tiny changes. 05b_separate_datasets.py working now

Author: jjacobson95

build/broad_sanger/05b_separate_datasets.py

@@ -6,11 +6,6 @@
 
 def main():
 
-    print("ls:\n")
-    files = os.listdir(".")
-    print(files)
-    print("\n")
-    
     datasets_to_process = ["CCLE", "CTRPv2", "PRISM", "GDSCv1", "GDSCv2", "FIMM", "gCSI", "NCI60"]
     omics_datatypes = ["transcriptomics","proteomics", "copy_number","mutations"] # csv 
     samples_datatypes = ["samples"] #csv
@@ -42,7 +37,7 @@ def main():
         exp_improve_drug_ids = exp["improve_drug_id"].unique().to_list()
 
         #Ensure that the improve_sample_id column is in integer form.
-        exp = exp.with_column(pl.col("improve_sample_id").cast(pl.Float64).cast(pl.Int64))
+        exp = exp.with_columns(pl.col("improve_sample_id").cast(pl.Float64).cast(pl.Int64))
 
         # Write Filtered Experiments File to TSV. Then delete it from memory.
         exp_filename_out = f"/tmp/{dataset}_experiments.tsv".lower()

build/docker/Dockerfile.genes

@@ -3,16 +3,16 @@ ENV DEBIAN_FRONTEND=noninteractive
 RUN apt-get update  --fix-missing
 RUN apt-get install -y --fix-missing --allow-unauthenticated build-essential python3-pip python3-setuptools python3-dev python3-venv libcurl4-openssl-dev libglpk-dev libxml2-dev libpq-dev
 
-
 WORKDIR /app
 
+# installing r libraries
+ADD build/genes/requirements.r .
+RUN Rscript requirements.r
+
+# Add files last to optimize Docker caching
 ADD build/genes/*.R ./
 ADD build/genes/*sh ./
 
-ADD build/genes/requirements.r .
-
-# installing r libraries
-RUN Rscript requirements.r