Add tests

.tagitrc

@@ -3,7 +3,7 @@
 changelog = docs/CHANGELOG.md
 
 ; Whether publish the package after the tag pushed to server.
-publish = py:True
+publish = py:False
 
 ; Whether check the version (__version__) in source file.
 checksource = py:False

.travis.yml

@@ -0,0 +1,25 @@
+language: python
+matrix:
+  include:
+    - python: 3.6
+    - python: 3.7
+      dist: xenial
+before_install:
+  - pip install poetry
+  - sudo apt-get update
+  - sudo apt-get install r-base
+  - sudo R -e 'install.packages(c("ggplot2", "ggrepel"))'
+install:
+  - poetry install -v
+script:
+  - pytest tests/ -s
+after_success: |
+  if [ "$TRAVIS_PYTHON_VERSION" == "3.7" ]; then
+    python-codacy-coverage -r .coverage.xml
+  fi
+deploy:
+  provider: script
+  script: poetry publish --build -u $PYPI_USER -p $PYPI_PASSWORD
+  on:
+    tags: true
+    condition: "$TRAVIS_PYTHON_VERSION == 3.7"

docs/cliargs.md

@@ -5,11 +5,14 @@ Description:
   vcfstats v0.0.1: Powerful VCF statistics.
 
 Usage:
-  vcfstats <--vcf AUTO> <--outdir AUTO> [OPTIONS]
+  vcfstats <--vcf AUTO> <--outdir AUTO> <-f LIST> <-t LIST> [OPTIONS]
 
 Required options:
   -v, --vcf <AUTO>         - The VCF file
   -o, --outdir <AUTO>      - The output directory.
+  -f, --formula <LIST>     - The formulas for plotting in format of [Y] ~ [X],
+                             where [Y] or [X] should be an entry or an aggregation
+  -t, --title <LIST>       - The title of each figure, will be used to name the output files.
 
 Optional options:
   --loglevel <STR>         - The logging level. Default: 'INFO'
@@ -29,11 +32,6 @@ Optional options:
                              Default: False
   --macro <AUTO>           - User-defined macro file.
                              Default: None
-  -f, --formula <LIST>     - The formulas for plotting in format of [Y] ~ [X],
-                             where [Y] or [X] should be an entry or an aggregation
-                             Default: []
-  -t, --title <LIST>       - The title of each figure, will be used to name the output files.
-                             Default: []
   --ggs <LIST>             - Extra ggplot2 expression for each plot
                              Default: []
   --devpars <DICT>         - The device parameters for plots.

docs/macros.md

@@ -16,7 +16,8 @@ We are using `cyvcf2` to get variant information, please refer to its [API docum
 
 !!! note
 
-	`vcf` is initialized with `gts012 = True`, which is not the default value of `cyvcf2`
+	`vcf` is initialized with `gts012 = True`, which is not the default value of `cyvcf2`. \
+	`gts012 = True` indicates that genotype 2 as `HOM_ALT` and 3 as `UNKNOWN`.
 
 
 ## Shortcuts for macro decorators
@@ -78,6 +79,7 @@ While when you use it, you can specify macros as filter and group for it. For ex
 ## Built-in macros
 ```python
 
+
 @categorical
 def VARTYPE(variant):
 	"""Variant type, one of deletion, indel, snp or sv"""
@@ -106,7 +108,7 @@ def GTTYPEs(variant):
 @categorical
 def FILTER(variant):
 	"""Get the FILTER of a variant."""
-	return variant.FILTER
+	return variant.FILTER or 'PASS'
 
 @categorical
 def SUBST(variant):
@@ -128,7 +130,7 @@ def QUAL(variant):
 	"""Variant quality from QUAL field."""
 	return variant.QUAL
 
-@continuous
+@continuous(alias = 'DPs')
 def DEPTHs(variant):
 	"""Get the read-depth for each sample as a numpy array."""
 	return [sum(dp) for dp in variant.format('DP')]
@@ -161,6 +163,8 @@ def SUM(entries):
 @aggregation(alias = 'AVG')
 def MEAN(entries):
 	"""Get the mean of the values"""
+	if not entries:
+		return 0.0
 	return sum(entries) / len(entries)
 ```
 

