Steps

1. Query data - map training and testing data OR split 1 set of nodes into training and testing by defining ratio for training
2. Run the confusion matrix procedure.

Confusion matrix of decision tree based on Information Gain (without tree visualization) using Neo4j nodes.

RETURN main.confmIG("targetAttribute","prune","max_depth")

This procedure retrieves the confusion matrix of the decision tree based on Information Gain from Neo4j nodes.

"prune": "True" if you want to prune the tree and "False" otherwise.

"max_depth": "depth level" when you want to prune and "0" otherwise. For example "3" for a depth level of 3.

Confusion matrix of decision tree based on Gini Index (without tree visualization) using Neo4j nodes.

RETURN main.confmGI("targetAttribute","prune","max_depth")

This procedure retrieves the confusion matrix of the decision tree based on Gini Index from Neo4j nodes.

"prune": "True" if you want to prune the tree and "False" otherwise.

"max_depth": "depth level" when you want to prune and "0" otherwise. For example "3" for a depth level of 3.

Confusion matrix of decision tree based on Information Gain (without tree visualization) using Neo4j nodes.

RETURN main.confmIG("targetAttribute","prune","max_depth")

This procedure retrieves the confusion matrix of the decision tree based on Information Gain from Neo4j nodes.

"prune": "True" if you want to prune the tree and "False" otherwise.

"max_depth": "depth level" when you want to prune and "0" otherwise. For example "3" for a depth level of 3.

Steps of creating Confusion matrix from CSV files

1. Run confusion matrix procedure - map two sets of CSV file paths for training and testing respectively

Confusion matrix of the decision tree based on Gain Ratio (without tree visualization) using CSV file.

RETURN main.confmGRcsv("trainPath","testPath","targetAttribute","prune","max_depth")

This procedure retrieves the confusion matrix of the decision tree based on Gain Ratio from CSV file paths.

"prune": "True" if you want to prune the tree and "False" otherwise.

"max_depth": "depth level" when you want to prune and "0" otherwise. For example "3" for a depth level of 3.

Confusion matrix of decision tree based on Gini Index (without tree visualization) using CSV file.

RETURN main.confmGIcsv("trainPath","testPath","targetAttribute","prune","max_depth")

This procedure retrieves the confusion matrix of the decision tree based on Gini Index from CSV file paths.

"prune": "True" if you want to prune the tree and "False" otherwise.

"max_depth": "depth level" when you want to prune and "0" otherwise. For example "3" for a depth level of 3.

Confusion matrix of decision tree based on Information Gain (without tree visualization) using CSV file.

RETURN main.confmIGcsv("trainPath","testPath","targetAttribute","prune","max_depth")

This procedure retrieves the confusion matrix of the decision tree based on Information Gain from CSV file paths.

"prune": "True" if you want to prune the tree and "False" otherwise.

"max_depth": "depth level" when you want to prune and "0" otherwise. For example "3" for a depth level of 3.