Spaces:
Sleeping
Sleeping
File size: 5,564 Bytes
74c716c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 |
# MIT License
#
# Copyright (c) 2023 Victor Calderon
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
"""
Module for preparing the input dataset.
"""
import logging
from pathlib import Path
from typing import Dict
from src.classes import data_preparation as dp
from src.utils import default_variables as dv
from src.utils import general_utilities as gu
__author__ = ["Victor Calderon"]
__copyright__ = ["Copyright 2023 Victor Calderon"]
__all__ = []
logger = logging.getLogger(__name__)
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s [%(levelname)s]: %(message)s",
)
logger.setLevel(logging.INFO)
# ---------------------------- PROJECT VARIABLES ------------------------------
MODULE_DESCRIPTION = "Module for data preparation"
MODULE_VERSION = "1.0"
# ----------------------------- INPUT PARAMETERS ------------------------------
def get_parser():
"""
Function to get the input parameters to the script.
"""
# Defining the 'parser' object to use
parser = gu._get_parser_obj(description=MODULE_DESCRIPTION)
# Path to the input dataset
parser.add_argument(
"--dataset-path",
dest="dataset_path",
default=dv.cicero_dataset_url,
type=str,
help="""
Path / URL to the input dataset.
[Default: '%(default)s']
""",
)
return parser.parse_args()
# ------------------------------- FUNCTIONS ----------------------------------
def _resolve_input_object_path(object_path: str) -> str:
"""
Check whether or not the path corresponds to a local file or a URL.
Parameters
-------------
object_path : str
Path of the input object.
Returns
----------
parsed_object_path : str
Modified / parsed version of the input object ``object_path``.
Raises
------------
TypeError ; Error
This error gets raised whenever the input object is neither
a 'file' nor a valid 'url'.
"""
object_type = gu.check_url_or_file_type(object_path=object_path)
if object_type == "unspecified":
msg = (
f">>> Unspecified data type for '{object_path}' or does not exist"
)
logger.error(msg)
raise TypeError(msg)
return (
object_path
if object_type == "url"
else str(Path(object_path).resolve())
)
def _temp_create_dataset_with_summaries():
"""
Function to **temporarily** create the Dataset object in HuggingFace
using the dataset with summaries for each of the articles.
Notes
--------
This is a temporary solution UNTIL the ``Summarizer`` is put in place.
"""
# Path to the dataset
dataset_filepath = str(
(
gu.get_project_paths()
.get("src")
.joinpath(
"utils",
"gpt35_summaries",
"df_embed_out2.csv",
)
).resolve()
)
# Reading in dataset
data_prep_obj = dp.DatasetPrep(dataset_path=dataset_filepath)
# Uploading it to HuggingFace Hub
data_prep_obj.push_dataset_to_hub(
dataset=data_prep_obj.raw_dataset,
dataset_name=dv.summaries_dataset_name,
)
return
# ------------------------------ MAIN FUNCTIONS -------------------------------
def main(params_dict: Dict):
"""
Main function to process the data.
"""
# Determine if the path corresponds to a file or a URL
params_dict["object_path"] = _resolve_input_object_path(
params_dict["dataset_path"]
)
# Showing set of input parameters
gu.show_params(params_dict=params_dict, logger=logger)
# Initializing input parameters
data_prep_obj = dp.DatasetPrep(dataset_path=params_dict["object_path"])
data_prep_obj.show_params()
clean_dataset = data_prep_obj.clean_dataset()
logger.info(f"\n>>> Raw dataset: \n{data_prep_obj.raw_dataset}\n")
logger.info(f"\n>>> Clean dataset: \n{clean_dataset}\n")
# --- Pushing datasets to HuggingFace Hub
# 'Raw' dataset
data_prep_obj.push_dataset_to_hub(
dataset=data_prep_obj.raw_dataset,
dataset_name=dv.raw_dataset_name,
)
# 'Clean' dataset
data_prep_obj.push_dataset_to_hub(
dataset=clean_dataset,
dataset_name=dv.clean_dataset_name,
)
# Dataset with summaries
_temp_create_dataset_with_summaries()
return
if __name__ == "__main__":
# Getting input parameters
params_dict = vars(get_parser())
# Running main function
main(params_dict=params_dict)
|