def dict_to_csv(data_dic: dict, root_dir: str, file_io: FileIO, zip_output: bool = True) -> str: """Saves input dictionary to a csv file and zips if requested Parameters --------- data_dic: dict input dict to be converted to a zipped csv file root_dir: str path to save the output file file_io: FileIO file I/O handler objects for reading and writing data zip_output: bool boolean value indicates whether the output should be zipped Returns ------- `str` path to the created zip file """ # creating zip dir final_dir_path = os.path.join(root_dir, TEMPERATURE_SCALE) file_io.make_directory(final_dir_path) csv_path = os.path.join(final_dir_path, f'{TEMPERATURE_SCALE}.csv') # creating .csv pd.DataFrame.from_dict(data_dic).to_csv(csv_path, index=False) if zip_output: # creating .zip file shutil.make_archive(final_dir_path, "zip", root_dir, TEMPERATURE_SCALE) # removing the dir, keeping only the zip shutil.rmtree(final_dir_path) return final_dir_path
def read(data_dir: str, feature_config: FeatureConfig, tfrecord_type: str, tfrecord_dir: str, file_io: FileIO, batch_size: int = 128, preprocessing_keys_to_fns: dict = {}, use_part_files: bool = False, max_sequence_size: int = 25, parse_tfrecord: bool = True, logger=None, **kwargs) -> tf.data.TFRecordDataset: """ Create a TFRecordDataset from directory of CSV files using the FeatureConfig Current execution plan: 1. Load CSVs as pandas dataframes 2. Convert each query into tf.train.SequenceExample protobufs 3. Write the protobufs into a .tfrecord file 4. Load .tfrecord file into a TFRecordDataset and parse the protobufs Parameters data_dir : str Path to directory containing csv files to read feature_config : FeatureConfig object FeatureConfig object that defines the features to be loaded in the dataset and the preprocessing functions to be applied to each of them tfrecord_dir : str Path to directory where the serialized .tfrecord files will be stored batch_size : int value specifying the size of the data batch use_part_files : bool load dataset from part files checked using "part-" prefix max_sequence_size : int value specifying max number of records per query logger : Logger object logging handler to print and save status messages Returns ------- `TFRecordDataset` object tensorflow TFRecordDataset loaded from the CSV file """ csv_files: List[str] = file_io.get_files_in_directory( data_dir, extension="" if use_part_files else ".csv", prefix="part-" if use_part_files else "", ) # Create a directory for storing tfrecord files file_io.make_directory(tfrecord_dir, clear_dir=True) # Write tfrecord files tfrecord_writer.write_from_files( csv_files=csv_files, tfrecord_file=os.path.join(tfrecord_dir, TFRECORD_FILE), feature_config=feature_config, tfrecord_type=tfrecord_type, file_io=file_io, logger=logger, ) dataset = tfrecord_reader.read( data_dir=tfrecord_dir, feature_config=feature_config, tfrecord_type=tfrecord_type, max_sequence_size=max_sequence_size, batch_size=batch_size, preprocessing_keys_to_fns=preprocessing_keys_to_fns, parse_tfrecord=parse_tfrecord, file_io=file_io, logger=logger, ) return dataset
def read(data_dir: str, feature_config: FeatureConfig, tfrecord_type: str, tfrecord_dir: str, file_io: FileIO, batch_size: int = 128, preprocessing_keys_to_fns: dict = {}, use_part_files: bool = False, max_sequence_size: int = 25, parse_tfrecord: bool = True, logger=None, keep_additional_info=0, non_zero_features_only=1, **kwargs) -> tf.data.TFRecordDataset: """ - reads ranklib-formatted data from an input directory - selects relevant features - creates Dataset X and y Current execution plan: 1. Convert ranklib to a dataframe 2. Convert each query into tf.train.SequenceExample protobufs 3. Write the protobufs into a .tfrecord file 4. Load .tfrecord file into a TFRecordDataset