Update to SQLExecutor and Visualization Code Exporting

.github/workflows/python-app.yml

@@ -58,6 +58,7 @@ jobs:
       run: |
         python lux/data/upload_car_data.py
         python lux/data/upload_aug_test_data.py
+        python lux/data/upload_airbnb_nyc_data.py
     - name: Lint check with black
       run: |
         black --target-version py37 --line-length 105 --check .

examples/GeneralDatabase_Executor_Example.py.ipynb

@@ -0,0 +1,138 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "expected-facility",
+   "metadata": {},
+   "source": [
+    "This notebook is an example of how to use the General Database Executor in Lux. This execution backend allows users to switch what kind of queries are being used to query their database system. Here we show how to switch from using a SQL template for Postgresql to MySQL."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "helpful-liberty",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "97a93a0b783743fab041362d66d72125",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Button(description='Toggle Table/Lux', layout=Layout(bottom='6px', top='6px', width='200px'), style=ButtonStyl…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e216a8adf9584b6e8a3cc5374ae73209",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Output()"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import sys\n",
+    "sys.path.insert(1, 'C:\\\\Users\\\\thyne\\\\Documents\\\\GitHub\\\\lux')\n",
+    "\n",
+    "import lux\n",
+    "import psycopg2\n",
+    "import pandas as pd\n",
+    "from lux import LuxSQLTable\n",
+    "\n",
+    "connection = psycopg2.connect(\"host=localhost user=postgres password=lux dbname=postgres\")\n",
+    "lux.config.set_SQL_connection(connection)\n",
+    "lux.config.read_query_template(\"postgres_query_template.txt\")\n",
+    "lux.config.quoted_queries = True\n",
+    "\n",
+    "sql_tbl = LuxSQLTable(table_name='car')\n",
+    "sql_tbl.intent = [\"Cylinders\"]\n",
+    "sql_tbl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "searching-nancy",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a2c12d8447494178aa6c38fc0a4c59f6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Button(description='Toggle Table/Lux', layout=Layout(bottom='6px', top='6px', width='200px'), style=ButtonStyl…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "26b23f594155417e9fb7ff2b4695477c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Output()"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import sqlalchemy\n",
+    "import lux\n",
+    "from sqlalchemy.ext.declarative import declarative_base\n",
+    "\n",
+    "engine = sqlalchemy.create_engine('mysql+mysqlconnector://luxuser:lux@localhost:3306/sys',echo=False)\n",
+    "lux.config.set_SQL_connection(engine)\n",
+    "lux.config.read_query_template(\"mysql_query_template.txt\")\n",
+    "lux.config.quoted_queries = False\n",
+    "\n",
+    "sql_df = lux.LuxSQLTable(table_name='car')\n",
+    "\n",
+    "sql_df.intent = ['Cylinders']\n",
+    "sql_df"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/mysql_query_template.txt

@@ -0,0 +1,19 @@
+preview_query:SELECT * from {table_name} LIMIT {num_rows}
+length_query:SELECT COUNT(*) as length FROM {table_name} {where_clause}
+sample_query:SELECT * FROM {table_name} {where_clause} LIMIT {num_rows}
+scatter_query:SELECT {columns} FROM {table_name} {where_clause}
+colored_barchart_counts:SELECT {groupby_attr}, {color_attr}, COUNT({groupby_attr}) as count FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+colored_barchart_average:SELECT {groupby_attr}, {color_attr}, AVG({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+colored_barchart_sum:SELECT {groupby_attr}, {color_attr}, SUM({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+colored_barchart_max:SELECT {groupby_attr}, {color_attr}, MAX({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+barchart_counts:SELECT {groupby_attr}, COUNT({groupby_attr}) as count FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+barchart_average:SELECT {groupby_attr}, AVG({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+barchart_sum:SELECT {groupby_attr}, SUM({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+barchart_max:SELECT {groupby_attr}, MAX({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+histogram_counts:SELECT width_bucket, count(width_bucket) as count from (SELECT ({bucket_cases}) as width_bucket from {table_name} {where_clause}) as buckets GROUP BY width_bucket order by width_bucket
+heatmap_counts:SELECT width_bucket1, width_bucket2, count(*) as count FROM (SELECT ({bucket_cases1}) as width_bucket1, ({bucket_cases2}) as width_bucket2 FROM {table_name} {where_clause}) as labeled_data GROUP BY width_bucket1, width_bucket2
+table_attributes_query:SELECT COLUMN_NAME as column_name FROM INFORMATION_SCHEMA.COLUMNS where TABLE_NAME = '{table_name}'
+min_max_query:SELECT MIN({attribute}) as min, MAX({attribute}) as max FROM {table_name}
+cardinality_query:SELECT COUNT(Distinct({attribute})) as count FROM {table_name} WHERE {attribute} IS NOT NULL
+unique_query:SELECT Distinct({attribute}) FROM {table_name} WHERE {attribute} IS NOT NULL
+datatype_query:SELECT DATA_TYPE as data_type FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_NAME = '{table_name}' AND COLUMN_NAME = '{attribute}'

