closes #82

.gitignore

@@ -7,4 +7,4 @@ __pycache__/
 *.yml
 
 # ignore lock files created by spreadsheet programs
-.~lock*.tsv
+*.~lock*.tsv

README.md

@@ -54,14 +54,9 @@ The following **optional arguments** can be set for further customization:
 The input spreadsheet file needs to have the following columns:
 - `package_name` (the offical name of the package)
 - `version` (specify the version of the package you need by following the [package match specification syntax](https://docs.conda.io/projects/conda-build/en/latest/resources/package-spec.html#package-match-specifications))
-- `installation_command` (the full installation command)
-- `package_manager` (pip, conda, cran)
+- `package_manager` (can be 'pip', 'conda', or 'cran')
 - `conda_channel` (which conda channel to install from)
-- `area` (e.g. "data wrangling", "plotting", etc.)
-- `link` (the link to the package itself)
-- `necessity` ("required": you find that this package should be available for all lab members, "optional": only you need it for your current project but maybe any future lab member might find it also useful in the future)
-- `description` (a short description of what this package does)
-- `comment` (optional comments if something is buggy or if you want to tell other users some useful information)
+- `necessity` (can be 'required', 'optional')
 - `language` (python, r, julia)
 - `bug_flag` (can be 'linux','windows' or 'cross_platform')
 

environments/packages.tsv

@@ -1,4 +1,4 @@
-package_name	version	installation_command	package_manager	conda_channel	area	link	necessity	description	comment	language	bug_flag
-python		conda install -c conda-forge python	conda	conda-forge	language	https://anaconda.org/conda-forge/python	required	the python programming language itself		python	
-r-essentials		conda install -c conda-forge r-essentials	conda	conda-forge	data wrangling	https://tinyurl.com/54j96j5x	required	The R Essentials bundle contains approximately 200 of the most popular R packages for data science, including the IRKernel, dplyr, shiny, ggplot2, tidyr, caret, and nnet. It is used as an example in the following guides.		r	
-r-base		conda install -c conda-forge r-base	conda	conda-forge	language	https://anaconda.org/conda-forge/r-base	required	the R programming language itself		r	
+package_name	version	package_manager	conda_channel	necessity	language	bug_flag
+python		conda	conda-forge	required	python	
+r-essentials		conda	conda-forge	required	r	
+r-base		conda	conda-forge	required	r	

tcy.py

@@ -107,7 +107,7 @@ def run(operating_system,yml_name=None,yml_file_name='environment.yml',pip_requi
     if not languages == 'all':
         df = df.loc[df['language'].isin(languages),:]
 
-    # filter for necessitiy if specified by user
+    # filter for necessity if specified by user
     if not necessity == 'all':
         df = df.loc[df['necessity'].isin(necessity),:]
 

test_configs.json

@@ -1,10 +1,7 @@
 {
-  "valid_columns": ["package_name", "version", "installation_command", "package_manager", "conda_channel", "area","link", "necessity", "description", "comment", "language", "bug_flag"],
+  "valid_columns": ["package_name", "version","package_manager","conda_channel","necessity","language","bug_flag"],
   "filled_out_columns": ["package_name","language"],
   "valid_options": {"package_manager":["conda","pip","cran"],"language":["python","r","julia"],"bug_flag":["linux","windows","cross-platform"]},
   "column_dependencies": null,
   "multi_option_columns": null
 }
-
-
-

test_tsv_file.py

@@ -74,15 +74,14 @@ def create_mask(cell):
             message = f"These cells have either leading or trailing whitespaces: {', '.join(cells)}"
             pytest.fail(message)
 
-    # FIXME: Should test for equality not for subset!
     def test_valid_columns(self):
         '''Test that dataframe has all necessary columns'''
 
         if self.valid_columns:
-    
-            if list(self.df.columns) != self.valid_columns:
-                pytest.fail(f"datasets.tsv must have only these columns in that exact order: {', '.join(self.valid_columns)}")
-            
+
+            if not set(self.df.columns).issubset(self.valid_columns):
+                pytest.fail(f"The .tsv file must have at least these columns: {', '.join(self.valid_columns)}")
+
     def test_filled_out_columns(self):
         '''Check that certain columns are completely filled out'''