1 Microsoft« OLE DB Provider for Data Mining Services
8193 Microsoft Decision Trees
8194 The Microsoft Decision Trees algorithm chooses significant characteristics in the data and narrows sets of data based on those characteristics until clear correlations are established. Decision trees are useful when you want to make specific predictions based on information in the source data.
8195 Microsoft Clustering
8196 Clustering finds natural groupings of data in a multidimensional space. Clustering is useful when you want to see general groupings in your data.
8293 Identifies the algorithm used to control the growth of a decision tree. This algorithm selects the attributes that constitute the tree, the order in which the attributes are used, the way in which the attribute s values should be split up, and the point at which the tree should stop growing.
8294 Describes the various ways that SCORE_METHOD should consider splitting up an attribute s values. For example, if an attribute has 5 potential values, the values could be split into a binary partition (for example, 3 and 1,2,4,5), or the values could be split into 5 separate partitions, or some other combination may be considered.
8295 Controls the growth of the tree by preventing the creation of leaf nodes that contain fewer than MINIMUM_LEAF_CASES cases. For example, if SCORE_METHOD is considering a split on a node that contains 30 cases, and the value of MINIMUM_LEAF_CASES is 10, and one potential branch of the split receives 23 of the cases while the other branch receives 7 cases, then the split will not be allowed.
8296 A floating point number between 0 and 1 that acts as a penalty for growing a tree. The parameter is applied at each additional split. A value of 0 applies no penalty, and a value close but not equal to 1 (1.0 is outside the range) applies a high penalty. Applying a penalty will limit the depth and complexity of learned trees, which avoids overfitting. However, using too strong a penalty may adversely affect the predictive ability of the learned model.
8297 Identifies the algorithm used to group cases into clusters. Some algorithms are faster or better scaled to large data sets, but there may be some cost, such as quality.
8298 Controls the number of times the algorithm will try to cluster before selecting the best answer from the set of tries. Because clustering algorithms involve some randomness, different attempts at clustering may produce quite different results.
8299 How many clusters of similar cases the algorithm should attempt to find.
8300 Clustering algorithms repeatedly scan the data. With each iteration they get closer to an optimal solution. This parameter controls how little a solution should change between iterations in order to be considered complete (converged). The values are between 0 and 1.
8301 The minimum number of cases that can make up a cluster. If a cluster contains too few cases, it will be discarded, and it may be reassigned to a new location.
8302 The percentage of cases from the training query to consider while training.
8303 The percentage of training cases to hold out from training and use for scoring the model.
8304 The seed for the sampling random number generator.
8305 The seed for the holdout random number generator.
16485 Processing query
16486 Training column [%s]
16487 Training marginal model: %ld cases seen
16488 Training Clusters: candidate model %ld, iteration %ld
16489 Training Clusters: %ld cases scanned
16490 Culling feature set
16491 Training Trees (counting correlations): %ld cases counted
16492 Training Trees: %ld cases left to classify
16493 Training mining model
16494 Scoring model: [%ld] cases seen
24576 The element was not found
24577 End Of Data
24578 The prediction succeeded, but unknown values or attributes were encountered
24579 The following aggregated DM providers were successfully loaded in-process: %1
24580 Warning: The following aggregated DM providers currently loaded in-process are potentially unsafe: %1
24832 Unable to load the parsing tables
24833 Unknown parsing error
24834 Catastrophic parse failure
24835 The mining model '%1' already exists
24836 The data mining database already exists
24837 No query was provided
24838 Unknown algorithm
24839 Unknown command
24840 Query column [%1] cannot be converted to model type
24841 Analysis Services component error (has to be mapped)
24842 Unexpected end of statement
24843 Reference column '%1' does not exist within the current context
24844 The model '%1' does not exist
24845 invalid value in DMColumn member
24846 Case consumer initialization error
24847 A discrete operation was attempted on a continuous column
24848 Initial catalog was not specified, or it was invalid
24849 A column with the specified name already exists in the current context (%1 = column name)
24850 An operation that can be performed only during training occurred
24851 Integer conversion error on '%1'
24852 Real conversion error on '%1'
24853 The syntax requires a table column for '%1'
24854 The syntax requires a scalar column for '%1'
24855 Table column '%1' does not allow a distribution to be specified with it
24856 Table column '%1' does not allow a modeling qualifier to be specified with it
24857 Table column '%1' does not allow a content type (discrete, continuous, and so on) to be specified with it
24858 Table column '%1' does not allow a content qualifier (ordered, cyclical, and so on) to be specified with it
