From c70bbff607ec4777e93806c483f42109e6debbff Mon Sep 17 00:00:00 2001
From: Yang Chen <60239063+yangchen2@users.noreply.github.com>
Date: Sun, 22 Oct 2023 13:26:46 -0700
Subject: [PATCH 1/4] update MIT license to BSD-3 license

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index b21f048..456e061 100644
--- a/README.md
+++ b/README.md
@@ -103,4 +103,4 @@ See the [tutorial](tutorial.md) page for a walkthroughon using Qadabra workflow
 Coming soon: An [FAQs](FAQs.md) page of commonly asked question on the statistics and code pertaining to Qadabra.
 
 ## Citation
-The manuscript for Qadabra is currently in progress. Please cite this GitHub page if Qadabra is used for your analysis. This project is licensed under the MIT License. See the [license](LICENSE) file for details.
\ No newline at end of file
+The manuscript for Qadabra is currently in progress. Please cite this GitHub page if Qadabra is used for your analysis. This project is licensed under the BSD-3 License. See the [license](LICENSE) file for details.

From c09d96f750508b7b9ebbfac811bd10377b099e5a Mon Sep 17 00:00:00 2001
From: Yang Chen <60239063+yangchen2@users.noreply.github.com>
Date: Sun, 5 Nov 2023 18:05:58 -0800
Subject: [PATCH 2/4] Metadata with all numerical SampleIDs not accepted, issue
 #50

---
 qadabra/utils.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/qadabra/utils.py b/qadabra/utils.py
index 9b0c816..ae7104d 100644
--- a/qadabra/utils.py
+++ b/qadabra/utils.py
@@ -17,7 +17,7 @@ def _validate_input(
     confounders: List[str] = None,
 ):
     logger.info("Loading metadata...")
-    md = pd.read_table(metadata, sep="\t", index_col=0)
+    md = pd.read_table(metadata, sep="\t", index_col=0, dtype={0:'str'})
 
     if factor_name not in md.columns:
         raise ValueError(f"{factor_name} not found in metadata!")
@@ -69,4 +69,4 @@ def _validate_input(
             raise ValueError("Tree tips are not a subset of table features!")
     else:
         logger.info("Reading phylogenetic tree...")
-        logger.info("(Optional tree file not provided. Skipping tree validation.)")
\ No newline at end of file
+        logger.info("(Optional tree file not provided. Skipping tree validation.)")

From 28bfa7345afe8f69b3a146eb36f18995c5af778d Mon Sep 17 00:00:00 2001
From: Yang Chen <60239063+yangchen2@users.noreply.github.com>
Date: Sun, 5 Nov 2023 18:14:04 -0800
Subject: [PATCH 3/4] Confounders not accepted as string, issue #51

---
 qadabra/workflow/rules/common.smk | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/qadabra/workflow/rules/common.smk b/qadabra/workflow/rules/common.smk
index 46643b9..40a6d8f 100644
--- a/qadabra/workflow/rules/common.smk
+++ b/qadabra/workflow/rules/common.smk
@@ -8,7 +8,7 @@ names = datasets.index
 def get_dataset_cfg(wildcards, keys):
     d = datasets.loc[wildcards.dataset, keys].to_dict()
     if "confounders" in keys:
-        if not np.isnan(d["confounders"]):
+        if not np.isnull(d["confounders"]):
             d["confounders"] = d["confounders"].split(";")
         else:
             d["confounders"] = []
@@ -20,7 +20,7 @@ def get_songbird_formula(wildcards):
     covariate = d["factor_name"]
     reference = d["reference_level"]
     formula = f"C({covariate}, Treatment('{reference}'))"
-    if not np.isnan(d["confounders"]):
+    if not np.isnull(d["confounders"]):
         confounders = d["confounders"].split(";")
         formula = f"{formula} + {' + '.join(confounders)}"
     return formula
@@ -126,4 +126,4 @@ for dataset in datasets.iterrows():
             dataset=names,
             out=["empress"]
             )
-        all_input = all_input + empress_output
\ No newline at end of file
+        all_input = all_input + empress_output

From 2aaff90054677e5f9b86123de77e91fe8519ea5f Mon Sep 17 00:00:00 2001
From: Yang Chen <60239063+yangchen2@users.noreply.github.com>
Date: Sun, 5 Nov 2023 18:22:44 -0800
Subject: [PATCH 4/4] last commit should be pd.null not np.null

---
 qadabra/workflow/rules/common.smk | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/qadabra/workflow/rules/common.smk b/qadabra/workflow/rules/common.smk
index 40a6d8f..c3298d1 100644
--- a/qadabra/workflow/rules/common.smk
+++ b/qadabra/workflow/rules/common.smk
@@ -8,7 +8,7 @@ names = datasets.index
 def get_dataset_cfg(wildcards, keys):
     d = datasets.loc[wildcards.dataset, keys].to_dict()
     if "confounders" in keys:
-        if not np.isnull(d["confounders"]):
+        if not pd.isnull(d["confounders"]):
             d["confounders"] = d["confounders"].split(";")
         else:
             d["confounders"] = []
@@ -20,7 +20,7 @@ def get_songbird_formula(wildcards):
     covariate = d["factor_name"]
     reference = d["reference_level"]
     formula = f"C({covariate}, Treatment('{reference}'))"
-    if not np.isnull(d["confounders"]):
+    if not pd.isnull(d["confounders"]):
         confounders = d["confounders"].split(";")
         formula = f"{formula} + {' + '.join(confounders)}"
     return formula