Merge pull request #76 from arnor-sigurdsson/minor-target-label-optim…

…izations Minor target label optimizations
arnor-sigurdsson · Apr 13, 2024 · 1bc1082 · 1bc1082
2 parents 172ddc5 + 62bef82
commit 1bc1082
Show file tree

Hide file tree

Showing 236 changed files with 13,778 additions and 13,202 deletions.
diff --git a/.github/workflows/coverage.yml b/.github/workflows/coverage.yml
@@ -9,9 +9,9 @@ jobs:
     name: Test group ${{ matrix.group }}
     runs-on: ubuntu-22.04
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Setup Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: '3.11'
         architecture: x64
@@ -22,7 +22,8 @@ jobs:
         pip install tox==4.14.1
         pip install poetry==1.8.2
         tox -e py_partial
-    - name: Publish coverage to Codecov
-      uses: codecov/codecov-action@v3
+    - name: Generate report
+      uses: codecov/codecov-action@v4
       with:
         fail_ci_if_error: true
+        token: ${{ secrets.CODECOV_TOKEN }}
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
@@ -15,9 +15,9 @@ jobs:
         python-version: ['3.11']
         group: [1, 2, 3, 4, 5]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }} on ${{ matrix.os }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Run tests with Python ${{ matrix.python-version }} on ${{ matrix.os }}
@@ -53,7 +53,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Release
         id: release
@@ -68,8 +68,8 @@ jobs:
     needs: [build]
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: '3.11'
           architecture: x64

diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -10,9 +10,9 @@ jobs:
         python-version: ['3.11']
         group: [1, 2, 3, 4, 5]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }} on ${{ matrix.os }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Run tests with Python ${{ matrix.python-version }} on ${{ matrix.os }}

diff --git a/docs/acknowledgements.rst b/docs/acknowledgements.rst
@@ -114,7 +114,7 @@ and so on:
 
 - ``tomlkit``  – Sébastien Eustace: Style preserving TOML library
 
-- ``gdown``  – Kentaro Wada: Google Drive direct download of big files.
+- ``gdown`` : Google Drive Public File/Folder Downloader
 
 - ``hypothesis``  – David R. MacIver and Zac Hatfield-Dodds: A library for property-based testing
 

diff --git a/docs/doc_modules/a_using_eir/h_array_tutorial.py b/docs/doc_modules/a_using_eir/h_array_tutorial.py
@@ -452,6 +452,8 @@ def plot_validation_perf_average(data: pd.DataFrame) -> plt.Figure:
             color_index = 1
         elif model_type == "TRANSFORMER":
             color_index = 2
+        else:
+            raise ValueError(f"Unknown model type: {model_type}")
 
         line_style = line_style_dict[model_dim.lower()]
 

diff --git a/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/GLN_1_DEPLOY.txt b/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/GLN_1_DEPLOY.txt
@@ -1,2 +1,2 @@
 eirserve \
---model-path eir_tutorials/tutorial_runs/a_using_eir/tutorial_01_run/saved_models/tutorial_01_run_model_600_perf-average=0.8834.pt
+--model-path eir_tutorials/tutorial_runs/a_using_eir/tutorial_01_run/saved_models/tutorial_01_run_model_600_perf-average=0.8764.pt
diff --git a/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/GLN_1_PREDICT.txt b/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/GLN_1_PREDICT.txt
@@ -2,6 +2,6 @@ eirpredict \
 --global_configs eir_tutorials/a_using_eir/01_basic_tutorial/conf/tutorial_01_globals.yaml \
 --input_configs eir_tutorials/a_using_eir/01_basic_tutorial/conf/tutorial_01_input.yaml \
 --output_configs eir_tutorials/a_using_eir/01_basic_tutorial/conf/tutorial_01_outputs.yaml \
---model_path eir_tutorials/tutorial_runs/a_using_eir/tutorial_01_run/saved_models/tutorial_01_run_model_600_perf-average=0.8834.pt \
+--model_path eir_tutorials/tutorial_runs/a_using_eir/tutorial_01_run/saved_models/tutorial_01_run_model_600_perf-average=0.8764.pt \
 --evaluate \
 --output_folder eir_tutorials/tutorial_runs/a_using_eir/tutorial_01_run/test_predictions/known_outputs
diff --git a/...tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/GLN_1_PREDICT_UNKNOWN.txt b/...tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/GLN_1_PREDICT_UNKNOWN.txt
@@ -2,5 +2,5 @@ eirpredict \
 --global_configs eir_tutorials/a_using_eir/01_basic_tutorial/conf/tutorial_01_globals.yaml \
 --input_configs eir_tutorials/a_using_eir/01_basic_tutorial/conf/tutorial_01_input.yaml \
 --output_configs eir_tutorials/a_using_eir/01_basic_tutorial/conf/tutorial_01_outputs_unknown.yaml \
---model_path eir_tutorials/tutorial_runs/a_using_eir/tutorial_01_run/saved_models/tutorial_01_run_model_600_perf-average=0.8834.pt \
+--model_path eir_tutorials/tutorial_runs/a_using_eir/tutorial_01_run/saved_models/tutorial_01_run_model_600_perf-average=0.8764.pt \
 --output_folder eir_tutorials/tutorial_runs/a_using_eir/tutorial_01_run/test_predictions/unknown_outputs
diff --git a/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/eirpredict_help.txt b/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/eirpredict_help.txt
@@ -1,4 +1,4 @@
-06:51:34 - INFO - eir.train_utils.utils - Global random seed set to 0.
+14:39:24 - INFO - eir.train_utils.utils - Global random seed set to 0.
 usage: eirpredict [-h] [--global_configs [GLOBAL_CONFIGS ...]]
                   [--input_configs [INPUT_CONFIGS ...]]
                   [--fusion_configs [FUSION_CONFIGS ...]]

