update readme

FLMNH-MGCL · Mar 31, 2021 · 6962c15 · 6962c15
1 parent aea9c18
commit 6962c15
Show file tree

Hide file tree

Showing 4 changed files with 17 additions and 14 deletions.
diff --git a/README.md b/README.md
@@ -10,7 +10,20 @@ $ pip3 install --user -r requirements.txt
 
 ## Scripts
 
-There is a selection of scripts available in the [`scripts`](https://github.com/FLMNH-MGCL/digitization/tree/main/scripts) directory. They all have unique CLI structures, so be sure to run whichever is needed with the `--help` flag to get started.
+There is a selection of scripts available in the [`scripts`](https://github.com/FLMNH-MGCL/digitization/tree/main/scripts) directory. They all have unique CLI structures, so be sure to run whichever is needed with the `--help` flag to get started. The below table provides a brief overview for each script:
+
+| Script               | Description                                                                                                |
+| -------------------- | ---------------------------------------------------------------------------------------------------------- |
+| `dynaiello.py`       | A version of the Aiello script with less column restrictions. Copy and rename entries based on a CSV file. |
+| `gene_copy.py`       | Removes divergent consensus sequences (IBA pipeline) from .fas/.fasta files                                |
+| `gene_parser.py`     | Parses .fa/.fasta files to extract accession numbers and gene names                                        |
+| `mgcl_tracker.py`    | Tracks the used catalog numbers in the filesystem against a range/csv of numbers                           |
+| `protein_combine.py` | Combines separated protein/nucleotide files into one combined file                                         |
+| `relocate.py`        | _(deprecated)_ Relocates 'troublesome' images based on the log output of other scripts                     |
+| `suspect_numbers.py` | Agreggates 'suspect' catalog numbers in a filesystem                                                       |
+| `unique_values.py`   | Outputs all the unique values in the columns of a CSV or XLSX file                                         |
+| `wls.py`             | _(deprecated)_ Generates CSV of specimen at current working directory                                      |
+| `wrangler.py`        | Assigns BOMBID numbers to collection specimen                                                              |
 
 ## Digitization Program
 

diff --git a/scripts/gene_parser.py b/scripts/gene_parser.py
@@ -209,9 +209,6 @@ def collect_gene_data(self):
                 if not header_line:
                     break
 
-                # gene_line = f.readline()
-
-                # gene = tuple((header_line.strip(), gene_line.strip()))
                 gene = GeneParser.parse_gene_header(header_line.strip())
                 self.genes.append(gene)
 

diff --git a/scripts/unique_values.py b/scripts/unique_values.py
@@ -106,7 +106,7 @@ def verify_grouping(self):
             for col in self.group_by:
                 try:
                     self.raw_data[col]
-                except:
+                except Exception:
                     error_message(
                         "{} does not exist in the provided input file".format(col)
                     )
@@ -115,7 +115,7 @@ def verify_grouping(self):
             for col in self.group_for:
                 try:
                     self.raw_data[col]
-                except:
+                except Exception:
                     error_message(
                         "{} does not exist in the provided input file".format(col)
                     )
@@ -134,7 +134,6 @@ def write_out(self):
 
     def write_groups(self):
         logfile = Uniquer.generate_logname("UNIQUE_VALUES", self.destination)
-        # merged = None
         for heading, frame in self.unique_frames:
             with open(logfile, "a") as f:
                 f.write(heading + "\n")
@@ -149,11 +148,6 @@ def write_groups(self):
         # print(merged)
 
     def run(self):
-
-        # print("\nParsing CSV...\n")
-        # self.raw_csv_data = pd.read_csv(
-        #     self.csv_path, header=0, encoding="ISO-8859-1", low_memory=False)
-
         if self.group_by:
             if self.group_for is not None:
                 for col in self.group_for:

diff --git a/scripts/wls.py b/scripts/wls.py
@@ -218,6 +218,7 @@ def extract_filter(argument_list, arg_len):
 def main():
     argument_list = sys.argv
     arg_len = len(argument_list)
+
     filter = extract_filter(argument_list, arg_len)
 
     if filter[0] == "BAD":
@@ -274,8 +275,6 @@ def main():
             # unknown option
             print("Unknown usage.")
 
-        # input("Press enter to exit...")
-
 
 if __name__ == "__main__":
     main()