Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Pandas based logistic regression #316

Merged
merged 19 commits into from
Dec 23, 2020
Merged

Pandas based logistic regression #316

Changes from 1 commit
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
6a2a976
initial work
henrydavidge Dec 1, 2020
770c621
Merge branch 'master' of github.com:projectglow/glow into logistic-re…
henrydavidge Dec 3, 2020
9df2d0f
add file
henrydavidge Dec 3, 2020
95241a3
workign score test
henrydavidge Dec 10, 2020
ad8a137
seems to work
henrydavidge Dec 10, 2020
ce7f08f
continue
henrydavidge Dec 11, 2020
13f28a7
offset support; more tests
henrydavidge Dec 11, 2020
8a9a46b
delete lin_reg.py
henrydavidge Dec 11, 2020
62562e9
add docs, few more tests
henrydavidge Dec 12, 2020
c9dfad1
add test file
henrydavidge Dec 12, 2020
d753b19
fix last test
henrydavidge Dec 12, 2020
b48975d
Fix docs, tests
henrydavidge Dec 21, 2020
daa8766
memory limit
henrydavidge Dec 21, 2020
fd2edd0
try explicitly broadcasting
henrydavidge Dec 21, 2020
cc47711
clean up missingness tests
henrydavidge Dec 22, 2020
97b0a5a
update environment
henrydavidge Dec 22, 2020
f15c0eb
undo explicit broadcast
henrydavidge Dec 22, 2020
138559c
fix typo
henrydavidge Dec 22, 2020
3ea40cd
f97b0a5aee82445baa8bb4770a4a7ed0437dc6b13ormatting; karen's comment
henrydavidge Dec 23, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
fix last test 
Signed-off-by: Henry D <[email protected]>
  • Loading branch information
@henrydavidge
henrydavidge committed Dec 12, 2020
commit d753b19f535d95ef0702be1b8a99e648cf05ea39
30 changes: 17 additions & 13 deletions python/glow/wgr/linear_model/tests/test_logistic_regression.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,12 +12,16 @@
# See the License for the specific language governing permissions and
# limitations under the License.

from pyspark.sql.pandas.functions import PandasUDFType
from glow.wgr.linear_model.functions import *
from glow.wgr.linear_model.logistic_udfs import *
from glow.wgr.linear_model.logistic_model import *
from pyspark.sql import functions as f
import json
import math
import pytest
import pandas as pd
import numpy as np

data_root = 'test-data/wgr/logistic-regression'

Expand Down Expand Up @@ -58,7 +62,7 @@ def test_map_irls_eqn(spark):
with open(f'{data_root}/test_map_irls_eqn.json') as json_file:
test_values = json.load(json_file)
map_key_pattern = ['sample_block', 'label', 'alpha_name']
map_udf = pandas_udf(
map_udf = f.pandas_udf(
lambda key, pdf: map_irls_eqn(key, map_key_pattern, pdf, labeldf, sample_blocks, covdf,
beta_cov_dict, maskdf, alphas), irls_eqn_struct,
PandasUDFType.GROUPED_MAP)
Expand Down Expand Up @@ -92,13 +96,13 @@ def test_reduce_irls_eqn(spark):
map_key_pattern = ['sample_block', 'label', 'alpha_name']
reduce_key_pattern = ['header_block', 'header', 'label', 'alpha_name']

map_udf = pandas_udf(
map_udf = f.pandas_udf(
lambda key, pdf: map_irls_eqn(key, map_key_pattern, pdf, labeldf, sample_blocks, covdf,
beta_cov_dict, maskdf, alphas), irls_eqn_struct,
PandasUDFType.GROUPED_MAP)

reduce_udf = pandas_udf(lambda key, pdf: reduce_irls_eqn(key, reduce_key_pattern, pdf),
irls_eqn_struct, PandasUDFType.GROUPED_MAP)
reduce_udf = f.pandas_udf(lambda key, pdf: reduce_irls_eqn(key, reduce_key_pattern, pdf),
irls_eqn_struct, PandasUDFType.GROUPED_MAP)

reducedf = lvl1df \
.withColumn('alpha_name', f.explode(f.array([f.lit(n) for n in alphas.keys()]))) \
Expand Down Expand Up @@ -133,15 +137,15 @@ def test_solve_irls_eqn(spark):
reduce_key_pattern = ['header_block', 'header', 'label', 'alpha_name']
model_key_pattern = ['sample_block', 'label', 'alpha_name']

map_udf = pandas_udf(
map_udf = f.pandas_udf(
lambda key, pdf: map_irls_eqn(key, map_key_pattern, pdf, labeldf, sample_blocks, covdf,
beta_cov_dict, maskdf, alphas), irls_eqn_struct,
PandasUDFType.GROUPED_MAP)

reduce_udf = pandas_udf(lambda key, pdf: reduce_irls_eqn(key, reduce_key_pattern, pdf),
irls_eqn_struct, PandasUDFType.GROUPED_MAP)
reduce_udf = f.pandas_udf(lambda key, pdf: reduce_irls_eqn(key, reduce_key_pattern, pdf),
irls_eqn_struct, PandasUDFType.GROUPED_MAP)

model_udf = pandas_udf(
model_udf = f.pandas_udf(
lambda key, pdf: solve_irls_eqn(key, model_key_pattern, pdf, labeldf, alphas, covdf),
model_struct, PandasUDFType.GROUPED_MAP)

Expand Down Expand Up @@ -183,19 +187,19 @@ def test_score_logistic_model(spark):
model_key_pattern = ['sample_block', 'label', 'alpha_name']
score_key_pattern = ['sample_block', 'label']

map_udf = pandas_udf(
map_udf = f.pandas_udf(
lambda key, pdf: map_irls_eqn(key, map_key_pattern, pdf, labeldf, sample_blocks, covdf,
beta_cov_dict, maskdf, alphas), irls_eqn_struct,
PandasUDFType.GROUPED_MAP)

reduce_udf = pandas_udf(lambda key, pdf: reduce_irls_eqn(key, reduce_key_pattern, pdf),
irls_eqn_struct, PandasUDFType.GROUPED_MAP)
reduce_udf = f.pandas_udf(lambda key, pdf: reduce_irls_eqn(key, reduce_key_pattern, pdf),
irls_eqn_struct, PandasUDFType.GROUPED_MAP)

model_udf = pandas_udf(
model_udf = f.pandas_udf(
lambda key, pdf: solve_irls_eqn(key, model_key_pattern, pdf, labeldf, alphas, covdf),
model_struct, PandasUDFType.GROUPED_MAP)

score_udf = pandas_udf(
score_udf = f.pandas_udf(
lambda key, pdf: score_models(key,
score_key_pattern,
pdf,
Expand Down