Related
I am only able to gain limited/top-level access to my aws s3. I can see the buckets, but not their contents; neither subfolders nor files. I'm running everything from inside a conda environment. I've tried accessing files in private and public buckets without success. What am I doing wrong?
This block of code works as expected
>>> import s3fs
>>> AKEY = 'XXXX'
>>> SKEY = 'XXXX'
>>> fs = s3fs.S3FileSystem(key=AKEY,secret=SKEY)
>>> fs.ls('s3://')
['my-bucket-1',
'my-bucket-2',
'my-bucket-3']
This block doesn't
>>> fs.ls('s3://my-bucket-1')
[]
what I expect
>>> fs.ls('s3://my-bucket-1')
['my-bucket-1/test.txt',
'my-bucket-1/test.csv']
When I try to open a file I get a FileNotFoundError
import pandas as pd
pd.read_csv(
's3://my-bucket-1/test.csv',
storage_options={'key':AKEY,'secret':SKEY}
)
---------------------------------------------------------------------------
FileNotFoundError Traceback (most recent call last)
Cell In[8], line 2
1 import pandas as pd
----> 2 pd.read_csv(
3 's3://my-bucket-1/test.csv'',
4 storage_options={'key':AKEY,'secret':SKEY}
5 )
File ~\anaconda3\envs\env-2\lib\site-packages\pandas\util\_decorators.py:211, in deprecate_kwarg.<locals>._deprecate_kwarg.<locals>.wrapper(*args, **kwargs)
209 else:
210 kwargs[new_arg_name] = new_arg_value
--> 211 return func(*args, **kwargs)
File ~\anaconda3\envs\env-2\lib\site-packages\pandas\util\_decorators.py:331, in deprecate_nonkeyword_arguments.<locals>.decorate.<locals>.wrapper(*args, **kwargs)
325 if len(args) > num_allow_args:
326 warnings.warn(
327 msg.format(arguments=_format_argument_list(allow_args)),
328 FutureWarning,
329 stacklevel=find_stack_level(),
330 )
--> 331 return func(*args, **kwargs)
File ~\anaconda3\envs\env-2\lib\site-packages\pandas\io\parsers\readers.py:950, in read_csv(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, error_bad_lines, warn_bad_lines, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options)
935 kwds_defaults = _refine_defaults_read(
936 dialect,
937 delimiter,
(...)
946 defaults={"delimiter": ","},
947 )
948 kwds.update(kwds_defaults)
--> 950 return _read(filepath_or_buffer, kwds)
File ~\anaconda3\envs\env-2\lib\site-packages\pandas\io\parsers\readers.py:605, in _read(filepath_or_buffer, kwds)
602 _validate_names(kwds.get("names", None))
604 # Create the parser.
--> 605 parser = TextFileReader(filepath_or_buffer, **kwds)
607 if chunksize or iterator:
608 return parser
File ~\anaconda3\envs\env-2\lib\site-packages\pandas\io\parsers\readers.py:1442, in TextFileReader.__init__(self, f, engine, **kwds)
1439 self.options["has_index_names"] = kwds["has_index_names"]
1441 self.handles: IOHandles | None = None
-> 1442 self._engine = self._make_engine(f, self.engine)
File ~\anaconda3\envs\env-2\lib\site-packages\pandas\io\parsers\readers.py:1735, in TextFileReader._make_engine(self, f, engine)
1733 if "b" not in mode:
1734 mode += "b"
-> 1735 self.handles = get_handle(
1736 f,
1737 mode,
1738 encoding=self.options.get("encoding", None),
1739 compression=self.options.get("compression", None),
1740 memory_map=self.options.get("memory_map", False),
1741 is_text=is_text,
1742 errors=self.options.get("encoding_errors", "strict"),
1743 storage_options=self.options.get("storage_options", None),
1744 )
1745 assert self.handles is not None
1746 f = self.handles.handle
File ~\anaconda3\envs\env-2\lib\site-packages\pandas\io\common.py:713, in get_handle(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)
710 codecs.lookup_error(errors)
712 # open URLs
--> 713 ioargs = _get_filepath_or_buffer(
714 path_or_buf,
715 encoding=encoding,
716 compression=compression,
717 mode=mode,
718 storage_options=storage_options,
719 )
721 handle = ioargs.filepath_or_buffer
722 handles: list[BaseBuffer]
File ~\anaconda3\envs\env-2\lib\site-packages\pandas\io\common.py:409, in _get_filepath_or_buffer(filepath_or_buffer, encoding, compression, mode, storage_options)
406 pass
408 try:
--> 409 file_obj = fsspec.open(
410 filepath_or_buffer, mode=fsspec_mode, **(storage_options or {})
411 ).open()
412 # GH 34626 Reads from Public Buckets without Credentials needs anon=True
413 except tuple(err_types_to_retry_with_anon):
File ~\anaconda3\envs\env-2\lib\site-packages\fsspec\core.py:135, in OpenFile.open(self)
128 def open(self):
129 """Materialise this as a real open file without context
130
131 The OpenFile object should be explicitly closed to avoid enclosed file
132 instances persisting. You must, therefore, keep a reference to the OpenFile
133 during the life of the file-like it generates.