examples/postgres_query_template.txt

@@ -0,0 +1,19 @@
+preview_query:SELECT * from {table_name} LIMIT {num_rows}
+length_query:SELECT COUNT(1) as length FROM {table_name} {where_clause}
+sample_query:SELECT * FROM {table_name} {where_clause} ORDER BY random() LIMIT {num_rows}
+scatter_query:SELECT {columns} FROM {table_name} {where_clause}
+colored_barchart_counts:SELECT "{groupby_attr}", "{color_attr}", COUNT("{groupby_attr}") FROM {table_name} {where_clause} GROUP BY "{groupby_attr}", "{color_attr}"
+colored_barchart_average:SELECT "{groupby_attr}", "{color_attr}", AVG("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}", "{color_attr}"
+colored_barchart_sum:SELECT "{groupby_attr}", "{color_attr}", SUM("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}", "{color_attr}"
+colored_barchart_max:SELECT "{groupby_attr}", "{color_attr}", MAX("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}", "{color_attr}"
+barchart_counts:SELECT "{groupby_attr}", COUNT("{groupby_attr}") FROM {table_name} {where_clause} GROUP BY "{groupby_attr}"
+barchart_average:SELECT "{groupby_attr}", AVG("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}"
+barchart_sum:SELECT "{groupby_attr}", SUM("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}"
+barchart_max:SELECT "{groupby_attr}", MAX("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}"
+histogram_counts:SELECT width_bucket, COUNT(width_bucket) FROM (SELECT width_bucket(CAST ("{bin_attribute}" AS FLOAT), '{upper_edges}') FROM {table_name} {where_clause}) as Buckets GROUP BY width_bucket ORDER BY width_bucket
+heatmap_counts:SELECT width_bucket1, width_bucket2, count(*) FROM (SELECT width_bucket(CAST ("{x_attribute}" AS FLOAT), '{x_upper_edges_string}') as width_bucket1, width_bucket(CAST ("{y_attribute}" AS FLOAT), '{y_upper_edges_string}') as width_bucket2 FROM {table_name} {where_clause}) as foo GROUP BY width_bucket1, width_bucket2
+table_attributes_query:SELECT column_name FROM INFORMATION_SCHEMA.COLUMNS where TABLE_NAME = '{table_name}'
+min_max_query:SELECT MIN("{attribute}") as min, MAX("{attribute}") as max FROM {table_name}
+cardinality_query:SELECT Count(Distinct("{attribute}")) FROM {table_name} WHERE "{attribute}" IS NOT NULL
+unique_query:SELECT Distinct("{attribute}") FROM {table_name} WHERE "{attribute}" IS NOT NULL
+datatype_query:SELECT DATA_TYPE FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_NAME = '{table_name}' AND COLUMN_NAME = '{attribute}'

