Statistics over the produced data

@@ -3,107 +3,11 @@ nohup.out
 jobstats.csv
 jobstats.csv
 log_of_the_run.sh
 log_of_the_run.sh
 
 
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-.hypothesis/
-.pytest_cache/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# pyenv
-.python-version
-
-# celery beat schedule file
-celerybeat-schedule
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
+# temporary results files
+data/*.npy
+data/*.npz
+data/olddata
+
+# environment stuff
+.vscode/
+*.pyc
\ No newline at end of file

@@ -916,7 +916,7 @@ def execute_joblist(fulljoblist, printstats=False):
 
 
     if printstats:
     if printstats:
         # Write statistics in a file (header here)
         # Write statistics in a file (header here)
-        f = open("jobstats.csv", "w")
+        f = open("data/jobstats.csv", "w")
         f.write("label,comp_time,max_mem\n")
         f.write("label,comp_time,max_mem\n")
         f.close()
         f.close()
 
 
@@ -948,7 +948,7 @@ def execute_joblist(fulljoblist, printstats=False):
                 mems = [ r[1] for r in raw_results ]
                 mems = [ r[1] for r in raw_results ]
 
 
                 # Write them to file
                 # Write them to file
-                f = open("jobstats.csv", "a")
+                f = open("data/jobstats.csv", "a")
                 for j, t, m in zip(bunch, times, mems):
                 for j, t, m in zip(bunch, times, mems):
                     j.comp_time = t
                     j.comp_time = t
                     j.max_mem = m
                     j.max_mem = m
@@ -1636,7 +1636,7 @@ if __name__ == "__main__":
         n_pdb = [ len(rfam_acc_to_download[f]) for f in fam_stats["rfam_acc"] ]
         n_pdb = [ len(rfam_acc_to_download[f]) for f in fam_stats["rfam_acc"] ]
         fam_stats["n_pdb_seqs"] = n_pdb
         fam_stats["n_pdb_seqs"] = n_pdb
         fam_stats["total_seqs"] = fam_stats["n_seq"] + fam_stats["n_pdb_seqs"]
         fam_stats["total_seqs"] = fam_stats["n_seq"] + fam_stats["n_pdb_seqs"]
-        fam_stats.to_csv(path_to_seq_data + "realigned/statistics.csv")
+        fam_stats.to_csv(path_to_seq_data + "data/statistics.csv")
         # print the stats
         # print the stats
         for f in fam_list:
         for f in fam_list:
             line = fam_stats[fam_stats["rfam_acc"]==f]
             line = fam_stats[fam_stats["rfam_acc"]==f]