Dask dataframe merge memory error with large csv files - python

Here's a simplified version of my code.
import dask
import dask.dataframe as dask_frame
from dask.distributed import Client, LocalCluster
def main():
cluster = LocalCluster(n_workers=4, threads_per_worker=2)
client = Client(cluster)
csv_path_one = "" # both have 70 columns and around 70 million rows. at a size of about 25 gigabytes
csv_path_two = ""
# the columns are a mix of ints floats datetimes and strings
# almost all string lengths are less than 15 two of the longest string columns have a max length of 70
left_df = dask_frame.read_csv(csv_path_one, sep="|", quotechar="+", encoding="Latin-1", dtype="object")
right_df = dask_frame.read_csv(csv_path_one, sep=",", quotechar="\"", encoding="utf-8", dtype="object")
cand_keys = [""] # I have 3
merged = dask_frame.merge(left_df, right_df, how='outer', on=cand_keys, suffixes=("_L", "_R"),indicator=True)
missing_mask = merged._merge != 'both'
missing_findings: dask_frame.DataFrame = merged.loc[missing_mask, cand_keys + ["_merge"]]
print(f"Running {client}")
missing_findings.to_csv("results/findings-*.csv")
cluster.close()
client.close()
if __name__ == '__main__':
main()
This example never finishes, dask gets to a certain part then one or more workers instantly exceed the memory limit and the nanny kills them and rolls back all of the worker's progress
Looking at the diagnostics page usually the memory spikes happen about halfway through the shuffle-split tasks.
I'm running Dask 2.9.1 on Windows.
I can update Dask but it's pain with my current setup and I don't know if it'll fix my issue

An Update to 2.15 fixed this issue.

Related

map.pool running out of memory - when to close and join

I am parallelizing ingestion and analysis of a dataset using Pool.map. However I keep running into 'an out of memory' error. This is despite me working on a cluster with 100GB of memory and working with a compressed file of ~25gb (the uncompressed is likely larger than 100GB). I believe I am running out of memory because I am joining and closing processes incorrectly i.e. All the chunks are being stored in memory. Here is my code:
##load df
df_chunk = pd.read_csv(f'{file}', sep = '\t' , chunksize = 10000)
## parallel process
pool = Pool(16)
processed_results = pool.map(conduct_analysis, df_chunk)
## merge all results together
df_all = reduce(merge_results, processed_results)
pool.close()
pool.join()
With the following function definition for the analysis:
def conduct_analysis(df):
##dictionary to store results
pvalue = {}
##clean columns
df = df.replace('./.', '0/0')
##run analysis
for group in df.groupby(pos):
sample = pd.DataFrame(group[1]['age_of_onset'])
#ANOVA test
f_val, p_val = stats.f_oneway(*sample)
p_value[pos] = p_val[0]
return p_value
Note reduce(merge results) just takes in the mapped results and joins them together.
I can provide output examples too but i believe this is not necessary for my issue. I believe I am running out of memory as the function calls are not being closed when the new one is being opened. is there a way to close the chunk but still retain the output? If I run this code in a for loop one chunk at a time I do not get such an error.
Thanks!

Read a lot of data using pool.map ('error("'i' format requires -2147483648 <= number <= 2147483647")')

