Eric Czech eric-czech

This script verifies that Triton can be built and minimally tested on ARM64 systems, specifically on AWS Graviton2 instances. Instructions:

Create a g5g.xlarge instance using the following AWS CLI command and make sure to add at least 30G storage:

aws ec2 run-instances \
    --instance-type g5g.xlarge \
--image-id ami-02dcfe5d1d39baa4e \

	(
	pd.read_gbq(
	"SELECT pmid, EXTRACT(YEAR from pub_date) AS pub_year FROM `pmdb-bq.pmdb.article` WHERE pub_date IS NOT NULL",
	use_bqstorage_api=True
	)
	.to_parquet("pub_years.parquet")
	)

	playerID,yearID,stint,teamID,lgID,G,AB,R,H,2B,3B,HR,RBI,SB,CS,BB,SO,IBB,HBP,SH,SF,GIDP
	abercda01,1871,1,TRO,NA,1,4,0,0,0,0,0,0,0,0,0,0,,,,,0
	addybo01,1871,1,RC1,NA,25,118,30,32,6,0,0,13,8,1,4,0,,,,,0
	allisar01,1871,1,CL1,NA,29,137,28,40,4,5,0,19,3,1,2,5,,,,,1
	allisdo01,1871,1,WS3,NA,27,133,28,44,10,2,2,27,1,1,0,2,,,,,0
	ansonca01,1871,1,RC1,NA,25,120,29,39,11,3,0,16,6,2,2,1,,,,,0
	armstbo01,1871,1,FW1,NA,12,49,9,11,2,1,0,5,0,1,0,1,,,,,0
	barkeal01,1871,1,RC1,NA,1,4,0,1,0,0,0,2,0,0,1,0,,,,,0
	barnero01,1871,1,BS1,NA,31,157,66,63,10,9,0,34,11,6,13,1,,,,,1
	barrebi01,1871,1,FW1,NA,1,5,1,1,1,0,0,1,0,0,0,0,,,,,0

	playerID,yearID,stint,teamID,lgID,G,AB,R,H,2B,3B,HR,RBI,SB,CS,BB,SO,IBB,HBP,SH,SF,GIDP
	abercda01,1871,1,TRO,NA,1,4,0,0,0,0,0,0,0,0,0,0,,,,,0
	addybo01,1871,1,RC1,NA,25,118,30,32,6,0,0,13,8,1,4,0,,,,,0
	allisar01,1871,1,CL1,NA,29,137,28,40,4,5,0,19,3,1,2,5,,,,,1
	allisdo01,1871,1,WS3,NA,27,133,28,44,10,2,2,27,1,1,0,2,,,,,0
	ansonca01,1871,1,RC1,NA,25,120,29,39,11,3,0,16,6,2,2,1,,,,,0
	armstbo01,1871,1,FW1,NA,12,49,9,11,2,1,0,5,0,1,0,1,,,,,0
	barkeal01,1871,1,RC1,NA,1,4,0,1,0,0,0,2,0,0,1,0,,,,,0
	barnero01,1871,1,BS1,NA,31,157,66,63,10,9,0,34,11,6,13,1,,,,,1
	barrebi01,1871,1,FW1,NA,1,5,1,1,1,0,0,1,0,0,0,0,,,,,0

	def get_clustered_order(df: pd.DataFrame, metric: str='euclidean', method: str='average') -> pd.DataFrame:
	from scipy.cluster.hierarchy import linkage, leaves_list
	return leaves_list(linkage(df, metric=metric, method=method))

	def get_clustered_dataframe(df: pd.DataFrame, fill_value: Any=None, **kwargs) -> pd.DataFrame:
	dfs = df if fill_value is None else df.fillna(fill_value)
	return df.iloc[get_clustered_order(dfs, kwargs), get_clustered_order(dfs.T, kwargs)]

	import plotly.express as px
	px.imshow(get_clustered_dataframe(df))