diff --git a/.domino/compiled_metadata.json b/.domino/compiled_metadata.json index c0f947c..0396e19 100644 --- a/.domino/compiled_metadata.json +++ b/.domino/compiled_metadata.json @@ -1,98 +1,4 @@ { - "TrainRandomForestClassifierPiece": { - "name": "TrainRandomForestClassifierPiece", - "dependency": { - "dockerfile": null, - "requirements_file": "requirements_0.txt" - }, - "tags": [ - "modeling", - "machine_learning" - ], - "style": { - "node_label": "Train Random Forest Classifier Piece", - "node_type": "default", - "node_style": { - "backgroundColor": "#38b2be" - }, - "useIcon": true, - "icon_class_name": "carbon:machine-learning-model", - "iconStyle": { - "cursor": "pointer" - } - }, - "description": "Train a Random Forest Classifier model over the input data.", - "input_schema": { - "$defs": { - "Criterion": { - "enum": [ - "gini", - "entropy", - "log_loss" - ], - "title": "Criterion", - "type": "string" - } - }, - "properties": { - "train_data_path": { - "description": "The path to the train data to train the data.", - "from_upstream": "always", - "title": "Train Data Path", - "type": "string" - }, - "n_estimators": { - "default": 100, - "description": "The number of trees in the forest.", - "title": "Number of Estimators", - "type": "integer" - }, - "criterion": { - "allOf": [ - { - "$ref": "#/$defs/Criterion" - } - ], - "default": "gini", - "description": "The function to measure the quality of a split.", - "title": "Criterion" - }, - "max_depth": { - "anyOf": [ - { - "type": "integer" - }, - { - "type": "null" - } - ], - "default": null, - "description": "The maximum depth of the tree.", - "title": "Max Depth" - } - }, - "required": [ - "train_data_path" - ], - "title": "InputModel", - "type": "object" - }, - "output_schema": { - "properties": { - "random_forest_model_path": { - "title": "Random Forest Model Path", - "type": "string" - } - }, - "required": [ - "random_forest_model_path" - ], - "title": "OutputModel", - "type": "object" - }, - "secrets_schema": null, - "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/TrainRandomForestClassifierPiece" - }, "StandardScalerPiece": { "name": "StandardScalerPiece", "dependency": { @@ -159,8 +65,8 @@ "secrets_schema": null, "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/StandardScalerPiece" }, - "TSNEPiece": { - "name": "TSNEPiece", + "PCAInferencePiece": { + "name": "PCAInferencePiece", "dependency": { "dockerfile": null, "requirements_file": "requirements_0.txt" @@ -171,7 +77,7 @@ "reduction" ], "style": { - "node_label": "t-SNE Piece", + "node_label": "PCA Inference Piece", "node_type": "default", "node_style": { "backgroundColor": "#38b2be" @@ -182,21 +88,21 @@ "cursor": "pointer" } }, - "description": "Applies t-SNE to the data", + "description": "Use the trained PCA model to transform the data", "input_schema": { "properties": { + "model_path": { + "description": "The path to the PCA model.", + "from_upstream": "always", + "title": "Model Path", + "type": "string" + }, "data_path": { - "description": "The path to data to apply t-SNE.", + "description": "The path to the train data to apply PCA.", "from_upstream": "always", "title": "Data Path", "type": "string" }, - "n_components": { - "default": 2, - "description": "The number of dimensions t-SNE.", - "title": "Number of Dimensions", - "type": "integer" - }, "use_class_column": { "default": false, "description": "Whether to use the target column as class to plot.", @@ -205,6 +111,7 @@ } }, "required": [ + "model_path", "data_path" ], "title": "InputModel", @@ -212,9 +119,9 @@ }, "output_schema": { "properties": { - "tsne_data_path": { + "pca_data_path": { "default": null, - "title": "Tsne Data Path", + "title": "Pca Data Path", "type": "string" } }, @@ -222,10 +129,10 @@ "type": "object" }, "secrets_schema": null, - "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/TSNEPiece" + "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/PCAInferencePiece" }, - "PCAInferencePiece": { - "name": "PCAInferencePiece", + "PCATrainPiece": { + "name": "PCATrainPiece", "dependency": { "dockerfile": null, "requirements_file": "requirements_0.txt" @@ -236,7 +143,7 @@ "reduction" ], "style": { - "node_label": "PCA Inference Piece", + "node_label": "PCA Train Piece", "node_type": "default", "node_style": { "backgroundColor": "#38b2be" @@ -247,21 +154,21 @@ "cursor": "pointer" } }, - "description": "Use the trained PCA model to transform the data", + "description": "Applies PCA to the input data", "input_schema": { "properties": { - "model_path": { - "description": "The path to the PCA model.", - "from_upstream": "always", - "title": "Model Path", - "type": "string" - }, "data_path": { "description": "The path to the train data to apply