Merge pull request #35 from avantonder/apha

rewrite python scripts
avantonder · Nov 14, 2022 · c89edb1 · c89edb1
2 parents a953d80 + 6fdc55c
commit c89edb1
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 0 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,14 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v1.2 - [14/11/22]
+
+- Add test profile and dataset so pipeline can be run with test.conf
+- Rewrite python scripts
+- Add skip_alignment, skip_kraken2 and skip_clusters parameters
+- Update nextflow_schema.json
+- Add parameters.md to docs
+
 ## v1.1 - [26/10/22]
 
 - Fix masking bug

diff --git a/bin/read_stats.py b/bin/read_stats.py
@@ -121,10 +121,12 @@ def main(args=None):
     ## Create dataframe of raw reads fastq-scan results
     raw_json_df = json_to_dataframe(raw_json_files)
     raw_json_df = raw_json_df.rename(columns = {'read_total' : 'NumRawReads'})
+    raw_json_df['Sample'] = raw_json_df['Sample'].str.replace('.raw','')
 
     ## Create dataframe of trimmed reads fastq-scan results
     trim_json_df = json_to_dataframe(trim_json_files)
     trim_json_df = trim_json_df.rename(columns = {'read_total' : 'NumTrimReads'})
+    trim_json_df['Sample'] = trim_json_df['Sample'].str.replace('.trim','')
 
     ## Merge fastq-scan dataframes
     fastqscan_merged = pd.merge(raw_json_df, trim_json_df, on = ['Sample'])