Exploratory Data Analysis

src.actions.eda.extract_full_eda_df(mseq_list, options, output_path_list, lseq_list=None)[source]

Creates and saves a list of full size image EDA dataframes from a list MaskSequences.

Parameters

  • mseq_list (List[MaskSequence]) – A list of MaskSequence objects

  • options (Dict) – the options of what should be included in the dataframe; the option name should be the key and the value should be either true or false

  • output_path_list (List[str]) – the list of output csv file paths

  • lseq_list (Optional[List[LeafSequence]]) – A list of LeafSequence objects; this is only required if the linked filename option is used

Return type

None

Returns

None

src.actions.eda.extract_tiles_eda_df(mseq_list, options, output_path_list, lseq_list=None)[source]

Creates and saves a list of tile image EDA dataframes from a list MaskSequences.

Parameters

  • mseq_list (List[MaskSequence]) – A list of MaskSequence objects

  • options (Dict) – the options of what should be included in the dataframe; the option name should be the key and the value should be either true or false

  • output_path_list (List[str]) – the list of output csv file paths

  • lseq_list (Optional[List[LeafSequence]]) – A list of LeafSequence objects; this is only required if the linked filename option is used

Return type

None

Returns

None

src.actions.eda.extract_full_databunch_df(lseq_list, mseq_list, output_path_list, embolism_only=False)[source]

Extracts a databunch dataframe of full size images. The first field is the leaf path and the second field is the mask name. This is useful for Fastai.

Parameters

  • lseq_list (List[LeafSequence]) – A list of LeafSequence objects

  • mseq_list (List[MaskSequence]) – A list of MaskSequence objects

  • output_path_list (List[str]) – the list of output csv file paths

  • embolism_only – whether only leaves with embolisms should be used

Return type

None

Returns

None

src.actions.eda.extract_tiles_databunch_df(lseq_list, mseq_list, output_path_list, tile_embolism_only=False, leaf_embolism_only=False)[source]

Extracts a databunch dataframe of full size images. The first field is the leaf path and the second field is the mask name. This is useful for Fastai.

Parameters

  • lseq_list (List[LeafSequence]) – A list of LeafSequence objects

  • mseq_list (List[MaskSequence]) – A list of MaskSequence objects

  • output_path_list (List[str]) – the list of output csv file paths

  • tile_embolism_only (bool) – whether only tiles with embolisms should be used

  • leaf_embolism_only (bool) – whether only leaves with embolisms should be used

Return type

None

Returns

None