examples/query_template.txt

@@ -0,0 +1,23 @@
+##############################################################################
+#########################Example Query Template      #########################
+# Details on query function see: https://readthedocs...                     ##
+##############################################################################
+preview_query:
+length_query:
+sample_query:
+scatter_query:
+colored_barchart_counts:SELECT {groupby_attr}, {color_attr}, COUNT({groupby_attr}) as count FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+colored_barchart_average:SELECT {groupby_attr}, {color_attr}, AVG({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+colored_barchart_sum:SELECT {groupby_attr}, {color_attr}, SUM({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+colored_barchart_max:SELECT {groupby_attr}, {color_attr}, MAX({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+barchart_counts:SELECT {groupby_attr}, COUNT({groupby_attr}) as count FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+barchart_average:SELECT {groupby_attr}, AVG({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+barchart_sum:SELECT {groupby_attr}, SUM({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+barchart_max:SELECT {groupby_attr}, MAX({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+histogram_counts:SELECT width_bucket, count(width_bucket) as count from (SELECT ({bucket_cases}) as width_bucket from {table_name} {where_clause}) as buckets GROUP BY width_bucket order by width_bucket
+heatmap_counts:SELECT width_bucket1, width_bucket2, count(*) as count FROM (SELECT ({bucket_cases1}) as width_bucket1, ({bucket_cases2}) as width_bucket2 FROM {table_name} {where_clause}) as labeled_data GROUP BY width_bucket1, width_bucket2
+table_attributes_query:SELECT COLUMN_NAME as column_name FROM INFORMATION_SCHEMA.COLUMNS where TABLE_NAME = '{table_name}'
+min_max_query:SELECT MIN({attribute}) as min, MAX({attribute}) as max FROM {table_name}
+cardinality_query:SELECT COUNT(Distinct({attribute})) as count FROM {table_name} WHERE {attribute} IS NOT NULL
+unique_query:SELECT Distinct({attribute}) FROM {table_name} WHERE {attribute} IS NOT NULL
+datatype_query:SELECT DATA_TYPE as data_type FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_NAME = '{table_name}' AND COLUMN_NAME = '{attribute}'

lux/__init__.py

@@ -16,6 +16,8 @@
 from lux.vis.Clause import Clause
 from lux.core.frame import LuxDataFrame
 from lux.core.sqltable import LuxSQLTable
+from lux.core.joinedsqltable import JoinedSQLTable
+from lux.utils.tracing_utils import LuxTracer
 from ._version import __version__, version_info
 from lux._config import config
 from lux._config.config import warning_format

lux/_config/config.py

@@ -6,6 +6,9 @@
 from typing import Any, Callable, Dict, Iterable, List, Optional, Union
 import lux
 import warnings
+from lux.utils.tracing_utils import LuxTracer
+import os
+from lux._config.template import postgres_template, mysql_template
 
 RegisteredOption = namedtuple("RegisteredOption", "name action display_condition args")
 
@@ -32,13 +35,18 @@ def __init__(self):
         self._pandas_fallback = True
         self._interestingness_fallback = True
         self.heatmap_bin_size = 40
+        self.tracer_relevant_lines = []
+        self.tracer = LuxTracer()
+        self.query_templates = {}
+        self.handle_quotes = True
         #####################################
         #### Optimization Configurations ####
         #####################################
         self._sampling_start = 100000
         self._sampling_cap = 1000000
         self._sampling_flag = True
         self._heatmap_flag = True
+        self._heatmap_start = 5000
         self.lazy_maintain = True
         self.early_pruning = True
         self.early_pruning_sample_cap = 30000
@@ -377,11 +385,28 @@ def set_SQL_connection(self, connection):
         self.set_executor_type("SQL")
         self.SQLconnection = connection
 
+    def read_query_template(self, query_template):
+        from lux.executor.SQLExecutor import SQLExecutor
+
+        query_dict = {}
+        if type(query_template) is str:
+            for line in query_template.split("\n"):
+                (key, val) = line.split(":")
+                query_dict[key] = val.strip()
+        else:
+            with open(query_file) as f:
+                for line in f:
+                    (key, val) = line.split(":")
+                    query_dict[key] = val.strip()
+        self.query_templates = query_dict
+        self.executor = SQLExecutor()
+
     def set_executor_type(self, exe):
         if exe == "SQL":
             from lux.executor.SQLExecutor import SQLExecutor
 
             self.executor = SQLExecutor()
+            self.read_query_template(postgres_template)
         elif exe == "Pandas":
             from lux.executor.PandasExecutor import PandasExecutor
 