134 """
--> 135 return self.__enter__()
File ~\anaconda3\envs\env-2\lib\site-packages\fsspec\core.py:103, in OpenFile.__enter__(self)
100 def __enter__(self):
101 mode = self.mode.replace("t", "").replace("b", "") + "b"
--> 103 f = self.fs.open(self.path, mode=mode)
105 self.fobjects = [f]
107 if self.compression is not None:
File ~\anaconda3\envs\env-2\lib\site-packages\fsspec\spec.py:1106, in AbstractFileSystem.open(self, path, mode, block_size, cache_options, compression, **kwargs)
1104 else:
1105 ac = kwargs.pop("autocommit", not self._intrans)
-> 1106 f = self._open(
1107 path,
1108 mode=mode,
1109 block_size=block_size,
1110 autocommit=ac,
1111 cache_options=cache_options,
1112 **kwargs,
1113 )
1114 if compression is not None:
1115 from fsspec.compression import compr
File ~\anaconda3\envs\env-2\lib\site-packages\s3fs\core.py:640, in S3FileSystem._open(self, path, mode, block_size, acl, version_id, fill_cache, cache_type, autocommit, requester_pays, cache_options, **kwargs)
637 if cache_type is None:
638 cache_type = self.default_cache_type
--> 640 return S3File(
641 self,
642 path,
643 mode,
644 block_size=block_size,
645 acl=acl,
646 version_id=version_id,
647 fill_cache=fill_cache,
648 s3_additional_kwargs=kw,
649 cache_type=cache_type,
650 autocommit=autocommit,
651 requester_pays=requester_pays,
652 cache_options=cache_options,
653 )
File ~\anaconda3\envs\env-2\lib\site-packages\s3fs\core.py:1989, in S3File.__init__(self, s3, path, mode, block_size, acl, version_id, fill_cache, s3_additional_kwargs, autocommit, cache_type, requester_pays, cache_options)
1987 self.details = s3.info(path)
1988 self.version_id = self.details.get("VersionId")
-> 1989 super().__init__(
1990 s3,
1991 path,
1992 mode,
1993 block_size,
1994 autocommit=autocommit,
1995 cache_type=cache_type,
1996 cache_options=cache_options,
1997 )
1998 self.s3 = self.fs # compatibility
2000 # when not using autocommit we want to have transactional state to manage
File ~\anaconda3\envs\env-2\lib\site-packages\fsspec\spec.py:1462, in AbstractBufferedFile.__init__(self, fs, path, mode, block_size, autocommit, cache_type, cache_options, size, **kwargs)
1460 self.size = size
1461 else:
-> 1462 self.size = self.details["size"]
1463 self.cache = caches[cache_type](
1464 self.blocksize, self._fetch_range, self.size, **cache_options
1465 )
1466 else:
File ~\anaconda3\envs\env-2\lib\site-packages\fsspec\spec.py:1475, in AbstractBufferedFile.details(self)
1472 #property
1473 def details(self):
1474 if self._details is None:
-> 1475 self._details = self.fs.info(self.path)
1476 return self._details
File ~\anaconda3\envs\env-2\lib\site-packages\fsspec\asyn.py:113, in sync_wrapper.<locals>.wrapper(*args, **kwargs)
110 #functools.wraps(func)
111 def wrapper(*args, **kwargs):
112 self = obj or args[0]
--> 113 return sync(self.loop, func, *args, **kwargs)
File ~\anaconda3\envs\env-2\lib\site-packages\fsspec\asyn.py:98, in sync(loop, func, timeout, *args, **kwargs)
96 raise FSTimeoutError from return_result
97 elif isinstance(return_result, BaseException):