diff --git a/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/eirtrain_help.txt b/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/eirtrain_help.txt
@@ -1,4 +1,4 @@
-06:51:27 - INFO - eir.train_utils.utils - Global random seed set to 0.
+14:39:17 - INFO - eir.train_utils.utils - Global random seed set to 0.
 usage: eirtrain [-h] --global_configs GLOBAL_CONFIGS [GLOBAL_CONFIGS ...]
                 [--input_configs [INPUT_CONFIGS ...]]
                 [--fusion_configs [FUSION_CONFIGS ...]] --output_configs

diff --git a/.../tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/experiment_01_folder.txt b/.../tutorials/tutorial_files/a_using_eir/01_basic_tutorial/commands/experiment_01_folder.txt
@@ -28,5 +28,18 @@ eir_tutorials/tutorial_runs/a_using_eir/tutorial_01_run/
 │           ├── training_curve_MCC.pdf
 │           └── training_curve_ROC-AUC-MACRO.pdf
 ├── saved_models
+├── test_predictions
+│   ├── known_outputs
+│   │   ├── ancestry_output
+│   │   │   └── Origin
+│   │   │       ├── confusion_matrix.pdf
+│   │   │       ├── mc_pr_curve.pdf
+│   │   │       ├── mc_roc_curve.pdf
+│   │   │       └── predictions.csv
+│   │   └── calculated_metrics.json
+│   └── unknown_outputs
+│       └── ancestry_output
+│           └── Origin
+│               └── predictions.csv
 ├── training_curve_LOSS-AVERAGE.pdf
 └── training_curve_PERF-AVERAGE.pdf
diff --git a/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/csv_preview.html b/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/csv_preview.html
@@ -14,59 +14,59 @@
   </thead>
   <tbody>
     <tr>
-      <td>A306</td>
-      <td>Europe</td>
-      <td>2</td>
-      <td>0.56</td>
-      <td>-2.86</td>
-      <td>3.78</td>
-      <td>-1.07</td>
-      <td>1.51</td>
-      <td>-2.90</td>
+      <td>MAL-005</td>
+      <td>Sub-Saharan_Africa</td>
+      <td>5</td>
+      <td>-1.61</td>
+      <td>-1.88</td>
+      <td>-2.82</td>
+      <td>0.81</td>
+      <td>-0.37</td>
+      <td>4.79</td>
     </tr>
     <tr>
-      <td>A325</td>
-      <td>Europe</td>
-      <td>2</td>
-      <td>0.66</td>
-      <td>-2.69</td>
-      <td>2.85</td>
-      <td>-1.91</td>
-      <td>2.80</td>
-      <td>-2.72</td>
+      <td>MAL-009</td>
+      <td>Sub-Saharan_Africa</td>
+      <td>5</td>
+      <td>-1.92</td>
+      <td>-2.09</td>
+      <td>-2.75</td>
+      <td>0.75</td>
+      <td>0.03</td>
+      <td>4.65</td>
     </tr>
     <tr>
-      <td>A343</td>
-      <td>Europe</td>
-      <td>2</td>
-      <td>0.52</td>
-      <td>-2.22</td>
-      <td>2.57</td>
-      <td>-2.39</td>
-      <td>3.27</td>
-      <td>-2.18</td>
+      <td>MAL-011</td>
+      <td>Sub-Saharan_Africa</td>
+      <td>5</td>
+      <td>-1.91</td>
+      <td>-2.12</td>
+      <td>-2.75</td>
+      <td>1.32</td>
+      <td>-0.56</td>
+      <td>4.68</td>
     </tr>
     <tr>
-      <td>A362</td>
-      <td>Europe</td>
-      <td>2</td>
-      <td>2.12</td>
-      <td>-2.69</td>
-      <td>3.00</td>
-      <td>-1.51</td>
-      <td>0.75</td>
-      <td>-3.09</td>
+      <td>MAL-012</td>
+      <td>Sub-Saharan_Africa</td>
+      <td>5</td>
+      <td>-1.53</td>
+      <td>-1.95</td>
+      <td>-2.84</td>
+      <td>0.56</td>
+      <td>-0.20</td>
+      <td>4.67</td>
     </tr>
     <tr>
-      <td>A374</td>
-      <td>Europe</td>
-      <td>2</td>
-      <td>0.16</td>
-      <td>-2.47</td>
-      <td>3.08</td>
-      <td>-1.93</td>
-      <td>2.75</td>
-      <td>-2.60</td>
+      <td>MAL-014</td>
+      <td>Sub-Saharan_Africa</td>
+      <td>5</td>
+      <td>-1.56</td>
+      <td>-2.02</td>
+      <td>-2.85</td>
+      <td>0.73</td>
+      <td>-0.27</td>
+      <td>4.80</td>
     </tr>
   </tbody>
 </table><br>
diff --git a/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/csv_preview_unknown.html b/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/csv_preview_unknown.html
@@ -13,48 +13,48 @@
   <tbody>
     <tr>
       <td>HGDP01358</td>
-      <td>0.29</td>
-      <td>-2.02</td>
-      <td>4.00</td>
-      <td>-1.76</td>
-      <td>1.01</td>
-      <td>-2.96</td>
+      <td>-0.48</td>
+      <td>-2.05</td>
+      <td>4.80</td>
+      <td>-0.62</td>
+      <td>-0.21</td>
+      <td>-2.98</td>
     </tr>
     <tr>
       <td>HG04182.SG</td>
-      <td>4.82</td>
-      <td>-0.38</td>
-      <td>-1.41</td>
-      <td>-1.28</td>
-      <td>-2.03</td>
-      <td>-1.59</td>
+      <td>4.23</td>
+      <td>0.50</td>
+      <td>-1.97</td>
+      <td>-0.91</td>
+      <td>-2.86</td>
+      <td>-1.24</td>
     </tr>
     <tr>
       <td>HG02870.SG</td>
-      <td>-1.56</td>
-      <td>-2.16</td>
