heatmap zscores

fractalis/analytics/tasks/heatmap/main.py

 """Module containing analysis code for heatmap analytics."""
 
-from typing import List
+from typing import List, TypeVar
 from functools import reduce
 
 import pandas as pd
+from scipy.stats import zscore
 
 from fractalis.analytics.task import AnalyticTask
 
 
+T = TypeVar('T')
+
+
 class HeatmapTask(AnalyticTask):
     """Heatmap Analysis Task implementing AnalyticsTask. This class is a
     submittable celery task."""
@@ -16,8 +20,29 @@ class HeatmapTask(AnalyticTask):
 
     def main(self, numerical_arrays: List[pd.DataFrame],
              numericals: List[pd.DataFrame],
-             categoricals: List[pd.DataFrame]) -> dict:
+             categoricals: List[pd.DataFrame],
+             subsets: List[List[T]]) -> dict:
         df = reduce(lambda a, b: a.append(b), numerical_arrays)
+        variables = df['variable']
+        df = df.drop('variable', axis=1)
+        zscores = df.apply(zscore, axis=1)
+
+        #prepare output for front-end
+        df = df.transpose()
+        df.columns = variables
+        df.index.name = 'id'
+        df.reset_index(inplace=True)
+        df = pd.melt(df, id_vars='id')
+
+        zscores = zscores.transpose()
+        zscores.columns = variables
+        zscores.index.name = 'id'
+        zscores.reset_index(inplace=True)
+        zscores = pd.melt(zscores, id_vars='id')
+
+        df = pd.merge(df, zscores, on=['id', 'variable'])
+        df.columns = ['id', 'variable', 'value', 'zscore']
+
         return {
             'data': df.to_json(orient='index')
         }
\ No newline at end of file

fractalis/data/etls/ada/etl_double_array.py

@@ -32,9 +32,15 @@ class DoubleArrayETL(ETL):
     def transform(self, raw_data: List[dict], descriptor: dict) -> pd.DataFrame:
         data = shared.prepare_ids(raw_data)
         name = descriptor['dictionary']['name']
-        df = [[row['id']] + row[name] for row in raw_data]
-        colnames = ['id'] + list(range(len(df[0]) - 1))
-        df = pd.DataFrame(df, columns=colnames)
-        df = pd.melt(df, id_vars=['id'])
+        ids = []
+        values = []
+        for row in raw_data:
+            ids.append(row['id'])
+            values.append(row[name])
+        df = pd.DataFrame(values)
+        df = df.transpose()
+        df.columns = ids
+        variables = pd.Series(range(df.shape[0]))
+        df.insert(0, 'variable', variables)
         return df