From 94ea87881e50863f734e052f5749b386ea5795df Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 16:14:55 -0400
Subject: [PATCH 01/16] GIT: update workflow

---
 .github/workflows/main.yml       | 2 +-
 ChemSpaceAL/tests/test_config.py | 7 +++++++
 tests/test_config.py             | 6 ------
 3 files changed, 8 insertions(+), 7 deletions(-)
 create mode 100644 ChemSpaceAL/tests/test_config.py
 delete mode 100644 tests/test_config.py

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 840bd69..7af98e4 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -2,7 +2,7 @@ name: Python application test with pytest
 
 on:
   push:
-    branches: [ main ]
+    branches: [ main, sandbox ]
 
 jobs:
   build:
diff --git a/ChemSpaceAL/tests/test_config.py b/ChemSpaceAL/tests/test_config.py
new file mode 100644
index 0000000..11e3cdb
--- /dev/null
+++ b/ChemSpaceAL/tests/test_config.py
@@ -0,0 +1,7 @@
+import ChemSpaceAL.InitializeWorkspace as iw
+import os
+
+def test_config():
+    base_path = os.getcwd() + "/PaperRuns/"
+    assert isinstance(iw.FOLDER_STRUCTURE, dict)
+    assert True
diff --git a/tests/test_config.py b/tests/test_config.py
deleted file mode 100644
index 1662e2c..0000000
--- a/tests/test_config.py
+++ /dev/null
@@ -1,6 +0,0 @@
-import ChemSpaceAL.InitializeWorkspace
-import os
-
-def test_config():
-    base_path = os.getcwd() + "/PaperRuns/"
-    assert True

From c94601b266d5de8260034e1927fe8cd02f0b94f2 Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 16:17:14 -0400
Subject: [PATCH 02/16] GIT: update workflow

---
 .github/workflows/main.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 7af98e4..ea3d213 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -28,7 +28,7 @@ jobs:
         python setup.py install
 
     - name: Run tests and collect coverage
-      run: pytest --cov
+      run: pytest --cov=ChemSpaceAL
     - name: Upload coverage to Codecov
       uses: codecov/codecov-action@v4-beta
       env:

From f1306ee895e2d289f756e515725cfb23afbc2113 Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 16:21:34 -0400
Subject: [PATCH 03/16] TESTS: check folder creation

---
 ChemSpaceAL/tests/test_config.py               |  7 -------
 ChemSpaceAL/tests/test_initialize_workspace.py | 18 ++++++++++++++++++
 2 files changed, 18 insertions(+), 7 deletions(-)
 delete mode 100644 ChemSpaceAL/tests/test_config.py
 create mode 100644 ChemSpaceAL/tests/test_initialize_workspace.py

diff --git a/ChemSpaceAL/tests/test_config.py b/ChemSpaceAL/tests/test_config.py
deleted file mode 100644
index 11e3cdb..0000000
--- a/ChemSpaceAL/tests/test_config.py
+++ /dev/null
@@ -1,7 +0,0 @@
-import ChemSpaceAL.InitializeWorkspace as iw
-import os
-
-def test_config():
-    base_path = os.getcwd() + "/PaperRuns/"
-    assert isinstance(iw.FOLDER_STRUCTURE, dict)
-    assert True
diff --git a/ChemSpaceAL/tests/test_initialize_workspace.py b/ChemSpaceAL/tests/test_initialize_workspace.py
new file mode 100644
index 0000000..3438fec
--- /dev/null
+++ b/ChemSpaceAL/tests/test_initialize_workspace.py
@@ -0,0 +1,18 @@
+import os
+import tempfile
+from unittest.mock import patch
+import ChemSpaceAL.InitializeWorkspace as iw
+
+
+def test_create_default_folders():
+    # Using a temporary directory for testing
+    with tempfile.TemporaryDirectory() as tempdir:
+        iw.create_folders(base_path=tempdir)
+
+        # Check if the main folders are created
+        assert os.path.exists(os.path.join(tempdir, "1_Pretraining"))
+        assert os.path.exists(os.path.join(tempdir, "2_Generation"))
+
+        # Check if subfolders are created
+        assert os.path.exists(os.path.join(tempdir, "1_Pretraining", "datasets"))
+        # ... (add more assertions for other subfolders)

