From 37e6b4a22866c2b87041f68683e5cf4e88f39c3d Mon Sep 17 00:00:00 2001
From: Andy Eschbacher <andy.eschbacher@gmail.com>
Date: Tue, 20 Mar 2018 11:58:42 -0400
Subject: [PATCH] fixes release path copy error [ci skip]

---
 release/crankshaft--0.8.1--0.9.0.sql          | 112 ++++++++++++++++--
 release/python/0.9.0/crankshaft/.setup.py.swp | Bin 12288 -> 0 bytes
 2 files changed, 99 insertions(+), 13 deletions(-)
 delete mode 100644 release/python/0.9.0/crankshaft/.setup.py.swp

diff --git a/release/crankshaft--0.8.1--0.9.0.sql b/release/crankshaft--0.8.1--0.9.0.sql
index d32bebc..50689a7 100644
--- a/release/crankshaft--0.8.1--0.9.0.sql
+++ b/release/crankshaft--0.8.1--0.9.0.sql
@@ -4,7 +4,7 @@
 -- Version number of the extension release
 CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
 RETURNS text AS $$
-  SELECT '0.8.1'::text;
+  SELECT '0.9.0'::text;
 $$ language 'sql' IMMUTABLE STRICT PARALLEL SAFE;
 
 -- Internal identifier of the installed extension instence
@@ -71,7 +71,8 @@ AS $$
     import numpy as np
     import plpy
 
-    from crankshaft.segmentation import create_and_predict_segment_agg
+    from crankshaft.segmentation import Segmentation
+    seg = Segmentation()
     model_params = {'n_estimators': n_estimators,
                     'max_depth': max_depth,
                     'subsample': subsample,
@@ -80,22 +81,24 @@ AS $$
 
     def unpack2D(data):
         dimension = data.pop(0)
-        a = np.array(data, dtype=float)
-        return a.reshape(len(a)/dimension, dimension)
+        a = np.array(data, dtype=np.float64)
+        return a.reshape(int(len(a)/dimension), int(dimension))
 
-    return create_and_predict_segment_agg(np.array(target, dtype=float),
-            unpack2D(features),
-            unpack2D(target_features),
-            target_ids,
-            model_params)
+    return seg.create_and_predict_segment_agg(
+        np.array(target, dtype=np.float64),
+        unpack2D(features),
+        unpack2D(target_features),
+        target_ids,
+        model_params)
 
 $$ LANGUAGE plpythonu VOLATILE PARALLEL RESTRICTED;
 
