples contained in any window classified as clear
idx = _clear_sample_index(clear_windows, samples_per_window, 'center',
H)
idx = _clear_sample_index(clear_windows, samples_per_window, gaps, H,
'center')
clear_samples[idx] = True

# Assign NaN to datapoints that were originally NaNs
where_nan = np.argwhere(np.isnan(meas.values))
clear_samples[where_nan] = np.nan

# find a new alpha
previous_alpha = alpha
clear_meas = meas[clear_samples]
clear_clear = clear[clear_samples]
clear_meas = meas[idx]
clear_clear = clear[idx]

def rmse(alpha):
return np.sqrt(np.mean((clear_meas - alpha*clear_clear)**2))
Expand Down
64 changes: 64 additions & 0 deletions pvlib/data/detect_clearsky_data_missing1.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,64 @@
# latitude: 35.04
# longitude: -106.62
# elevation: 1619.0
,CS,GHI,Clear or not
2020-01-01 11:00:00-07:00,536.302172709558,509.4870640740801,1.0
2020-01-01 11:01:00-07:00,537.591516239233,510.7119404272713,1.0
2020-01-01 11:02:00-07:00,538.8629773699926,511.91982850149293,1.0
2020-01-01 11:03:00-07:00,540.1165267379411,513.110700401044,1.0
2020-01-01 11:04:00-07:00,541.3521354397624,514.2845286677742,1.0
2020-01-01 11:05:00-07:00,542.5697750193947,515.441286268425,1.0
2020-01-01 11:06:00-07:00,543.7694182656351,516.5809473523533,1.0
2020-01-01 11:07:00-07:00,544.9510360161104,517.7034842153048,1.0
2020-01-01 11:08:00-07:00,546.1146019716558,518.808871873073,1.0
2020-01-01 11:09:00-07:00,547.2600894760479,519.8970850022455,1.0
2020-01-01 11:10:00-07:00,548.3874723122931,520.9680986966785,1.0
2020-01-01 11:11:00-07:00,549.4967247102148,522.021888474704,1.0
2020-01-01 11:12:00-07:00,550.5878213431366,523.0584302759797,1.0
2020-01-01 11:13:00-07:00,551.6607373248604,524.0777004586174,1.0
2020-01-01 11:14:00-07:00,552.7154482165139,525.0796758056882,1.0
2020-01-01 11:15:00-07:00,553.7519300136697,526.0643335129862,1.0
2020-01-01 11:16:00-07:00,554.7701591532945,527.0316511956297,1.0
2020-01-01 11:17:00-07:00,555.7701131753,527.981607516535,1.0
2020-01-01 11:18:00-07:00,556.7517680497913,528.9141796473017,1.0
2020-01-01 11:19:00-07:00,557.7151022068979,529.829347096553,1.0
2020-01-01 11:20:00-07:00,558.6600938303893,530.7270891388698,1.0
2020-01-01 11:21:00-07:00,559.5867215409612,531.6073854639131,1.0
2020-01-01 11:22:00-07:00,560.4949643935382,532.4702161738613,1.0
2020-01-01 11:23:00-07:00,561.3848018765772,533.3155617827483,1.0
2020-01-01 11:24:00-07:00,562.2562139096694,534.1434032141859,1.0
2020-01-01 11:25:00-07:00,563.1091808493264,534.9537218068601,1.0
2020-01-01 11:26:00-07:00,563.9436834785143,535.7464993045886,1.0
2020-01-01 11:27:00-07:00,564.7597030125947,536.5217178619649,1.0
2020-01-01 11:28:00-07:00,565.5572210969589,537.2793600421109,1.0
2020-01-01 11:29:00-07:00,566.336220321224,538.0194093051628,1.0
2020-01-01 11:31:00-07:00,567.8385900341821,539.446660532473,1.0
2020-01-01 11:32:00-07:00,568.5619273418005,540.1338309747105,1.0
2020-01-01 11:33:00-07:00,569.2666778570792,540.8033439642253,1.0