PCA.", "from_upstream": "always", - "title": "Data Path", + "title": "Train Data Path", "type": "string" }, + "n_components": { + "default": 2, + "description": "The number of components for PCA.", + "title": "Number of Components", + "type": "integer" + }, "use_class_column": { "default": false, "description": "Whether to use the target column as class to plot.", @@ -270,7 +177,6 @@ } }, "required": [ - "model_path", "data_path" ], "title": "InputModel", @@ -279,90 +185,102 @@ "output_schema": { "properties": { "pca_data_path": { - "default": null, "title": "Pca Data Path", "type": "string" + }, + "pca_model_path": { + "title": "Pca Model Path", + "type": "string" } }, + "required": [ + "pca_data_path", + "pca_model_path" + ], "title": "OutputModel", "type": "object" }, "secrets_schema": null, - "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/PCAInferencePiece" + "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/PCATrainPiece" }, - "TrainTestSplitPiece": { - "name": "TrainTestSplitPiece", + "OpenCVFilterPiece": { + "name": "OpenCVFilterPiece", "dependency": { - "dockerfile": null, - "requirements_file": "requirements_0.txt" + "dockerfile": "Dockerfile_opencv", + "requirements_file": null }, "tags": [ - "preprocessing", - "datasets" + "image", + "processing", + "filter" ], "style": { - "node_label": "Split Data", + "node_label": "OpenCV Filter Piece", "node_type": "default", "node_style": { - "backgroundColor": "#b3cde8" + "backgroundColor": "#38b2be" }, "useIcon": true, - "icon_class_name": "icon-park-outline:split", + "icon_class_name": "material-symbols:image-outline", "iconStyle": { "cursor": "pointer" } }, - "description": "Split data into train and test sets", + "description": "Piece that uses OpenCV filter on an Image", "input_schema": { + "$defs": { + "FilterNaem": { + "enum": [ + "canny", + "binary" + ], + "title": "FilterNaem", + "type": "string" + } + }, "properties": { - "data_path": { - "description": "The path to the data to be split.", + "image_path": { + "description": "The path to the image to apply filter.", "from_upstream": "always", - "title": "Data Path", + "title": "Image Path", "type": "string" }, - "test_data_size": { - "default": 0.2, - "description": "The size (%) of the test data.", - "title": "Test Data Ratio", - "type": "number" - }, - "random_state": { - "default": 42, - "description": "The random state for the split.", - "title": "Random State", - "type": "integer" + "filter_name": { + "allOf": [ + { + "$ref": "#/$defs/FilterNaem" + } + ], + "default": "canny", + "description": "The name of the filter to apply.", + "title": "Filter Name" } }, "required": [ - "data_path" + "image_path" ], "title": "InputModel", "type": "object" }, "output_schema": { "properties": { - "train_data_path": { - "title": "Train Data Path", - "type": "string" - }, - "test_data_path": { - "title": "Test Data Path", + "image_path": { + "description": "The path to the image with the filter applied.", + "title": "Output image Path", "type": "string" } }, "required": [ - "train_data_path", - "test_data_path" + "image_path" ], "title": "OutputModel", "type": "object" }, "secrets_schema": null, - "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/TrainTestSplitPiece" + "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/OpenCVFilterPiece" }, - "PCATrainPiece": { - "name": "PCATrainPiece", + "UMAPPiece": { + "name": "UMAPPiece", "dependency": { "dockerfile": null, "requirements_file": "requirements_0.txt" @@ -373,7 +291,7 @@ "reduction" ], "style": { - "node_label": "PCA Train Piece", + "node_label": "UMAP Piece", "node_type": "default", "node_style": { "backgroundColor": "#38b2be" @@ -384,19 +302,29 @@ "cursor": "pointer" } }, - "description": "Applies PCA to the input data", + "description": "Applies t-SNE to the data", + "container_resources": { + "requests": { + "cpu": 1000, + "memory": 1024 + }, + "limits": { + "cpu": 1000, + "memory": 1024 + } + }, "input_schema": { "properties": { "data_path": { - "description": "The path to the train data to apply PCA.", + "description": "The path to the data to apply UMAP.", "from_upstream": "always", - "title": "Train Data Path", + "title": "Data Path", "type": "string" }, "n_components": { "default": 2, - "description": "The number of components for PCA.", - "title": "Number of Components", + "description": "The number of dimensions for UMAP.", + "title": "Number of Dimensions", "type": "integer" }, "use_class_column": { @@ -414,235 +342,307 @@ }, "output_schema": { "properties": { - "pca_data_path": { - "title": "Pca Data Path", - "type": "string" - }, - "pca_model_path": { - "title": "Pca Model Path", + "umap_data_path": { + "default": null, + "title": "Umap Data