 CREATE OR REPLACE FUNCTION
-  CDB_CreateAndPredictSegment (
+  CDB_CreateAndPredictSegment(
       query TEXT,
       variable_name TEXT,
       target_table TEXT,
+      model_name text DEFAULT NULL,
       n_estimators INTEGER DEFAULT 1200,
       max_depth INTEGER DEFAULT 3,
       subsample DOUBLE PRECISION DEFAULT 0.5,
@@ -103,9 +106,92 @@ CREATE OR REPLACE FUNCTION
       min_samples_leaf INTEGER DEFAULT 1)
 RETURNS TABLE (cartodb_id TEXT, prediction NUMERIC, accuracy NUMERIC)
 AS $$
-  from crankshaft.segmentation import create_and_predict_segment
-  model_params = {'n_estimators': n_estimators, 'max_depth':max_depth, 'subsample' : subsample, 'learning_rate': learning_rate, 'min_samples_leaf' : min_samples_leaf}
-  return create_and_predict_segment(query,variable_name,target_table, model_params)
+    from crankshaft.segmentation import Segmentation
+    seg = Segmentation()
+    model_params = {
+        'n_estimators': n_estimators,
+        'max_depth': max_depth,
+        'subsample': subsample,
+        'learning_rate': learning_rate,
+        'min_samples_leaf': min_samples_leaf
+    }
+    all_cols = list(plpy.execute('''
+        select * from ({query}) as _w limit 0
+    '''.format(query=query)).colnames())
+    feature_cols = [a for a in all_cols
+                    if a not in [variable_name, 'cartodb_id', ]]
+    return seg.create_and_predict_segment(
+        query,
+        variable_name,
+        feature_cols,
+        target_table,
+        model_params,
+        model_name=model_name
+    )
+$$ LANGUAGE plpythonu VOLATILE PARALLEL UNSAFE;
+
+CREATE OR REPLACE FUNCTION
+  CDB_RetrieveModelParams(
+    model_name text,
+    param_name text
+  )
+RETURNS TABLE(param numeric, feature_name text) AS $$
+
+import pickle
+from collections import Iterable
+
+plan = plpy.prepare('''
+    SELECT model, feature_names FROM model_storage
+    WHERE name = $1;
+''', ['text', ])
+
+try:
+    model_encoded = plpy.execute(plan, [model_name, ])
+except plpy.SPIError as err:
+    plpy.error('ERROR: {}'.format(err))
+plpy.notice(model_encoded[0]['feature_names'])
+model = pickle.loads(
+    model_encoded[0]['model']
+)
+
+res = getattr(model, param_name) 
+if not isinstance(res, Iterable):
+    raise Exception('Cannot return `{}` as a table'.format(param_name))
+return zip(res, model_encoded[0]['feature_names'])
+
+$$ LANGUAGE plpythonu VOLATILE PARALLEL UNSAFE;
+
+CREATE OR REPLACE FUNCTION
+  CDB_CreateAndPredictSegment(
+      query TEXT,
+      variable TEXT,
+      feature_columns TEXT[],
+      target_query TEXT,
+      model_name TEXT DEFAULT NULL,
+      n_estimators INTEGER DEFAULT 1200,
+      max_depth INTEGER DEFAULT 3,
+      subsample DOUBLE PRECISION DEFAULT 0.5,
+      learning_rate DOUBLE PRECISION DEFAULT 0.01,
+      min_samples_leaf INTEGER DEFAULT 1)
+RETURNS TABLE (cartodb_id TEXT, prediction NUMERIC, accuracy NUMERIC)
+AS $$
+    from crankshaft.segmentation import Segmentation
+    seg = Segmentation()
+    model_params = {
+        'n_estimators': n_estimators,
+        'max_depth': max_depth,
+        'subsample': subsample,
+        'learning_rate': learning_rate,
+        'min_samples_leaf': min_samples_leaf
+    }
+    return seg.create_and_predict_segment(
+        query,
+        variable,
+        feature_columns,
+        target_query,
+        model_params,
+        model_name=model_name
+    )
 $$ LANGUAGE plpythonu VOLATILE PARALLEL UNSAFE;
 CREATE OR REPLACE FUNCTION CDB_Gravity(
     IN target_query text,
diff --git a/release/python/0.9.0/crankshaft/.setup.py.swp b/release/python/0.9.0/crankshaft/.setup.py.swp
deleted file mode 100644
index 548384445df3d966d35139cdfa2e016a412c2605..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 12288
zcmeI2-EJH;6vrJTkf0P0ynvHlOe1AyKZ-(FX(YA{7b_)A)GQw&Dv{UY-7z~eHnwNe
zZB=*??&w9Oz6e)v0hiDh=q*S{Ai>|Wvvh-mlv^r0`e$bB<KuIF$0KDFk2@a^59waq
zA!u(Avh%}}&z=oGC*AuSL<`HaG2@vqe)K<^)UEFOy;gU3uhnhsc4EPMu`Hc1CCk?*
zeYNJWy)W#{Dc!y`xHCFxr()g`<-E-eD`z%i6W6wexAo#ek8qWa^<v#;xDNyZflCmm
z+@!U4mE7oc>sS5S)+T-D?T;=oF_;7bfj}S-2m}IwKp+qZ1OkD;i$cKZ4e~XTd8tXL
z+gvyPb!{HQB@hS%0)apv5C{YUfj}S-2m}IwKp+qZ1pbEvSW3vBuM+a}YX~0y|6hIo
z|Meyze?UJ%-$Rd~N6@#>IW&h9^eOZSbQ2mtuRt$DKfQsu&|~NUbRU{R6KDi&L%&~z
zZ|ECn2Bi>(HX#Z<eVveBpzok3&_ierRnQ)E1$uOakS%Bv`VBe!3O$8<KF^@g0)apv
z5C{YUfj}S-2n1dL0^5Y5Ibq$It)vr4<nJT=)re-qmz6ZaCa0G)i}b>>JldgASrvNW
zZ|p1=%#_jHouyA%TF3JI?78pg3pLK=I7vG3UVP)9$w|_UcjIpDgG;^e<K1`Tj_;_K
z@doIqXIL(0(zWWP8pC>~7OrH4NRnRM^C9@GuF>J)@zI^p;P!~#J{o=4ryBFDps6Y&
zM|sA|sh}>Cmgce)F&!dg!BQ%%tpsJ%Nj?*fIz{aQBZZ|CWvH05ykbtOGH#a9M$M%~
zhrrwt9tA~LT5)egtuS+8?8<nAQJyKu1yvKuRiQDjbky6x++uZ_O7570xAB6WXUs)*
z$@JkeF`wMBe0_QvRi$)wEqyhV6`ot6_-uutw#H%M=z?*>NZfOV*;SE}2g`Ld<1;qJ
zewfHIJzG6p7x#Exr6M_vxGJ5IW4~0Yxb;^bf{pHOH|3v+#kn%6O`?KnOYuv~atf9z
zx72FzV>x9w?Yyu^cq$Zji<1_};cXd36Jj0zu~AdQio*LiK;0^YNBezxyl@#9<E|IK
zhl$?Ux99+XOVk=8M<+u%(7s3@is!@Oh&IFPGe$~FUXS~Ly<HRY$j7{HImAKjGKI52
zl}b^fl55tesILg#2~tPmgV`5zkt<#JI-elVs`h__w&)<&8EZ^=&a9OaiH(q)E)nF*
zERqN@!>abkDx_@AM8Ra9L@9IF(q;}r`vGUhsdOA8hQ{a8IEnUQMo$_$IufkF;<vo{
z{>_!+%D`XdoVNXTdn#R4)t=go+1j!4)r=IU-Hp_Kn<r6YMo*gJ4pzl&YIGpSh8fSL
zPNUiHNz{q)v+Av1;^_I2cJy0+g#9``gN-WiGT~vli6q_}<CZ-;^ukWX_wCjexl}6T
NM2J4QWbCzD@;BW|_n`m)