skoot
Skoot is a lightweight python library of machine learning transformer classes that interact with scikit-learn and pandas. Its objective is to expedite data munging and pre-processing tasks that can tend to take up so much of data science practitioners' time. See the documentation for more info.
Note that skoot is the preferred alternative to the now deprecated skutil library
Two minutes to model-readiness
Real world data is nasty. Most data scientists spend the majority of their time tackling data cleansing tasks. With skoot, we can automate away so much of the bespoke hacking solutions that consume data scientists' time.
In this example, we'll examine a common dataset (the adult dataset from the UCI machine learning repo) that requires significant pre-processing.
from skoot.datasets import load_adult_df
from skoot.feature_selection import FeatureFilter
from skoot.decomposition import SelectivePCA
from skoot.preprocessing import DummyEncoder
from skoot.utils.dataframe import get_numeric_columns
from skoot.utils.dataframe import get_categorical_columns
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
# load the dataset with the skoot-native loader & split it
adult = load_adult_df(tgt_name="target")
y = adult.pop("target")
X_train, X_test, y_train, y_test = train_test_split(
adult, y, random_state=42, test_size=0.2)
# get numeric and categorical feature names
num_cols = get_numeric_columns(X_train).columns
obj_cols = get_categorical_columns(X_train).columns
# remove the education-num from the num_cols since we're going to remove it
num_cols = num_cols[~(num_cols == "education-num")]
# build a pipeline
pipe = Pipeline([
# drop out the ordinal level that's otherwise equal to "education"
("dropper", FeatureFilter(cols=["education-num"])),
# decompose the numeric features with PCA
("pca", SelectivePCA(cols=num_cols)),
# dummy encode the categorical features
("dummy", DummyEncoder(cols=obj_cols, handle_unknown="ignore")),
# and a simple classifier class
("clf", RandomForestClassifier(n_estimators=100, random_state=42))
])
pipe.fit(X_train, y_train)
# produce predictions
preds = pipe.predict(X_test)
print("Test accuracy: %.3f" % accuracy_score(y_test, preds))
For more tutorials, check out the documentation.
![[MRG] Mac builds](https://avatars.githubusercontent.com/u/21350310?v=4)
11.6k Jan 02, 2023
10 Oct 22, 2022
0 Jul 05, 2022
35 Jan 02, 2023
652 Jan 03, 2023
7 Nov 09, 2022
10 Apr 04, 2022
240 Dec 26, 2022
37 Oct 24, 2022
1 Mar 17, 2022
1 Oct 22, 2021
6.7k Jan 08, 2023
66 Dec 06, 2022
892 Jan 03, 2023
5.2k Jan 03, 2023
2 Sep 13, 2022
6.7k Jan 07, 2023
720 Dec 25, 2022
6 Jul 06, 2022
6 May 13, 2022