---> 98 raise return_result
99 else:
100 return return_result
File ~\anaconda3\envs\env-2\lib\site-packages\fsspec\asyn.py:53, in _runner(event, coro, result, timeout)
51 coro = asyncio.wait_for(coro, timeout=timeout)
52 try:
---> 53 result[0] = await coro
54 except Exception as ex:
55 result[0] = ex
File ~\anaconda3\envs\env-2\lib\site-packages\s3fs\core.py:1257, in S3FileSystem._info(self, path, bucket, key, refresh, version_id)
1245 if (
1246 out.get("KeyCount", 0) > 0
1247 or out.get("Contents", [])
1248 or out.get("CommonPrefixes", [])
1249 ):
1250 return {
1251 "name": "/".join([bucket, key]),
1252 "type": "directory",
1253 "size": 0,
1254 "StorageClass": "DIRECTORY",
1255 }
-> 1257 raise FileNotFoundError(path)
1258 except ClientError as e:
1259 raise translate_boto_error(e, set_cause=False)
FileNotFoundError: my-bucket-1/test.csv
s3fs-2022.11.0, aiobotocore-2.4.0, botocore-1.27.59
fs = s3fs.S3FileSystem(anon=True)
fs.ls('s3://dask-data/nyc-taxi/2015')
ParseError
Check the bucket policy / IAM role that gives you permissions to access the bucket. It should have /* after the name of the resource:
"Action": "s3:GetObject",
"Resource": "arn:aws:s3:::my-bucket-1/*"
to allow you access the objects in the bucket, not just the bucket itself.
Have you tried boto3? s3fs is no longer supported.
I am trying the following code which replace an empty list with unique array of a column("apples_set") when the condition "all" is satisfied.
The column "apple_logic_string" is of type Array[String]
Data frame looks like this:
apples_patterns.show()
+--------------------+-----------------+
| apples_logic_string|apples_set |
+--------------------+-----------------+
| "234" |["43","54"] |
| "65" |["95"] |
| "all" |[] |
| "76" |["84","67"] |
+--------------------+-----------------+
The code:
unique_all_apples = set(apples_patterns.agg(F.flatten(F.collect_set('apples_set'))).head()[0]) # noqa
error_patterns = apples_patterns.withColumn('apples_set', F.when(F.col('apples_logic_string') == 'all',
unique_all_apples).otherwise(F.col('apples_set')))
The Error:
Traceback (most recent call last):
File "/myproject/datasets/apples_matching.py", line 24, in compute
apples_patterns = apples_patterns.withColumn('apples_set', F.when(F.col('apples_logic_string') == 'all',
File "/scratch/asset-install/1c9821b4f6adc95ac4d5f15ff109001b/miniconda38/lib/python3.8/site-packages/pyspark/sql/functions.py", line 1518, in when
jc = sc._jvm.functions.when(condition._jc, v)
File "/scratch/asset-install/1c9821b4f6adc95ac4d5f15ff109001b/miniconda38/lib/python3.8/site-packages/py4j/java_gateway.py", line 1321, in __call__
return_value = get_return_value(
File "/scratch/asset-install/1c9821b4f6adc95ac4d5f15ff109001b/miniconda38/lib/python3.8/site-packages/pyspark/sql/utils.py", line 111, in deco
return f(*a, **kw)
File "/scratch/asset-install/1c9821b4f6adc95ac4d5f15ff109001b/miniconda38/lib/python3.8/site-packages/py4j/protocol.py", line 326, in get_return_value
raise Py4JJavaError(
py4j.protocol.Py4JJavaError: An error occurred while calling z:org.apache.spark.sql.functions.when.
