skitlearn decision tree
from sklearn.datasets import load_iris
from sklearn.model_selection import cross_val_score
from sklearn.tree import DecisionTreeClassifier
clf = DecisionTreeClassifier(random_state=0)
iris = load_iris()
cross_val_score(clf, iris.data, iris.target, cv=10)decision tree
from sklearn.datasets import load_iris
>>> from sklearn import tree
>>> X, y = load_iris(return_X_y=True)
>>> clf = tree.DecisionTreeClassifier()
>>> clf = clf.fit(X, y)Decision tree learning algorithm for classification
# Decision tree learning algorithm for classification
from pyspark.ml.linalg import Vectors
from pyspark.ml.feature import StringIndexer
df = spark.createDataFrame([
(1.0, Vectors.dense(1.0)),
(0.0, Vectors.sparse(1, [], []))], ["label", "features"])
stringIndexer = StringIndexer(inputCol="label", outputCol="indexed")
si_model = stringIndexer.fit(df)
td = si_model.transform(df)
dt = DecisionTreeClassifier(maxDepth=2, labelCol="indexed")
model = dt.fit(td)
model.numNodes
# 3
model.depth
# 1
model.featuresImportances
# SparseVector(1, {0: 1.0})
model.numFeatures
# 1
model.numClasses
# 2
print(model.toDebugString)
# DecisionTreeClassificationModel (uid=...) of depth 1 with 3 nodes...
test0 = spark.createDataFrame([(Vectors.dense(-1.0),)], ["features"])
result = model.transform(test0).head()
result.prediction
# 0.0
result.probability
# DenseVectors([1.0, 0.0])
result.rawPrediction
# DenseVector([1.0, 0.0])
test1 = spark.createDataFrame([Vectors.sparse(1, [0], [1.0]),)], ["features"])
model.transform(test1).head().prediction
# 1.0
dtc_path = temp_path + "/dtc"
dt.save(dtc_path)
dt2 = DecisionTreeClassifier.load(dtc_path)
dt2.getMaxDepth()
# 2
model_path = temp_path + "/dtc_model"
model.save(model_path)
model2 = DecisionTreeClassificationModel.load(model_path)
model.featureImportances == model2.featureImportances
# TrueDecision tree learning algorithm for regression
# Decision tree learning algorithm for regression
from pyspark.ml.linalg import Vectors
df = spark.createDataFrame([
(1.0, Vectors.dense(1.0)),
(0.0, Vectors.sparse(1, [], []))], ["label", "features"])
dt = DecisionTreeRegressor(maxDepth=2, varianceCol="variance")
model = dt.fit(df)
model.depth
# 1
model.numNodes
# 3
model.featureImportances
# SparseVector(1, {0: 1.0}
model.numFeatures
# 1
test0 = spark.createDataFrame([(Vectors.dense(-1.0),)], ["features"])
model.transform(test0).head().prediction
# 0.0
test1 = spark.createDataFrame([(Vectors.sparse(1, [0], [1.0]),)], ["features"])
model.transform(test1).head().prediction
# 1.0
dtr_path = temp_path + "/dtr"
dt.save(dtr_path)
dt2 = DecisionTreeRegressor.load(dtr_path)
dt2.getMaxDepth()
# 2
model_path = temp_path + "/dtr_model"
model.save(model_path)
model2 = DecisionTreeRegressionModel.load(model_path)
model.numNodes == model2.numNodes
# True
model.depth == model2.depth
# True
model.transform(test1).head().variance
# 0.0decision trees
Training Data Set Accuracy: 0.9610705596107056
Training Data F1 Score 0.972027972027972
Validation Mean F1 Score: 0.6348494236272646
Validation Mean Accuracy: 0.7030561269468117Copyright © 2021 Codeinu
Forgot your account's password or having trouble logging into your Account? Don't worry, we'll help you to get back your account. Enter your email address and we'll send you a recovery link to reset your password. If you are experiencing problems resetting your password contact us
