0

For some dataset group_1 I need to iterate over all rows k times for robustness and find a matching random sample of another data frame group_2 according to some criteria expressed as data frame columns. Unfortunately, this is fairly slow. How can I improve performance?

The bottleneck is the apply-ed function, i.e. randomMatchingCondition.

import tqdm                                                                                                   
import numpy as np
import pandas as pd
from tqdm import tqdm
tqdm.pandas()

seed = 47
np.random.seed(seed)

###################################################################
# generate dummy data
size = 10000
df = pd.DataFrame({i: np.random.randint(1,100,size=size) for i in ['metric']})
df['label'] =  np.random.randint(0,2, size=size)
df['group_1'] =  pd.Series(np.random.randint(1,12, size=size)).astype(object)
df['group_2'] =  pd.Series(np.random.randint(1,10, size=size)).astype(object)

group_0 = df[df['label'] == 0]
group_0 = group_0.reset_index(drop=True)
group_0 = group_0.rename(index=str, columns={"metric": "metric_group_0"})

join_columns_enrich = ['group_1', 'group_2']
join_real = ['metric_group_0']
join_real.extend(join_columns_enrich)
group_0 = group_0[join_real]
display(group_0.head())
group_1 = df[df['label'] == 1]
group_1 = group_1.reset_index(drop=True)
display(group_1.head())

###################################################################
# naive find random element matching condition
def randomMatchingCondition(original_element, group_0, join_columns, random_state):
    limits_dict = original_element[join_columns_enrich].to_dict()
    query = ' & '.join([f"{k} == {v}" for k, v in limits_dict.items()])
    candidates = group_0.query(query)
    if len(candidates) > 0:
        return candidates.sample(n=1, random_state=random_state)['metric_group_0'].values[0]
    else:
        return np.nan
###################################################################
# iterate over pandas dataframe k times for more robust sampling
k = 3
resulting_df = None
for i in range(1, k+1):
    group_1['metric_group_0'] = group_1.progress_apply(randomMatchingCondition,
                                                                  args=[group_0, join_columns_enrich, None],
                                                                  axis = 1)
    group_1['run'] = i
    if resulting_df is None:
        resulting_df = group_1.copy()
    else:
        resulting_df = pd.concat([resulting_df, group_1])
resulting_df.head()

Experimenting with pre-sorting the data:

group_0 = group_0.sort_values(join_columns_enrich)
group_1 = group_1.sort_values(join_columns_enrich)

does not show any difference.

Georg Heiler
  • 16,916
  • 36
  • 162
  • 292
  • I think the bottleneck is the `for` loop here. `apply` is surely bad but a `for` loop on top of that is purely evil IMO – enterML May 12 '19 at 07:42

2 Answers2

0

  1. IIUC you want to end up with k number of random samples for each row (combination of metrics) in your input dataframe. So why not candidates.sample(n=k, ...), and get rid of the for loop? Alternatively you could concatenate you dataframe k times with pd.concat([group1] * k).

  2. It depends on your real data but I would give a shot for grouping the input dataframe by metric columns with group1.groupby(join_columns_enrich) (if their cardinality is sufficiently low), and apply the random sampling on these groups, picking k * len(group.index) random samples for each. groupby is expensive, OTOH you might save a lot on the iteration/sampling once it's done.

somiandras
  • 227
  • 2
  • 7
0

@smiandras, you are correct. Getting rid of the for loop is important.

Variant 1: multiple samples:

def randomMatchingCondition(original_element, group_0, join_columns, k, random_state):
    limits_dict = original_element[join_columns_enrich].to_dict()
    query = ' & '.join([f"{k} == {v}" for k, v in limits_dict.items()])
    candidates = group_0.query(query)
    if len(candidates) > 0:
        return candidates.sample(n=k, random_state=random_state, replace=True)['metric_group_0'].values
    else:
        return np.nan
###################################################################
# iterate over pandas dataframe k times for more robust sampling
k = 3
resulting_df = None

#######################
# trying to improve performance: sort both dataframes
group_0 = group_0.sort_values(join_columns_enrich)
group_1 = group_1.sort_values(join_columns_enrich)
#######################

group_1['metric_group_0'] = group_1.progress_apply(randomMatchingCondition,
                                                   args=[group_0, join_columns_enrich, k, None],
                                                   axis = 1)
print(group_1.isnull().sum())
group_1 = group_1[~group_1.metric_group_0.isnull()]
display(group_1.head())

s=pd.DataFrame({'metric_group_0':np.concatenate(group_1.metric_group_0.values)},index=group_1.index.repeat(group_1.metric_group_0.str.len()))
s = s.join(group_1.drop('metric_group_0',1),how='left')
s['pos_in_array'] = s.groupby(s.index).cumcount()
s.head()

Variant 2: all possible samples optimized by native JOIN operation.

WARN this is a bit unsafe as it might generate a gigantic number of rows:

size = 1000
df = pd.DataFrame({i: np.random.randint(1,100,size=size) for i in ['metric']})
df['label'] =  np.random.randint(0,2, size=size)
df['group_1'] =  pd.Series(np.random.randint(1,12, size=size)).astype(object)
df['group_2'] =  pd.Series(np.random.randint(1,10, size=size)).astype(object)

group_0 = df[df['label'] == 0]
group_0 = group_0.reset_index(drop=True)
join_columns_enrich = ['group_1', 'group_2']
join_real = ['metric']
join_real.extend(join_columns_enrich)
group_0 = group_0[join_real]
display(group_0.head())
group_1 = df[df['label'] == 1]
group_1 = group_1.reset_index(drop=True)
display(group_1.head())
df = group_1.merge(group_0, on=join_columns_enrich)
display(df.head())
print(group_1.shape)
df.shape
Georg Heiler
  • 16,916
  • 36
  • 162
  • 292