SQL functions for naive Bayes. More...
Functions | |
| args_and_value_double | argmax_transition (args_and_value_double oldmax, integer newkey, float8 newvalue) |
| args_and_value_double | argmax_combine (args_and_value_double max1, args_and_value_double max2) |
| integer [] | argmax_final (args_and_value_double finalstate) |
| aggregate integer [] | argmax (integer key, float8 value) |
| void | create_nb_prepared_data_tables (varchar trainingSource, varchar trainingClassColumn, varchar trainingAttrColumn, integer numAttrs, varchar featureProbsDestName, varchar classPriorsDestName) |
| Precompute all class priors and feature probabilities. More... | |
| void | create_nb_prepared_data_tables (varchar trainingSource, varchar trainingClassColumn, varchar trainingAttrColumn, varchar numericAttrsColumnIndices, integer numAttrs, varchar featureProbsDestName, varchar numericFeatureStatsDestName, varchar classPriorsDestName) |
| void | create_nb_classify_view (varchar featureProbsSource, varchar classPriorsSource, varchar classifySource, varchar classifyKeyColumn, varchar classifyAttrColumn, integer numAttrs, varchar destName) |
Create a view with columns (key, nb_classification) More... | |
| void | create_nb_classify_view (varchar featureProbsSource, varchar classPriorsSource, varchar classifySource, varchar classifyKeyColumn, varchar classifyAttrColumn, integer numAttrs, varchar numericFeatureStatsSource, varchar destName) |
| void | create_nb_classify_view (varchar trainingSource, varchar trainingClassColumn, varchar trainingAttrColumn, varchar classifySource, varchar classifyKeyColumn, varchar classifyAttrColumn, integer numAttrs, varchar destName) |
| void | create_nb_classify_view (varchar trainingSource, varchar trainingClassColumn, varchar trainingAttrColumn, varchar numericAttrsColumnIndices, varchar classifySource, varchar classifyKeyColumn, varchar classifyAttrColumn, integer numAttrs, varchar destName) |
| void | create_nb_probs_view (varchar featureProbsSource, varchar classPriorsSource, varchar classifySource, varchar classifyKeyColumn, varchar classifyAttrColumn, integer numAttrs, varchar destName) |
Create view with columns (key, class, nb_prob) More... | |
| void | create_nb_probs_view (varchar featureProbsSource, varchar classPriorsSource, varchar classifySource, varchar classifyKeyColumn, varchar classifyAttrColumn, integer numAttrs, varchar numericFeatureStatsSource, varchar destName) |
| void | create_nb_probs_view (varchar trainingSource, varchar trainingClassColumn, varchar trainingAttrColumn, varchar classifySource, varchar classifyKeyColumn, varchar classifyAttrColumn, integer numAttrs, varchar destName) |
| void | create_nb_probs_view (varchar trainingSource, varchar trainingClassColumn, varchar trainingAttrColumn, varchar numericAttrsColumnIndices, varchar classifySource, varchar classifyKeyColumn, varchar classifyAttrColumn, integer numAttrs, varchar destName) |
| aggregate integer [] argmax | ( | integer | key, |
| float8 | value | ||
| ) |
| args_and_value_double argmax_combine | ( | args_and_value_double | max1, |
| args_and_value_double | max2 | ||
| ) |
| integer [] argmax_final | ( | args_and_value_double | finalstate | ) |
| args_and_value_double argmax_transition | ( | args_and_value_double | oldmax, |
| integer | newkey, | ||
| float8 | newvalue | ||
| ) |
| void create_nb_classify_view | ( | varchar | featureProbsSource, |
| varchar | classPriorsSource, | ||
| varchar | classifySource, | ||
| varchar | classifyKeyColumn, | ||
| varchar | classifyAttrColumn, | ||
| integer | numAttrs, | ||
| varchar | destName | ||
| ) |
The created relation will be
{TABLE|VIEW} destName (key, nb_classification)
where nb_classification is an array containing the most likely class(es) of the record in classifySource identified by key.