24859 Table column '%1' does not allow a column qualifier (key, support, and so on) to be specified with it
24860 Subselect from clause has an unexpected type (other than a colref or a histogram)
24861 The file '%1' is already opened
24862 The file '%1' does not exist
24863 Sharing violation on file '%1'
24864 General file error: %1
24865 The context of the $<column> reference is incorrect
24866 The column '%1' was expected to be a nested table
24888 Invalid selection list for a SELECT ... FROM <dmm>.CONTENT statement (only schema column references are supported)
24889 Invalid WHERE clause in SELECT ... FROM <dmm>.CONTENT statement
24890 Unable to parse XML string
24891 Invalid mining model flag '%1'
24892 The mining model flag '%1' is not valid for the current data mining algorithm
24893 The mining model flag '%1' is specified more than once
24894 The mining model flag '%1' has an invalid data type value
24896 The mining model is already trained and does not support incremental update. You must use DELETE * FROM <dmm> before you use INSERT
24897 A resource was not found
24898 The value of the 'Extended Properties' property is invalid
24899 The model is not trained
24900 Selections from model must be distinct
24901 The insertion and query columns do not match
24902 '%1' is not the current catalog
24903 Error setting LCID or CompareString flags during initialization
24904 Sample percentage must be between 1 and 100 inclusive
24905 Holdout percentage must be between 1 and 99 inclusive
24912 Training seed must be between 1 and %1 inclusive
24913 Invalid selection list for a SELECT ... FROM <dmm>.XML statement (only schema column references are supported)
24914 Invalid value for Mining EXecution Location property
24915 Cannot execute remotely - no server connection available. Check the Mining Execution Location property.
24916 Tree operator is invalid without restriction for NODE_UNIQUE_NAME column
24917 Mining model remains in an untrained state due to insufficient training data
24918 Only SELECT statements can be executed remotely on the Analysis Server (use DSO for model creation/maintenance). Check Mining Execution Location property.
24919 Could not find a local mining model named '%1' to execute this statement on (it cannot be executed on server mining models).
24921 Analysis Server does not allow use of the provider specified in OPENROWSET
25088 An empty prediction is obtained
25089 Table-returning expressions cannot be used in calculation expressions
25090 Invalid FROM clause
25091 The WHERE clause must contain a logical/relational operator
25092 Two SELECT expressions in a UNION statement must produce the same number of columns
25093 An attempt to predict a nonpredictable column was detected
25094 A table.column column reference cannot be used in a SELECT list, a FROM clause, or the WHERE clause of a SELECT statement with PREDICTION JOIN
25095 Only predictable columns, columns that are related to a predictable column, or columns inside a predictable table column can select from the mining model
25096 The first argument for Top*/Bottom* functions is invalid. The expression must return a table
25097 The second argument for Top*/Bottom* functions is invalid. It must be a column reference
25098 The third argument for Top*/Bottom* functions is invalid. It must be a nonnegative constant expression
25099 No function can be used in <SELECT DISTINCT FROM model>
25100 Invalid column reference in <SELECT DISTINCT FROM model>
25101 Prediction function '%1' cannot be used in the given FROM context
25102 Invalid argument for a prediction function, '%1'
25103 No cluster function can be used in the context
25104 Invalid flag is given in Predict()
25105 A Boolean operand is expected in an AND, OR, or NOT operator
25106 Invalid SELECT statement
25107 Invalid column reference
25108 Function '%1' is not supported
25109 Statistics on table prediction can be used only when there is at most one predictable column inside the table
25110 A Boolean expression cannot either be selected or used inside an arithmetic expression
25111 Range function '%1' cannot be used in the given FROM context
25112 Invalid argument for a range function, '%1'
25113 Function '%s' cannot be used in SELECT DISTINCT ... FROM model
25114 Invalid operator used
25115 Aggregate functions cannot be used together with nonaggregate functions or columns
25116 Aggregate functions can only be used in top-level SELECT list
25117 WHERE clause is not supported if an aggregate function is used
25344 Column [%1] is not a valid RELATE TO target in a nested table
25345 The column [%1] is in a RELATE TO relation and is of a nondiscrete type
25346 Invalid relation in the definition of column [%1]
25348 Different properties were specified in the same hierarchy
25349 Circular reference in the definition of column [%1]
25350 Discretization failed on column [%1]
25352 Table column [%1] is inside another table column, which is not supported
25602 Errors occurred during training
25604 Column [%1] cannot be distinctly selected
25605 Unrelated columns cannot be distinctly selected together
25606 There are too many distinct states in column [%1] for the selected algorithm
25607 Invalid ON mapping
25608 Read NULL value on nonnullable column [%1]
25609 Duplicate columns on INSERT INTO
25616 Not all key columns were specified for nested table [%1]