I'm reading data from databases. I need to read from several servers (nodes) simultaniuosly, so I want to use pool.map.
I'm trying to do this way:
import pathos.pools as pp
import pandas as pd
import urllib
class DataProvider():
def __init__(self, hosts):
self.hosts_read = hosts
def read_data(self, host_index):
'''
Read data from current node
'''
limit = 1000000
host = self.hosts_read[host_index]
query = f"select FIELD1 from table_name limit {limit}"
url = urllib.parse.urlencode({'query': query})
df = pd.io.parsers.read_csv(f'http://{host}:8123/?{url}',
sep="\t", names=['FIELD1'], low_memory=False)
return df
def pool_read(self, num_workers):
'''
Read from data using Pool of workers.
Return list of lists - every list is a data from current worker.
'''
pool = pp.ProcessPool(num_workers)
result = pool.map(self.read_data, range(len(self.hosts_read)))
return result
if __name__ == '__main__':
provider = DataProvider(host=['server01.com', 'server02.com'])
data = provider.pool_read(num_workers=n_cpu)
It works perfect while limit is not so much (below 4 millions). And crushes if it is bigger:
multiprocess.pool.MaybeEncodingError: Error sending result:
'[my_pandas_dataframe]'. Reason: 'error("'i' format requires
-2147483648 <= number <= 2147483647")'
I found some answers about it: it is because we cannot return from the pool peace of data bigger than 2 GB. For example: SO link. But there is no any ideas or solutions, how to work if I need load bigger parts!
P.S. I use pathos module but it is not important here - the same error for multiprocessing module too.

RAM consumption by pandas DataFrame

I am trying to work with around 100 csv files to do a time series analysis.
To build an efficient algorithm to use I've structured my data read_csv function such that it only reads all the files at once and don't have to repeat the same process again and again. To explain further following is my code:
start_date = '2016-06-01'
end_date = '2017-09-02'
allocation = 170000
#contains 100 symbols
usesymbols = ['']
cost_matrix = []
def data():
dates=pd.date_range(start_date,end_date)
df=pd.DataFrame(index=dates)
for symbol in usesymbols:
df_temp=pd.read_csv('/home/furqan/Desktop/python_data/{}.csv'.format(str(symbol)),usecols=['Date','Close'],
parse_dates=True,index_col='Date',na_values=['nan'])
df_temp = df_temp.rename(columns={'Close': symbol})
df=df.join(df_temp)
df=df.fillna(method='ffill')
df=df.fillna(method='bfill')
return df
def powerset(iterable):
s = list(iterable)
return chain.from_iterable(combinations(s, r) for r in range(1, len(s)+1))
power_set = list(powerset(usesymbols))
dataframe = data()
Problem is that if I run the above code with 15 symbols it works perfectly.
But that's not sufficient, I want to use 100 symbols.
If I run the code with 100 items in usesymbols, my RAM is used up completely and the machine freezes.
Is there anything that can be done to avoid this situation?
Edited Part:
1) I've 16 GB RAM.
2) the issue is with the variable power_set, if I don't call powerset function data gets retrieved easily.
DataFrame.memory_usage(index=False)
Return:
sizes : Series
A series with column names as index and memory usage of columns with units of bytes.