| featureProbsSource | Name of table with precomputed feature probabilities, as created with create_nb_prepared_data_tables() |
| classPriorsSource | Name of table with precomputed class priors, as created with create_nb_prepared_data_tables() |
| classifySource | Name of the relation that contains data to be classified |
| classifyKeyColumn | Name of column in classifySource that can serve as unique identifier (the key of the source relation) |
| classifyAttrColumn | Name of attributes-array column in classifySource |
| numAttrs | Number of attributes to use for classification |
| destName | Name of the view to create |
create_nb_classify_view can be called in an ad-hoc fashion. See Naive Bayes Classification for instructions.SELECT create_nb_classify_view( 'featureProbsName', 'classPriorsName', 'classifySource', 'classifyKeyColumn', 'classifyAttrColumn', numAttrs, 'destName' );
SELECT * FROM destName;
| void create_nb_classify_view | ( | varchar | featureProbsSource, |
| varchar | classPriorsSource, | ||
| varchar | classifySource, | ||
| varchar | classifyKeyColumn, | ||
| varchar | classifyAttrColumn, | ||
| integer | numAttrs, | ||
| varchar | numericFeatureStatsSource, | ||
| varchar | destName | ||
| ) |
| void create_nb_classify_view | ( | varchar | trainingSource, |
| varchar | trainingClassColumn, | ||
| varchar | trainingAttrColumn, | ||
| varchar | classifySource, | ||
| varchar | classifyKeyColumn, | ||
| varchar | classifyAttrColumn, | ||
| integer | numAttrs, | ||
| varchar | destName | ||
| ) |
| void create_nb_classify_view | ( | varchar | trainingSource, |
| varchar | trainingClassColumn, | ||
| varchar | trainingAttrColumn, | ||
| varchar | numericAttrsColumnIndices, | ||
| varchar | classifySource, | ||
| varchar | classifyKeyColumn, | ||
| varchar | classifyAttrColumn, | ||
| integer | numAttrs, | ||
| varchar | destName | ||
| ) |
| void create_nb_prepared_data_tables | ( | varchar | trainingSource, |
| varchar | trainingClassColumn, | ||
| varchar | trainingAttrColumn, | ||
| integer | numAttrs, | ||
| varchar | featureProbsDestName, | ||
| varchar | classPriorsDestName | ||
| ) |
Feature probabilities are stored in a table of format
TABLE featureProbsDestName (
class INTEGER,
attr INTEGER,
value INTEGER,
cnt INTEGER,
attr_cnt INTEGER
)Class priors are stored in a table of format
TABLE classPriorsDestName (
class INTEGER,
class_cnt INTEGER,
all_cnt INTEGER
)| trainingSource | Name of relation containing the training data |
| trainingClassColumn | Name of class column in training data |
| trainingAttrColumn | Name of attributes-array column in training data |
| numAttrs | Number of attributes to use for classification |
| featureProbsDestName | Name of feature-probabilities table to create |
| classPriorsDestName | Name of class-priors table to create |
SELECT create_nb_prepared_data_tables( 'trainingSource', 'trainingClassColumn', 'trainingAttrColumn', numAttrs, 'featureProbsName', 'classPriorsName' );
| void create_nb_prepared_data_tables | ( | varchar | trainingSource, |
| varchar | trainingClassColumn, | ||
| varchar | trainingAttrColumn, | ||
| varchar | numericAttrsColumnIndices, | ||
| integer | numAttrs, | ||
| varchar | featureProbsDestName, | ||
| varchar | numericFeatureStatsDestName, | ||
| varchar | classPriorsDestName | ||
| ) |
| void create_nb_probs_view | ( | varchar | featureProbsSource, |
| varchar | classPriorsSource, | ||
| varchar | classifySource, | ||
| varchar | classifyKeyColumn, | ||
| varchar | classifyAttrColumn, | ||
| integer | numAttrs, | ||
| varchar | destName | ||
| ) |
The created view will be of the following form:
VIEW destName (
key ANYTYPE,
class INTEGER,
nb_prob FLOAT8
)where nb_prob is the Naive-Bayes probability that class is the true class of the record in classifySource identified by key.
| featureProbsSource | Name of table with precomputed feature probabilities, as created with create_nb_prepared_data_tables() |
| classPriorsSource | Name of table with precomputed class priors, as created with create_nb_prepared_data_tables() |
| classifySource | Name of the relation that contains data to be classified |
| classifyKeyColumn | Name of column in classifySource that can serve as unique identifier (the key of the source relation) |
| classifyAttrColumn | Name of attributes-array column in classifySource |
| numAttrs | Number of attributes to use for classification |
| destName | Name of the view to create |
create_nb_probs_view can be called in an ad-hoc fashion. See Naive Bayes Classification for instructions.SELECT create_nb_probs_view( 'featureProbsName', 'classPriorsName', 'classifySource', 'classifyKeyColumn', 'classifyAttrColumn', numAttrs, 'destName' );
SELECT * FROM destName;
| void create_nb_probs_view | ( | varchar | featureProbsSource, |
| varchar | classPriorsSource, | ||
| varchar | classifySource, | ||
| varchar | classifyKeyColumn, | ||
| varchar | classifyAttrColumn, | ||
| integer | numAttrs, | ||
| varchar | numericFeatureStatsSource, | ||
| varchar | destName | ||
| ) |
| void create_nb_probs_view | ( | varchar | trainingSource, |
| varchar | trainingClassColumn, | ||
| varchar | trainingAttrColumn, | ||
| varchar | classifySource, | ||
| varchar | classifyKeyColumn, | ||
| varchar | classifyAttrColumn, | ||
| integer | numAttrs, | ||
| varchar | destName | ||
| ) |
| void create_nb_probs_view | ( | varchar | trainingSource, |
| varchar | trainingClassColumn, | ||
| varchar | trainingAttrColumn, | ||
| varchar | numericAttrsColumnIndices, | ||
| varchar | classifySource, | ||
| varchar | classifyKeyColumn, | ||
| varchar | classifyAttrColumn, | ||
| integer | numAttrs, | ||
| varchar | destName | ||
| ) |