mlbend-datasets Releases (6): 0.1.6.0 0xf3d145d639153c61b826e4f60d3c0dcd indexed https://jend.leeeet.dev/files.txt?path=mlbend-datasets@0.1.6.0 0.1.5.0 0x508fc33b44130576819939e645eba7da unindexed https://jend.leeeet.dev/files.txt?path=mlbend-datasets@0.1.5.0 0.1.4.0 0x805aa9d73de5385dd9f66c3249152265 unindexed https://jend.leeeet.dev/files.txt?path=mlbend-datasets@0.1.4.0 0.1.3.0 0xa77cd723e17e54a2544513eecb372be6 unindexed https://jend.leeeet.dev/files.txt?path=mlbend-datasets@0.1.3.0 0.1.2.0 0xad30062b0524c338451286e334fa0726 unindexed https://jend.leeeet.dev/files.txt?path=mlbend-datasets@0.1.2.0 0.1.1.0 0x8c96353d3ca49c6a162373dab83cd9f4 invalid https://jend.leeeet.dev/files.txt?path=mlbend-datasets@0.1.1.0 expected a package named mlbend-huggingface@0.1.0.0 on https://hub.bend-lang.com At https://jend.leeeet.dev/read.txt?path=mlbend-datasets@0.1.1.0/main.bend&start_line=22. Files that do not load: main.bend. Definitions (44): MlbendDatasets.Table (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=Table) type Table is Data: Table{rows: List<&2, List<&2, F32>>, labels: List<&2, F32>} MlbendDatasets.Row (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=Row) # One row of the file: its features and its label. type Row is Data: Row{features: List<&2, F32>, label: F32} MlbendDatasets.Rows (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=Rows) # The rows read so far. type Rows is Data: Rows{rows: List<&2, Row>, labels: List<&2, F32>} MlbendDatasets.add_features (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=add_features) # One row's features, appended to the rows so far. def add_features(acc: List<&2, List<&2, F32>>, r: Row) -> List<&2, List<&2, F32>>: MlbendDatasets.add_row_of (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=add_row_of) # The rows of a file, and the row one line makes. def add_row_of(acc: Rows, +r: Row) -> Rows: MlbendDatasets.feature_rows (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=feature_rows) # The rows of the features, one after the other. def feature_rows(rs: List<&2, Row>) -> List<&2, List<&2, F32>>: MlbendDatasets.data_of (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=data_of) # The dataset the rows make. def data_of(acc: Rows) -> Table: MlbendDatasets.not_empty (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=not_empty) # A line that holds something. def not_empty(line: String) -> Bool: MlbendDatasets.drop_empty (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=drop_empty) # The lines of a file without its empty ones: a file ends with a # newline, and the line after it is empty. def drop_empty(lines: List<&2, String>) -> List<&2, String>: MlbendDatasets.number_or_zero (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=number_or_zero) # A number that may be there, or zero when it is not. def number_or_zero(m: Maybe<&2, F32>) -> F32: MlbendDatasets.cell (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=cell) # A field of a row, as a number: a number is itself, True is 1, False is # 0, and anything else is 0. def cell(+text: String) -> F32: MlbendDatasets.cells_of (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=cells_of) # The cells of a row, as numbers. def cells_of(+xs: List<&2, String>) -> List<&2, F32>: MlbendDatasets.label_index (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=label_index) # The place of the label in a row: the last column, less the columns # that are left out at the end. def label_index(+xs: List<&2, String>, drop: Nat) -> Nat: MlbendDatasets.fields_before (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=fields_before) # The fields before the label. def fields_before(+xs: List<&2, String>, drop: Nat) -> List<&2, String>: MlbendDatasets.features_of (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=features_of) # The features of a row: the fields before the label, as numbers. def features_of(+xs: List<&2, String>, drop: Nat) -> List<&2, F32>: MlbendDatasets.class_of (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=class_of) # The class of a row, by name: 0, 1 or 2 for the three iris species. def class_of(name: String) -> F32: MlbendDatasets.class_or_number (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=class_or_number) # The label of a row: a class name is its class, a number is itself. def class_or_number(+text: String) -> F32: MlbendDatasets.label_at (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=label_at) # The label of a row, when the field is there. def label_at(m: Maybe<&2, String>) -> F32: MlbendDatasets.text_at (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=text_at) # The text of a field of a row. def text_at(+xs: List<&2, String>, n: Nat) -> Maybe<&2, String>: MlbendDatasets.label_of (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=label_of) # The label of a row: the column at its place. def label_of(+xs: List<&2, String>, drop: Nat) -> F32: MlbendDatasets.row_of_parts (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=row_of_parts) # One