def func(net): print('Calculating {}'.format(name)) nodes = pd.DataFrame(index=net.node_ids) flds = [target_variable] if target_variable else [] if target_value: flds += util.columns_in_filters( ["{} == {}".format(target_variable, target_value)]) if filters: flds += util.columns_in_filters(filters) flds.append('node_id') df = orca.get_table(agent).to_frame(flds) if target_value: df = util.apply_filter_query( df, ["{} == {}".format(target_variable, target_value)]) if filters: df = util.apply_filter_query(df, filters) net.set(df['node_id'], variable=df[target_variable] if target_variable else None) nodes[name] = net.aggregate(radius, type=agg_function, decay=decay) if log: nodes[name] = nodes[name].apply(eval('np.log1p')) return nodes[name]
def test_submodel_filters(m): """ Test that submodel filters generate the correct data subset. """ m.build_submodels() df = orca.get_table(m.defaults.choosers).to_frame() len1 = len( apply_filter_query(df.loc[df.group == 'A'], m.defaults.chooser_filters)) len2 = len(apply_filter_query(df, m.submodels['A'].chooser_filters)) assert len1 == len2
def get_data(tables, fallback_tables=None, filters=None, model_expression=None, extra_columns=None): """ Generate a ``pd.DataFrame`` for model estimation or simulation. Automatically loads tables from Orca, merges them, and removes columns not referenced in a model expression or data filter. Additional columns can be requested. If filters are provided, the output will include only rows that match the filter criteria. See ``urbansim_templates.utils.merge_tables()`` for a detailed description of how the merges are performed. Parameters ---------- tables : str or list of str Orca table(s) to draw data from. fallback_tables : str or list of str, optional Table(s) to use if first parameter evaluates to `None`. (This option will be removed shortly when estimation and simulation settings are separated.) filters : str or list of str, optional Filter(s) to apply to the merged data, using `pd.DataFrame.query()`. model_expression : str, optional Model expression that will be evaluated using the output data. Only used to drop non-relevant columns. PyLogit format is not yet supported. extra_columns : str or list of str, optional Columns to include, in addition to any in the model expression and filters. (If this and the model_expression are both None, all columns will be included.) Returns ------- pd.DataFrame """ if tables is None: tables = fallback_tables colnames = None # this will get all columns if (model_expression is not None) or (extra_columns is not None): colnames = list(set(columns_in_formula(model_expression) + \ columns_in_filters(filters) + to_list(extra_columns))) if not isinstance(tables, list): df = get_df(tables, colnames) else: df = merge_tables(tables, colnames) df = apply_filter_query(df, filters) return df
def _get_df(self, tables='unset', fallback_tables=None, filters='unset', model_expression=None): """ Generate a data table for estimation or prediction, relying on functionality from Orca and `urbansim.models.util`. This should be performed immediately before estimation or prediction so that it reflects the current data state. The output includes only the necessary columns: those mentioned in the model expression or filters, plus (it appears) the index of each merged table. Relevant row filters are also applied. TO DO - this method is a generalization of _get_data(), and should replace it, but does not currently support column filtering or PyLogit model expressions. Parameters ---------- tables : str or list of str, optional Name of table or tables. If not provided, `self.tables` will be used. fallback_tables : str or list of str, optional Table(s) to use if first argument evaluates to `None`. filters : str or list of str, optional Filter(s) to apply. If not provided, `self.filters` will be used. model_expression : NOT YET IMPLEMENTED Model expression, for determining which columns are needed. If not provided, `self.model_expression` will be used. TO DO - this needs to handle the large MNL case where there are two sets of data tables, so we can't use urbansim.models.util.columns_in_formula() Returns ------- DataFrame """ if tables == 'unset': tables = self.tables if tables is None: tables = fallback_tables if filters == 'unset': filters = self.filters if isinstance(tables, list): df = orca.merge_tables(target=tables[0], tables=tables) else: df = orca.get_table(tables).to_frame() df = util.apply_filter_query(df, filters) return df
def _get_data(self, task='fit'): """ DEPRECATED - this should be replaced by the more general utils.get_data() Generate a data table for estimation or prediction, relying on functionality from Orca and UrbanSim.models.util. This should be performed immediately before estimation or prediction so that it reflects the current data state. The output includes only the necessary columns: those mentioned in the model expression or filters, plus (it appears) the index of each merged table. Relevant filter queries are applied. Parameters ---------- task : 'fit' or 'predict' Returns ------- DataFrame """ # TO DO - verify input data if isinstance(self.model_expression, str): expr_cols = util.columns_in_formula(self.model_expression) if (task == 'fit'): tables = self.tables columns = expr_cols + util.columns_in_filters(self.filters) filters = self.filters elif (task == 'predict'): if self.out_tables is not None: tables = self.out_tables else: tables = self.tables columns = expr_cols + util.columns_in_filters(self.out_filters) if self.out_column is not None: columns += [self.out_column] filters = self.out_filters if isinstance(tables, list): df = orca.merge_tables(target=tables[0], tables=tables, columns=columns) else: df = orca.get_table(tables).to_frame(columns) df = util.apply_filter_query(df, filters) return df
def fit(self, mct=None): """ Fit the model; save and report results. This uses the ChoiceModels estimation engine (originally from UrbanSim MNL). The `fit()` method can be run as many times as desired. Results will not be saved with Orca or ModelManager until the `register()` method is run. After sampling alternatives for each chooser, the merged choice table is saved to the class object for diagnostic use (`mergedchoicetable` with type choicemodels.tools.MergedChoiceTable). Parameters ---------- mct : choicemodels.tools.MergedChoiceTable This parameter is a temporary backdoor allowing us to pass in a more complicated choice table than can be generated within the template, for example including sampling weights or interaction terms. Returns ------- None """ check_choicemodels_version() from choicemodels import MultinomialLogit from choicemodels.tools import MergedChoiceTable if (mct is not None): df_from_mct = mct.to_frame() idx_names = df_from_mct.index.names df_from_mct = df_from_mct.reset_index() df_from_mct = apply_filter_query( df_from_mct, self.chooser_filters).set_index(idx_names) mct = MergedChoiceTable.from_df(df_from_mct) else: observations = get_data(tables=self.choosers, filters=self.chooser_filters, model_expression=self.model_expression, extra_columns=self.choice_column) if (self.chooser_sample_size is not None): observations = observations.sample(self.chooser_sample_size) alternatives = get_data(tables=self.alternatives, filters=self.alt_filters, model_expression=self.model_expression) mct = MergedChoiceTable(observations=observations, alternatives=alternatives, chosen_alternatives=self.choice_column, sample_size=self.alt_sample_size) model = MultinomialLogit(data=mct, model_expression=self.model_expression) results = model.fit() self.name = self._generate_name() self.summary_table = str(results) print(self.summary_table) coefs = results.get_raw_results()['fit_parameters']['Coefficient'] self.fitted_parameters = coefs.tolist() self.model = results # Save merged choice table to the class object for diagnostics self.mergedchoicetable = mct
def apply_predict_filters(self, choosers): choosers = util.apply_filter_query( choosers, self.choosers_predict_filters) return choosers
def get_data(tables, fallback_tables=None, filters=None, model_expression=None, extra_columns=None): """ Generate a pd.DataFrame from one or more tables registered with Orca. Templates should call this function immediately before the data is needed, so that it's as up-to-date as possible. If filters are provided, the output will include only rows that match the filter criteria. Default behavior is for the output to inclue all columns. If a model_expression and/or extra_columns is provided, non-relevant columns will be dropped from the output. Relevant columns include any mentioned in the model expression, filters, or list of extras. Join keys will *not* be included in the final output even if the data is drawn from multiple tables, unless they appear in the model expression or filters as well. If a named column is not found in the source tables, it will just be skipped. This is to support use cases where data is assembled separately for choosers and alternatives and then merged together -- the model expression would include terms from both sets of tables. Duplicate column names are not recommended -- columns are expected to be unique within the set of tables they're being drawn from, with the exception of join keys. If column names are repeated, current behavior is to follow the Orca default and keep the left-most copy of the column. This may change later and should not be relied on. Parameters ---------- tables : str or list of str Orca table(s) to draw data from. fallback_tables : str or list of str, optional Table(s) to use if first parameter evaluates to `None`. (This option will be removed shortly when estimation and simulation settings are separated.) filters : str or list of str, optional Filter(s) to apply to the merged data, using `pd.DataFrame.query()`. model_expression : str, optional Model expression that will be evaluated using the output data. Only used to drop non-relevant columns. PyLogit format is not yet supported. extra_columns : str or list of str, optional Columns to include, in addition to any in the model expression and filters. (If this and the model_expression are both None, all columns will be included.) Returns ------- pd.DataFrame """ if tables is None: tables = fallback_tables tables = to_list(tables) colnames = None # this will get all columns from Orca utilities if (model_expression is not None) or (extra_columns is not None): colnames = set(columns_in_formula(model_expression) + \ columns_in_filters(filters) + to_list(extra_columns)) # skip cols not found in any of the source tables - have to check for this # explicitly because the orca utilities will raise an error if we request column # names that aren't there all_cols = [] for t in tables: dfw = orca.get_table(t) all_cols += list(dfw.index.names) + list(dfw.columns) colnames = [c for c in colnames if c in all_cols] if len(tables) == 1: df = orca.get_table(table_name=tables[0]).to_frame(columns=colnames) else: df = orca.merge_tables(target=tables[0], tables=tables, columns=colnames) if colnames is not None: if len(df.columns) > len(colnames): df = df[colnames] df = apply_filter_query(df, filters) return df
def _get_data(self, task='fit'): """ DEPRECATED - this should be replaced by the more general _get_df() Generate a data table for estimation or prediction, relying on functionality from Orca and UrbanSim.models.util. This should be performed immediately before estimation or prediction so that it reflects the current data state. The output includes only the necessary columns: those mentioned in the model expression or filters, plus (it appears) the index of each merged table. Relevant filter queries are applied. Parameters ---------- task : 'fit' or 'predict' Returns ------- DataFrame """ # TO DO - verify input data if isinstance(self.model_expression, str): expr_cols = util.columns_in_formula(self.model_expression) # This is for PyLogit model expressions elif isinstance(self.model_expression, OrderedDict): # TO DO - check that this works in Python 2.7 expr_cols = [t[0] for t in list(self.model_expression.items()) \ if t[0] is not 'intercept'] # TO DO - not very general, maybe we should just override the method # TO DO - and this only applies to the fit condition if self.choice_column is not None: expr_cols += [self.choice_column] if (task == 'fit'): tables = self.tables columns = expr_cols + util.columns_in_filters(self.filters) filters = self.filters elif (task == 'predict'): if self.out_tables is not None: tables = self.out_tables else: tables = self.tables columns = expr_cols + util.columns_in_filters(self.out_filters) if self.out_column is not None: columns += [self.out_column] filters = self.out_filters if isinstance(tables, list): df = orca.merge_tables(target=tables[0], tables=tables, columns=columns) else: df = orca.get_table(tables).to_frame(columns) df = util.apply_filter_query(df, filters) return df