initial groundwork

Author: lightstrike

.gitignore

@@ -0,0 +1,62 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 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
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+media/
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# DB
+*.sqlite3
+*.db

chronic_medicare/.admin.py.swp

@@ -0,0 +1,6 @@
+from django.contrib import admin
+from .models import MedicareFile, ChronicConditionLinearRegression
+
+
+admin.site.register(MedicareFile)
+admin.site.register(ChronicConditionLinearRegression)

chronic_medicare/__init__.py

@@ -0,0 +1,59 @@
+CHRONIC_COLUMN_NAMES = [
+    ('BENE_SEX_IDENT_CD', 'BENE_SEX_IDENT_CD'),
+    ('BENE_AGE_CAT_CD', 'BENE_AGE_CAT_CD'),
+    ('CC_ALZHDMTA', 'CC_ALZHDMTA'),
+    ('CC_CANCER', 'CC_CANCER'),
+    ('CC_CHF', 'CC_CHF'),
+    ('CC_CHRNKIDN', 'CC_CHRNKIDN'),
+    ('CC_COPD', 'CC_COPD'),
+    ('CC_DEPRESSN', 'CC_DEPRESSN'),
+    ('CC_DIABETES', 'CC_DIABETES'),
+    ('CC_ISCHMCHT', 'CC_ISCHMCHT'),
+    ('CC_OSTEOPRS', 'CC_OSTEOPRS'),
+    ('CC_RA_OA', 'CC_RA_OA'),
+    ('CC_STRKETIA', 'CC_STRKETIA'),
+    ('CC_2_OR_MORE', 'CC_2_OR_MORE'),
+    ('DUAL_STUS', 'DUAL_STUS'),
+    ('BENE_COUNT_PA_LT_12', 'BENE_COUNT_PA_LT_12'),
+    ('AVE_MO_EN_PA_LT_12', 'AVE_MO_EN_PA_LT_12'),
+    ('AVE_PA_PAY_PA_LT_12', 'AVE_PA_PAY_PA_LT_12'),
+    ('AVE_IP_PAY_PA_LT_12', 'AVE_IP_PAY_PA_LT_12'),
+    ('AVE_SNF_PAY_PA_LT_12', 'AVE_SNF_PAY_PA_LT_12'),
+    ('AVE_OTH_PAY_PA_LT_12', 'AVE_OTH_PAY_PA_LT_12'),
+    ('AVE_IP_ADM_PA_LT_12', 'AVE_IP_ADM_PA_LT_12'),
+    ('AVE_SNF_DAYS_PA_LT_12', 'AVE_SNF_DAYS_PA_LT_12'),
+    ('BENE_COUNT_PA_EQ_12', 'BENE_COUNT_PA_EQ_12'),
+    ('AVE_PA_PAY_PA_EQ_12', 'AVE_PA_PAY_PA_EQ_12'),
+    ('AVE_IP_PAY_PA_EQ_12', 'AVE_IP_PAY_PA_EQ_12'),
+    ('AVE_SNF_PAY_PA_EQ_12', 'AVE_SNF_PAY_PA_EQ_12'),
+    ('AVE_OTH_PAY_PA_EQ_12', 'AVE_OTH_PAY_PA_EQ_12'),
+    ('AVE_IP_ADM_PA_EQ_12', 'AVE_IP_ADM_PA_EQ_12'),
+    ('AVE_SNF_DAYS_PA_EQ_12', 'AVE_SNF_DAYS_PA_EQ_12'),
+    ('BENE_COUNT_PB_LT_12', 'BENE_COUNT_PB_LT_12'),
+    ('AVE_MO_EN_PB_LT_12', 'AVE_MO_EN_PB_LT_12'),
+    ('AVE_PB_PAY_PB_LT_12', 'AVE_PB_PAY_PB_LT_12'),
+    ('AVE_CA_PAY_PB_LT_12', 'AVE_CA_PAY_PB_LT_12'),
+    ('AVE_OP_PAY_PB_LT_12', 'AVE_OP_PAY_PB_LT_12'),
+    ('AVE_OTH_PAY_PB_LT_12', 'AVE_OTH_PAY_PB_LT_12'),
+    ('AVE_CA_VST_PB_LT_12', 'AVE_CA_VST_PB_LT_12'),
+    ('AVE_OP_VST_PB_LT_12', 'AVE_OP_VST_PB_LT_12'),
+    ('BENE_COUNT_PB_EQ_12', 'BENE_COUNT_PB_EQ_12'),
+    ('AVE_PB_PAY_PB_EQ_12', 'AVE_PB_PAY_PB_EQ_12'),
+    ('AVE_CA_PAY_PB_EQ_12', 'AVE_CA_PAY_PB_EQ_12'),
+    ('AVE_OP_PAY_PB_EQ_12', 'AVE_OP_PAY_PB_EQ_12'),
+    ('AVE_OTH_PAY_PB_EQ_12', 'AVE_OTH_PAY_PB_EQ_12'),
+    ('AVE_CA_VST_PB_EQ_12', 'AVE_CA_VST_PB_EQ_12'),
+    ('AVE_OP_VST_PB_EQ_12', 'AVE_OP_VST_PB_EQ_12'),
+    ('BENE_COUNT_PC_LT_12', 'BENE_COUNT_PC_LT_12'),
+    ('AVE_MO_EN_PC_LT_12', 'AVE_MO_EN_PC_LT_12'),
+    ('BENE_COUNT_PC_EQ_12', 'BENE_COUNT_PC_EQ_12'),
+    ('BENE_COUNT_PD_LT_12', 'BENE_COUNT_PD_LT_12'),
+    ('AVE_MO_EN_PD_LT_12', 'AVE_MO_EN_PD_LT_12'),
+    ('AVE_PDE_CST_PD_LT_12', 'AVE_PDE_CST_PD_LT_12'),
+    ('AVE_PDE_PD_LT_12', 'AVE_PDE_PD_LT_12'),
+    ('BENE_COUNT_PD_EQ_12', 'BENE_COUNT_PD_EQ_12'),
+    ('AVE_PDE_CST_PD_EQ_12', 'AVE_PDE_CST_PD_EQ_12'),
+    ('AVE_PDE_PD_EQ_12', 'AVE_PDE_PD_EQ_12'),
+]
+
+DEPENDENT_VARIABLE = 'AVE_PA_PAY_PA_LT_12'