Huge quantity of Dask computations causing memory issues

I am working on a task where I need to determine where two geospatial points are within 250 meters of each other and occur within 20 minutes of each other. My data set is approximately 1.2M rows and 10 columns. So, I need to determine a distance, time difference, and whether they meet my criteria by going through 1.2M**2 calculations.
I have been able to run the code below where I create 10,000 Dask objects to compute without problem. However, when I attempt to test 100,000 objects Dask runs up against memory limitations and I see significant CPU usage for swap. To be clear, I'm running this on a 32 core node with 125 GB of memory.
Admittedly, I'm quite new to Dask, so I'd like to know: is there a better way to solve this problem than processing in 10,000 row chunks?
#!/usr/bin/env python
import pandas as pd
import numpy as np
import dask.dataframe as dd
from dask.array import sqrt
import time
import multiprocessing as mp
df = pd.read_hdf(...) # Used to select single item for comparison
ddf = dd.read_hdf(...) # Used for Dask operations
def distCheck(item,df=ddf):
'''
Determine if any records in df are within 250m of item and within 20
minutes of item. Return Dask object for calculation.
'''
dist = sqrt(((ddf.LCC_x1-item.LCC_x1)**2+(ddf.LCC_y1-item.LCC_y1)**2))
distcrit = dist[dist < 250]
delta = (ddf.Date - item.Date).abs()
timecrit = delta[delta < np.timedelta64(20,'m')]
res1 = ddf.copy()
res1['dist'] = dist
res1['delta'] = delta
res1 = res1.loc[(distcrit.index) & (timecrit.index) & (idcrit.index)]
res1['MatchMMSI'] = item.MMSI
res1['MatchVoy'] = item.Voyage
out = res1
return out
def getDaskCalls(start,stop):
'''
Get Dask objects to assess temporal and spatial proximity for df
indices from start to stop.
'''
# Kick off multiprocessing pool, submit, and close
pool = mp.Pool(processes=32)
daskers = []
for i in range(start,stop):
result = pool.apply_async(distCheck,args=(df.iloc[i,:],ddf,))
daskers.append(result)
dasky = [i.get() for i in daskers]
pool.close()
return dasky
def runDask(calls):
result = pd.DataFrame([],columns=calls[0].columns)
output = dd.compute(calls)
result = pd.concat([result]+[i for i in output[0] if i.shape[0] != 0])
return result
###
### Process
###
# Get initial timestamp
start = time.time()
# Create Dask Calls & determine duration
dcalls = getDaskCalls(0,10000)
callsCreated = time.time()
# Print time required to create calls
print("Dask Calls Created.")
print(callsCreated-start)
# Compute the calls with Dask
print("Computing...")
result = runDask(dcalls)
# Print the time for computation
computation = time.time()
print(" ...Done.")
print(computation-callsCreated)

Pandas and Multiprocessing Memory Management: Splitting a DataFrame into Multiple Chunks

