yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-12-27 23:18:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

remove redundant imports (#426)

Browse Source 
* remove redundant imports

* getting ride of hf dataset
This commit is contained in:
Xueqing Liu 2022-01-24 17:24:14 -05:00 committed by GitHub
parent 6a7caa6a3d
commit 4814091d87
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 174 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
flaml/nlp/huggingface/switch_head_auto.py
View File

@ -5,14 +5,10 @@ import transformers
if transformers.__version__.startswith("3"):
from transformers.modeling_electra import ElectraClassificationHead
from transformers.modeling_roberta import RobertaClassificationHead
from transformers.models.electra.modeling_electra import ElectraForTokenClassification
from transformers.models.roberta.modeling_roberta import RobertaForTokenClassification
else:
from transformers.models.electra.modeling_electra import ElectraClassificationHead
from transformers.models.roberta.modeling_roberta import RobertaClassificationHead
from transformers.models.electra.modeling_electra import ElectraForTokenClassification
from transformers.models.roberta.modeling_roberta import RobertaForTokenClassification
MODEL_CLASSIFICATION_HEAD_MAPPING = OrderedDict(
[

66
test/nlp/test_autohf.py
View File

@ -7,19 +7,61 @@ import shutil
@pytest.mark.skipif(sys.platform == "darwin", reason="do not run on mac os")
def test_hf_data():
from flaml import AutoML
import requests
from datasets import load_dataset
import pandas as pd
try:
train_dataset = load_dataset("glue", "mrpc", split="train[:1%]").to_pandas()
dev_dataset = (
load_dataset("glue", "mrpc", split="train[1%:2%]").to_pandas().iloc[:4]
)
test_dataset = (
load_dataset("glue", "mrpc", split="test[2%:3%]").to_pandas().iloc[:4]
)
except requests.exceptions.ConnectionError:
return
train_data = {
"sentence1": [
'Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .',
"Yucaipa owned Dominick 's before selling the chain to Safeway in 1998 for $ 2.5 billion .",
"They had published an advertisement on the Internet on June 10 , offering the cargo for sale , he added .",
"Around 0335 GMT , Tab shares were up 19 cents , or 4.4 % , at A $ 4.56 , having earlier set a record high of A $ 4.57 .",
],
"sentence2": [
'Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .',
"Yucaipa bought Dominick 's in 1995 for $ 693 million and sold it to Safeway for $ 1.8 billion in 1998 .",
"On June 10 , the ship 's owners had published an advertisement on the Internet , offering the explosives for sale .",
"Tab shares jumped 20 cents , or 4.6 % , to set a record closing high at A $ 4.57 .",
],
"label": [1, 0, 1, 0],
"idx": [0, 1, 2, 3],
}
train_dataset = pd.DataFrame(train_data)
dev_data = {
"sentence1": [
"The stock rose $ 2.11 , or about 11 percent , to close Friday at $ 21.51 on the New York Stock Exchange .",
"Revenue in the first quarter of the year dropped 15 percent from the same period a year earlier .",
"The Nasdaq had a weekly gain of 17.27 , or 1.2 percent , closing at 1,520.15 on Friday .",
"The DVD-CCA then appealed to the state Supreme Court .",
],
"sentence2": [
"PG & E Corp. shares jumped $ 1.63 or 8 percent to $ 21.03 on the New York Stock Exchange on Friday .",
"With the scandal hanging over Stewart 's company , revenue the first quarter of the year dropped 15 percent from the same period a year earlier .",
"The tech-laced Nasdaq Composite .IXIC rallied 30.46 points , or 2.04 percent , to 1,520.15 .",
"The DVD CCA appealed that decision to the U.S. Supreme Court .",
],
"label": [1, 1, 0, 1],
"idx": [4, 5, 6, 7],
}
dev_dataset = pd.DataFrame(dev_data)
test_data = {
"sentence1": [
"That compared with $ 35.18 million , or 24 cents per share , in the year-ago period .",
"Shares of Genentech , a much larger company with several products on the market , rose more than 2 percent .",
"Legislation making it harder for consumers to erase their debts in bankruptcy court won overwhelming House approval in March .",
"The Nasdaq composite index increased 10.73 , or 0.7 percent , to 1,514.77 .",
],
"sentence2": [
"Earnings were affected by a non-recurring $ 8 million tax benefit in the year-ago period .",
"Shares of Xoma fell 16 percent in early trade , while shares of Genentech , a much larger company with several products on the market , were up 2 percent .",
"Legislation making it harder for consumers to erase their debts in bankruptcy court won speedy , House approval in March and was endorsed by the White House .",
"The Nasdaq Composite index , full of technology stocks , was lately up around 18 points .",
],
"label": [0, 0, 0, 0],
"idx": [8, 10, 11, 12],
}
test_dataset = pd.DataFrame(test_data)
custom_sent_keys = ["sentence1", "sentence2"]
label_key = "label"

