Open weixuanfu opened 6 years ago
The codes below can reproduce the warning message:
from tpot import TPOTClassifier
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
import numpy as np
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data.astype(np.float64),
iris.target.astype(np.float64), train_size=0.75, test_size=0.25)
tpot1 = TPOTClassifier(generations=1, population_size=10, verbosity=2)
tpot1.fit(X_train, y_train)
# no warning message during 1st fit()
tpot2 = TPOTClassifier(generations=1, population_size=10, verbosity=2)
tpot2.fit(X_train, y_train)
# warning message shows up during 2nd fit()
Thank you for the nice project!
In this ci test for TPOT with the latest deap (v1.2.2), there are a lot runtimewarning messages as below
It is weird that these warning messages only showed in python3.6 but not in python2.7 on both Windows and Linux. And these warning messages have not happened before with previous version of deap (e.g. 1.0.2). Any suggestions? Thanks.