Merge pull request #1718 from CartoDB/develop

Release/1.1.1

CHANGELOG.md

@@ -5,6 +5,11 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.1.1] - 2021-02-12
+
+### Fixed
+- Fix geocoding status columns when using cached parameter (#1717)
+
 ## [1.1.0] - 2020-12-04
 
 ### Added

README.rst

@@ -4,8 +4,8 @@ CARTOframes
 
 .. image:: https://travis-ci.org/CartoDB/cartoframes.svg?branch=develop
     :target: https://travis-ci.org/CartoDB/cartoframes
-.. image:: https://img.shields.io/badge/pypi-v1.1.0-orange
-    :target: https://pypi.org/project/cartoframes/1.1.0
+.. image:: https://img.shields.io/badge/pypi-v1.1.1-orange
+    :target: https://pypi.org/project/cartoframes/1.1.1
 
 A Python package for integrating `CARTO <https://carto.com/>`__ maps, analysis, and data services into data science workflows.
 
@@ -14,11 +14,11 @@ Python data analysis workflows often rely on the de facto standards `pandas <htt
 Try it Out
 ==========
 
-* Stable (1.1.0): |stable|
+* Stable (1.1.1): |stable|
 * Latest (develop branch): |develop|
 
 .. |stable| image:: https://mybinder.org/badge_logo.svg
-    :target: https://mybinder.org/v2/gh/cartodb/cartoframes/v1.1.0?filepath=examples
+    :target: https://mybinder.org/v2/gh/cartodb/cartoframes/v1.1.1?filepath=examples
 
 .. |develop| image:: https://mybinder.org/badge_logo.svg
     :target: https://mybinder.org/v2/gh/cartodb/cartoframes/develop?filepath=examples

binder/requirements.txt

@@ -1,4 +1,4 @@
-cartoframes==1.1.0
+cartoframes==1.1.1
 # Additional dependencies from examples
 matplotlib
 dask

cartoframes/_version.py

@@ -1 +1 @@
-__version__ = '1.1.0'
+__version__ = '1.1.1'

cartoframes/data/services/geocoding.py

@@ -174,7 +174,7 @@ def geocode(self, source, street,
             if not table_name:
                 raise ValueError('There is no "table_name" to cache the data')
             return self._cached_geocode(source, table_name, street, city=city, state=state, country=country,
-                                        dry_run=dry_run)
+                                        dry_run=dry_run, status=status)
 
         city, state, country = [
             geocoding_utils.column_or_value_arg(arg, self.columns) for arg in [city, state, country]
@@ -201,14 +201,15 @@ def geocode(self, source, street,
 
         return result
 
-    def _cached_geocode(self, source, table_name, street, city, state, country, dry_run):
+    def _cached_geocode(self, source, table_name, street, city, state, country, status, dry_run):
         """Geocode a dataframe caching results into a table.
         If the same dataframe if geocoded repeatedly no credits will be spent.
         But note there is a time overhead related to uploading the dataframe to a
         temporary table for checking for changes.
 
         """
         has_cache = has_table(table_name, self._credentials)
+        cache_columns = []
 
         if has_cache:
             cache_source_manager = SourceManager(table_name, self._credentials)
@@ -218,7 +219,7 @@ def _cached_geocode(self, source, table_name, street, city, state, country, dry_
 
         if geocoding_constants.HASH_COLUMN in self.columns or not has_cache:
             return self.geocode(
-                source, street=street, city=city, state=state,
+                source, street=street, city=city, state=state, status=status,
                 country=country, table_name=table_name, dry_run=dry_run, if_exists='replace')
 
         tmp_table_name = self._new_temporary_table_name()
@@ -227,22 +228,33 @@ def _cached_geocode(self, source, table_name, street, city, state, country, dry_
 
         to_carto(source, tmp_table_name, self._credentials, log_enabled=False)
 
-        self._execute_query(
-            """
-            ALTER TABLE {tmp_table} ADD COLUMN IF NOT EXISTS {hash} text
-            """.format(tmp_table=tmp_table_name, hash=geocoding_constants.HASH_COLUMN))
+        _, status_columns = geocoding_utils.status_assignment_columns(status)
+        add_columns = [c for c in status_columns if c[0] in cache_columns]
+        add_columns += [(geocoding_constants.HASH_COLUMN, 'text')]
+
+        log.debug("Adding columns %s if needed", ', '.join([c[0] for c in add_columns]))
+        alter_sql = "ALTER TABLE {tmp_table} {add_columns};".format(
+            tmp_table=tmp_table_name,
+            add_columns=','.join([
+                'ADD COLUMN IF NOT EXISTS {} {}'.format(name, type) for name, type in add_columns]))
+        self._execute_query(alter_sql)
 