25617 Related clauses of appended tables do not match
25618 Incorrect row ordering or duplicate keys detected on SHAPE
25635 Input provider does not support restart functionality required to train mining models
25636 Input provider read error '%1'
25857 The column [%1] is declared to be both predictable and continuous, which is not supported
25858 The column [%1] is declared to be both key and continuous, which is not supported
25859 The column [%1] is declared to be both discrete and having normal (or lognormal) distribution, which is not supported
25860 Because the column [%1] is declared to be related to another column, a distribution cannot be specified
25862 There are no predictable columns declared but the model uses the Microsoft Decision Trees algorithm, which requires the existence of at least one predictable column
25863 The model flag '%1' has an invalid value
25864 The column [%1] is declared of having type text but is not discrete or key (this is a required condition)
25865 The aggregation type for the measure [%1] is not supported
25866 There are no key columns declared for the model
25867 There are no key columns declared for the nested table [%1]
25868 The column [%1] is declared to be in an OF relation with the key, which is not supported
25869 The column [%1] is in a RELATE TO relation and is of a nondiscrete type
25870 The column [%1] is declared to be in an OF relation but it has an invalid content type for this relation
25872 Because the virtual dimension '%1' was created using SQL Server 7.0 OLAP Services, it cannot be used in an OLAP mining model
25873 The column [%1] is declared as being key and having a modeling flag, which is not supported
25874 The column [%1] is declared to be both a predictable and a RELATED TO entity (property), which is not supported
25875 The model [%1] is a server mining model, being available for INSERT INTO statements only from DSO
25876 The model [%1] is a server mining model, being available for DELETE statements only from DSO
25877 The model [%1] is a server mining model, being available for DROP statements only from DSO
25878 The model [%1] is a server mining model, being available for RENAME statements only from DSO
25879 The hierarchy '%1' must use at least one level that is not an (All) level; otherwise it cannot be used in an OLAP mining model
26113 The PREDICTION JOIN entity '%1' was expected to be a singleton query
26114 The value '%1' is an invalid bucket count for the DISCRETIZED content type
26369 An unknown error was encountered in the prediction engine
26370 This operation cannot be performed during training.
26371 This model has already been trained.
26372 This model has not yet been trained.
26373 No input attributes were specified.
26374 The decision tree algorithm cannot build a tree for a continuous attribute
26375 Invalid cluster ID.
26376 Failure during loading of model XML
26377 The discrete attribute value is out of range (0..0x007FFFFFL)
26378 The continuous attribute value is out of range (-3.4E38..3.4E38)
26379 Mining model remains in an untrained state due to insufficient training data
26625 An unknown error was encountered in the Data Mining Provider Aggregator
26626 Errors occurred while initializing aggregatable DM providers - the following provider(s) will not aggregated: %1
26627 The specified DM provider (ProgID='%s') is not available
26628 Schema rowset from a provider does not comply with the OLE DB for DM specification
26630 Errors occurred while getting model lists from the following aggregatable DM providers: %1
26631 Errors occurred while getting supported services from the following aggregatable DM providers: %1
26632 Aggregatable DM provider '%1'does not support mandatory security interface for aggregation
26633 Errors occurred while initializing security interfaces on the following aggregatable DM providers (they will not be aggregated): %1
28991 Invalid XML in model '%1' around '%2'
29016 External provider '%1' failed with error '%2'
29443 Unknown token specified outside of training
29447 Invalid state '%2' on column [%1]
29696 Connection failed with error '%2' on provider '%1'
29697 Query failed with error '%2' on input provider '%1'
29715 Data read error on case %1 column [%2]
29716 Data read error on case %1 column [%2]
29717 Data conversion error on case %1 column [%2]
29718 Data read error on case %1 column [%2]
29719 Data overflow error on case %1 column [%2]
29720 Integrity violation error on case %1 column [%2]
29721 Permission denied case %1 column [%2]
29728 Schema violation error on case %1 column [%2]
29729 Sign mismatch error on case %1 column [%2]
29730 Data read error on case %1 column [%2]
29957 The columns [%1] and [%2] are logically duplicates, which is not supported
29967 The column [%1] is declared to be the reference of an OF relation for the column [%2], but it has an invalid content type for this relation
30211 Syntax error at line %1, offset %2, token '%3'
30212 The expression list of a select statement must contain aggregation functions, but the expression selected in position number %1 (under the name: %2) is not aggregated
30213 The expression list of a select statement must not contain aggregation functions, but the expression selected in position number %1 (under the name: %2) is aggregated
30725 Invalid XML in '%2' node getting properties for aggregated DM provider '%1'