chronic_medicare/admin.py

@@ -0,0 +1,25 @@
+from django import forms
+from .models import MedicareFile, ChronicConditionLinearRegression
+from .constants import CHRONIC_COLUMN_NAMES
+
+
+class ChronicConditionAnalysisQueryForm(forms.Form):
+    '''
+    This form validates that valid query choices have been made
+    '''
+    parameters = forms.MultipleChoiceField(choices=CHRONIC_COLUMN_NAMES,
+        widget=forms.CheckboxSelectMultiple())
+    create_dummies = forms.BooleanField(required=False)
+    input_file = forms.ModelChoiceField(queryset=MedicareFile.objects.all())
+
+    def clean_input_file(self):
+        return self.cleaned_data['input_file'].csv_file
+
+class ChronicConditionLinearRegressionForm(forms.ModelForm):
+    '''
+    This model form is used to validate output from
+    sklearn LinearRegression to ensure data saved is legitimate
+    '''
+    class Meta:
+        model = ChronicConditionLinearRegression
+        fields = ['parameters', 'coefficient', 'constant', 'r_squared']

chronic_medicare/constants.py

@@ -0,0 +1,30 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='ChronicConditionLinearRegression',
+            fields=[
+                ('id', models.AutoField(primary_key=True, verbose_name='ID', serialize=False, auto_created=True)),
+                ('parameters', models.CharField(max_length=512)),
+                ('coefficient', models.FloatField(max_length=64)),
+                ('constant', models.FloatField(default=0, max_length=64)),
+                ('p_value', models.FloatField(max_length=64)),
+            ],
+        ),
+        migrations.CreateModel(
+            name='MedicareFile',
+            fields=[
+                ('id', models.AutoField(primary_key=True, verbose_name='ID', serialize=False, auto_created=True)),
+                ('csv_file', models.FileField(upload_to='medicare-files/')),
+            ],
+        ),
+    ]

chronic_medicare/forms.py

@@ -0,0 +1,19 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('chronic_medicare', '0001_initial'),
+    ]
+
+    operations = [
+        migrations.RenameField(
+            model_name='chronicconditionlinearregression',
+            old_name='p_value',
+            new_name='r_squared',
+        ),
+    ]

