resolving merge conflicts

.gitignore

@@ -9,4 +9,4 @@ env.yaml
 requirements.txt
 dist/
 *.DS_Store
-myvenv/
+myvenv/

README.md

@@ -1,10 +1,17 @@
 
-<img height="200" align="right" src="https://github.com/fanzhanglab/pyCellPhenoX/blob/163014ba1b31243a1aac4c27e0611a34c1495efe/logo/https://github.com/fanzhanglab/pyCellPhenoX/blob/main-clone/logo/cellphenoX_logo_banner.png>
+<p>
+   <img height="270" align="centre" src="https://github.com/fanzhanglab/pyCellPhenoX/blob/main/logo/cellphenoX_logo_banner.png">
+</p>
+
+![PyPI](https://img.shields.io/pypi/v/pyCellPhenoX.svg)
+![Python Version](https://img.shields.io/pypi/pyversions/pyCellPhenoX)
+[![License](https://img.shields.io/pypi/l/pyCellPhenoX)][license] 
+![Read the documentation at https://pyXcell.readthedocs.io/](https://img.shields.io/readthedocs/pyXcell/latest.svg?label=Read%20the%20Docs)
+![Codecov](https://codecov.io/gh/fanzhanglab/pyCellPhenoX/branch/main/graph/badge.svg)
+
+![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)
+![Black](https://img.shields.io/badge/code%20style-black-000000.svg)
 
-[![PyPI](https://img.shields.io/pypi/v/pyXcell.svg)][pypi]
-[![Status](https://img.shields.io/pypi/status/pyXcell.svg)][status]
-[![Python Version](https://img.shields.io/pypi/pyversions/pyXcell)][python version]
-[![License](https://img.shields.io/pypi/l/pyXcell)][license] 
 
 We introduce pyCellPhenoX.
 
@@ -34,7 +41,7 @@ git clone [email protected]:fanzhanglab/pyCellPhenoX.git
 ### Dependencies/ Requirements
 When using pyCellPhenoX please ensure you are using the following dependency versions or requirements
 ``` python 
-python = "^3.12"
+python = "^3.9"
 pandas = "^2.2.3"
 numpy = "^2.1.1"
 xgboost = "^2.0"
@@ -97,21 +104,7 @@ To create a virtual environment using **PIP** follow these steps:
    ```bash
    pip install -r requirements.txt
     ```
-#### Poetry
 
-1. **Create a new project:**
-``` bash
-poetry new {my_project_name}
-cd {my_project_name}
-```
-2. **Install dependencies:**
-``` bash
-poertry install
-```
-3. **Activate the environment:**
-``` bash
-poetry shell
-```
 
 ## Tutorials
 Please see the [Command-line Reference] for details. Additonally, please see [Walkthroughs] on the documentation page. 

pyCellPhenoX/CellPhenoX.py

@@ -245,16 +245,18 @@ def model_training_shap_val(self, outpath):
                 # TODO: could probably save the explainer for this modeltrain object
                 # Use SHAP to explain predictions using best estimator
                 # sv_start = time.time()
+
                 explainer = shap.TreeExplainer(result.best_estimator_)
                 shap_values = explainer.shap_values(X_test_outer)
 
                 # Extract SHAP information per fold per sample
+                print(shap_values.shape)
                 for k, test_index in enumerate(test_outer_ix):
                     test_index = self.X.index[test_index]
                     # TODO: here, I am selecting the second (1) shap array for a binary classification problem.
                     # TODO: we need a way to generalize this so that we select the array that corresponds to the
                     # TODO: positive class (disease).
-                    self.shap_values_per_cv[test_index][CV_repeat] = shap_values[1][k]
+                    self.shap_values_per_cv[test_index][CV_repeat] = shap_values[k]
                 sv_end = time.time()
                 # sv.append(sv_end - sv_start)
                 # self.CV_repeat_cumulative_times[4] += (sv_end - sv_start)
@@ -382,9 +384,10 @@ def get_shap_values(self, outpath):
         average_shap_values = []
         for i in range(0, len(self.X)):  # len(NAM)
             id = self.X.index[i]  # NAM.index[i]
-            # print(id)
+            #print(id)
+            #print(self.shap_values_per_cv)
             df_per_obs = pd.DataFrame.from_dict(
-                self.shap_values_per_cv[id]
+                self.shap_values_per_cv[id][0]
             )  # Get all SHAP values for sample number i
             # Get relevant statistics for every sample
             average_shap_values.append(df_per_obs.mean(axis=1).values)

pyCellPhenoX/__init__.py

@@ -1,7 +1,7 @@
 __project__ = "pyCellPhenoX"
 # These version placeholders are updated during build by poetry-dynamic-versioning
-__version__ = "0.2.0"
-__version_tuple__ = (0, 2, 0)
+__version__ = "0.3.0"
+__version_tuple__ = (0, 3, 0)
 __license__ = "MIT License"
 __author__ = "pyCellPhenoX Contributors"
 

pyCellPhenoX/utils/__init__.py

@@ -1,6 +1,6 @@
 __project__ = "pyCellPhenoX"
 # These version placeholders are updated during build by poetry-dynamic-versioning
-__version__ = "0.2.0"
-__version_tuple__ = (0, 2, 0)
+__version__ = "0.3.0"
+__version_tuple__ = (0, 3, 0)
 __license__ = "MIT License"
 __author__ = "pyCellPhenoX Contributors"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pyCellPhenoX"
-version = "0.2.0"
+version = "0.3.0"
 description = "An eXplainable Cell-specific machine learning method to predict clinical Phenotypes using single-cell multi-omics"
 authors = [ 
     "Fan Zhang", 
@@ -20,7 +20,7 @@ packages = [
 ]
 
 [tool.poetry.dependencies]
-python = "^3.12"
+python = "^3.9"
 pandas = "^2.2.3"
 numpy = "^2.0"
 xgboost = "^2.1.1"

requirements.txt

@@ -4,6 +4,9 @@ cycler==0.12.1
 dunamai==1.22.0
 fonttools==4.54.1
 iniconfig==2.0.0
+isort==5.13.2
+jedi==0.19.1
+Jinja2==3.1.4
 joblib==1.4.2
 kiwisolver==1.4.7
 llvmlite==0.43.0

test/__init__.py

@@ -1,6 +1,6 @@
 __project__ = "pyCellPhenoX"
 # These version placeholders are updated during build by poetry-dynamic-versioning
-__version__ = "0.2.0"
-__version_tuple__ = (0, 2, 0)
+__version__ = "0.3.0"
+__version_tuple__ = (0, 3, 0)
 __license__ = "MIT License"
 __author__ = "pyCellPhenoX Contributors"