import pandas as pd
df = pd.read_csv('http://bit.ly/kaggletrain', usecols=['Survived', 'Pclass', 'Fare'])
from sklearn.linear_model import LogisticRegression
clf = LogisticRegression()
X = df[['Pclass', 'Fare']]
y = df['Survived']
print(type(X))
print(type(y))
<class 'pandas.core.frame.DataFrame'> <class 'pandas.core.series.Series'>
# there's no need to use X.values or y.values
clf.fit(X, y)
LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True, intercept_scaling=1, l1_ratio=None, max_iter=100, multi_class='auto', n_jobs=None, penalty='l2', random_state=None, solver='lbfgs', tol=0.0001, verbose=0, warm_start=False)
© 2020 Data School. All rights reserved.