| \n", + " | plant_qr_code | \n", + "genotype | \n", + "replicate | \n", + "path | \n", + "qc_cylinder | \n", + "qc_code | \n", + "number_of_plants_cylinder | \n", + "primary_root_proofread | \n", + "lateral_root_proofread | \n", + "Unnamed: 9 | \n", + "Unnamed: 10 | \n", + "Unnamed: 11 | \n", + "Unnamed: 12 | \n", + "Instructions | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "1002_1 | \n", + "1002 | \n", + "1 | \n", + "h5s_predictions\\ES\\1002_1.h5 | \n", + "0 | \n", + "NaN | \n", + "3 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 1 | \n", + "5830_1 | \n", + "5830 | \n", + "1 | \n", + "h5s_predictions\\ES\\5830_1.h5 | \n", + "0 | \n", + "NaN | \n", + "2 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 2 | \n", + "5830_2 | \n", + "5830 | \n", + "2 | \n", + "h5s_predictions\\ES\\5830_2.h5 | \n", + "0 | \n", + "NaN | \n", + "3 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 3 | \n", + "5867_1 | \n", + "5867 | \n", + "1 | \n", + "h5s_predictions\\ES\\5867_1.h5 | \n", + "0 | \n", + "NaN | \n", + "3 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 4 | \n", + "5867_2 | \n", + "5867 | \n", + "2 | \n", + "h5s_predictions\\ES\\5867_2.h5 | \n", + "0 | \n", + "NaN | \n", + "3 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
4 rows × 316 columns
\n", + "3 rows × 316 columns
\n", "" ], "text/plain": [ " genotype lateral_count_min lateral_count_max lateral_count_mean \\\n", - "0 6039 1 7 5.082090 \n", - "1 7327 1 9 3.434109 \n", - "2 9535 1 13 6.007937 \n", - "3 997 4 9 7.000000 \n", + "0 7327 1 9 3.434109 \n", + "1 9535 1 13 6.007937 \n", + "2 997 4 9 7.000000 \n", "\n", " lateral_count_median lateral_count_std lateral_count_p5 \\\n", - "0 5.0 1.240176 3.00 \n", - "1 1.0 2.825260 1.00 \n", - "2 6.0 3.027640 1.00 \n", - "3 7.5 1.914854 4.25 \n", + "0 1.0 2.825260 1.00 \n", + "1 6.0 3.027640 1.00 \n", + "2 7.5 1.914854 4.25 \n", "\n", " lateral_count_p25 lateral_count_p75 lateral_count_p95 ... \\\n", - "0 4.0 6.00 7.0 ... \n", - "1 1.0 6.00 8.0 ... \n", - "2 4.0 8.00 11.0 ... \n", - "3 5.5 8.75 9.0 ... \n", + "0 1.0 6.00 8.0 ... \n", + "1 4.0 8.00 11.0 ... \n", + "2 5.5 8.75 9.0 ... \n", "\n", " network_distribution_ratio_p95 network_solidity_min network_solidity_max \\\n", - "0 0.757133 0.041121 0.150504 \n", - "1 0.679840 0.024168 0.293489 \n", - "2 0.677514 0.032377 0.166538 \n", - "3 0.550392 0.017635 0.028867 \n", + "0 0.679840 0.024168 0.293489 \n", + "1 0.677514 0.032377 0.166538 \n", + "2 0.550392 0.017635 0.028867 \n", "\n", " network_solidity_mean network_solidity_median network_solidity_std \\\n", - "0 0.062255 0.057276 0.019820 \n", - "1 0.092920 0.087395 0.062009 \n", - "2 0.055098 0.048888 0.023023 \n", - "3 0.021103 0.019285 0.004037 \n", + "0 0.092920 0.087395 0.062009 \n", + "1 0.055098 0.048888 0.023023 \n", + "2 0.021103 0.019285 0.004037 \n", "\n", " network_solidity_p5 network_solidity_p25 network_solidity_p75 \\\n", - "0 0.042815 0.048231 0.070095 \n", - "1 0.030521 0.041196 0.125539 \n", - "2 0.033393 0.038470 0.065840 \n", - "3 0.017699 0.017987 0.022816 \n", + "0 0.030521 0.041196 0.125539 \n", + "1 0.033393 0.038470 0.065840 \n", + "2 0.017699 0.017987 0.022816 \n", "\n", " network_solidity_p95 \n", - "0 0.098175 \n", - "1 0.214581 \n", - "2 0.092981 \n", - "3 0.027564 \n", + "0 0.214581 \n", + "1 0.092981 \n", + "2 0.027564 \n", "\n", - "[4 rows x 316 columns]" + "[3 rows x 316 columns]" ] }, - "execution_count": 92, + "execution_count": 30, "metadata": {}, "output_type": "execute_result" } diff --git a/sleap_roots/series.py b/sleap_roots/series.py index b6d35a4..5b9e4d6 100644 --- a/sleap_roots/series.py +++ b/sleap_roots/series.py @@ -39,6 +39,7 @@ class Series: series_name: Name of the series derived from the HDF5 filename. expected_count: Fetch the expected plant count for this series from the CSV. group: Group name for the series from the CSV. + qc_fail: Flag to indicate if the series failed QC from the CSV. """ h5_path: Optional[str] = None @@ -161,6 +162,20 @@ def group(self) -> str: