Merge pull request #39 from mitre/t23-package-reorg

Reorganized package

Author: eedrummer

.gitignore

@@ -135,4 +135,13 @@ dmypy.json
 .pytype/
 
 # Cython debug symbols
-cython_debug/
+cython_debug/
+
+# VSCode environment
+.history
+.vscode
+
+# Other local additions
+*.swo
+*.swp
+.DS_Store

GrowthViz-adults.ipynb

@@ -28,13 +28,14 @@
 # In[1]:
 
 
-import pandas as pd
-import numpy as np
 import matplotlib.pyplot as plt
 import matplotlib as mpl
+import numpy as np
+import pandas as pd
+import seaborn as sns
+
 from ipywidgets import interact, interactive, fixed, interact_manual
 import ipywidgets as widgets
-import seaborn as sns
 from IPython.display import FileLink, FileLinks
 import qgrid
 
@@ -76,11 +77,11 @@
 # In[6]:
 
 
-import processdata
-import sumstats
-import charts
-import compare
-import check_data
+from growthviz import charts
+from growthviz import check_data
+from growthviz import compare
+from growthviz import processdata
+from growthviz import sumstats
 
 
 # This cell reads in a data set that has been run through the [growthcleanr](https://github.com/carriedaymont/growthcleanr) algorithm. Details of the algorithm can be found in [Automated identification of implausible values in growth data from pediatric electronic health records](https://academic.oup.com/jamia/article/24/6/1080/3767271)
@@ -169,7 +170,7 @@
 
 
 # adult percentiles
-percentiles = pd.read_csv("vdsmeasures.csv", encoding ='latin1')
+percentiles = pd.read_csv("growthviz-data/ext/vdsmeasures.csv", encoding ='latin1')
 percentiles_clean = processdata.setup_percentiles_adults(percentiles)
 
 # save out smoothed percentiles
@@ -527,9 +528,3 @@ def on_button_clicked(b):
 
 
 # In addition, users can take advantage of all of the plotting capabilities of [Matplotlib](https://matplotlib.org/3.1.1/tutorials/index.html) and [Seaborn](https://seaborn.pydata.org/tutorial.html)
-
-# In[ ]:
-
-
-
-

GrowthViz-adults.py

@@ -28,12 +28,13 @@
 # In[1]:
 
 
+import matplotlib.pyplot as plt
 import pandas as pd
 import numpy as np
-import matplotlib.pyplot as plt
+import seaborn as sns
+
 from ipywidgets import interact, interactive, fixed, interact_manual
 import ipywidgets as widgets
-import seaborn as sns
 from IPython.display import FileLink, FileLinks
 import qgrid
 
@@ -75,11 +76,11 @@
 # In[6]:
 
 
-import processdata
-import sumstats
-import charts
-import compare
-import check_data
+from growthviz import charts
+from growthviz import check_data
+from growthviz import compare
+from growthviz import processdata
+from growthviz import sumstats
 
 
 # This cell reads in a data set that has been run through the [growthcleanr](https://github.com/carriedaymont/growthcleanr) algorithm. Details of the algorithm can be found in [Automated identification of implausible values in growth data from pediatric electronic health records](https://academic.oup.com/jamia/article/24/6/1080/3767271)
@@ -556,15 +557,3 @@ def on_button_clicked(b):
 
 compare.subject_stats_comparison(combined)
 
-
-# In[ ]:
-
-
-
-
-
-# In[ ]:
-
-
-
-

GrowthViz-pediatrics.ipynb

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 import os
 import sys
 
@@ -24,19 +26,23 @@ def check_for_file(file_name, not_found_message):
 
 # Check for the function library
 check_for_file(
-    "processdata.py", "Unable to find data processing library functions for GrowthViz."
+    "growthviz/charts.py",
+    "Unable to find visualization library functions for GrowthViz.",
 )
 check_for_file(
-    "sumstats.py", "Unable to find summary statistics library functions for GrowthViz."
+    "growthviz/check_data.py",
+    "Unable to find data checks library functions for GrowthViz.",
 )
 check_for_file(
-    "charts.py", "Unable to find visualization library functions for GrowthViz."
+    "growthviz/compare.py", "Unable to find comparison library functions for GrowthViz."
 )
 check_for_file(
-    "compare.py", "Unable to find comparison library functions for GrowthViz."
+    "growthviz/processdata.py",
+    "Unable to find data processing library functions for GrowthViz.",
 )
 check_for_file(
-    "check_data.py", "Unable to find data checks library functions for GrowthViz."
+    "growthviz/sumstats.py",
+    "Unable to find summary statistics library functions for GrowthViz.",
 )
 
