class JsonConfig(nlp.BuilderConfig):
"""BuilderConfig for JSON."""
read_options: paj.ReadOptions = paj.ReadOptions()
parse_options: paj.ParseOptions = paj.ParseOptions()
@property
def pa_read_options(self):
return self.read_options
@property
def pa_parse_options(self):
return self.parse_options
def convert_ndjsons_to_parquet(files: List[Path], file_name: str,
out_dir: Union[Path,
str], schema: pa.Schema) -> Path:
pq_file = Path(f"{out_dir}/{file_name}.parquet")
if not schema:
schema = pa_json.read_json(files[0]).schema
with pq.ParquetWriter(pq_file, schema) as writer:
parse_options = pa_json.ParseOptions(explicit_schema=schema)
for f in files:
logger.debug(f"Processing {f}")
table = pa_json.read_json(f, parse_options=parse_options)
writer.write_table(table)
remove(f)
return pq_file
def pa_parse_options(self):
return paj.ParseOptions(explicit_schema=self.schema,
newlines_in_values=self.newlines_in_values)
def pa_parse_options(self):
return paj.ParseOptions(newlines_in_values=self.newlines_in_values)
def _parse_data_to_pandas(filepath: str, table_params: dict, metadata: dict):
"""
Reads in the data from the given filepath and returns
a dataframe
"""
meta_col_names = [
c["name"] for c in metadata["columns"]
if c["name"] not in metadata.get("partitions", [])
]
# For string based file types convert make arrow readers read them in as strings
# validators will still treat these as dates but will run validation against strings
# cols expecting values to match a timestamp format
if "json" in metadata["file_format"] or "csv" in metadata["file_format"]:
md_obj = Metadata.from_dict(metadata)
cols = md_obj.columns
cols_to_force_str_read_in = []
for c in cols:
if c["type"].startswith("time") or c["type"].startswith("date"):
c["type"] = "string"
c["type_category"] = "string"
cols_to_force_str_read_in.append(c["name"])
md_obj.columns = cols
ac = ArrowConverter()
arrow_schema = ac.generate_from_meta(md_obj)
ts_as_str_schema = pa.schema([])
for cname in cols_to_force_str_read_in:
ts_as_str_schema = ts_as_str_schema.append(
arrow_schema.field(cname))
# Set the reader type
if filepath.startswith("s3://"):
reader_fs = fs.S3FileSystem(region="eu-west-1")
fp_for_file_reader = filepath.replace("s3://", "", 1)
else:
reader_fs = fs.LocalFileSystem()
fp_for_file_reader = filepath
with reader_fs.open_input_stream(fp_for_file_reader) as f:
if "csv" in metadata["file_format"]:
# Safer CSV load for newlines_in_values set to True
if table_params.get("expect-header", True):
po = csv.ParseOptions(newlines_in_values=True)
else:
po = csv.ParseOptions(newlines_in_values=True,
column_names=meta_col_names)
if ts_as_str_schema:
co = csv.ConvertOptions(column_types=ts_as_str_schema)
else:
co = None
df = pa_read_csv_to_pandas(
input_file=f,
schema=arrow_schema,
expect_full_schema=False,
parse_options=po,
convert_options=co,
)
# dates/datetimes == string
elif "json" in metadata["file_format"]:
po = json.ParseOptions(
newlines_in_values=True,
explicit_schema=ts_as_str_schema if ts_as_str_schema else None,
)
df = pa_read_json_to_pandas(
input_file=f,
schema=arrow_schema,
expect_full_schema=False,
parse_options=po,
)
# dates/datetimes == string
elif "parquet" in metadata["file_format"]:
df = arrow_to_pandas(pq.read_table(f))
# dates/datetimes == datetime / date
else:
raise ValueError(
f"Unknown file_format in metadata: {metadata['file_format']}.")
if table_params.get("row-limit"):
df = df.sample(table_params.get("row-limit"))
if table_params.get("headers-ignore-case"):
df_cols = [c.lower() for c in df.columns]
df.columns = df_cols
if table_params.get("only-test-cols-in-metadata", False):
keep_cols = [c for c in df.columns if c in meta_col_names]
df = df[keep_cols]
return df