-      <td>-2.62</td>
-      <td>1.95</td>
-      <td>-1.53</td>
-      <td>4.26</td>
+      <td>-1.68</td>
+      <td>-2.06</td>
+      <td>-2.74</td>
+      <td>1.93</td>
+      <td>-1.36</td>
+      <td>4.48</td>
     </tr>
     <tr>
       <td>HGDP00720</td>
-      <td>2.62</td>
-      <td>2.31</td>
-      <td>1.28</td>
-      <td>-2.43</td>
-      <td>-2.29</td>
-      <td>-2.79</td>
+      <td>2.44</td>
+      <td>3.63</td>
+      <td>-0.12</td>
+      <td>-2.71</td>
+      <td>-2.34</td>
+      <td>-2.55</td>
     </tr>
     <tr>
       <td>S_Kinh-1.DG</td>
-      <td>3.73</td>
-      <td>2.17</td>
-      <td>0.08</td>
-      <td>-2.93</td>
-      <td>-2.16</td>
-      <td>-2.66</td>
+      <td>3.01</td>
+      <td>3.51</td>
+      <td>-1.06</td>
+      <td>-2.78</td>
+      <td>-2.39</td>
+      <td>-2.51</td>
     </tr>
   </tbody>
 </table><br>
diff --git a/...es/a_using_eir/01_basic_tutorial/figures/tutorial_01_confusion_matrix_gln_1.png b/...es/a_using_eir/01_basic_tutorial/figures/tutorial_01_confusion_matrix_gln_1.png
diff --git a/...es/a_using_eir/01_basic_tutorial/figures/tutorial_01_confusion_matrix_gln_2.png b/...es/a_using_eir/01_basic_tutorial/figures/tutorial_01_confusion_matrix_gln_2.png
diff --git a/.../a_using_eir/01_basic_tutorial/figures/tutorial_01_training_curve_ACC_gln_1.png b/.../a_using_eir/01_basic_tutorial/figures/tutorial_01_training_curve_ACC_gln_1.png
diff --git a/.../a_using_eir/01_basic_tutorial/figures/tutorial_01_training_curve_ACC_gln_2.png b/.../a_using_eir/01_basic_tutorial/figures/tutorial_01_training_curve_ACC_gln_2.png
diff --git a/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/serve_results/predictions.json b/docs/tutorials/tutorial_files/a_using_eir/01_basic_tutorial/serve_results/predictions.json
@@ -7,12 +7,12 @@
             "result": {
                 "ancestry_output": {
                     "Origin": {
-                        "Asia": 0.03028767555952072,
-                        "Eastern_Asia": 0.002180263167247176,
-                        "Europe": 0.5578079223632812,
-                        "Latin_America_and_the_Caribbean": 0.0037452145479619503,
-                        "Middle_East": 0.40406593680381775,
-                        "Sub-Saharan_Africa": 0.0019129770807921886
+                        "Asia": 0.010410779155790806,
+                        "Eastern_Asia": 0.0011356589384377003,
+                        "Europe": 0.854654848575592,
+                        "Latin_America_and_the_Caribbean": 0.008827924728393555,
+                        "Middle_East": 0.1237422451376915,
+                        "Sub-Saharan_Africa": 0.00122847652528435
                     }
                 }
             }
@@ -26,12 +26,12 @@
             "result": {
                 "ancestry_output": {
                     "Origin": {
-                        "Asia": 0.0014066740404814482,
-                        "Eastern_Asia": 0.002691845176741481,
-                        "Europe": 0.0021231011487543583,
-                        "Latin_America_and_the_Caribbean": 0.012312699109315872,
-                        "Middle_East": 0.05595624819397926,
-                        "Sub-Saharan_Africa": 0.9255093932151794
+                        "Asia": 0.0017986423335969448,
+                        "Eastern_Asia": 0.0030721763614565134,
+                        "Europe": 0.0034481489565223455,
+                        "Latin_America_and_the_Caribbean": 0.026503251865506172,
+                        "Middle_East": 0.1034306138753891,
+                        "Sub-Saharan_Africa": 0.861747145652771
                     }
                 }
             }
@@ -45,12 +45,12 @@
             "result": {
                 "ancestry_output": {
                     "Origin": {
-                        "Asia": 0.02939583733677864,
-                        "Eastern_Asia": 0.0008371166186407208,
-                        "Europe": 0.9306607246398926,
-                        "Latin_America_and_the_Caribbean": 0.018582025542855263,
-                        "Middle_East": 0.01969936117529869,
-                        "Sub-Saharan_Africa": 0.0008249731035903096
+                        "Asia": 0.008015047758817673,
+                        "Eastern_Asia": 0.0006639149505645037,
+                        "Europe": 0.9414306282997131,
+                        "Latin_America_and_the_Caribbean": 0.03938961401581764,
+                        "Middle_East": 0.009529098868370056,
+                        "Sub-Saharan_Africa": 0.0009716283529996872
                     }
                 }
             }