2020-01-01 11:34:00-07:00,569.9528257924741,541.4551845028503,1.0
2020-01-01 11:35:00-07:00,570.6203557904192,542.0893380008982,1.0
2020-01-01 11:36:00-07:00,571.2692529152785,542.7057902695145,1.0
2020-01-01 11:37:00-07:00,571.8995026579759,543.304527525077,1.0
2020-01-01 11:38:00-07:00,572.5110909343163,543.8855363876004,1.0
2020-01-01 11:39:00-07:00,573.1040040834109,544.4488038792404,1.0
2020-01-01 11:40:00-07:00,573.6782292505169,544.994317787991,1.0
2020-01-01 11:41:00-07:00,574.2337528522768,545.522065209663,1.0
2020-01-01 11:42:00-07:00,574.7705628911892,546.0320347466297,1.0
2020-01-01 11:43:00-07:00,575.2886474013371,546.5242150312703,1.0
2020-01-01 11:44:00-07:00,575.7879948384899,546.9985950965654,1.0
2020-01-01 11:45:00-07:00,576.2685940834351,547.4551643792634,1.0
2020-01-01 11:46:00-07:00,576.7304344361013,547.8939127142962,1.0
2020-01-01 11:47:00-07:00,577.1735056190306,548.3148303380791,1.0
2020-01-01 11:48:00-07:00,577.5977977761287,548.7179078873222,1.0
2020-01-01 11:49:00-07:00,578.0033014716739,549.1031363980902,1.0
2020-01-01 11:50:00-07:00,578.3900076930416,549.4705073083895,1.0
2020-01-01 11:51:00-07:00,578.7579080863377,549.8200126820208,1.0
2020-01-01 11:52:00-07:00,579.1069939850056,550.1516442857553,1.0
2020-01-01 11:53:00-07:00,579.4372578890877,550.4653949946334,1.0
2020-01-01 11:54:00-07:00,579.7486924650192,550.7612578417682,1.0
2020-01-01 11:55:00-07:00,580.0412908007218,551.0392262606856,1.0
2020-01-01 11:56:00-07:00,580.3150464019636,551.2992940818655,1.0
2020-01-01 11:57:00-07:00,580.569953194532,551.5414555348053,1.0
2020-01-01 11:58:00-07:00,580.8060055234938,551.7657052473191,1.0
2020-01-01 11:59:00-07:00,581.0231981526458,551.9720382450136,1.0
2020-01-01 12:00:00-07:00,581.2215262659929,552.1604499526933,1.0
Expand Down
64 changes: 64 additions & 0 deletions pvlib/data/detect_clearsky_data_missing2.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,64 @@
# latitude: 35.04
# longitude: -106.62
# elevation: 1619.0
,CS,GHI,Clear or not
2020-01-01 11:00:00-07:00,536.302172709558,509.4870640740801,1.0
2020-01-01 11:01:00-07:00,537.591516239233,510.7119404272713,1.0
2020-01-01 11:02:00-07:00,538.8629773699926,511.91982850149293,1.0
2020-01-01 11:03:00-07:00,540.1165267379411,513.110700401044,1.0
2020-01-01 11:04:00-07:00,541.3521354397624,514.2845286677742,1.0
2020-01-01 11:05:00-07:00,542.5697750193947,515.441286268425,1.0
2020-01-01 11:06:00-07:00,543.7694182656351,516.5809473523533,1.0
2020-01-01 11:07:00-07:00,544.9510360161104,517.7034842153048,1.0
2020-01-01 11:08:00-07:00,546.1146019716558,518.808871873073,1.0
2020-01-01 11:09:00-07:00,547.2600894760479,519.8970850022455,1.0
2020-01-01 11:10:00-07:00,548.3874723122931,520.9680986966785,1.0
2020-01-01 11:11:00-07:00,549.4967247102148,522.021888474704,1.0
2020-01-01 11:12:00-07:00,550.5878213431366,523.0584302759797,1.0
2020-01-01 11:13:00-07:00,551.6607373248604,524.0777004586174,1.0
