From 6fdc55c194642d5757d3a60379938f2a94d660e9 Mon Sep 17 00:00:00 2001 From: avantonder Date: Mon, 14 Nov 2022 16:27:14 +0000 Subject: [PATCH] rewrite python scripts --- CHANGELOG.md | 8 ++++++++ bin/read_stats.py | 2 ++ 2 files changed, 10 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 63bf5b6..a200091 100644 --- 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 index b2f702f..0f22a8b 100755 --- 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'])