chronic_medicare/migrations/0001_initial.py

@@ -0,0 +1,37 @@
+from django.db import models
+from django.utils.encoding import python_2_unicode_compatible
+
+import numpy as np
+
+
+class MedicareFile(models.Model):
+    csv_file = models.FileField(upload_to='medicare-files/')
+
+    def __str__(self):
+        return self.csv_file.name.split('/')[-1]
+
+
+@python_2_unicode_compatible
+class ChronicConditionLinearRegression(models.Model):
+    # source_file = models.ForeignKey(MedicareFile, related_name="linear_regressions")
+    parameters = models.CharField(max_length=512)
+    coefficient = models.FloatField(max_length=64)
+    constant = models.FloatField(max_length=64, default=0)
+    r_squared = models.FloatField(max_length=64)
+
+    def __str__(self):
+        return str(self.id)
+
+    def chart_x_values(self, min_value=0, max_value=100, intervals=10):
+        initial_range = np.arange(min_value, max_value, max_value/intervals)
+        x_values = initial_range.tolist()
+        x_values.append(max_value)
+        x_values = [int(value) for value in x_values]
+        return x_values
+
+    def chart_y_values(self):
+        chart_y_values = []
+        for x in self.chart_x_values()[1:]:
+            y_value = self.coefficient * x + self.constant
+            chart_y_values.append(y_value)
+        return chart_y_values

chronic_medicare/migrations/0002_auto_20151008_2228.py

@@ -0,0 +1,40 @@
+import pandas as pd
+from sklearn.linear_model import LinearRegression
+
+from .models import ChronicConditionLinearRegression
+from .forms import ChronicConditionLinearRegressionForm
+from .constants import DEPENDENT_VARIABLE
+
+
+def run_linear_regression(input_data):
+    # df is standard short form for DataFrame object
+    df = pd.read_csv(input_data['input_file'])
+
+    independent = input_data['parameters'][0]
+    try:
+        dependent = input_data['dependent']
+    except KeyError:
+        dependent = DEPENDENT_VARIABLE
+
+    # FIXME: Implement dummy variable logic
+    X = df[[independent]].fillna(df[independent].mean())
+    Y = df[[dependent]].fillna(df[dependent].mean())
+
+    reg = LinearRegression()
+    reg.fit(X, Y)
+    results = {
+        'parameters': independent,
+        'coefficient': reg.coef_,
+        'constant': reg.intercept_,
+        'r_squared': reg.score(X, Y),
+        }
+    return results
+
+
+def save_linear_regression(results):
+    form = ChronicConditionLinearRegressionForm(results)
+    if form.is_valid():
+        regression_results, created = ChronicConditionLinearRegression.objects.get_or_create(**form.cleaned_data)
+        return regression_results
+    else:
+        raise Exception("Invalid regression results!")

chronic_medicare/migrations/__init__.py

@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.

chronic_medicare/models.py

@@ -0,0 +1,10 @@
+from django.conf.urls import patterns, url
+from . import views
+
+
+urlpatterns = patterns('reports.views',
+	url(r'^$', views.results_list, name='results_list'),
+	url(r'^query/$', views.query_view, name='query'),
+	url(r'^results/(?P<pk>[0-9]+)/$', views.results_detail, name='results_detail'),
+)
+

chronic_medicare/regression.py

@@ -0,0 +1,26 @@
+from django.shortcuts import render, redirect, get_object_or_404
+from .models import ChronicConditionLinearRegression
+from .forms import ChronicConditionAnalysisQueryForm
+from .regression import run_linear_regression, save_linear_regression
+
+
+def query_view(request):
+    if request.method == 'POST':
+        form = ChronicConditionAnalysisQueryForm(request.POST)
+        if form.is_valid():
+            regression_results = run_linear_regression(form.cleaned_data)
+            saved_regression = save_linear_regression(regression_results)
+            return redirect('chronic:results_detail', pk=saved_regression.pk)
+    else:
+        form = ChronicConditionAnalysisQueryForm()
+    return render(request, 'chronic_medicare/query.html', {'form': form})
+
+
+def results_list(request):
+    results = ChronicConditionLinearRegression.objects.all()
+    return render(request, 'chronic_medicare/results_list.html', {'results': results})
+
+
+def results_detail(request, pk):
+    result = get_object_or_404(ChronicConditionLinearRegression, pk=pk)
+    return render(request, 'chronic_medicare/results_detail.html', {'result': result})