TinyAutoML
Meta - Pipeline for Stat'App project. Only Work for binary classification for now.
Example:
import pandas as pd
import TinyAutoML as tam
from sklearn.datasets import load_breast_cancer
ds = load_breast_cancer()
X = pd.DataFrame(data=ds.data, columns=ds.feature_names)
y = ds.target
cut = int(len(y) * 0.8)
X_train, X_test = X[:cut], X[cut:]
y_train, y_test = y[:cut], y[cut:]
mp = tam.Estimator.MetaPipeline()
mp.fit(X_train, y_train, grid_search=False)
print(mp.classification_report(X_test, y_test))Methods available :
metapipe = tam.Estimator.Metapipeline(model, grid_search)
model = 'orfa' or 'metamodel'
grid_search: bool
.predict(self, X: pd.DataFrame)
.transform(self, X: pd.DataFrame, y=None)
.fit_transform(self, X: pd.DataFrame, y: pd.Series)
.get_scores(self)
.classification_report(self, X: pd.DataFrame, y: pd.Series)
.roc_curve(self,X: pd.DataFrame, y:pd.Series)
