def table_definition(table_name):
"""
Get the source of a table function.
If a table is registered DataFrame and not a function then all that is
returned is {'type': 'dataframe'}.
If the table is a registered function then the JSON returned has keys
"type", "filename", "lineno", "text", and "html". "text" is the raw
text of the function, "html" has been marked up by Pygments.
"""
if orca.table_type(table_name) == 'dataframe':
return jsonify(type='dataframe')
filename, lineno, source = \
orca.get_raw_table(table_name).func_source_data()
html = highlight(source, PythonLexer(), HtmlFormatter())
return jsonify(type='function',
filename=filename,
lineno=lineno,
text=source,
html=html)
def drop_table(table_name):
if orca.is_table(table_name):
logger.debug("drop_table dropping orca table '%s'" % table_name)
# don't trigger function call of TableFuncWrapper
t = orca.get_raw_table(table_name)
t.clear_cached()
for column_name in orca.list_columns_for_table(table_name):
# logger.debug("pop %s.%s: %s" % (table_name, column_name, t.column_type(column_name)))
orca.orca._COLUMNS.pop((table_name, column_name), None)
# remove from orca's table list
orca.orca._TABLES.pop(table_name, None)
if table_name in _PIPELINE.replaced_tables:
logger.debug("drop_table forgetting replaced_tables '%s'" % table_name)
del _PIPELINE.replaced_tables[table_name]
if table_name in _PIPELINE.last_checkpoint:
logger.debug("drop_table removing table %s from last_checkpoint" % table_name)
_PIPELINE.last_checkpoint[table_name] = ''
def rewrap(table_name, df=None):
"""
Add or replace an orca registered table as a unitary DataFrame-backed DataFrameWrapper table
if df is None, then get the dataframe from orca (table_name should be registered, or
an error will be thrown) which may involve evaluating added columns, etc.
If the orca table already exists, deregister it along with any associated columns before
re-registering it.
The net result is that the dataframe is a registered orca DataFrameWrapper table with no
computed or added columns.
Parameters
----------
table_name
df
Returns
-------
the underlying df of the rewrapped table
"""
logger.debug("rewrap table %s inplace=%s" % (table_name, (df is None)))
if orca.is_table(table_name):
if df is None:
logger.debug("rewrap - orca.get_table(%s)" % (table_name, ))
t = orca.get_table(table_name)
df = t.to_frame()
else:
logger.debug("rewrap - orca.get_raw_table(%s)" % (table_name, ))
# don't trigger function call of TableFuncWrapper
t = orca.get_raw_table(table_name)
t.clear_cached()
for column_name in orca.list_columns_for_table(table_name):
# logger.debug("pop %s.%s: %s" % (table_name, column_name, t.column_type(column_name)))
orca.orca._COLUMNS.pop((table_name, column_name), None)
# remove from orca's table list
orca.orca._TABLES.pop(table_name, None)
assert df is not None
logger.debug("rewrap - orca.add_table(%s)" % (table_name, ))
orca.add_table(table_name, df)
return df
def table_definition(table_name):
"""
Get the source of a table function.
If a table is registered DataFrame and not a function then all that is
returned is {'type': 'dataframe'}.
If the table is a registered function then the JSON returned has keys
"type", "filename", "lineno", "text", and "html". "text" is the raw
text of the function, "html" has been marked up by Pygments.
"""
if orca.table_type(table_name) == "dataframe":
return jsonify(type="dataframe")
filename, lineno, source = orca.get_raw_table(table_name).func_source_data()
html = highlight(source, PythonLexer(), HtmlFormatter())
return jsonify(type="function", filename=filename, lineno=lineno, text=source, html=html)
def assert_table_can_be_generated(table_name):
"""
Does a registered table exist as a DataFrame? If a table was registered as a function
wrapper, this assertion evaluates the function and fails is there are any errors.
In other UrbanSim code, it seem like the accepted way of triggering a table to be
evaluated is to run .to_frame() on it. I'm using ._call_func() instead, because I
don't need the output and this saves the overhead of copying the DataFrame. Either of
those methods will be aware of caching, and not regenerate the table if it already
exists. There no way to tell externally whether a table is cached or not. That might
be a useful thing to add to the orca API.
"""
assert_table_is_registered(table_name)
if (orca.table_type(table_name) == 'function'):
try:
_ = orca.get_raw_table(table_name)._call_func()
except:
msg = "Table '%s' is registered but cannot be generated" % table_name
raise OrcaAssertionError(msg)
return
def household_income_category(persons):
# calling households_for_estimation.income_category returns an non-indexed
# array, so converting to df for now.
df = orca.get_raw_table('households').to_frame()
return misc.reindex(df.income_category, persons.household_id)