tabtk 1.0.3__tar.gz → 1.0.4__tar.gz

{tabtk-1.0.3 → tabtk-1.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tabtk
-Version: 1.0.3
+Version: 1.0.4
 Summary: tabtk: A toolkit for sequence similarity analysis based on tabular data
 Author-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>
 Maintainer-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>

{tabtk-1.0.3 → tabtk-1.0.4}/tabtk/__init__.py

@@ -1,4 +1,4 @@
 """tabkit: A toolkit for sequence similarity analysis based on tabular data"""
 
-__version__ = "1.0.3"
+__version__ = "1.0.4"
 

{tabtk-1.0.3 → tabtk-1.0.4}/tabtk/tabtk.py

@@ -181,17 +181,19 @@ def blastSimilarity(cmdValues):
     blastData = pd.read_csv(tmpOut2,delimiter="\t",dtype={'pident': float,'qcovs': float})
     blastData["tmp"] = blastData.apply(lambda x: (x["qcovs"] * x["pident"])/100,axis=1)
 
+    blastDataR = blastData[["qseqid","sseqid","tmp"]].groupby(['qseqid','sseqid']).agg({'tmp':'mean'})
+    blastDataR = blastDataR.reset_index()
+
     blastData["qseqidR"] = blastData.apply(lambda x: x["qseqid"] if x["qseqid"] > x["sseqid"] else x["sseqid"],axis=1)
     blastData["sseqidR"] = blastData.apply(lambda x: x["sseqid"] if x["qseqid"] > x["sseqid"] else x["qseqid"],axis=1)
 
     blastData["qseqid"] = blastData["qseqidR"]
     blastData["sseqid"] = blastData["sseqidR"]
 
-    blastData["cov"] = blastData[["qseqid","sseqid","tmp"]].groupby(["qseqid","sseqid"])["tmp"].transform(lambda x: statistics.mean(x))
-    blastDataR = blastData.groupby(["qseqid","sseqid"]).first().reset_index()
+    blastDataR = blastData[["qseqid","sseqid","tmp"]].groupby(['qseqid','sseqid']).agg({'tmp':'min'})
+    blastDataR = blastDataR.reset_index()
 
-    blastData = blastDataR.drop(columns=["tmp","length","pident","qseqidR","sseqidR"])
-    blastDataFinal = blastData[["sseqid","qseqid","cov"]].rename(columns={"sseqid":"seq1","qseqid":"seq2","cov":"pid"}).values.tolist()
+    blastDataFinal = blastDataR[["sseqid","qseqid","tmp"]].rename(columns={"sseqid":"seq1","qseqid":"seq2","tmp":"pid"}).values.tolist()
 
     bar = ChargingBar("Cleaning temporary files", max=len(fileNames))
     for fileName in tmpFileNames:

{tabtk-1.0.3 → tabtk-1.0.4}/tabtk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tabtk
-Version: 1.0.3
+Version: 1.0.4
 Summary: tabtk: A toolkit for sequence similarity analysis based on tabular data
 Author-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>
 Maintainer-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>