Merge branch 'master' of https://github.com/HealthRex/CDSS

scripts/cost_variability_2024/scripts/pipeline/combine_tab.py

@@ -0,0 +1,36 @@
+import pandas as pd
+import numpy as np
+import os
+
+def res_fold(to_res, out):
+    return [i for i in os.listdir(to_res) if i.startswith(f'res_{out}')][0]
+
+class comb_tab:
+    def __init__(self, to_res, comb):
+        self.comb = comb
+        self.to_res = to_res
+        self.folder = {'hi': f'{to_res}/{res_fold(to_res, 'hi')}/{self.comb}', 'lo': f'{to_res}/{res_fold(to_res, 'lo')}/{self.comb}'}
+        self.file_names_hi = os.listdir(self.folder['hi'])
+        self.file_names_lo = os.listdir(self.folder['lo'])
+
+    def combine(self):
+        dfs = []
+        for file_name in self.file_names_hi:
+            for out in ['hi', 'lo']:
+                drg_no = ''.join([char for char in file_name if char.isdigit()])   
+                df = pd.read_csv(os.path.join(self.folder[out], file_name))
+                df['drg_no'] = drg_no
+                df['outlier'] = out
+                dfs.append(df)
+        self.df = pd.concat(dfs).sort_values(by='odds_ratio', ascending=False)
+
+    def export(self):
+        if not os.path.exists('scripts/pipeline/res/res_comb'):
+            os.makedirs(f'{self.to_res}/res_comb')
+        self.df.to_csv(f'{self.to_res}/res_comb/res_{self.comb}.csv', index=False)
+
+comp_list = ['comp_medorderset', 'comp_proc', 'comp_diag', 'comp_procorderset', 'comp_med']
+for comp in comp_list:
+    comb = comb_tab('scripts/pipeline/res', comp)
+    comb.combine()
+    comb.export()

scripts/cost_variability_2024/scripts/pipeline/export.yml

@@ -0,0 +1,64 @@
+name: comb_tab
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - appnope=0.1.4=pyhd8ed1ab_0
+  - asttokens=2.4.1=pyhd8ed1ab_0
+  - bzip2=1.0.8=h80987f9_6
+  - ca-certificates=2024.7.4=hf0a4a13_0
+  - comm=0.2.2=pyhd8ed1ab_0
+  - debugpy=1.6.7=py312h313beb8_0
+  - decorator=5.1.1=pyhd8ed1ab_0
+  - exceptiongroup=1.2.2=pyhd8ed1ab_0
+  - executing=2.0.1=pyhd8ed1ab_0
+  - expat=2.6.2=h313beb8_0
+  - importlib-metadata=8.2.0=pyha770c72_0
+  - importlib_metadata=8.2.0=hd8ed1ab_0
+  - ipykernel=6.29.5=pyh57ce528_0
+  - ipython=8.26.0=pyh707e725_0
+  - jedi=0.19.1=pyhd8ed1ab_0
+  - jupyter_client=8.6.2=pyhd8ed1ab_0
+  - jupyter_core=5.7.2=py312hca03da5_0
+  - libcxx=14.0.6=h848a8c0_0
+  - libffi=3.4.4=hca03da5_1
+  - libsodium=1.0.18=h27ca646_1
+  - matplotlib-inline=0.1.7=pyhd8ed1ab_0
+  - ncurses=6.4=h313beb8_0
+  - nest-asyncio=1.6.0=pyhd8ed1ab_0
+  - openssl=3.3.1=hfb2fe0b_2
+  - packaging=24.1=pyhd8ed1ab_0
+  - parso=0.8.4=pyhd8ed1ab_0
+  - pexpect=4.9.0=pyhd8ed1ab_0
+  - pickleshare=0.7.5=py_1003
+  - pip=24.0=py312hca03da5_0
+  - platformdirs=4.2.2=pyhd8ed1ab_0
+  - prompt-toolkit=3.0.47=pyha770c72_0
+  - psutil=5.9.0=py312h80987f9_0
+  - ptyprocess=0.7.0=pyhd3deb0d_0
+  - pure_eval=0.2.3=pyhd8ed1ab_0
+  - pygments=2.18.0=pyhd8ed1ab_0
+  - python=3.12.4=h99e199e_1
+  - python-dateutil=2.9.0=pyhd8ed1ab_0
+  - pyzmq=25.1.2=py312h313beb8_0
+  - readline=8.2=h1a28f6b_0
+  - setuptools=69.5.1=py312hca03da5_0
+  - six=1.16.0=pyh6c4a22f_0
+  - sqlite=3.45.3=h80987f9_0
+  - stack_data=0.6.2=pyhd8ed1ab_0
+  - tk=8.6.14=h6ba3021_0
+  - tornado=6.4.1=py312h80987f9_0
+  - traitlets=5.14.3=pyhd8ed1ab_0
+  - typing_extensions=4.12.2=pyha770c72_0
+  - wcwidth=0.2.13=pyhd8ed1ab_0
+  - wheel=0.43.0=py312hca03da5_0
+  - xz=5.4.6=h80987f9_1
+  - zeromq=4.3.5=h313beb8_0
+  - zipp=3.19.2=pyhd8ed1ab_0
+  - zlib=1.2.13=h18a0788_1
+  - pip:
+      - numpy==2.0.1
+      - pandas==2.2.2
+      - pytz==2024.1
+      - tzdata==2024.1
+prefix: /opt/anaconda3/envs/comb_tab