Decision Tree

Machine Learning with PySpark

Andrew Collier

Data Scientist, Fathom Data

Anatomy of a Decision Tree: Root node

Root node of a decision tree.

Anatomy of a Decision Tree: First split

Decision tree with single split

Anatomy of a Decision Tree: Second split

Decision tree with second split

Anatomy of a Decision Tree: Third split

Decision tree with third split

Classifying cars

Classify cars according to country of manufacture.

+---+----+------+------+----+-----------+----------------------------------+-----+
|cyl|size|mass  |length|rpm |consumption|features                          |label|
+---+----+------+------+----+-----------+----------------------------------+-----+
|6  |3.0 |1451.0|4.775 |5200|9.05       |[6.0,3.0,1451.0,4.775,5200.0,9.05]|1.0  |
|4  |2.2 |1129.0|4.623 |5200|6.53       |[4.0,2.2,1129.0,4.623,5200.0,6.53]|0.0  |
|4  |2.2 |1399.0|4.547 |5600|7.84       |[4.0,2.2,1399.0,4.547,5600.0,7.84]|1.0  |
|4  |1.8 |1147.0|4.343 |6500|7.84       |[4.0,1.8,1147.0,4.343,6500.0,7.84]|0.0  |
|4  |1.6 |1111.0|4.216 |5750|9.05       |[4.0,1.6,1111.0,4.216,5750.0,9.05]|0.0  |
+---+----+------+------+----+-----------+----------------------------------+-----+

label = 0 -> manufactured in the USA
      = 1 -> manufactured elsewhere

Split train/test

Split data into training and testing sets.

# Specify a seed for reproducibility
cars_train, cars_test = cars.randomSplit([0.8, 0.2], seed=23)

Two DataFrames: cars_train and cars_test.

[cars_train.count(), cars_test.count()]

[79, 13]

Build a Decision Tree model

from pyspark.ml.classification import DecisionTreeClassifier

Create a Decision Tree classifier.

tree = DecisionTreeClassifier()

Learn from the training data.

tree_model = tree.fit(cars_train)

Evaluating

Make predictions on the testing data and compare to known values.

prediction = tree_model.transform(cars_test)

+-----+----------+---------------------------------------+
|label|prediction|probability                            |
+-----+----------+---------------------------------------+
|1.0  |0.0       |[0.9615384615384616,0.0384615384615385]|
|1.0  |1.0       |[0.2222222222222222,0.7777777777777778]|
|1.0  |1.0       |[0.2222222222222222,0.7777777777777778]|
|0.0  |0.0       |[0.9615384615384616,0.0384615384615385]|
|1.0  |1.0       |[0.2222222222222222,0.7777777777777778]|
+-----+----------+---------------------------------------+

Confusion matrix

A confusion matrix is a table which describes performance of a model on testing data.

prediction.groupBy("label", "prediction").count().show()

+-----+----------+-----+
|label|prediction|count|
+-----+----------+-----+
|  1.0|       1.0|    8| <- True positive  (TP)
|  0.0|       1.0|    2| <- False positive (FP)
|  1.0|       0.0|    3| <- False negative (FN)
|  0.0|       0.0|    6| <- True negative  (TN)
+-----+----------+-----+

Accuracy = (TN + TP) / (TN + TP + FN + FP) — proportion of correct predictions.

Let's build Decision Trees!

Machine Learning with PySpark