In [2]:
%matplotlib inline
from matplotlib import pyplot as plt
import seaborn
import xgboost
import pandas as pd
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_curve
In [ ]:
import time
from tqdm import tqdm_notebook
for i in tqdm_notebook(range(1000)):
time.sleep(0.1)
In [33]:
X, Y = datasets.make_classification(10000, 30)
pd.DataFrame(X).head(5)
Out[33]:
In [34]:
X_train, X_test, y_train, y_test = train_test_split(X, Y)
clsf = xgboost.XGBClassifier(n_estimators=1000)
clsf.fit(X_train, y_train)
prediction = clsf.predict_proba(X_test)
In [36]:
fpr, tpr, _ = roc_curve(y_test, prediction[:,1])
plt.plot(fpr, tpr)
Out[36]: