Skip to content
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

Jump to bottom

Update to custom static and streaming methods to use a specific column #73

Merged
merged 2 commits into from
Oct 12, 2021
Merged

Update to custom static and streaming methods to use a specific column #73

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
abecf89
Update to custom static and streaming methods to use a specific column
kaklise Oct 11, 2021
301a5e2
Updated release notes
kaklise Oct 11, 2021
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
1 change: 1 addition & 0 deletions documentation/whatsnew/v0.2.1.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
v0.2.1 (main)
--------------------------

* Bug fix in custom static and streaming quality control tests to use a specific column
* Minor updates for testing and documentation
* Added GitHub Actions and Python 3.9 tests

6 changes: 3 additions & 3 deletions pecos/monitoring.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -788,7 +788,7 @@ def check_custom_static(self, quality_control_func, key=None, min_failures=1,

# Function that operates on the entire dataset and returns a mask and
# metadata for the entire dataset
mask, metadata = quality_control_func(self.df)
mask, metadata = quality_control_func(df)
assert isinstance(mask, pd.DataFrame), 'mask returned by quality_control_func must be of type pd.DataFrame'
assert isinstance(metadata, pd.DataFrame), 'metadata returned by quality_control_func must be of type pd.DataFrame'

Expand Down Expand Up @@ -852,7 +852,7 @@ def check_custom_streaming(self, quality_control_func, window, key=None,
# The streaming framework uses numpy arrays to improve performance but
# still expects pandas DataFrames and Series in the user defined quality
# control function to keep data types consitent on the user side.
np_mask = pd.DataFrame(True, index=self.df.index, columns=self.df.columns).values
np_mask = pd.DataFrame(True, index=df.index, columns=df.columns).values
np_data = df.values.astype('float64')

ti = df.index.get_loc(df.index[0]+history_window)
Expand Down Expand Up @@ -881,7 +881,7 @@ def check_custom_streaming(self, quality_control_func, window, key=None,
np_data[t][check_rebase] = df.iloc[t][check_rebase]
rebase_count = rebase_count + sum(check_rebase)

mask = pd.DataFrame(np_mask, index=self.df.index, columns=self.df.columns)
mask = pd.DataFrame(np_mask, index=df.index, columns=df.columns)
self._append_test_results(mask, error_message, min_failures)

# Convert metadata to a dataframe
Expand Down
10 changes: 9 additions & 1 deletion pecos/tests/test_monitoring.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -590,11 +590,15 @@ def custom_func(data):
percent = 1-self.pm.test_results['Timesteps'].sum()/N
assert_almost_equal(percent, 0.95, 2) # 95% within 2 std

# using a specific key
metadata_A = self.pm.check_custom_static(custom_func, key='A', error_message='Static')
assert_frame_equal(metadata[['A']], metadata_A)

# Functional tests
results = pecos.monitoring.check_custom_static(self.pm.data, custom_func, error_message='Static')
percent = 1-results['test_results']['Timesteps'].sum()/N
assert_almost_equal(percent, 0.95, 2) # 95% within 2 std

def test_custom_streaming(self):

def custom_func(data_pt, history):
Expand All @@ -607,6 +611,10 @@ def custom_func(data_pt, history):
percent = 1-self.pm.test_results['Timesteps'].sum()/N
assert_almost_equal(percent, 0.95, 2) # 95% within 2 std

# using a specific key
metadata_A = self.pm.check_custom_streaming(custom_func, 50, key='A', error_message='Streaming')
assert_frame_equal(metadata[['A']], metadata_A)

# Functional tests
results = pecos.monitoring.check_custom_streaming(self.pm.data, custom_func, 50, error_message='Streaming')
percent = 1-results['test_results']['Timesteps'].sum()/N
Expand Down