row of the file, from its fields. def row_of_parts(+fs: List<&2, F32>, l: F32) -> Row: MlbendDatasets.row_of (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=row_of) # One row of the file. def row_of(+line: String, +drop: Nat) -> Row: MlbendDatasets.rows_go (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=rows_go) # The rows of a file, one line at a time. def rows_go(lines: List<&2, String>, +drop: Nat, +acc: Rows) -> Rows: MlbendDatasets.rows_of (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=rows_of) # The rows of a file. def rows_of(lines: List<&2, String>, drop: Nat) -> Rows: MlbendDatasets.build (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=build) # The dataset a file of rows makes. def build(text: String, drop: Nat) -> Table: MlbendDatasets.build_csv_rows (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=build_csv_rows) # The dataset the rows of a CSV make. def build_csv_rows(+lines: List<&2, String>, drop: Nat) -> Table: MlbendDatasets.drop_first (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=drop_first) # The lines of a file without its first. def drop_first(+lines: List<&2, String>) -> List<&2, String>: MlbendDatasets.build_csv (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=build_csv) # The dataset a file of CSV makes: the first line is the header and the # label is the column before the ones left out at the end. def build_csv(text: String, drop: Nat) -> Table: MlbendDatasets.csv_text (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=csv_text) # The dataset the text of a file makes. def csv_text(+text: String, header: Bool, +drop: Nat) -> Table: MlbendDatasets.csv_of_text (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=csv_of_text) # The dataset a file of text makes. def csv_of_text(t: Result<&1, &1, Hf.Err, String>, header: Bool, drop: Nat) -> Result<&1, &1, Hf.Err, Table>: MlbendDatasets.cached_path (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=cached_path) def cached_path(dir: String, repo: String, path: String) -> String: MlbendDatasets.read_result (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=read_result) def read_result(result: Result<&1, &1, U32 & String, String>) -> IO(Maybe<&1, String>): MlbendDatasets.read_done (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=read_done) def read_done(pair: File & Result<&1, &1, U32 & String, String>) -> IO(Maybe<&1, String>): MlbendDatasets.sized_done (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=sized_done) def sized_done(pair: File & Result<&1, &1, U32 & String, U32>) -> IO(Maybe<&1, String>): MlbendDatasets.opened (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=opened) def opened(r: Result<&1, &1, U32 & String, File>) -> IO(Maybe<&1, String>): MlbendDatasets.read_cached (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=read_cached) # The text of a cached file, or None when it is not there. def read_cached(path: String) -> IO(Maybe<&1, String>): MlbendDatasets.cached_or_fail (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=cached_or_fail) # A table from the cache when it is there. With MLBEND_DATA set the cache is # the source of the run: a miss is an error, not a quiet fetch, or the # manifest would hash one file and the program would read another. def cached_or_fail(m: Maybe<&1, String>, +repo: String, +path: String, header: Bool, drop: Nat) -> IO(Result<&1, &1, Hf.Err, Table>): MlbendDatasets.fetch_csv (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=fetch_csv) # A table from the hub, when there is no cache to read. def fetch_csv(repo: String, rev: String, path: String, header: Bool, drop: Nat) -> IO(Result<&1, &1, Hf.Err, Table>): MlbendDatasets.from_env (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=from_env) def from_env(e: Result<&1, &1, U32 & String, String>, +repo: String, rev: String, +path: String, header: Bool, drop: Nat) -> IO(Result<&1, &1, Hf.Err, Table>): MlbendDatasets.csv_of (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=csv_of) # A file of a dataset's repository, and the dataset it makes. def csv_of(repo: String, rev: String, path: String, header: Bool, drop: Nat) -> IO(Result<&1, &1, Hf.Err, Table>): MlbendDatasets.cancer (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=cancer) # The breast cancer dataset: 683 rows, nine features, and the label. def cancer() -> IO(Result<&1, &1, Hf.Err, Table>): MlbendDatasets.heart (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=heart) # The heart failure dataset: 299 rows, twelve features, and the label. def heart() -> IO(Result<&1, &1, Hf.Err, Table>): MlbendDatasets.iris (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=iris) # The iris dataset, fetched from the hub. def iris() -> IO(Result<&1, &1, Hf.Err, Table>): MlbendDatasets.wine (https://jend.leeeet.dev/definition.txt?path=mlbend-datasets@0.1.6.0/main.bend&name=wine) # The wine dataset: 6497 rows, eleven features, and the quality. def wine() -> IO(Result<&1, &1, Hf.Err, Table>):