print(f"No group found for series {self.series_name} in CSV.") return np.nan + @property + def qc_fail(self) -> Union[int, float]: + """Flag to indicate if the series failed QC from the CSV.""" + if not self.csv_path or not Path(self.csv_path).exists(): + print("CSV path is not set or the file does not exist.") + return np.nan + df = pd.read_csv(self.csv_path) + try: + # Match the series_name (or plant_qr_code in the CSV) to fetch the QC flag + return df[df["plant_qr_code"] == self.series_name]["qc_cylinder"].iloc[0] + except IndexError: + print(f"No QC flag found for series {self.series_name} in CSV.") + return np.nan + def __len__(self) -> int: """Length of the series (number of images).""" return len(self.video) diff --git a/sleap_roots/trait_pipelines.py b/sleap_roots/trait_pipelines.py index 66a7475..ac1f8c0 100644 --- a/sleap_roots/trait_pipelines.py +++ b/sleap_roots/trait_pipelines.py @@ -401,12 +401,13 @@ def compute_multiple_dicots_traits( csv_suffix: The suffix to append to the CSV file name. Default is ".all_frames_summary.csv". Returns: - A dictionary containing the series name, group, aggregated traits, and summary statistics. + A dictionary containing the series name, group, qc_fail, aggregated traits, and summary statistics. """ # Initialize the return structure with the series name and group result = { "series": str(series.series_name), "group": str(series.group), + "qc_fail": series.qc_fail, "traits": {}, "summary_stats": {}, } @@ -528,6 +529,11 @@ def compute_multiple_dicots_traits_for_groups( # Group series by their group property series_groups = {} for series in series_list: + # Exclude series with qc_fail flag set to 1 + if int(series.qc_fail) == 1: + print(f"Skipping series '{series.series_name}' due to qc_fail flag.") + continue + # Get the group name from the series object group_name = str(series.group) if group_name not in series_groups: series_groups[group_name] = {"names": [], "series": []} @@ -733,7 +739,7 @@ def compute_batch_multiple_dicots_traits_for_groups( Returns: A pandas DataFrame of computed traits summarized over all frames of each - series. The resulting dataframe will have a row for each series and a column + group. The resulting dataframe will have a row for each series and a column for each series-level summarized trait. Summarized traits are prefixed with the trait name and an underscore, diff --git a/tests/data/multiple_arabidopsis_11do/merged_proofread_samples_03122024.csv b/tests/data/multiple_arabidopsis_11do/merged_proofread_samples_03122024.csv index a7a9ae7..2e100ad 100644 --- a/tests/data/multiple_arabidopsis_11do/merged_proofread_samples_03122024.csv +++ b/tests/data/multiple_arabidopsis_11do/merged_proofread_samples_03122024.csv @@ -15,7 +15,7 @@ 6030_2,6030,2,h5s_predictions\ES\6030_2.h5,0,,3,,,,,,, 6035_1,6035,1,h5s_predictions\ES\6035_1.h5,0,,3,,,,,,, 6035_2,6035,2,h5s_predictions\ES\6035_2.h5,0,,3,,,,,,, -6039_1,6039,1,h5s_predictions\ES\6039_1.h5,0,,2,1,1,,,,, +6039_1,6039,1,h5s_predictions\ES\6039_1.h5,1,,2,1,1,,,,, 6039_2,6039,2,h5s_predictions\ES\6039_2.h5,0,,3,,,,,,, 6042_1,6042,1,h5s_predictions\ES\6042_1.h5,0,,3,,,,,,, 6042_2,6042,2,h5s_predictions\ES\6042_2.h5,0,,3,,,,,,, diff --git a/tests/test_series.py b/tests/test_series.py index 9c528a1..207f438 100644 --- a/tests/test_series.py +++ b/tests/test_series.py @@ -52,7 +52,7 @@ def csv_path(tmp_path): # Create a dummy CSV file csv_path = tmp_path / "dummy.csv" csv_path.write_text( - "plant_qr_code,number_of_plants_cylinder,genotype\ndummy,10,1100\nseries2,15,Kitaake-X\n" + "plant_qr_code,number_of_plants_cylinder,genotype,qc_cylinder\ndummy,10,1100,0\nseries2,15,Kitaake-X,1\n" ) return csv_path @@ -85,6 +85,11 @@ def test_expected_count(series_instance, csv_path): assert series_instance.expected_count == 10 +def test_qc_cylinder(series_instance, csv_path): + series_instance.csv_path = csv_path + assert series_instance.qc_fail == 0 + + def test_len(): series = Series(video=["frame1", "frame2"]) assert len(series) == 2