41
test/nlp/test_autohf_classificationhead.py
View File

@ -1,17 +1,36 @@
def test_classification_head():
from flaml import AutoML
import requests
from datasets import load_dataset
import pandas as pd
try:
train_dataset = (
load_dataset("emotion", split="train[:1%]").to_pandas().iloc[0:10]
)
dev_dataset = (
load_dataset("emotion", split="train[1%:2%]").to_pandas().iloc[0:10]
)
except requests.exceptions.ConnectionError:
return
train_data = {
"text": [
"i didnt feel humiliated",
"i can go from feeling so hopeless to so damned hopeful just from being around someone who cares and is awake",
"im grabbing a minute to post i feel greedy wrong",
"i am ever feeling nostalgic about the fireplace i will know that it is still on the property",
"i am feeling grouchy",
"ive been feeling a little burdened lately wasnt sure why that was",
"ive been taking or milligrams or times recommended amount and ive fallen asleep a lot faster but i also feel like so funny",
"i feel as confused about life as a teenager or as jaded as a year old man",
"i have been with petronas for years i feel that petronas has performed well and made a huge profit",
"i feel romantic too",
"i feel like i have to make the suffering i m seeing mean something",
"i do feel that running is a divine experience and that i can expect to have some type of spiritual encounter",
],
"label": [0, 0, 3, 2, 3, 0, 5, 4, 1, 2, 0, 1],
}
train_dataset = pd.DataFrame(train_data)
dev_data = {
"text": [
"i think it s the easiest time of year to feel dissatisfied",
"i feel low energy i m just thirsty",
"i have immense sympathy with the general point but as a possible proto writer trying to find time to write in the corners of life and with no sign of an agent let alone a publishing contract this feels a little precious",
"i do not feel reassured anxiety is on each side",
],
"label": [3, 0, 1, 1],
}
dev_dataset = pd.DataFrame(dev_data)
custom_sent_keys = ["text"]
label_key = "label"

45
test/nlp/test_autohf_custom_metric.py
View File

@ -42,16 +42,43 @@ def custom_metric(
@pytest.mark.skipif(sys.platform == "darwin", reason="do not run on mac os")
def test_custom_metric():
from flaml import AutoML
import requests
from datasets import load_dataset
import pandas as pd
try:
train_dataset = (
load_dataset("glue", "mrpc", split="train").to_pandas().iloc[0:4]
)
dev_dataset = load_dataset("glue", "mrpc", split="train").to_pandas().iloc[0:4]
except requests.exceptions.ConnectionError:
return
train_data = {
"sentence1": [
'Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .',
"Yucaipa owned Dominick 's before selling the chain to Safeway in 1998 for $ 2.5 billion .",
"They had published an advertisement on the Internet on June 10 , offering the cargo for sale , he added .",
"Around 0335 GMT , Tab shares were up 19 cents , or 4.4 % , at A $ 4.56 , having earlier set a record high of A $ 4.57 .",
],
"sentence2": [
'Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .',
"Yucaipa bought Dominick 's in 1995 for $ 693 million and sold it to Safeway for $ 1.8 billion in 1998 .",
"On June 10 , the ship 's owners had published an advertisement on the Internet , offering the explosives for sale .",
"Tab shares jumped 20 cents , or 4.6 % , to set a record closing high at A $ 4.57 .",
],
"label": [1, 0, 1, 0],
"idx": [0, 1, 2, 3],
}
train_dataset = pd.DataFrame(train_data)
dev_data = {
"sentence1": [
"The stock rose $ 2.11 , or about 11 percent , to close Friday at $ 21.51 on the New York Stock Exchange .",
"Revenue in the first quarter of the year dropped 15 percent from the same period a year earlier .",
"The Nasdaq had a weekly gain of 17.27 , or 1.2 percent , closing at 1,520.15 on Friday .",
"The DVD-CCA then appealed to the state Supreme Court .",
],
"sentence2": [
"PG & E Corp. shares jumped $ 1.63 or 8 percent to $ 21.03 on the New York Stock Exchange on Friday .",
"With the scandal hanging over Stewart 's company , revenue the first quarter of the year dropped 15 percent from the same period a year earlier .",
"The tech-laced Nasdaq Composite .IXIC rallied 30.46 points , or 2.04 percent , to 1,520.15 .",
"The DVD CCA appealed that decision to the U.S. Supreme Court .",
],
"label": [1, 1, 0, 1],
"idx": [4, 5, 6, 7],
}
dev_dataset = pd.DataFrame(dev_data)
custom_sent_keys = ["sentence1", "sentence2"]
label_key = "label"