 # Check for tests
@@ -51,17 +57,19 @@ def check_for_file(file_name, not_found_message):
 
 # Check for the CDC growth charts
 check_for_file(
-    "bmiagerev.csv", "Unable to find pediatric CDC growth charts for BMI at age."
+    "growthviz-data/ext/bmiagerev.csv",
+    "Unable to find pediatric CDC growth charts for BMI at age.",
 )
 check_for_file(
-    "statage.csv",
+    "growthviz-data/ext/statage.csv",
     "Unable to find pediatric CDC growth charts for height / stature at age.",
 )
 check_for_file(
-    "wtage.csv", "Unable to find pediatric CDC growth charts for weight at age."
+    "growthviz-data/ext/wtage.csv",
+    "Unable to find pediatric CDC growth charts for weight at age.",
 )
 check_for_file(
-    "vdsmeasures.csv",
+    "growthviz-data/ext/vdsmeasures.csv",
     "Unable to find CDC growth charts for adult weight, height and BMI.",
 )
 

GrowthViz-pediatrics.py

@@ -1,6 +1,7 @@
-import numpy as np
 import math
+
 import matplotlib.pyplot as plt
+import numpy as np
 
 
 def weight_distr(df, mode):

check_setup.py

@@ -1,5 +1,5 @@
-import pandas as pd
 import numpy as np
+import pandas as pd
 
 
 def check_patient_data(file):

bmiagerev.csv growthviz-data/ext/bmiagerev.csv

@@ -1,5 +1,5 @@
-import pandas as pd
 import numpy as np
+import pandas as pd
 
 
 def prepare_for_comparison(frame_dict):

statage.csv growthviz-data/ext/statage.csv

@@ -1,8 +1,8 @@
-import pandas as pd
-import numpy as np
-import matplotlib.pyplot as plt
-import matplotlib as mpl
 from IPython.display import FileLinks
+import matplotlib as mpl
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
 
 
 def setup_individual_obs_df(obs_df):
@@ -95,7 +95,7 @@ def setup_percentiles_pediatrics(percentiles_file):
     Processes pediatrics percentiles from CDC
     """
     percentiles = pd.read_csv(
-        percentiles_file,
+        f'growthviz-data/ext/{percentiles_file}',
         dtype={
             "Agemos": float,
             "P5": float,

swaps.csv growthviz-data/ext/swaps.csv

@@ -1,5 +1,5 @@
-import numpy as np
 from IPython.display import Markdown
+import numpy as np
 
 
 def setup_percentile_zscore_adults(percentiles_clean):

vdsmeasures.csv growthviz-data/ext/vdsmeasures.csv

@@ -1,6 +1,8 @@
 import unittest
+
 import pandas as pd
-import processdata
+
+from growthviz import processdata
 
 
 class DataTestCase(unittest.TestCase):
@@ -72,7 +74,7 @@ def test_sex(self):
 
 class PctAdultTestCase(unittest.TestCase):
     def setUp(self):
-        self.df = pd.read_csv("vdsmeasures.csv", encoding="latin1")
+        self.df = pd.read_csv("growthviz-data/ext/vdsmeasures.csv", encoding="latin1")
 
     def test_vdsmeasures_data(self):
         self.assertEqual(0, self.df["Number of examined persons"].isnull().sum())

wtage.csv growthviz-data/ext/wtage.csv

@@ -1,12 +1,14 @@
 import unittest
+
 import pandas as pd
-import processdata
-import sumstats
+
+from growthviz import processdata
+from growthviz import sumstats
 
 
 class StatAdultTestCase(unittest.TestCase):
     def setUp(self):
-        self.df = pd.read_csv("vdsmeasures.csv")
+        self.df = pd.read_csv("growthviz-data/ext/vdsmeasures.csv")
 
     def test_setup_percentiles_adults(self):
         setup_df = processdata.setup_percentiles_adults(self.df)