: java.lang.RuntimeException: Unsupported literal type class java.util.ArrayList [43,54,95,84,67]
You can use array function: array documentation
In your case you may use it like this:
F.array([F.lit(x) for x in unique_all_apples])
sample code
import pyspark.sql.functions as F
x = [("234", ["43", "54"]), ("65", ["95"]), ("all", []), ("76", ["84", "67"])]
apples_patterns = spark.createDataFrame(x, schema=["apples_logic_string", "apples_set"])
unique_all_apples = set(
apples_patterns.agg(F.flatten(F.collect_set("apples_set"))).head()[0]
)
error_patterns = apples_patterns.withColumn(
"apples_set",
F.when(
F.col("apples_logic_string") == "all",
F.array([F.lit(x) for x in unique_all_apples]),
).otherwise(F.col("apples_set")),
)
And the output:
+-------------------+--------------------+
|apples_logic_string| apples_set|
+-------------------+--------------------+
| 234| [43, 54]|
| 65| [95]|
| all|[54, 95, 43, 67, 84]|
| 76| [84, 67]|
+-------------------+--------------------+
The easiest solution is to create another dataframe with one row that contains all distinct apples_set using explode than collect_set, after that joined to the original dataframe:
import spark.implicits._
val data = Seq(
("234", Seq("43", "54")),
("65", Seq("95")),
("all", Seq()),
("76", Seq("84", "67"))
)
val df = spark.sparkContext.parallelize(data).toDF("apples_logic_string", "apples_set")
val allDf = df.select(explode(col("apples_set")).as("apples_set")).agg(collect_set("apples_set").as("all_apples_set"))
.withColumn("apples_logic_string", lit("all"))
df.join(broadcast(allDf), Seq("apples_logic_string"), "left")
.withColumn("apples_set", when(col("apples_logic_string").equalTo("all"), col("all_apples_set")).otherwise(col("apples_set")))
.drop("all_apples_set").show(false)
+-------------------+--------------------+
|apples_logic_string|apples_set |
+-------------------+--------------------+
|234 |[43, 54] |
|65 |[95] |
|all |[84, 95, 67, 54, 43]|
|76 |[84, 67] |
+-------------------+--------------------+
In the following line of code, I get the error shown below.
d3["WOE"] = np.where(((d3.DIST_EVENT==0) | (d3.DIST_NON_EVENT ==0)) ,np.nan ,np.log(d3.DIST_EVENT/d3.DIST_NON_EVENT))
I if the numerator or denominator is 0, then the condition for np.nan should satisfy and d3["WOE"] shoud be nan. Why is the following error being produced?
---------------------------------------------------------------------------
FloatingPointError Traceback (most recent call last)
<ipython-input-56-a9b015683238> in <module>
----> 1 final_iv, IV = data_vars(df_leads_short,df_leads_short.close_flag)
2 IV.sort_values('IV')
<ipython-input-55-5530ad13fa5a> in data_vars(df1, target)
122 count = count + 1
123 else:
--> 124 conv = char_bin(target, df1[i])
125 conv["VAR_NAME"] = i
126 count = count + 1
<ipython-input-55-5530ad13fa5a> in char_bin(Y, X)
92 d3["DIST_EVENT"] = d3.EVENT/d3.sum().EVENT
93 d3["DIST_NON_EVENT"] = d3.NONEVENT/d3.sum().NONEVENT
---> 94 d3["WOE"] = np.where(((d3.DIST_EVENT==0) | (d3.DIST_NON_EVENT ==0)) ,np.nan ,np.log(d3.DIST_EVENT/d3.DIST_NON_EVENT))
95 #d3["WOE"] = np.log(d3.DIST_EVENT/d3.DIST_NON_EVENT)
96 d3["IV"] = np.where((d3.DIST_EVENT==0) | (d3.DIST_NON_EVENT ==0 ),np.nan ,(d3.DIST_EVENT-d3.DIST_NON_EVENT)*np.log(d3.DIST_EVENT/d3.DIST_NON_EVENT))
/opt/conda/lib/python3.7/site-packages/pandas/core/generic.py in __array_ufunc__(self, ufunc, method, *inputs, **kwargs)
1934 self, ufunc: Callable, method: str, *inputs: Any, **kwargs: Any
1935 ):
-> 1936 return arraylike.array_ufunc(self, ufunc, method, *inputs, **kwargs)
1937
1938 # ideally we would define this to avoid the getattr checks, but
/opt/conda/lib/python3.7/site-packages/pandas/core/arraylike.py in array_ufunc(self, ufunc, method, *inputs, **kwargs)
356 # ufunc(series, ...)
