added client, updated gitignore

.gitignore

@@ -19,10 +19,6 @@ lib64/
 parts/
 sdist/
 var/
-reports/
-models/
-src/api/embeddings
-src/api/models
 *.egg-info/
 .installed.cfg
 *.egg
@@ -80,7 +76,22 @@ target/
 .ipynb_checkpoints/
 
 # exclude data from source control by default
-/data/
+data/*
+!data/.gitkeep
+
+# exclude model dir
+models/*
+!models/.gitkeep
+
+# exclude reports dir
+reports/*
+!reports/.gitkeep
+
+# exclude api data dirs
+src/api/embeddings/*
+src/api/models/*
+!src/api/embeddings/.gitkeep
+!src/api/models/.gitkeep
 
 # exclude keras tuner
 /reports/keras_tuner/

client.py

+import argparse
+import os
+from src.data import parse_and_clean_data, make_screenings
+from src.data import make_clusters, make_dataset_full
+from src.data import make_dataset_count, make_dataset_emb
+
+def dir_path(string):
+    if os.path.isdir(string):
+        return string
+    else:
+        raise NotADirectoryError(string)
+
+def parse_arguments():
+    parser = argparse.ArgumentParser(description='A client for AIR')
+    #parser.add_argument('--path', type=dir_path,
+    #                help='path to data dictionary with raw files')
+    return parser.parse_args()
+
+def main():
+    parsed_args = parse_arguments()
+    #data_path = parsed_args.path
+    print("Client started. Now parsing and cleaning data ...")
+    parse_and_clean_data.main()
+    
+    print("Extracting screenings ...")
+    make_screenings.main()
+    
+    print("Making clusters ...")
+    make_clusters.main()
+    
+    print("Making full dataset ...")
+    make_dataset_full.main()
+    
+    print("Making dataset with embedded ats ...")
+    make_dataset_emb.main()
+    
+    print("Making dataset with one-hot encoded ats ...")
+    make_dataset_count.main()
+    
+if __name__ == "__main__":
+    main()
\ No newline at end of file

conf.py

@@ -19,7 +19,7 @@
 
 project = 'air'
 copyright = '2021, Christian Marius Lillelund'
-author = 'Christian Marius Lillelund'
+author = 'Christian Marius Lillelund, Christian Fischer Pedersen'
 
 # The full version, including alpha/beta/rc tags
 release = '0.0.1'

setup.py

@@ -6,9 +6,9 @@ setup(
     packages=find_packages(where='src'),
 	setup_requires=["pytest-runner"],
 	tests_require=["pytest"],
-    version='0.1.0',
+    version='0.0.1',
     description='AIR is an open-source ML project to model and find patterns in health care data.',
-    author='Christian Marius Lillelund',
+    author='Christian Marius Lillelund, Christian Fischer Pedersen',
     author_email='cl@ece.au.dk',
     license='MIT',
 )
\ No newline at end of file

src/data/make_dataset_full.py

@@ -4,7 +4,7 @@ from tools import file_reader, file_writer, feature_maker
 from tools import preprocessor
 import pandas as pd
 
-USE_CAT_NAMES = True
+USE_CAT_NAMES = False
 
 def main():
     clusters = file_reader.read_csv(cfg.INTERIM_DATA_DIR, 'cl.csv',