def import_from_parquet(filename_or_fobj, *args, **kwargs):
'Import data from a Parquet file'
filename, fobj = get_filename_and_fobj(filename_or_fobj, mode='rb')
# TODO: should look into `schema.converted_type` also
types = OrderedDict([(schema.name, PARQUET_TO_ROWS[schema.type])
for schema in parquet._read_footer(fobj).schema
if schema.type is not None])
header = list(types.keys())
table_rows = list(parquet.reader(fobj)) # TODO: be lazy
meta = {'imported_from': 'parquet', 'filename': filename,}
return create_table([header] + table_rows, meta=meta, force_types=types,
*args, **kwargs)
def read(self, path: Path):
try:
import parquet
except ImportError as e:
raise ImportError(f"{e}. HINT: You can install Parquet by running "
"'pip install parquet'")
with path.open("rt") as tf:
columns = [self.lhs_col, self.rhs_col]
if self.rel_col is not None:
columns.append(self.rel_col)
for row in parquet.reader(tf, columns=columns):
if self.rel_col is not None:
yield row
else:
yield (row[0], row[1], None)
def import_from_parquet(filename_or_fobj, *args, **kwargs):
"""Import data from a Parquet file and return with rows.Table."""
filename, fobj = get_filename_and_fobj(filename_or_fobj, mode="rb")
# TODO: should look into `schema.converted_type` also
types = OrderedDict([(schema.name, PARQUET_TO_ROWS[schema.type])
for schema in parquet._read_footer(fobj).schema
if schema.type is not None])
header = list(types.keys())
table_rows = list(parquet.reader(fobj)) # TODO: be lazy
meta = {"imported_from": "parquet", "filename": filename}
return create_table([header] + table_rows,
meta=meta,
force_types=types,
*args,
**kwargs)
def import_from_parquet(filename_or_fobj, *args, **kwargs):
"""Import data from a Parquet file and return with rows.Table."""
filename, fobj = get_filename_and_fobj(filename_or_fobj, mode="rb")
# TODO: should look into `schema.converted_type` also
types = OrderedDict(
[
(schema.name, PARQUET_TO_ROWS[schema.type])
for schema in parquet._read_footer(fobj).schema
if schema.type is not None
]
)
header = list(types.keys())
table_rows = list(parquet.reader(fobj)) # TODO: be lazy
meta = {"imported_from": "parquet", "filename": filename}
return create_table(
[header] + table_rows, meta=meta, force_types=types, *args, **kwargs
)
def import_from_parquet(filename_or_fobj, *args, **kwargs):
'Import data from a Parquet file'
filename, fobj = get_filename_and_fobj(filename_or_fobj, mode='rb')
# TODO: should look into `schema.converted_type` also
types = OrderedDict([(schema.name, PARQUET_TO_ROWS[schema.type])
for schema in parquet._read_footer(fobj).schema
if schema.type is not None])
header = list(types.keys())
table_rows = list(parquet.reader(fobj)) # TODO: be lazy
meta = {
'imported_from': 'parquet',
'filename': filename,
}
return create_table([header] + table_rows,
meta=meta,
force_types=types,
*args,
**kwargs)
def read(self, path: Path):
try:
import parquet
except ImportError as e:
raise ImportError(f"{e}. HINT: You can install Parquet by running "
"'pip install parquet'")
with path.open("rb") as tf:
columns = [
self.lhs_col, self.rhs_col, self.rel_col, self.weight_col
]
fetch_columns = [c for c in columns if c is not None]
for row in parquet.reader(tf, columns=fetch_columns):
offset = 0
ret = []
for c in columns:
if c is not None:
ret.append(row[offset])
offset += 1
else:
ret.append(None)
yield tuple(ret)
#!/usr/bin/python
import parquet as pq
import sys
from io import BytesIO
# Purpose: Read parquet files fro stdin to pipeline in MemSQL
# Read binary input from stdin
# Python 2
#file = sys.stdin.read()
# Python 3
file = sys.stdin.buffer.read()
# Convert file object
data = BytesIO(file)
# Read the rows in the parquet file
# Print out CSV to MemSQL
for row in pq.reader(data):
memsql_row = (str(row[0]) + ',' + str(row[1]) + ',' + str(row[2]) + ',' +
str(row[3]))
print(memsql_row.encode('ascii'))
import parquet
import pandas as pd
home = os.path.expanduser("~")
dir = "/media/sumeyer/SSD_2/ML_DATA/"
filename = "part-r-00000-67ebd6f0-bfb4-42e0-b516-d7aaa77cbcb8.snappy.parquet"
datafile = dir + filename
print("open file : ", datafile)
## assuming parquet file with two rows and three columns:
## foo bar baz
## 1 2 3
## 4 5 6
with open(datafile) as fo:
# prints:
# {"foo": 1, "bar": 2}
# {"foo": 4, "bar": 5}
for row in parquet.DictReader(fo):
print(json.dumps(row))
with open(datafile) as fo:
# prints:
# 1,2
# 4,5
for row in parquet.reader(fo):
print(",".join([str(r) for r in row]))
print(df.info())
print(df)
# https://github.com/jcrobak/parquet-python
# sudo pip3 install parquet
import parquet
import json
## assuming parquet file with two rows and three columns:
## foo bar baz
## 1 2 3
## 4 5 6
with open("test.parquet") as fo:
# prints:
# {"foo": 1, "bar": 2}
# {"foo": 4, "bar": 5}
for row in parquet.DictReader(fo, columns=['foo', 'bar']):
print(json.dumps(row))
with open("test.parquet") as fo:
# prints:
# 1,2
# 4,5
for row in parquet.reader(fo, columns=['foo', 'bar]):
print(",".join([str(r) for r in row]))
# content = fs.read()
#s = str(content, 'utf-8')
#file = open("D:\data.csv", "w")
#file.write(s)
#df = pd.read_csv("D:\data.csv", names=COLUMNNAMES)
#print df
import parquet
import json
## assuming parquet file with two rows and three columns:
## foo bar baz
## 1 2 3
## 4 5 6
with open("test.parquet") as fo:
# prints:
# {"foo": 1, "bar": 2}
# {"foo": 4, "bar": 5}
for row in parquet.DictReader(fo, columns=['foo', 'bar']):
print(json.dumps(row))
with open("test.parquet") as fo:
# prints:
# 1,2
# 4,5
for row in parquet.reader(fo, columns=['foo', 'bar]):
print(",".join([str(r) for r in row]))