357 inputs = tuple(extract_array(x, extract_numpy=True) for x in inputs)
--> 358 result = getattr(ufunc, method)(*inputs, **kwargs)
359 else:
360 # ufunc(dataframe)
FloatingPointError: divide by zero encountered in log
We can do
cond = ((d3.DIST_EVENT==0) | (d3.DIST_NON_EVENT ==0))
d3.loc[~cond,"WOE"] = np.log(d3.loc[~cond,"DIST_EVENT"]/d3.loc[~cond,"DIST_NON_EVENT"]))
Since the np.where still need calculated the np.log(d3.DIST_EVENT/d3.DIST_NON_EVENT) which will still yield the same error.np.where is just selection.
I'm working with a Dask Cluster on GCP. I'm using this code to deploy it:
from dask_cloudprovider.gcp import GCPCluster
from dask.distributed import Client
enviroment_vars = {
'EXTRA_PIP_PACKAGES': '"gcsfs"'
}
cluster = GCPCluster(
n_workers=32,
docker_image='daskdev/dask:2021.2.0',
env_vars=enviroment_vars,
network='my-network',
#filesystem_size=150,
machine_type='e2-standard-16',
projectid='my-project-id',
zone='us-central1-a',
on_host_maintenance="MIGRATE"
client = Client(cluster)
Then I read csv files, with the following code:
import dask.dataframe as dd
import csv
col_dtypes = {
'var1': 'float64',
'var2': 'object',
'var3': 'object',
'var4': 'float64'
}
df = dd.read_csv('gs://my_bucket/files-*.csv', blocksize=None, dtype= col_dtypes)
df = df.persist()
Everything works fine, but when I try to do some queries, or calculation, I get an error. For instance this piece of code:
df.var1.value_counts().compute()
This is the output:
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-14-711a7c21ed42> in <module>
----> 1 df.var1.value_counts().compute()
/opt/conda/lib/python3.8/site-packages/dask/base.py in compute(self, **kwargs)
279 dask.base.compute
280 """
--> 281 (result,) = compute(self, traverse=False, **kwargs)
282 return result
283
/opt/conda/lib/python3.8/site-packages/dask/base.py in compute(*args, **kwargs)
561 postcomputes.append(x.__dask_postcompute__())
562
--> 563 results = schedule(dsk, keys, **kwargs)
564 return repack([f(r, *a) for r, (f, a) in zip(results, postcomputes)])
565
/opt/conda/lib/python3.8/site-packages/distributed/client.py in get(self, dsk, keys, workers, allow_other_workers, resources, sync, asynchronous, direct, retries, priority, fifo_timeout, actors, **kwargs)
2653 should_rejoin = False
2654 try:
-> 2655 results = self.gather(packed, asynchronous=asynchronous, direct=direct)
2656 finally:
2657 for f in futures.values():
/opt/conda/lib/python3.8/site-packages/distributed/client.py in gather(self, futures, errors, direct, asynchronous)
1962 else:
1963 local_worker = None
-> 1964 return self.sync(
1965 self._gather,
1966 futures,
/opt/conda/lib/python3.8/site-packages/distributed/client.py in sync(self, func, asynchronous, callback_timeout, *args, **kwargs)
836 return future
837 else:
--> 838 return sync(
839 self.loop, func, *args, callback_timeout=callback_timeout, **kwargs
840 )
/opt/conda/lib/python3.8/site-packages/distributed/utils.py in sync(loop, func, callback_timeout, *args, **kwargs)
338 if error[0]:
339 typ, exc, tb = error[0]
--> 340 raise exc.with_traceback(tb)
341 else:
342 return result[0]
/opt/conda/lib/python3.8/site-packages/distributed/utils.py in f()