From 317f91ff5b2ce58c7b0221ef1d5157efa5c8399e Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 16:35:05 -0400
Subject: [PATCH 04/16] TESTS: do absolute imports

---
 ChemSpaceAL/tests/test_initialize_workspace.py | 2 +-
 README.md                                      | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/ChemSpaceAL/tests/test_initialize_workspace.py b/ChemSpaceAL/tests/test_initialize_workspace.py
index 3438fec..fa4bf24 100644
--- a/ChemSpaceAL/tests/test_initialize_workspace.py
+++ b/ChemSpaceAL/tests/test_initialize_workspace.py
@@ -1,7 +1,7 @@
 import os
 import tempfile
 from unittest.mock import patch
-import ChemSpaceAL.InitializeWorkspace as iw
+from ChemSpaceAL import InitializeWorkspace as iw
 
 
 def test_create_default_folders():
diff --git a/README.md b/README.md
index 400eaf6..156487d 100644
--- a/README.md
+++ b/README.md
@@ -3,5 +3,6 @@ ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein- Specif
 
 [![Checked with mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](https://mypy-lang.org/)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![codecov](https://codecov.io/gh/batistagroup/ChemSpaceAL/graph/badge.svg?token=ROJSISYJWC)](https://codecov.io/gh/batistagroup/ChemSpaceAL)
 
 ![A description of the active learning methodology](media/toc_figure.jpg)

From 4a1f3882d73e529add0871f7f896e818e59fd7ec Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 16:42:34 -0400
Subject: [PATCH 05/16] TESTS: add codecov components

---
 codecov.yml | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)
 create mode 100644 codecov.yml

diff --git a/codecov.yml b/codecov.yml
new file mode 100644
index 0000000..6b4e5e0
--- /dev/null
+++ b/codecov.yml
@@ -0,0 +1,31 @@
+codecov:
+  project:
+    enabled: false
+  patch:
+    only_pulls: true
+  notify:
+    require_ci_to_pass: yes
+
+coverage:
+  precision: 2
+  round: down
+  range: "0...90"
+
+  status:
+    project: yes
+    patch: yes
+    changes: no
+
+comment:
+  layout: "header, diff, components"
+
+component_management:
+  default_rules:
+    statuses:
+      - type: patch
+        target: auto
+  individual_components:
+    - component_id: module_iw
+      name: InitializeWorkspace
+      paths:
+        - "ChemSpaceAL/InitializeWorkspace.py"

From aeb8580db218a86f15a1f03e51fb2c7b4571ebe1 Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 16:46:56 -0400
Subject: [PATCH 06/16] TESTS: update codecov.yml

---
 codecov.yml | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/codecov.yml b/codecov.yml
index 6b4e5e0..4cea1e8 100644
--- a/codecov.yml
+++ b/codecov.yml
@@ -1,11 +1,3 @@
-codecov:
-  project:
-    enabled: false
-  patch:
-    only_pulls: true
-  notify:
-    require_ci_to_pass: yes
-
 coverage:
   precision: 2
   round: down

From 4b9c2e1f85012741355f1b52e96f8e4132dcc459 Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 16:55:17 -0400
Subject: [PATCH 07/16] TESTS: add more checks

---
 ChemSpaceAL/tests/test_initialize_workspace.py | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/ChemSpaceAL/tests/test_initialize_workspace.py b/ChemSpaceAL/tests/test_initialize_workspace.py
index fa4bf24..b03ce7c 100644
--- a/ChemSpaceAL/tests/test_initialize_workspace.py
+++ b/ChemSpaceAL/tests/test_initialize_workspace.py
@@ -16,3 +16,11 @@ def test_create_default_folders():
         # Check if subfolders are created
         assert os.path.exists(os.path.join(tempdir, "1_Pretraining", "datasets"))
         # ... (add more assertions for other subfolders)
+    assert isinstance(iw.FOLDER_STRUCTURE, dict)
+
+
+@patch("builtins.input", return_value="Y")
+def test_create_folders_without_base_path(mock_input):
+    with tempfile.TemporaryDirectory() as tempdir:
+        os.chdir(tempdir)  # Change working directory
+        iw.create_folders()

