From 610f2631c0296127bba1dc6066acec82b0748107 Mon Sep 17 00:00:00 2001
From: onesuper <onesuperclark@gmail.com>
Date: Wed, 16 Nov 2016 17:24:42 +0800
Subject: [PATCH] support stats/extended_stats result extraction

---
 CHANGELOG.md                 | 1 +
 README.md                    | 6 +++++-
 pandasticsearch/operators.py | 4 ++--
 pandasticsearch/queries.py   | 7 +++++--
 pandasticsearch/types.py     | 8 ++++++++
 5 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 558b862..da0e63f 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,7 @@
 
 ### 0.2.0
 
+* support metric agg: `stats`, `extended_stats`
 * support boolean filter: `like`, `rlike`, `startswith`, `notnull`
 * display time in `df.show()`
 
diff --git a/README.md b/README.md
index 9f7152a..161cbb2 100644
--- a/README.md
+++ b/README.md
@@ -100,7 +100,7 @@ df.sort(ScriptSorter('doc["age"].value * 2')).collect()
 df[df.gender == 'male'].agg(df.age.avg).collect()
 # [Row(avg(age)=12)]
 
-# Groupby
+# Groupby only (will give the `doc_count`)
 df.groupby('gender').collect()
 # [Row(doc_count=1), Row(doc_count=2)]
 
@@ -120,6 +120,10 @@ df[df.gender == 'male'].agg(df.age.avg).to_pandas()
 #    avg(age)
 # 0        12
 
+# Advanced ES functinality
+df.groupby(df.gender).agg(df.age.stats).to_pandas()
+df.agg(df.age.extended_stats).to_pandas()
+df.agg(df.age.percentiles).to_pandas()
 ```
 
 
diff --git a/pandasticsearch/operators.py b/pandasticsearch/operators.py
index 0bfcb04..f2d5706 100644
--- a/pandasticsearch/operators.py
+++ b/pandasticsearch/operators.py
@@ -1,7 +1,7 @@
 # -*- coding: UTF-8 -*-
 
-_metric_aggs = ('avg', 'min', 'max', 'cardinality', 'value_count', 'sum'
-                'percentiles', 'percentile_ranks')
+_metric_aggs = ('avg', 'min', 'max', 'cardinality', 'value_count', 'sum',
+                'percentiles', 'percentile_ranks', 'stats', 'extended_stats')
 
 _sort_mode = ('min', 'max', 'sum', 'avg', 'median')
 
diff --git a/pandasticsearch/queries.py b/pandasticsearch/queries.py
index ff6a506..0bd4ff6 100644
--- a/pandasticsearch/queries.py
+++ b/pandasticsearch/queries.py
@@ -192,8 +192,11 @@ def _process_agg(cls, bucket, indexes=(), names=()):
                     row[k] = v['value']
                 elif 'values' in v:  # percentiles
                     row = v['values']
-            if k == 'doc_count':  # count docs
-                row['doc_count'] = v
+                else:
+                    row.update(v)    # stats
+            else:
+                if k == 'doc_count':  # count docs
+                    row['doc_count'] = v
 
         if len(row) > 0:
             yield (names, indexes, row)
diff --git a/pandasticsearch/types.py b/pandasticsearch/types.py
index 44fbf48..44530bd 100644
--- a/pandasticsearch/types.py
+++ b/pandasticsearch/types.py
@@ -96,6 +96,14 @@ def percentiles(self):
     def percentile_ranks(self):
         return MetricAggregator(self._field, 'percentile_ranks')
 
+    @property
+    def stats(self):
+        return MetricAggregator(self._field, 'stats')
+
+    @property
+    def extended_stats(self):
+        return MetricAggregator(self._field, 'extended_stats')
+
 
 class Row(tuple):
     """