322 if callback_timeout is not None:
323 future = asyncio.wait_for(future, callback_timeout)
--> 324 result[0] = yield future
325 except Exception as exc:
326 error[0] = sys.exc_info()
/opt/conda/lib/python3.8/site-packages/tornado/gen.py in run(self)
760
761 try:
--> 762 value = future.result()
763 except Exception:
764 exc_info = sys.exc_info()
/opt/conda/lib/python3.8/site-packages/distributed/client.py in _gather(self, futures, errors, direct, local_worker)
1827 exc = CancelledError(key)
1828 else:
-> 1829 raise exception.with_traceback(traceback)
1830 raise exc
1831 if errors == "skip":
/opt/conda/lib/python3.8/site-packages/dask/optimization.py in __call__()
961 if not len(args) == len(self.inkeys):
962 raise ValueError("Expected %d args, got %d" % (len(self.inkeys), len(args)))
--> 963 return core.get(self.dsk, self.outkey, dict(zip(self.inkeys, args)))
964
965 def __reduce__(self):
/opt/conda/lib/python3.8/site-packages/dask/core.py in get()
149 for key in toposort(dsk):
150 task = dsk[key]
--> 151 result = _execute_task(task, cache)
152 cache[key] = result
153 result = _execute_task(out, cache)
/opt/conda/lib/python3.8/site-packages/dask/core.py in _execute_task()
119 # temporaries by their reference count and can execute certain
120 # operations in-place.
--> 121 return func(*(_execute_task(a, cache) for a in args))
122 elif not ishashable(arg):
123 return arg
/opt/conda/lib/python3.8/site-packages/dask/utils.py in apply()
33 def apply(func, args, kwargs=None):
34 if kwargs:
---> 35 return func(*args, **kwargs)
36 else:
37 return func(*args)
/opt/conda/lib/python3.8/site-packages/dask/dataframe/core.py in apply_and_enforce()
5474 return meta
5475 if is_dataframe_like(df):
-> 5476 check_matching_columns(meta, df)
5477 c = meta.columns
5478 else:
/opt/conda/lib/python3.8/site-packages/dask/dataframe/utils.py in check_matching_columns()
690 def check_matching_columns(meta, actual):
691 # Need nan_to_num otherwise nan comparison gives False
--> 692 if not np.array_equal(np.nan_to_num(meta.columns), np.nan_to_num(actual.columns)):
693 extra = methods.tolist(actual.columns.difference(meta.columns))
694 missing = methods.tolist(meta.columns.difference(actual.columns))
/opt/conda/lib/python3.8/site-packages/pandas/core/generic.py in __getattr__()
5268 or name in self._accessors
5269 ):
-> 5270 return object.__getattribute__(self, name)
5271 else:
5272 if self._info_axis._can_hold_identifiers_and_holds_name(name):
pandas/_libs/properties.pyx in pandas._libs.properties.AxisProperty.__get__()
/opt/conda/lib/python3.8/site-packages/pandas/core/generic.py in __getattr__()
5268 or name in self._accessors
5269 ):
-> 5270 return object.__getattribute__(self, name)
5271 else:
5272 if self._info_axis._can_hold_identifiers_and_holds_name(name):
AttributeError: 'DataFrame' object has no attribute '_data'
The version of Pandas in my docker file is 1.0.1, so I already try upgrading Pandas (to version 1.2.2), but it didn't work, what am I doing wrong?
My guess is that you have a version mismatch somewhere. What does client.get_versions(check=True) say?
I am using Koalas and I want to change the value of a column based on a condition.