2020-01-01 11:14:00-07:00,552.7154482165139,525.0796758056882,1.0
2020-01-01 11:15:00-07:00,553.7519300136697,526.0643335129862,1.0
2020-01-01 11:16:00-07:00,554.7701591532945,527.0316511956297,1.0
2020-01-01 11:17:00-07:00,555.7701131753,527.981607516535,1.0
2020-01-01 11:18:00-07:00,556.7517680497913,528.9141796473017,1.0
2020-01-01 11:19:00-07:00,557.7151022068979,529.829347096553,1.0
2020-01-01 11:20:00-07:00,558.6600938303893,530.7270891388698,1.0
2020-01-01 11:21:00-07:00,559.5867215409612,531.6073854639131,1.0
2020-01-01 11:22:00-07:00,560.4949643935382,532.4702161738613,1.0
2020-01-01 11:23:00-07:00,561.3848018765772,533.3155617827483,1.0
2020-01-01 11:24:00-07:00,562.2562139096694,534.1434032141859,1.0
2020-01-01 11:25:00-07:00,563.1091808493264,534.9537218068601,1.0
2020-01-01 11:26:00-07:00,563.9436834785143,535.7464993045886,1.0
2020-01-01 11:27:00-07:00,564.7597030125947,536.5217178619649,1.0
2020-01-01 11:28:00-07:00,565.5572210969589,537.2793600421109,1.0
2020-01-01 11:29:00-07:00,566.336220321224,538.0194093051628,1.0
2020-01-01 11:31:00-07:00,567.8385900341821,539.446660532473,0.0
2020-01-01 11:32:00-07:00,568.5619273418005,540.1338309747105,0.0
2020-01-01 11:33:00-07:00,569.2666778570792,540.8033439642253,0.0
2020-01-01 11:34:00-07:00,569.9528257924741,541.4551845028503,0.0
2020-01-01 11:35:00-07:00,570.6203557904192,300.0,0.0
2020-01-01 11:36:00-07:00,571.2692529152785,200.0,0.0
2020-01-01 11:37:00-07:00,571.8995026579759,250.0,0.0
2020-01-01 11:38:00-07:00,572.5110909343163,310.0,0.0
2020-01-01 11:39:00-07:00,573.1040040834109,330.0,0.0
2020-01-01 11:40:00-07:00,573.6782292505169,544.994317787991,1.0
2020-01-01 11:41:00-07:00,574.2337528522768,545.522065209663,1.0
2020-01-01 11:42:00-07:00,574.7705628911892,546.0320347466297,1.0
2020-01-01 11:43:00-07:00,575.2886474013371,546.5242150312703,1.0
2020-01-01 11:44:00-07:00,575.7879948384899,546.9985950965654,1.0
2020-01-01 11:45:00-07:00,576.2685940834351,547.4551643792634,1.0
2020-01-01 11:46:00-07:00,576.7304344361013,547.8939127142962,1.0
2020-01-01 11:47:00-07:00,577.1735056190306,548.3148303380791,1.0
2020-01-01 11:48:00-07:00,577.5977977761287,548.7179078873222,1.0
2020-01-01 11:49:00-07:00,578.0033014716739,549.1031363980902,1.0
2020-01-01 11:50:00-07:00,578.3900076930416,549.4705073083895,1.0
2020-01-01 11:51:00-07:00,578.7579080863377,549.8200126820208,1.0
2020-01-01 11:52:00-07:00,579.1069939850056,550.1516442857553,1.0
2020-01-01 11:53:00-07:00,579.4372578890877,550.4653949946334,1.0
2020-01-01 11:54:00-07:00,579.7486924650192,550.7612578417682,1.0
2020-01-01 11:55:00-07:00,580.0412908007218,551.0392262606856,1.0
2020-01-01 11:56:00-07:00,580.3150464019636,551.2992940818655,1.0
2020-01-01 11:57:00-07:00,580.569953194532,551.5414555348053,1.0
2020-01-01 11:58:00-07:00,580.8060055234938,551.7657052473191,1.0
2020-01-01 11:59:00-07:00,581.0231981526458,551.9720382450136,1.0
2020-01-01 12:00:00-07:00,581.2215262659929,552.1604499526933,1.0
Expand Down
Loading