From 3edbe102ba82b012e6266aafe733a48cea45dd6b Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 16:58:36 -0400
Subject: [PATCH 08/16] TESTS: modify workflow

---
 .github/workflows/main.yml | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index ea3d213..a09261d 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -23,10 +23,6 @@ jobs:
         python -m pip install --upgrade pip
         pip install pytest pytest-cov
 
-    - name: Install package
-      run: |
-        python setup.py install
-
     - name: Run tests and collect coverage
       run: pytest --cov=ChemSpaceAL
     - name: Upload coverage to Codecov

From 5866267ddc25ed8c41824f1002df20cdb6b88954 Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 17:00:19 -0400
Subject: [PATCH 09/16] GIT: try relative imports

---
 ChemSpaceAL/tests/test_initialize_workspace.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ChemSpaceAL/tests/test_initialize_workspace.py b/ChemSpaceAL/tests/test_initialize_workspace.py
index b03ce7c..1a2476b 100644
--- a/ChemSpaceAL/tests/test_initialize_workspace.py
+++ b/ChemSpaceAL/tests/test_initialize_workspace.py
@@ -1,7 +1,7 @@
 import os
 import tempfile
 from unittest.mock import patch
-from ChemSpaceAL import InitializeWorkspace as iw
+from .. import InitializeWorkspace as iw
 
 
 def test_create_default_folders():

From 799351d8112a71b7f6e8e79d6b5100b6dafeb960 Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 17:01:37 -0400
Subject: [PATCH 10/16] GIT: make tests a module folder

---
 ChemSpaceAL/tests/__init__.py | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 create mode 100644 ChemSpaceAL/tests/__init__.py

diff --git a/ChemSpaceAL/tests/__init__.py b/ChemSpaceAL/tests/__init__.py
new file mode 100644
index 0000000..e69de29

From efb218d80395f1dbcedc2b8d711a514b7b5b3cae Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 17:07:01 -0400
Subject: [PATCH 11/16] TESTS: add .coveragerc

---
 .coveragerc                  | 10 ++++++++++
 ChemSpaceAL/Configuration.py |  2 +-
 2 files changed, 11 insertions(+), 1 deletion(-)
 create mode 100644 .coveragerc

diff --git a/.coveragerc b/.coveragerc
new file mode 100644
index 0000000..147c6da
--- /dev/null
+++ b/.coveragerc
@@ -0,0 +1,10 @@
+[run]
+source = 
+    ChemSpaceAL/InitializeWorkspace.py
+
+omit =
+    ChemSpaceAL/Model.py
+    ChemSpaceAL/Dataset.py
+    ChemSpaceAL/Docking.py
+    ChemSpaceAL/Generation.py
+    ChemSpaceAL/Training.py
diff --git a/ChemSpaceAL/Configuration.py b/ChemSpaceAL/Configuration.py
index 48d1943..69a8399 100644
--- a/ChemSpaceAL/Configuration.py
+++ b/ChemSpaceAL/Configuration.py
@@ -2,7 +2,7 @@
 from torch.nn import Module
 import os
 from typing import Union, Dict, Any, List, Tuple, Optional, Any, Set, Callable, cast
-from ChemSpaceAL.InitializeWorkspace import FOLDER_STRUCTURE as fldr_struc
+from .InitializeWorkspace import FOLDER_STRUCTURE as fldr_struc
 import textwrap
 from rdkit.Chem import Descriptors
 from rdkit import Chem

From dd84f3413ad7416da0497bf2e12ec3edde2ab450 Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 17:10:27 -0400
Subject: [PATCH 12/16] TESTS: remove patch tracking?

