Revert "Update LuxSQLTable __len__() and metadata computation"

This reverts commit 7c7dcd3.

lux/action/correlation.py

@@ -62,7 +62,7 @@ def correlation(ldf: LuxDataFrame, ignore_transpose: bool = True):
     }
     ignore_rec_flag = False
     # Doesn't make sense to compute correlation if less than 4 data values
-    if len(ldf) < 5:
+    if ldf._length < 5:
         ignore_rec_flag = True
     # Then use the data populated in the vis list to compute score
     for vis in vlist:

lux/action/univariate.py

@@ -59,7 +59,7 @@ def univariate(ldf, *args):
             "long_description": f"Distribution displays univariate histogram distributions of all quantitative attributes{examples}. Visualizations are ranked from most to least skewed.",
         }
         # Doesn't make sense to generate a histogram if there is less than 5 datapoints (pre-aggregated)
-        if len(ldf) < 5:
+        if ldf._length < 5:
             ignore_rec_flag = True
     elif data_type_constraint == "nominal":
         possible_attributes = [
@@ -98,7 +98,7 @@ def univariate(ldf, *args):
             "long_description": "Temporal displays line charts for all attributes related to datetimes in the dataframe.",
         }
         # Doesn't make sense to generate a line chart if there is less than 3 datapoints (pre-aggregated)
-        if len(ldf) < 3:
+        if ldf._length < 3:
             ignore_rec_flag = True
     if ignore_rec_flag:
         recommendation["collection"] = []

lux/core/frame.py

@@ -82,6 +82,7 @@ def __init__(self, *args, **kw):
         self._toggle_pandas_display = True
         self._message = Message()
         self._pandas_only = False
+        self._length = len(self)
         # Metadata
         self._data_type = {}
         self.unique_values = None

lux/core/sqltable.py

@@ -55,8 +55,6 @@ class LuxSQLTable(lux.LuxDataFrame):
         "_pandas_only",
         "pre_aggregated",
         "_type_override",
-        "_length",
-        "_setup_done",
     ]
 
     def __init__(self, *args, table_name="", **kw):
@@ -66,16 +64,12 @@ def __init__(self, *args, table_name="", **kw):
         lux.config.executor = SQLExecutor()
 
         self._length = 0
-        self._setup_done = False
         if table_name != "":
             self.set_SQL_table(table_name)
         warnings.formatwarning = lux.warning_format
 
-    def __len__(self):
-        if self._setup_done:
-            return self._length
-        else:
-            return super(LuxSQLTable, self).__len__()
+    def len(self):
+        return self._length
 
     def set_SQL_table(self, t_name):
         # function that ties the Lux Dataframe to a SQL database table
@@ -132,7 +126,7 @@ def _ipython_display_(self):
                 layout=widgets.Layout(width="200px", top="6px", bottom="6px"),
             )
             self.output = widgets.Output()
-            self._sampled = lux.config.executor.execute_preview(self)
+            lux.config.executor.execute_preview(self)
             display(button, self.output)
 
             def on_button_clicked(b):

lux/executor/SQLExecutor.py

@@ -25,11 +25,10 @@ def __repr__(self):
         return f"<SQLExecutor>"
 
     @staticmethod
-    def execute_preview(tbl: LuxSQLTable, preview_size=5):
-        output = pandas.read_sql(
-            "SELECT * from {} LIMIT {}".format(tbl.table_name, preview_size), lux.config.SQLconnection
+    def execute_preview(tbl: LuxSQLTable):
+        tbl._sampled = pandas.read_sql(
+            "SELECT * from {} LIMIT 5".format(tbl.table_name), lux.config.SQLconnection
         )
-        return output
 
     @staticmethod
     def execute_sampling(tbl: LuxSQLTable):
@@ -612,8 +611,9 @@ def compute_dataset_metadata(self, tbl: LuxSQLTable):
         -------
         None
         """
-        if not tbl._setup_done:
-            self.get_SQL_attributes(tbl)
+        self.get_SQL_attributes(tbl)
+        for attr in list(tbl.columns):
+            tbl[attr] = None
         tbl._data_type = {}
         #####NOTE: since we aren't expecting users to do much data processing with the SQL database, should we just keep this
         #####      in the initialization and do it just once
@@ -644,7 +644,6 @@ def get_SQL_attributes(self, tbl: LuxSQLTable):
         attributes = list(pandas.read_sql(attr_query, lux.config.SQLconnection)["column_name"])
         for attr in attributes:
             tbl[attr] = None
-        tbl._setup_done = True
 
     def compute_stats(self, tbl: LuxSQLTable):
         """

lux/interestingness/interestingness.py

@@ -235,7 +235,7 @@ def deviation_from_overall(
         from lux.executor.SQLExecutor import SQLExecutor
 
         v_filter_size = SQLExecutor.get_filtered_size(filter_specs, ldf)
-        v_size = len(ldf)
+        v_size = ldf.len()
         vdata = vis.data
     v_filter = vdata[msr_attribute]
     total = v_filter.sum()

lux/utils/utils.py

@@ -13,7 +13,6 @@
 #  limitations under the License.
 import pandas as pd
 import matplotlib.pyplot as plt
-import lux
 
 
 def convert_to_list(x):
@@ -84,12 +83,7 @@ def check_if_id_like(df, attribute):
     if is_string:
         # For string IDs, usually serial numbers or codes with alphanumerics have a consistent length (eg., CG-39405) with little deviation. For a high cardinality string field but not ID field (like Name or Brand), there is less uniformity across the string lengths.
         if len(df) > 50:
-            if lux.config.executor.name == "PandasExecutor":
-                sampled = df[attribute].sample(50, random_state=99)
-            else:
-                from lux.executor.SQLExecutor import SQLExecutor
-
-                sampled = SQLExecutor.execute_preview(df, preview_size=50)
+            sampled = df[attribute].sample(50, random_state=99)
         else:
             sampled = df[attribute]
         str_length_uniformity = sampled.apply(lambda x: type(x) == str and len(x)).std() < 3