lux/_config/mysql_query_template.txt

@@ -0,0 +1,19 @@
+preview_query:SELECT * from {table_name} LIMIT {num_rows}
+length_query:SELECT COUNT(*) as length FROM {table_name} {where_clause}
+sample_query:SELECT * FROM {table_name} {where_clause} LIMIT {num_rows}
+scatter_query:SELECT {columns} FROM {table_name} {where_clause}
+colored_barchart_counts:SELECT {groupby_attr}, {color_attr}, COUNT({groupby_attr}) as count FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+colored_barchart_average:SELECT {groupby_attr}, {color_attr}, AVG({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+colored_barchart_sum:SELECT {groupby_attr}, {color_attr}, SUM({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+colored_barchart_max:SELECT {groupby_attr}, {color_attr}, MAX({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}, {color_attr}
+barchart_counts:SELECT {groupby_attr}, COUNT({groupby_attr}) as count FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+barchart_average:SELECT {groupby_attr}, AVG({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+barchart_sum:SELECT {groupby_attr}, SUM({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+barchart_max:SELECT {groupby_attr}, MAX({measure_attr}) as {measure_attr} FROM {table_name} {where_clause} GROUP BY {groupby_attr}
+histogram_counts:SELECT width_bucket, count(width_bucket) as count from (SELECT ({bucket_cases}) as width_bucket from {table_name} {where_clause}) as buckets GROUP BY width_bucket order by width_bucket
+heatmap_counts:SELECT width_bucket1, width_bucket2, count(*) as count FROM (SELECT ({bucket_cases1}) as width_bucket1, ({bucket_cases2}) as width_bucket2 FROM {table_name} {where_clause}) as labeled_data GROUP BY width_bucket1, width_bucket2
+table_attributes_query:SELECT COLUMN_NAME as column_name FROM INFORMATION_SCHEMA.COLUMNS where TABLE_NAME = '{table_name}'
+min_max_query:SELECT MIN({attribute}) as min, MAX({attribute}) as max FROM {table_name}
+cardinality_query:SELECT COUNT(Distinct({attribute})) as count FROM {table_name} WHERE {attribute} IS NOT NULL
+unique_query:SELECT Distinct({attribute}) FROM {table_name} WHERE {attribute} IS NOT NULL
+datatype_query:SELECT DATA_TYPE as data_type FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_NAME = '{table_name}' AND COLUMN_NAME = '{attribute}'

lux/_config/postgres_query_template.txt

@@ -0,0 +1,19 @@
+preview_query:SELECT * from {table_name} LIMIT {num_rows}
+length_query:SELECT COUNT(1) as length FROM {table_name} {where_clause}
+sample_query:SELECT * FROM {table_name} {where_clause} ORDER BY random() LIMIT {num_rows}
+scatter_query:SELECT {columns} FROM {table_name} {where_clause}
+colored_barchart_counts:SELECT "{groupby_attr}", "{color_attr}", COUNT("{groupby_attr}") FROM {table_name} {where_clause} GROUP BY "{groupby_attr}", "{color_attr}"
+colored_barchart_average:SELECT "{groupby_attr}", "{color_attr}", AVG("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}", "{color_attr}"
+colored_barchart_sum:SELECT "{groupby_attr}", "{color_attr}", SUM("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}", "{color_attr}"
+colored_barchart_max:SELECT "{groupby_attr}", "{color_attr}", MAX("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}", "{color_attr}"
+barchart_counts:SELECT "{groupby_attr}", COUNT("{groupby_attr}") FROM {table_name} {where_clause} GROUP BY "{groupby_attr}"
+barchart_average:SELECT "{groupby_attr}", AVG("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}"
+barchart_sum:SELECT "{groupby_attr}", SUM("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}"
+barchart_max:SELECT "{groupby_attr}", MAX("{measure_attr}") as "{measure_attr}" FROM {table_name} {where_clause} GROUP BY "{groupby_attr}"
+histogram_counts:SELECT width_bucket, COUNT(width_bucket) FROM (SELECT width_bucket(CAST ("{bin_attribute}" AS FLOAT), '{upper_edges}') FROM {table_name} {where_clause}) as Buckets GROUP BY width_bucket ORDER BY width_bucket
+heatmap_counts:SELECT width_bucket1, width_bucket2, count(*) FROM (SELECT width_bucket(CAST ("{x_attribute}" AS FLOAT), '{x_upper_edges_string}') as width_bucket1, width_bucket(CAST ("{y_attribute}" AS FLOAT), '{y_upper_edges_string}') as width_bucket2 FROM {table_name} {where_clause}) as foo GROUP BY width_bucket1, width_bucket2
+table_attributes_query:SELECT column_name FROM INFORMATION_SCHEMA.COLUMNS where TABLE_NAME = '{table_name}'
+min_max_query:SELECT MIN("{attribute}") as min, MAX("{attribute}") as max FROM {table_name}
+cardinality_query:SELECT Count(Distinct("{attribute}")) FROM {table_name} WHERE "{attribute}" IS NOT NULL
+unique_query:SELECT Distinct("{attribute}") FROM {table_name} WHERE "{attribute}" IS NOT NULL
+datatype_query:SELECT DATA_TYPE FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_NAME = '{table_name}' AND COLUMN_NAME = '{attribute}'