---
 codecov.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/codecov.yml b/codecov.yml
index 4cea1e8..289ecd5 100644
--- a/codecov.yml
+++ b/codecov.yml
@@ -5,7 +5,7 @@ coverage:
 
   status:
     project: yes
-    patch: yes
+    patch: no
     changes: no
 
 comment:

From b8c3352bc2142011b09860d26ade9464aa446e09 Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 17:25:29 -0400
Subject: [PATCH 13/16] TESTS: probability conversion tests

---
 ChemSpaceAL/ALConstruction.py             |  4 +-
 ChemSpaceAL/Configuration.py              |  2 +-
 ChemSpaceAL/tests/test_al_construction.py | 75 +++++++++++++++++++++++
 codecov.yml                               |  6 +-
 4 files changed, 82 insertions(+), 5 deletions(-)
 create mode 100644 ChemSpaceAL/tests/test_al_construction.py

diff --git a/ChemSpaceAL/ALConstruction.py b/ChemSpaceAL/ALConstruction.py
index 0bcc3cf..afba815 100644
--- a/ChemSpaceAL/ALConstruction.py
+++ b/ChemSpaceAL/ALConstruction.py
@@ -67,7 +67,6 @@ def _preprocess_scores_linearly(
     normalized = {k: v / total for k, v in negated.items()}
     return normalized
 
-
 def _preprocess_scores_softmax(
     scores: Dict[int, Number],
     do_negation: bool = False,
@@ -89,8 +88,7 @@ def _preprocess_scores_softmax(
     total = sum(exponentiate.values())
     softmax = {k: v / total for k, v in exponentiate.items()}
     return softmax
-
-
+    
 def balance_cluster_to_n(
     cluster_to_n: Dict[int, int], cluster_to_len: Dict[int, int]
 ) -> Dict[int, int]:
diff --git a/ChemSpaceAL/Configuration.py b/ChemSpaceAL/Configuration.py
index 69a8399..48d1943 100644
--- a/ChemSpaceAL/Configuration.py
+++ b/ChemSpaceAL/Configuration.py
@@ -2,7 +2,7 @@
 from torch.nn import Module
 import os
 from typing import Union, Dict, Any, List, Tuple, Optional, Any, Set, Callable, cast
-from .InitializeWorkspace import FOLDER_STRUCTURE as fldr_struc
+from ChemSpaceAL.InitializeWorkspace import FOLDER_STRUCTURE as fldr_struc
 import textwrap
 from rdkit.Chem import Descriptors
 from rdkit import Chem
diff --git a/ChemSpaceAL/tests/test_al_construction.py b/ChemSpaceAL/tests/test_al_construction.py
new file mode 100644
index 0000000..a872a6f
--- /dev/null
+++ b/ChemSpaceAL/tests/test_al_construction.py
@@ -0,0 +1,75 @@
+from ..ALConstruction import _preprocess_scores_linearly, _preprocess_scores_softmax
+import pytest
+
+
+@pytest.mark.parametrize(
+    "scores, do_negation, expected",
+    [
+        (
+            {1: 2, 2: 2, 3: 2},
+            False,
+            {1: 1 / 3, 2: 1 / 3, 3: 1 / 3},
+        ),
+        (
+            {1: 1, 2: 0, 3: 0},
+            False,
+            {1: 1, 2: 0, 3: 0},
+        ),
+        ({}, False, {}),
+        (
+            {1: 0, 2: -2, 3: -2},
+            True,
+            {1: 0, 2: 0.5, 3: 0.5},
+        ),
+    ],
+)
+def test_preprocess_scores_linearly(scores, do_negation, expected):
+    result = _preprocess_scores_linearly(scores, do_negation)
+    for k, v in expected.items():
+        assert result[k] == pytest.approx(v)
+
+
+@pytest.mark.parametrize(
+    "scores, do_negation, divide, divide_factor, expected",
+    [
+        (
+            {1: 2, 2: 2, 3: 2},
+            False,
+            False,
+            None,
+            {1: 1 / 3, 2: 1 / 3, 3: 1 / 3},
+        ),
+        (
+            {1: 1, 2: 0, 3: 0},
+            False,
+            False,
+            None,
+            {1: 0.5761168847658291, 2: 0.21194155761708544, 3: 0.21194155761708544},
+        ),
+        (
+            {1: 1, 2: 0, 3: 0},
+            False,
+            True,
+            0.5,
+            {1: 0.7869860421615985, 2: 0.10650697891920075, 3: 0.10650697891920075},
+        ),
+        (
+            {1: -1, 2: -1, 3: 0},
+            True,
+            True,
+            0.5,
+            {1: 0.4683105308334812, 2: 0.4683105308334812, 3: 0.06337893833303762},
+        ),
+    ],
+)
+def test_preprocess_scores_softmax(
+    scores, do_negation, divide, divide_factor, expected
+):
+    result = _preprocess_scores_softmax(scores, do_negation, divide, divide_factor)
+    for k, v in expected.items():
+        assert result[k] == pytest.approx(v)
+
+
+def test_preprocess_scores_softmax_exception():
+    with pytest.raises(AssertionError):
+        _preprocess_scores_softmax({1: 2, 2: 3, 3: 4}, False, True, None)
diff --git a/codecov.yml b/codecov.yml
index 289ecd5..32bbacd 100644
--- a/codecov.yml
+++ b/codecov.yml
@@ -5,7 +5,7 @@ coverage:
 
