python vowpalwabbit regression for big data files with FEARTURES INTERACTION
$10-30 USD
En curso
Publicado hace más de 2 años
$10-30 USD
Pagado a la entrega
python vowpalwabbit regression for big data files with FEARTURES INTERACTION
1 ridge
2 lasso
3 quantile for both ridge and lasso !
FEATURES BOTH CATEGORICAL AND CONTINUES
IMPORTANT to HAVE INTERACTION BETWEEN CATEGORICAL FEARTURES : SECOND ORDER AND THIRED ORDER
like
from vowpalwabbit.sklearn_vw import VW, VWClassifier, VWRegressor
vw_squared = VWRegressor(loss_function='squared' , normalized = True, interactions = 'abc')
but better to use
from vowpalwabbit import pyvw
for big data like
us-used-cars-dataset 9 GB 3ml rows 66 features predict price
[login to view URL]
but start you can from
[login to view URL]
all calculations done in vowpalwabbit python including one hot for categorical data (not scikit learn one hot)
data has both categorical and continues features
code starter
[login to view URL]
[login to view URL]
[login to view URL]
[login to view URL]
[login to view URL]
[login to view URL]:~:text=Use%20chunksize%20to%20read%20a,be%20read%20in%20per%20chunk.
[login to view URL]
[login to view URL]
[login to view URL]
[login to view URL]
[login to view URL]
vw [login to view URL] -f [login to view URL] –binary –passes 20 -c -q ff –sgd –l1
0.00000001 –l2 0.0000001 –learning_rate 0.5 –loss_function logistic
[login to view URL]
test3 <- c("-t", [login to view URL]("test", "train-sets", "[login to view URL]", package="RVowpalWabbit"),
"-f", [login to view URL](tempdir(), "[login to view URL]"),
"--cache_file", [login to view URL](tempdir(), "[login to view URL]"))
also [login to view URL] many example for VW
maybe >>> from [login to view URL] import DFtoVW
>>> import pandas as pd
>>> df = [login to view URL]({"y": [1], "x": [2]})
>>> conv = DFtoVW.from_colnames(y="y", x="x", df=df)
>>> conv.convert_df()
['1 | x:2']