         hcity, hstate, hcountry = [
             geocoding_utils.column_or_value_arg(arg, self.columns) for arg in [city, state, country]
         ]
 
         hash_expr = geocoding_utils.hash_expr(street, hcity, hstate, hcountry, table_prefix=tmp_table_name)
+        columns_to_update = [c[0] for c in add_columns]
+        columns_to_update.append('the_geom')
+        columns_expr = ','.join(["""{c} = {t}.{c} """.format(t=table_name, c=c) for c in columns_to_update])
         self._execute_query(
             """
-            UPDATE {tmp_table} SET {hash}={table}.{hash}, the_geom={table}.the_geom
+            UPDATE {tmp_table}
+            SET {columns_to_update}
             FROM {table} WHERE {hash_expr}={table}.{hash}
             """.format(
                 tmp_table=tmp_table_name,
+                columns_to_update=columns_expr,
                 table=table_name,
                 hash=geocoding_constants.HASH_COLUMN,
                 hash_expr=hash_expr
@@ -260,7 +272,7 @@ def _cached_geocode(self, source, table_name, street, city, state, country, dry_
         # TODO: refactor to share code with geocode() and call self._geocode() here instead
         # actually to keep hashing knowledge encapsulated (AFW) this should be handled by
         # _geocode using an additional parameter for an input table
-        gdf, metadata = self.geocode(table_name, street=street, city=city,
+        gdf, metadata = self.geocode(table_name, street=street, city=city, status=status,
                                      state=state, country=country, dry_run=dry_run)
         return self.result(data=gdf, metadata=metadata)
 

docs/RELEASING.md

@@ -75,6 +75,9 @@ Then, a docs branch must be created. This is used by the Developer Center, and i
 ```
 git checkout -b docs/vM.m.u
 git push origin docs/vM.m.u
+
+git checkout -b docs-vM.m.u
+git push origin docs-vM.m.u
 ```
 
 ## The developer center "party" (production)

docs/examples/use_cases/building_a_dashboard.ipynb → docs/examples/advanced_use_cases/building_a_dashboard.ipynb

@@ -12,7 +12,7 @@
     "\n",
     "In this notebook, we will build a dashboard combining different data from CARTO's Data Observatory to help identify the locations with specific characteristics described below.\n",
     "\n",
-    "**Note** this use case leverages premium datasets from [CARTO Data Observatory](https://carto.com/spatial-data-catalog/).\n",
+    "**Note:** This use case leverages premium datasets from [CARTO's Data Observatory](https://carto.com/spatial-data-catalog/).\n",
     "\n",
     "\n",
     "### Use case description\n",
@@ -140,7 +140,7 @@
    "source": [
     "We can get the pharmacies from [Pitney Bowes' Consumer Points of Interest](https://carto.com/spatial-data-catalog/browser/dataset/pb_consumer_po_62cddc04/) dataset. This is a premium dataset, so we first need to check that we are subscribed to it.\n",
     "\n",
-    "Take a look at <a href='#example-access-premium-data' target='_blank'>this template</a> for more details on how to access and download a premium dataset."
+    "Take a look at <a href='#example-access-premium-data-from-the-data-observatory' target='_blank'>this template</a> for more details on how to access and download a premium dataset."
    ]
   },
   {
@@ -10900,7 +10900,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.7.3"
   }
  },
  "nbformat": 4,

docs/examples/use_cases/combining_two_datasets.ipynb → docs/examples/advanced_use_cases/combining_two_datasets.ipynb

@@ -6,7 +6,7 @@
     "id": "IkfOIflwHsJN"
    },
    "source": [
-    "## Combining two datasets. Using geosocial media data to understand retail performance\n",
+    "## Combining geosocial and financial data to understand retail performance\n",
     "\n",
     "Geosocial data is location-based social media data that can be interpreted and analyzed as part of any location-oriented business decision. \n",
     "\n",
@@ -105,7 +105,7 @@
     "\n",
     "In this section, we'll download the two datasets we're interested in and combine them into a single dataframe.\n",
     "\n",
-    "For more information on how to access Data Observatory datasets using CARTOframes visit the [Guides](https://carto.com/developers/cartoframes/guides/) or take a look at the <a href='https://carto.com/developers/cartoframes/examples/#example-access-premium-data' target='_blank'>Access Premium Data</a> template."
+    "For more information on how to access Data Observatory datasets using CARTOframes visit the [Guides](https://carto.com/developers/cartoframes/guides/) or take a look at the <a href='https://carto.com/developers/cartoframes/examples/#example-access-premium-data-from-the-data-observatory' target='_blank'>Access Premium Data</a> template."
    ]
   },
   {