examples/sample.vcf

@@ -50,7 +50,7 @@
 1	10329	.	ACCCC	ACCC	26.4	MinMQ	INDEL;DP=315;VDB=0.0160;AF1=0.2047;AC1=2;DP4=2,42,9,16;MQ=17;FQ=29.3;PV4=0.0011,1,0.061,1;AN=8;AC=1	GT:PL:DP:SP:GQ	0/0:0,4,68:22:10:7	0/0:2,0,16:7:0:3	0/0:0,15,61:18:0:17	0/1:46,0,34:22:7:40
 1	10352	.	TACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCC	TAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCC	253	MinMQ	INDEL;DP=413;VDB=0.0226;AF1=0.8598;AC1=7;DP4=7,17,13,44;MQ=15;FQ=4.35;PV4=0.58,1,1,0.0055;AN=8;AC=7	GT:PL:DP:SP:GQ	1/1:67,6,0:18:2:11	1/1:14,7,0:12:0:12	1/1:111,22,0:23:0:26	0/1:83,0,22:28:2:18
 1	10492	.	C	T	999	PASS	DP=213;VDB=0.0102;AF1=0.375;AC1=3;DP4=84,74,34,19;MQ=32;FQ=999;PV4=0.2,0.11,0.057,0.13;AN=8;AC=3	GT:PL:DP:SP:GQ	0/1:85,0,255:57:3:86	0/0:0,123,255:41:0:99	0/1:255,0,255:47:0:99	0/1:114,0,255:66:4:99
-1	10583	.	G	A	20	PASS	DP=134;VDB=0.0071;AF1=0.1242;AC1=1;DP4=78,41,6,6;MQ=32;FQ=20;PV4=0.35,0.29,0.052,1;AN=8;AC=1	GT:PL:DP:SP:GQ	0/1:26,0,227:40:8:21	0/0:0,35,255:21:0:40	0/0:0,108,255:36:0:99	0/0:0,21,255:34:0:26
+1	10583	.	G	A,C	20	PASS	DP=134;VDB=0.0071;AF1=0.1242;AC1=1;DP4=78,41,6,6;MQ=32;FQ=20;PV4=0.35,0.29,0.052,1;AN=8;AC=1	GT:PL:DP:SP:GQ	0/1:26,0,227:40:8:21	2/2:0,35,255:21:0:40	0/0:0,108,255:36:0:99	0/0:0,21,255:34:0:26
 1	10797	.	CAGA	CAGAGA	90.4	MinMQ	INDEL;DP=37;VDB=0.0243;AF1=0.2819;AC1=2;DP4=7,3,0,6;MQ=29;FQ=93.3;PV4=0.011,1,1,1;AN=8;AC=2	GT:PL:DP:SP:GQ	0/0:0,9,104:3:0:10	0/0:0,6,39:2:0:8	0/1:59,0,36:5:0:43	0/1:56,0,32:6:4:39
 1	10821	.	T	A	49.7	PASS	DP=9;VDB=0.0091;AF1=1;AC1=5;DP4=1,3,0,4;MQ=12;FQ=7.75;PV4=1,1,1,1;AN=8;AC=6	GT:PL:DP:SP:GQ	1/1:42,9,0:33:0:20	0/1:0,3,4:1:0:2	1/1:12,1,0:2:0:4	0/1:0,6,8:2:0:2
 2	14907	.	A	G	999	MinMQ	DP=461;VDB=0.0384;AF1=0.5;G3=8.874e-45,1,8.011e-40;HWE=0.0185;AC1=4;DP4=101,122,129,102;MQ=25;FQ=999;PV4=0.031,0.011,1,1;AN=8;AC=4	GT:PL:DP:SP:GQ	0/1:225,0,255:133:0:99	0/1:213,0,225:91:20:99	0/1:255,0,188:104:0:99	0/1:255,0,208:126:4:99