   status:
     project: yes
-    patch: no
+    patch: yes
     changes: no
 
 comment:
@@ -21,3 +21,7 @@ component_management:
       name: InitializeWorkspace
       paths:
         - "ChemSpaceAL/InitializeWorkspace.py"
+    - component_id: module_al_construct
+      name: AL Training Set Construction
+      paths:
+        - "ChemSpaceAL/ALConstruction.py"

From dc2169afc5c8ae974ccb5a9424344d9e4ae362b0 Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 17:26:43 -0400
Subject: [PATCH 14/16] GIT: add dependencies to workflow

---
 .github/workflows/main.yml    | 1 +
 ChemSpaceAL/ALConstruction.py | 3 +--
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index a09261d..6a18e2a 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -21,6 +21,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
+        pip install pandas, numpy
         pip install pytest pytest-cov
 
     - name: Run tests and collect coverage
diff --git a/ChemSpaceAL/ALConstruction.py b/ChemSpaceAL/ALConstruction.py
index afba815..7b6a1da 100644
--- a/ChemSpaceAL/ALConstruction.py
+++ b/ChemSpaceAL/ALConstruction.py
@@ -1,7 +1,6 @@
 import pandas as pd
 import numpy as np
 import pickle
-import plotly.graph_objects as go
 
 from ChemSpaceAL.Configuration import Config
 from typing import Union, Dict, List, Callable, Optional, cast
@@ -88,7 +87,7 @@ def _preprocess_scores_softmax(
     total = sum(exponentiate.values())
     softmax = {k: v / total for k, v in exponentiate.items()}
     return softmax
-    
+
 def balance_cluster_to_n(
     cluster_to_n: Dict[int, int], cluster_to_len: Dict[int, int]
 ) -> Dict[int, int]:

From a705741f19ff290b925805b4e2124a6790d45868 Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 17:27:55 -0400
Subject: [PATCH 15/16] GIT: who writes commas in pip install....

---
 .github/workflows/main.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 6a18e2a..17e0bed 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -21,7 +21,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install pandas, numpy
+        pip install pandas numpy
         pip install pytest pytest-cov
 
     - name: Run tests and collect coverage

From 721152dc64dfbcd0a7752046ff315b460371694f Mon Sep 17 00:00:00 2001
From: Anton Morgunov <morgunov@mit.edu>
Date: Tue, 24 Oct 2023 17:33:59 -0400
Subject: [PATCH 16/16] GIT: add more dependencies to the workflow

---
 .github/workflows/main.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 17e0bed..d8342b9 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -21,7 +21,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install pandas numpy
+        pip install pandas numpy torch rdkit
         pip install pytest pytest-cov
 
     - name: Run tests and collect coverage