fix get_statistics_relevance_table #672
Conversation
|
🚀 Deployed on https://deploy-preview-672--etna-docs.netlify.app |
Codecov Report
@@ Coverage Diff @@
## master #672 +/- ##
==========================================
+ Coverage 83.80% 84.09% +0.28%
==========================================
Files 119 119
Lines 6399 6412 +13
==========================================
+ Hits 5363 5392 +29
+ Misses 1036 1020 -16
📣 Codecov can now indicate which changes are the most critical in Pull Requests. Learn more |
tests/test_analysis/test_feature_relevance/test_relevance_table.py
Outdated
Show resolved
Hide resolved
tests/test_analysis/test_feature_relevance/test_relevance_table.py
Outdated
Show resolved
Hide resolved
tests/test_analysis/test_feature_relevance/test_relevance_table.py
Outdated
Show resolved
Hide resolved
| ) | ||
| df_exog_now["target"] = df_now | ||
| df_exog_now = df_exog_now.dropna() | ||
| if len(df_exog_now) != len(df_now) and not none_warning: |
There was a problem hiding this comment.
Add this warning also to the second method and add test case
| ) | ||
| df_exog_now["target"] = df_now | ||
| df_exog_now = df_exog_now.dropna() | ||
| if len(df_exog_now) != len(df_now) and not none_warning_raised: |
There was a problem hiding this comment.
We need to drop the nan values before casting categoricals to float, exchange this two sections
| "Exogenous data contains columns with category type! It will be converted to float. If this is not desired behavior, use encoders." | ||
| ) | ||
| df_exog_now["target"] = df_now | ||
| df_exog_now = df_exog_now.dropna() |
There was a problem hiding this comment.
Let's drop nans the same way as here to make this step similar in both methods
| df = pd.DataFrame({"segment": seg, "timestamp": timestamps, "target": target}) | ||
| ts = TSDataset.to_dataset(df) | ||
|
|
||
| cast = ["1.1"] * 10 + ["2"] * 10 + ["56.1"] * 10 |
There was a problem hiding this comment.
Add nans to this column + test for this case(nans in castable categorical column)
|
|
||
| def test_target_none_model_table(exog_and_target_dfs): | ||
| df, df_exog = exog_and_target_dfs | ||
| tmp = np.arange(len(df["a", "target"]), dtype=float) |
There was a problem hiding this comment.
Let'c create the separate fixture for this case, you can make it out of the exog_and_target_dfs
IMPORTANT: Please do not create a Pull Request without creating an issue first.
Before submitting (must do checklist)
Type of Change
Proposed Changes
Related Issue
Closing issues
#668