26
test/nlp/test_autohf_cv.py
View File

@ -5,15 +5,25 @@ import pytest
@pytest.mark.skipif(sys.platform == "darwin", reason="do not run on mac os")
def test_cv():
from flaml import AutoML
import requests
from datasets import load_dataset
import pandas as pd
try:
train_dataset = (
load_dataset("glue", "mrpc", split="train[:1%]").to_pandas().iloc[0:4]
)
except requests.exceptions.ConnectionError:
return
train_data = {
"sentence1": [
'Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .',
"Yucaipa owned Dominick 's before selling the chain to Safeway in 1998 for $ 2.5 billion .",
"They had published an advertisement on the Internet on June 10 , offering the cargo for sale , he added .",
"Around 0335 GMT , Tab shares were up 19 cents , or 4.4 % , at A $ 4.56 , having earlier set a record high of A $ 4.57 .",
],
"sentence2": [
'Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .',
"Yucaipa bought Dominick 's in 1995 for $ 693 million and sold it to Safeway for $ 1.8 billion in 1998 .",
"On June 10 , the ship 's owners had published an advertisement on the Internet , offering the explosives for sale .",
"Tab shares jumped 20 cents , or 4.6 % , to set a record closing high at A $ 4.57 .",
],
"label": [1, 0, 1, 0],
"idx": [0, 1, 2, 3],
}
train_dataset = pd.DataFrame(train_data)
custom_sent_keys = ["sentence1", "sentence2"]
label_key = "label"

45
test/nlp/test_autohf_regression.py
View File

@ -9,16 +9,43 @@ def test_regression():
except ImportError:
return
from flaml import AutoML
import requests
from datasets import load_dataset
import pandas as pd
try:
train_dataset = load_dataset("glue", "stsb", split="train[:2%]").to_pandas()
dev_dataset = (
load_dataset("glue", "stsb", split="train[2%:3%]").to_pandas().iloc[:32]
)
except requests.exceptions.ConnectionError:
return
train_data = {
"sentence1": [
"A plane is taking off.",
"A man is playing a large flute.",
"A man is spreading shreded cheese on a pizza.",
"Three men are playing chess.",
],
"sentence2": [
"An air plane is taking off.",
"A man is playing a flute.",
"A man is spreading shredded cheese on an uncooked pizza.",
"Two men are playing chess.",
],
"label": [5.0, 3.799999952316284, 3.799999952316284, 2.5999999046325684],
"idx": [0, 1, 2, 3],
}
train_dataset = pd.DataFrame(train_data)
dev_data = {
"sentence1": [
"A man is playing the cello.",
"Some men are fighting.",
"A man is smoking.",
"The man is playing the piano.",
],
"sentence2": [
"A man seated is playing the cello.",
"Two men are fighting.",
"A man is skating.",
"The man is playing the guitar.",
],
"label": [4.25, 4.25, 0.5, 1.600000023841858],
"idx": [4, 5, 6, 7],
}
dev_dataset = pd.DataFrame(dev_data)
custom_sent_keys = ["sentence1", "sentence2"]
label_key = "label"