Download our e-book of Introduction To Python
Sulochana Kamshetty
3 years ago
import os
import pandas as pd
data=pd.read_csv("./train.csv")
print(data.shape)
print(type(data))
clf = BaggingClassifier(n_estimators=10)
clf.fit(X=X_train, y=y_train)
BaggingClassifier(base_estimator=None, bootstrap=True, bootstrap_features=False,
max_features=1.0, max_samples=1.0, n_estimators=10,
n_jobs=None, oob_score=False, random_state=None, verbose=0,warm_start=False)
from sklearn.tree import DecisionTreeClassifier
param_grid = {
'base_estimator__max_depth' : [1, 2, 3, 4, 5],'max_samples' : [0.05, 0.1, 0.2, 0.5]
}
clf = GridSearchCV(BaggingClassifier(DecisionTreeClassifier(),
n_estimators = 100, max_features = 0.5),param_grid,scoring='accuracy')
%time clf.fit(X_train, y_train)
/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_split.py:1978:
FutureWarning: The default value of cv will change from 3 to 5 in version 0.22.
Specify it explicitly to silence this warning.warnings.warn(CV_WARNING,
FutureWarning)CPU times: user 30.2 s, sys: 588 ms,
total: 30.8 sWall time: 33.1 s
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
import numpy as npimport statistics as statmodel1 = DecisionTreeClassifier()
model2 = KNeighborsClassifier()
model3= LogisticRegression()
metaclassifier=LogisticRegression()
metaclassifier.fit(stack_model_pred_dummy,y_train)