Path", "type": "string" } }, - "required": [ - "pca_data_path", - "pca_model_path" - ], "title": "OutputModel", "type": "object" }, "secrets_schema": null, - "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/PCATrainPiece" + "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/UMAPPiece" }, - "UMAPPiece": { - "name": "UMAPPiece", + "InferenceModelPiece": { + "name": "InferenceModelPiece", "dependency": { "dockerfile": null, "requirements_file": "requirements_0.txt" }, "tags": [ - "preprocessing", - "dimensionality", - "reduction" + "modeling", + "machine_learning" ], "style": { - "node_label": "UMAP Piece", + "node_label": "Inference Model Piece", "node_type": "default", "node_style": { "backgroundColor": "#38b2be" }, "useIcon": true, - "icon_class_name": "radix-icons:dimensions", + "icon_class_name": "carbon:machine-learning-model", "iconStyle": { "cursor": "pointer" } }, - "description": "Applies t-SNE to the data", - "container_resources": { - "requests": { - "cpu": 1000, - "memory": 1024 - }, - "limits": { - "cpu": 1000, - "memory": 1024 - } - }, + "description": "Load a trained model and use it to make predictions on new data.", "input_schema": { "properties": { "data_path": { - "description": "The path to the data to apply UMAP.", + "description": "Data path to inference on.", "from_upstream": "always", - "title": "Data Path", + "title": "Data path", "type": "string" }, - "n_components": { - "default": 2, - "description": "The number of dimensions for UMAP.", - "title": "Number of Dimensions", - "type": "integer" - }, - "use_class_column": { - "default": false, - "description": "Whether to use the target column as class to plot.", - "title": "Use Class Column", - "type": "boolean" + "model_path": { + "description": "Path to the model to use for inference.", + "from_upstream": "always", + "title": "Model path", + "type": "string" } }, "required": [ - "data_path" + "data_path", + "model_path" ], "title": "InputModel", "type": "object" }, "output_schema": { "properties": { - "umap_data_path": { - "default": null, - "title": "Umap Data Path", + "data_path": { + "title": "Data Path", "type": "string" } }, + "required": [ + "data_path" + ], "title": "OutputModel", "type": "object" }, "secrets_schema": null, - "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/UMAPPiece" + "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/InferenceModelPiece" }, - "OpenCVFilterPiece": { - "name": "OpenCVFilterPiece", + "TrainRandomForestClassifierPiece": { + "name": "TrainRandomForestClassifierPiece", "dependency": { - "dockerfile": "Dockerfile_opencv", - "requirements_file": null + "dockerfile": null, + "requirements_file": "requirements_0.txt" }, "tags": [ - "image", - "processing", - "filter" + "modeling", + "machine_learning" ], "style": { - "node_label": "OpenCV Filter Piece", + "node_label": "Train Random Forest Classifier Piece", "node_type": "default", "node_style": { "backgroundColor": "#38b2be" }, "useIcon": true, - "icon_class_name": "material-symbols:image-outline", + "icon_class_name": "carbon:machine-learning-model", "iconStyle": { "cursor": "pointer" } }, - "description": "Piece that uses OpenCV filter on an Image", + "description": "Train a Random Forest Classifier model over the input data.", "input_schema": { "$defs": { - "FilterNaem": { + "Criterion": { "enum": [ - "canny", - "binary" + "gini", + "entropy", + "log_loss" ], - "title": "FilterNaem", + "title": "Criterion", "type": "string" } }, "properties": { - "image_path": { - "description": "The path to the image to apply filter.", + "train_data_path": { + "description": "The path to the train data to train the data.", "from_upstream": "always", - "title": "Image Path", + "title": "Train Data Path", "type": "string" }, - "filter_name": { + "n_estimators": { + "default": 100, + "description": "The number of trees in the forest.", + "title": "Number of Estimators", + "type": "integer" + }, + "criterion": { "allOf": [ { - "$ref": "#/$defs/FilterNaem" + "$ref": "#/$defs/Criterion" } ], - "default": "canny", - "description": "The name of the filter to apply.", - "title": "Filter Name" + "default": "gini", + "description": "The function to measure the quality of a split.", + "title": "Criterion" + }, + "max_depth": { + "anyOf": [ + { + "type": "integer" + }, + { + "type": "null" + } + ], + "default": null, + "description": "The maximum depth of the tree.", + "title": "Max Depth" } }, "required": [ - "image_path" + "train_data_path" ], "title": "InputModel", "type": "object" }, "output_schema": { "properties": { - "image_path": { - "description": "The path to the image with the filter applied.", - "title": "Output image Path", + "random_forest_model_path": { + "title": "Random Forest Model