In pandas I can do that using:
import pandas as pd
df_test = pd.DataFrame({
'a': [1,2,3]
,'b': ['one','two','three']})
df_test2 = pd.DataFrame({
'c': [2,1,3]
,'d': ['one','two','three']})
df_test.loc[df_test.a.isin(df_test2['c']),'b'] = 'four'
df_test.head()
a b
0 1 four
1 2 four
2 3 four
I am trying to use the same in Koalas, but I have this error:
---------------------------------------------------------------------------
PandasNotImplementedError Traceback (most recent call last)
<ipython-input-15-814219258adb> in <module>
5 new_loans['write_offs'] = 0
6
----> 7 new_loans.loc[(new_loans['ID'].isin(userinput_write_offs['id'])),'write_offs'] = 1
8 new_loans.loc[new_loans['write_offs']==1,'is_active'] = 0
9 new_loans = new_loans.sort_values(by = ['ZOHOID','Disb Date'])
/usr/local/lib/python3.7/dist-packages/databricks/koalas/base.py in isin(self, values)
894 )
895
--> 896 return self._with_new_scol(self.spark.column.isin(list(values)))
897
898 def isnull(self) -> Union["Series", "Index"]:
/usr/local/lib/python3.7/dist-packages/databricks/koalas/series.py in __iter__(self)
5871
5872 def __iter__(self):
-> 5873 return MissingPandasLikeSeries.__iter__(self)
5874
5875 if sys.version_info >= (3, 7):
/usr/local/lib/python3.7/dist-packages/databricks/koalas/missing/__init__.py in unsupported_function(*args, **kwargs)
21 def unsupported_function(*args, **kwargs):
22 raise PandasNotImplementedError(
---> 23 class_name=class_name, method_name=method_name, reason=reason
24 )
25
PandasNotImplementedError: The method `pd.Series.__iter__()` is not implemented. If you want to collect your data as an NumPy array, use 'to_numpy()' instead.
How could I do the same operation in Koalas?
UPDATE
Following this question: Assign Koalas Column from Numpy Result I have done:
df_test.loc[df_test.a.isin(df_test2['c'].to_list()),'b'] = 'four'
But now I have this error:
---------------------------------------------------------------------------
PythonException Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/IPython/core/formatters.py in __call__(self, obj)
700 type_pprinters=self.type_printers,
701 deferred_pprinters=self.deferred_printers)
--> 702 printer.pretty(obj)
703 printer.flush()
704 return stream.getvalue()
/usr/local/lib/python3.7/dist-packages/IPython/lib/pretty.py in pretty(self, obj)
392 if cls is not object \
393 and callable(cls.__dict__.get('__repr__')):
--> 394 return _repr_pprint(obj, self, cycle)
395
396 return _default_pprint(obj, self, cycle)
/usr/local/lib/python3.7/dist-packages/IPython/lib/pretty.py in _repr_pprint(obj, p, cycle)
698 """A pprint that just redirects to the normal repr function."""
699 # Find newlines and replace them with p.break_()
--> 700 output = repr(obj)
701 lines = output.splitlines()
702 with p.group():
/usr/local/lib/python3.7/dist-packages/databricks/koalas/frame.py in __repr__(self)
10614 return self._to_internal_pandas().to_string()
10615
> 10616 pdf = self._get_or_create_repr_pandas_cache(max_display_count)
10617 pdf_length = len(pdf)
10618 pdf = pdf.iloc[:max_display_count]
/usr/local/lib/python3.7/dist-packages/databricks/koalas/frame.py in _get_or_create_repr_pandas_cache(self, n)
10606 def _get_or_create_repr_pandas_cache(self, n):
10607 if not hasattr(self, "_repr_pandas_cache") or n not in self._repr_pandas_cache:
> 10608 self._repr_pandas_cache = {n: self.head(n + 1)._to_internal_pandas()}
10609 return self._repr_pandas_cache[n]
10610
/usr/local/lib/python3.7/dist-packages/databricks/koalas/frame.py in _to_internal_pandas(self)
10602 This method is for internal use only.
10603 """
> 10604 return self._internal.to_pandas_frame
10605
10606 def _get_or_create_repr_pandas_cache(self, n):
/usr/local/lib/python3.7/dist-packages/databricks/koalas/utils.py in wrapped_lazy_property(self)
514 def wrapped_lazy_property(self):
515 if not hasattr(self, attr_name):
--> 516 setattr(self, attr_name, fn(self))
517 return getattr(self, attr_name)
518
/usr/local/lib/python3.7/dist-packages/databricks/koalas/internal.py in to_pandas_frame(self)
807 """ Return as pandas DataFrame. """
808 sdf = self.to_internal_spark_frame
--> 809 pdf = sdf.toPandas()
810 if len(pdf) == 0 and len(sdf.schema) > 0:
811 pdf = pdf.astype(
/usr/local/spark/python/pyspark/sql/pandas/conversion.py in toPandas(self)
136
137 # Below is toPandas without Arrow optimization.
--> 138 pdf = pd.DataFrame.from_records(self.collect(), columns=self.columns)
139 column_counter = Counter(self.columns)
140
/usr/local/spark/python/pyspark/sql/dataframe.py in collect(self)
594 """
595 with SCCallSiteSync(self._sc) as css:
--> 596 sock_info = self._jdf.collectToPython()
597 return list(_load_from_socket(sock_info, BatchedSerializer(PickleSerializer())))
598
/usr/local/lib/python3.7/dist-packages/py4j/java_gateway.py in __call__(self, *args)
1303 answer = self.gateway_client.send_command(command)
1304 return_value = get_return_value(
-> 1305 answer, self.gateway_client, self.target_id, self.name)
1306
1307 for temp_arg in temp_args:
/usr/local/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
132 # Hide where the exception came from that shows a non-Pythonic
133 # JVM exception message.
--> 134 raise_from(converted)
135 else:
136 raise
/usr/local/spark/python/pyspark/sql/utils.py in raise_from(e)
PythonException:
An exception was thrown from the Python worker. Please see the stack trace below.
Traceback (most recent call last):
File "/opt/spark/python/lib/pyspark.zip/pyspark/worker.py", line 589, in main
func, profiler, deserializer, serializer = read_udfs(pickleSer, infile, eval_type)
File "/opt/spark/python/lib/pyspark.zip/pyspark/worker.py", line 447, in read_udfs
udfs.append(read_single_udf(pickleSer, infile, eval_type, runner_conf, udf_index=i))
File "/opt/spark/python/lib/pyspark.zip/pyspark/worker.py", line 254, in read_single_udf
f, return_type = read_command(pickleSer, infile)
File "/opt/spark/python/lib/pyspark.zip/pyspark/worker.py", line 74, in read_command
command = serializer._read_with_length(file)
File "/opt/spark/python/lib/pyspark.zip/pyspark/serializers.py", line 172, in _read_with_length
return self.loads(obj)
File "/opt/spark/python/lib/pyspark.zip/pyspark/serializers.py", line 458, in loads
return pickle.loads(obj, encoding=encoding)
File "/opt/spark/python/lib/pyspark.zip/pyspark/cloudpickle.py", line 1110, in subimport
__import__(name)
ModuleNotFoundError: No module named 'pandas'
Why is trying to use pandas?
Koalas package exposes Pandas Like APIs on high level for the users but under the hood implementation is done using PySpark APIs.
I observed that within the stack track log you have pasted, a pandas dataframe is being created from sdf spark Dataframe using toPandas() method and assigned to pdf.
In the implementation of toPandas() function, pandas and numpy are being imported.
check line numbers 809 & 138.
/usr/local/lib/python3.7/dist-packages/databricks/koalas/internal.py in to_pandas_frame(self)
807 """ Return as pandas DataFrame. """
808 sdf = self.to_internal_spark_frame
--> 809 pdf = sdf.toPandas()
810 if len(pdf) == 0 and len(sdf.schema) > 0:
811 pdf = pdf.astype(
/usr/local/spark/python/pyspark/sql/pandas/conversion.py in toPandas(self)
136
137 # Below is toPandas without Arrow optimization.
--> 138 pdf = pd.DataFrame.from_records(self.collect(), columns=self.columns)
139 column_counter = Counter(self.columns)
140
/usr/local/spark/python/pyspark/sql/dataframe.py in collect(self)
594 """
595 with SCCallSiteSync(self._sc) as css:
--> 596 sock_info = self._jdf.collectToPython()
597 return list(_load_from_socket(sock_info, BatchedSerializer(PickleSerializer())))
598
you can check out the implementation of toPandas() function at the following link:
https://github.com/apache/spark/blob/master/python/pyspark/sql/pandas/conversion.py