diff --git a/...s/tutorial_files/a_using_eir/01_basic_tutorial/tutorial_data/calculated_metrics_test.json b/...s/tutorial_files/a_using_eir/01_basic_tutorial/tutorial_data/calculated_metrics_test.json
@@ -1 +1 @@
-{"ancestry_output": {"Origin": {"ancestry_output_Origin_mcc": 0.8737133375559296, "ancestry_output_Origin_acc": 0.8966221232368226, "ancestry_output_Origin_roc-auc-macro": 0.9888789446399321, "ancestry_output_Origin_ap-macro": 0.9429769802215945, "ancestry_output_Origin_loss": 0.3044101297855377}}, "average": {"average": {"loss-average": 0.3044101297855377, "perf-average": 0.9351897541391521}}}
+{"ancestry_output": {"Origin": {"ancestry_output_Origin_mcc": 0.8746216045087754, "ancestry_output_Origin_acc": 0.8966221232368226, "ancestry_output_Origin_roc-auc-macro": 0.9891791491808976, "ancestry_output_Origin_ap-macro": 0.9453594382357499, "ancestry_output_Origin_loss": 0.3013431131839752}}, "average": {"average": {"loss-average": 0.3013431131839752, "perf-average": 0.9363867306418076}}}
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		{"ancestry_output": {"Origin": {"ancestry_output_Origin_mcc": 0.8737133375559296, "ancestry_output_Origin_acc": 0.8966221232368226, "ancestry_output_Origin_roc-auc-macro": 0.9888789446399321, "ancestry_output_Origin_ap-macro": 0.9429769802215945, "ancestry_output_Origin_loss": 0.3044101297855377}}, "average": {"average": {"loss-average": 0.3044101297855377, "perf-average": 0.9351897541391521}}}
		{"ancestry_output": {"Origin": {"ancestry_output_Origin_mcc": 0.8746216045087754, "ancestry_output_Origin_acc": 0.8966221232368226, "ancestry_output_Origin_roc-auc-macro": 0.9891791491808976, "ancestry_output_Origin_ap-macro": 0.9453594382357499, "ancestry_output_Origin_loss": 0.3013431131839752}}, "average": {"average": {"loss-average": 0.3013431131839752, "perf-average": 0.9363867306418076}}}