Path", "type": "string" } }, "required": [ - "image_path" + "random_forest_model_path" ], "title": "OutputModel", "type": "object" }, "secrets_schema": null, - "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/OpenCVFilterPiece" + "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/TrainRandomForestClassifierPiece" }, - "InferenceModelPiece": { - "name": "InferenceModelPiece", + "TrainTestSplitPiece": { + "name": "TrainTestSplitPiece", "dependency": { "dockerfile": null, "requirements_file": "requirements_0.txt" }, "tags": [ - "modeling", - "machine_learning" + "preprocessing", + "datasets" ], "style": { - "node_label": "Inference Model Piece", + "node_label": "Split Data", "node_type": "default", "node_style": { - "backgroundColor": "#38b2be" + "backgroundColor": "#b3cde8" }, "useIcon": true, - "icon_class_name": "carbon:machine-learning-model", + "icon_class_name": "icon-park-outline:split", "iconStyle": { "cursor": "pointer" } }, - "description": "Load a trained model and use it to make predictions on new data.", + "description": "Split data into train and test sets", "input_schema": { "properties": { "data_path": { - "description": "Data path to inference on.", + "description": "The path to the data to be split.", "from_upstream": "always", - "title": "Data path", + "title": "Data Path", "type": "string" }, - "model_path": { - "description": "Path to the model to use for inference.", - "from_upstream": "always", - "title": "Model path", - "type": "string" + "test_data_size": { + "default": 0.2, + "description": "The size (%) of the test data.", + "title": "Test Data Ratio", + "type": "number" + }, + "random_state": { + "default": 42, + "description": "The random state for the split.", + "title": "Random State", + "type": "integer" } }, "required": [ - "data_path", - "model_path" + "data_path" ], "title": "InputModel", "type": "object" }, "output_schema": { + "properties": { + "train_data_path": { + "title": "Train Data Path", + "type": "string" + }, + "test_data_path": { + "title": "Test Data Path", + "type": "string" + } + }, + "required": [ + "train_data_path", + "test_data_path" + ], + "title": "OutputModel", + "type": "object" + }, + "secrets_schema": null, + "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/TrainTestSplitPiece" + }, + "TSNEPiece": { + "name": "TSNEPiece", + "dependency": { + "dockerfile": null, + "requirements_file": "requirements_0.txt" + }, + "tags": [ + "preprocessing", + "dimensionality", + "reduction" + ], + "style": { + "node_label": "t-SNE Piece", + "node_type": "default", + "node_style": { + "backgroundColor": "#38b2be" + }, + "useIcon": true, + "icon_class_name": "radix-icons:dimensions", + "iconStyle": { + "cursor": "pointer" + } + }, + "description": "Applies t-SNE to the data", + "input_schema": { "properties": { "data_path": { + "description": "The path to data to apply t-SNE.", + "from_upstream": "always", "title": "Data Path", "type": "string" + }, + "n_components": { + "default": 2, + "description": "The number of dimensions t-SNE.", + "title": "Number of Dimensions", + "type": "integer" + }, + "use_class_column": { + "default": false, + "description": "Whether to use the target column as class to plot.", + "title": "Use Class Column", + "type": "boolean" } }, "required": [ "data_path" ], + "title": "InputModel", + "type": "object" + }, + "output_schema": { + "properties": { + "tsne_data_path": { + "default": null, + "title": "Tsne Data Path", + "type": "string" + } + }, "title": "OutputModel", "type": "object" }, "secrets_schema": null, - "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/InferenceModelPiece" + "source_url": "https://github.com/Tauffer-Consulting/ml_domino_pieces/tree/main/pieces/TSNEPiece" } } \ No newline at end of file diff --git a/.domino/dependencies_map.json b/.domino/dependencies_map.json index 15e7a78..ac85ca0 100644 --- a/.domino/dependencies_map.json +++ b/.domino/dependencies_map.json @@ -5,17 +5,17 @@ "requirements_file": "requirements_0.txt" }, "pieces": [ - "TrainRandomForestClassifierPiece", "StandardScalerPiece", - "TSNEPiece", "PCAInferencePiece", - "TrainTestSplitPiece", "PCATrainPiece", "UMAPPiece", - "InferenceModelPiece" + "InferenceModelPiece", + "TrainRandomForestClassifierPiece", + "TrainTestSplitPiece", + "TSNEPiece" ], "secrets": [], - "source_image": "ghcr.io/tauffer-consulting/ml-domino-pieces:0.2.1-group0" + "source_image": "ghcr.io/tauffer-consulting/ml-domino-pieces:0.2.2-group0" }, "group1": { "dependency": { @@ -26,6 +26,6 @@ "OpenCVFilterPiece" ], "secrets": [], - "source_image": "ghcr.io/tauffer-consulting/ml-domino-pieces:0.2.1-group1" + "source_image": "ghcr.io/tauffer-consulting/ml-domino-pieces:0.2.2-group1" } } \ No newline at end of file