from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification
X, y = make_classification(n_samples=1000, n_features=4,
n_informative=2, n_redundant=0,
random_state=0, shuffle=False)
clf = RandomForestClassifier(max_depth=2, random_state=0)
clf.fit(X, y)
print(clf.feature_importances_)
print(clf.predict([[0, 0, 0, 0]]))
[0.17287856 0.80608704 0.01884792 0.00218648] [1]
/home/momukji/Python/Python/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22. "10 in version 0.20 to 100 in 0.22.", FutureWarning)
# Save Model
import pickle
with open('data/train.pk', 'wb') as f:
pickle.dump(clf, f)
# Load Model
clf = pickle.load(open("data/train.pk", "rb"))
print(clf.predict([[0,0,1,1]]))
>>> import pickle
>>> s = pickle.dumps(clf)
>>> clf2 = pickle.loads(s)
>>> clf2.predict(X[0:1])
array([0])
>>> y[0]
0
import numpy as np
import pandas as pd
from sklearn import datasets
from sklearn.ensemble import RandomForestClassifier
iris = datasets.load_iris()
mapping = dict(zip(np.unique(iris.target), iris.target_names))
mapping
{0: 'setosa', 1: 'versicolor', 2: 'virginica'}
X = pd.DataFrame(iris.data, columns=iris.feature_names)
y = pd.DataFrame(iris.target).replace(mapping)
X.head(3), y.head(3) # Train, Test DataFrame
( sepal length (cm) sepal width (cm) petal length (cm) petal width (cm)
0 5.1 3.5 1.4 0.2
1 4.9 3.0 1.4 0.2
2 4.7 3.2 1.3 0.2,
0
0 setosa
1 setosa
2 setosa)
clf = RandomForestClassifier()
clf.fit(X,y)
/home/momukji/Python/Python/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22. "10 in version 0.20 to 100 in 0.22.", FutureWarning) /home/momukji/Python/Python/lib/python3.6/site-packages/ipykernel_launcher.py:2: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().
RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
max_depth=None, max_features='auto', max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=10,
n_jobs=None, oob_score=False, random_state=None,
verbose=0, warm_start=False)
[0.17287856 0.80608704 0.01884792 0.00218648] [1]
/home/momukji/Python/Python/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22. "10 in version 0.20 to 100 in 0.22.", FutureWarning)
# Model Save & Load
>>> import pickle
>>> s = pickle.dumps(clf)
>>> clf2 = pickle.loads(s)
>>> clf2.predict(X[0:1])
array([0])
>>> y[0]
0