I have to process a huge pandas.DataFrame (several tens of GB) on a row by row bases, where each row operation is quite lengthy (a couple of tens of milliseconds). So I had the idea to split up the frame into chunks and process each chunk in parallel using multiprocessing. This does speed-up the task, but the memory consumption is a nightmare.
Although each child process should in principle only consume a tiny chunk of the data, it needs (almost) as much memory as the original parent process that contained the original DataFrame. Even deleting the used parts in the parent process does not help.
I wrote a minimal example that replicates this behavior. The only thing it does is creating a large DataFrame with random numbers, chunk it into little pieces with at most 100 rows, and simply print some information about the DataFrame during multiprocessing (here via a mp.Pool of size 4).
The main function that is executed in parallel:
def just_wait_and_print_len_and_idx(df):
"""Waits for 5 seconds and prints df length and first and last index"""
# Extract some info
idx_values = df.index.values
first_idx, last_idx = idx_values[0], idx_values[-1]
length = len(df)
pid = os.getpid()
# Waste some CPU cycles
time.sleep(1)
# Print the info
print('First idx {}, last idx {} and len {} '
'from process {}'.format(first_idx, last_idx, length, pid))
The helper generator to chunk a DataFrame into little pieces:
def df_chunking(df, chunksize):
"""Splits df into chunks, drops data of original df inplace"""
count = 0 # Counter for chunks
while len(df):
count += 1
print('Preparing chunk {}'.format(count))
# Return df chunk
yield df.iloc[:chunksize].copy()
# Delete data in place because it is no longer needed
df.drop(df.index[:chunksize], inplace=True)
And the main routine:
def main():
# Job parameters
n_jobs = 4 # Poolsize
size = (10000, 1000) # Size of DataFrame
chunksize = 100 # Maximum size of Frame Chunk
# Preparation
df = pd.DataFrame(np.random.rand(*size))
pool = mp.Pool(n_jobs)
print('Starting MP')
# Execute the wait and print function in parallel
pool.imap(just_wait_and_print_len_and_idx, df_chunking(df, chunksize))
pool.close()
pool.join()
print('DONE')
The standard output looks like this:
Starting MP
Preparing chunk 1
Preparing chunk 2
First idx 0, last idx 99 and len 100 from process 9913
First idx 100, last idx 199 and len 100 from process 9914
Preparing chunk 3
First idx 200, last idx 299 and len 100 from process 9915
Preparing chunk 4
...
DONE
The Problem:
The main process needs about 120MB of memory. However, the child processes of the pool need the same amount of memory, although they only contain 1% of the original DataFame (chunks of size 100 vs original length of 10000). Why?
What can I do about it? Does Python (3) send the whole DataFrame to each child process despite my chunking? Is that a problem of pandas memory management or the fault of multiprocessing and data pickling? Thanks!
Whole script for simple copy and paste in case you want to try it yourself:
import multiprocessing as mp
import pandas as pd
import numpy as np
import time
import os
def just_wait_and_print_len_and_idx(df):
"""Waits for 5 seconds and prints df length and first and last index"""
# Extract some info
idx_values = df.index.values
first_idx, last_idx = idx_values[0], idx_values[-1]
length = len(df)
pid = os.getpid()
# Waste some CPU cycles
time.sleep(1)
# Print the info
print('First idx {}, last idx {} and len {} '
'from process {}'.format(first_idx, last_idx, length, pid))
def df_chunking(df, chunksize):
"""Splits df into chunks, drops data of original df inplace"""
count = 0 # Counter for chunks
while len(df):
count += 1
print('Preparing chunk {}'.format(count))
# Return df chunk
yield df.iloc[:chunksize].copy()
# Delete data in place because it is no longer needed
df.drop(df.index[:chunksize], inplace=True)
def main():
# Job parameters
n_jobs = 4 # Poolsize
size = (10000, 1000) # Size of DataFrame
chunksize = 100 # Maximum size of Frame Chunk
# Preparation
df = pd.DataFrame(np.random.rand(*size))
pool = mp.Pool(n_jobs)
print('Starting MP')
# Execute the wait and print function in parallel
pool.imap(just_wait_and_print_len_and_idx, df_chunking(df, chunksize))
pool.close()
pool.join()
print('DONE')
if __name__ == '__main__':
main()
Ok, so I figured it out after the hint by Sebastian Opałczyński in the comments.
The problem is that the child processes are forked from the parent, so all of them contain a reference to the original DataFrame. However, the frame is manipulated in the original process, so the copy-on-write behavior kills the whole thing slowly and eventually when the limit of the physical memory is reached.
There is a simple solution: Instead of pool = mp.Pool(n_jobs), I use the new context feature of multiprocessing:
ctx = mp.get_context('spawn')
pool = ctx.Pool(n_jobs)
This guarantees that the Pool processes are just spawned and not forked from the parent process. Accordingly, none of them has access to the original DataFrame and all of them only need a tiny fraction of the parent's memory.
Note that the mp.get_context('spawn') is only available in Python 3.4 and newer.
A better implementation is just to use the pandas implementation of chunked dataframe as a generator and feed it into the "pool.imap" function
pd.read_csv('<filepath>.csv', chucksize=<chunksize>)
https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.read_csv.html
Benefit: It doesn't read in the whole df in your main process (save memory). Each child process will be pointed the chunk it needs only. --> solve the child memory issue.
Overhead: It requires you to save your df as csv first and read it in again using pd.read_csv --> I/O time.
Note: chunksize is not available to pd.read_pickle or other loading methods that are compressed on storage.
def main():
# Job parameters
n_jobs = 4 # Poolsize
size = (10000, 1000) # Size of DataFrame
chunksize = 100 # Maximum size of Frame Chunk
# Preparation
df = pd.DataFrame(np.random.rand(*size))
pool = mp.Pool(n_jobs)
print('Starting MP')
# Execute the wait and print function in parallel
df_chunked = pd.read_csv('<filepath>.csv',chunksize = chunksize) # modified
pool.imap(just_wait_and_print_len_and_idx, df_chunking(df, df_chunked) # modified
pool.close()
pool.join()
print('DONE')

Categories