and parse the protobufs Parameters ---------- data_dir: str Path to directory containing csv files to read feature_config: ml4ir.config.features.FeatureConfig object FeatureConfig object extracted from the feature config tfrecord_dir: str Path to directory where the serialized .tfrecord files will be stored batch_size: int Value specifying the size of the batch use_part_files: bool Value specifying whether to look for part files max_sequence_size: int Value specifying max number of records per query logger: logging object logging object keep_additional_info: int Option to keep additional info (All info after the "#") 1 to keep, 0 to ignore non_zero_features_only: int Only non zero features are stored. 1 for yes, 0 otherwise Returns ------- tensorflow TFRecordDataset Processed dataset """ ranklib_files: List[str] = file_io.get_files_in_directory( data_dir, extension="" if use_part_files else ".txt", prefix="part-" if use_part_files else "", ) gl_2_clicks = False # Create a directory for storing tfrecord files file_io.make_directory(tfrecord_dir, clear_dir=True) #Convert input ranklib file to dataframe df = pd.concat([ ranklib_helper.convert(f, keep_additional_info, gl_2_clicks, non_zero_features_only, feature_config.get_query_key()['name'], feature_config.get_label()['name']) for f in ranklib_files ]) #Write tfrecord files tfrecord_writer.write_from_df(df=df, tfrecord_file=os.path.join( tfrecord_dir, TFRECORD_FILE), feature_config=feature_config, tfrecord_type=tfrecord_type, logger=logger) dataset = tfrecord_reader.read( data_dir=tfrecord_dir, feature_config=feature_config, tfrecord_type=tfrecord_type, max_sequence_size=max_sequence_size, batch_size=batch_size, preprocessing_keys_to_fns=preprocessing_keys_to_fns, parse_tfrecord=parse_tfrecord, file_io=file_io, logger=logger, ) return dataset
def read(data_dir: str, feature_config: FeatureConfig, tfrecord_type: str, tfrecord_dir: str, file_io: FileIO, batch_size: int = 128, preprocessing_keys_to_fns: dict = {}, use_part_files: bool = False, max_sequence_size: int = 25, parse_tfrecord: bool = True, logger=None, **kwargs) -> tf.data.TFRecordDataset: """ - reads csv-formatted data from an input directory - selects relevant features - creates Dataset X and y Current execution plan: 1. Load CSVs as pandas dataframes 2. Convert each query into tf.train.SequenceExample protobufs 3. Write the protobufs into a .tfrecord file 4. Load .tfrecord file into a TFRecordDataset and parse the protobufs Args: - data_dir: Path to directory containing csv files to read - feature_config: ml4ir.config.features.FeatureConfig object extracted from the feature config - tfrecord_dir: Path to directory where the serialized .tfrecord files will be stored - batch_size: int value specifying the size of the batch - use_part_files: bool value specifying whether to look for part files - max_sequence_size: int value specifying max number of records per query - logger: logging object Returns: tensorflow TFRecordDataset """ csv_files: List[str] = file_io.get_files_in_directory( data_dir, extension="" if use_part_files else ".csv", prefix="part-" if use_part_files else "", ) # Create a directory for storing tfrecord files file_io.make_directory(tfrecord_dir, clear_dir=True) # Write tfrecord files tfrecord_writer.write_from_files( csv_files=csv_files, tfrecord_file=os.path.join(tfrecord_dir, TFRECORD_FILE), feature_config=feature_config, tfrecord_type=tfrecord_type, file_io=file_io, logger=logger, ) dataset = tfrecord_reader.read( data_dir=tfrecord_dir, feature_config=feature_config, tfrecord_type=tfrecord_type, max_sequence_size=max_sequence_size, batch_size=batch_size, preprocessing_keys_to_fns=preprocessing_keys_to_fns, parse_tfrecord=parse_tfrecord, file_io=file_io, logger=logger, ) return dataset