[Case Study] Logistic Regression using Python

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

1. from __future__ import print_function
   
2. 
   
3. import sys
   
4. 
   
5. from pyspark import SparkContext
   
6. from pyspark.ml.classification import LogisticRegression
   
7. from pyspark.mllib.evaluation import MulticlassMetrics
   
8. from pyspark.ml.feature import StringIndexer
   
9. from pyspark.sql import SQLContext
   
10. 
    
11. """
    
12. A simple example demonstrating a logistic regression with elastic net regularization Pipeline.
    
13. Run with:
    
14.   bin/spark-submit examples/src/main/python/ml/logistic_regression.py
    
15. """
    
16. 
    
17. if __name__ == "__main__":
    
18. 
    
19.     if len(sys.argv) > 1:
    
20.         print("Usage: logistic_regression", file=sys.stderr)
    
21.         exit(-1)
    
22. 
    
23.     sc = SparkContext(appName="PythonLogisticRegressionExample")
    
24.     sqlContext = SQLContext(sc)
    
25. 
    
26.     # Load the data stored in LIBSVM format as a DataFrame.
    
27.     df = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
    
28. 
    
29.     # Map labels into an indexed column of labels in [0, numLabels)
    
30.     stringIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel")
    
31.     si_model = stringIndexer.fit(df)
    
32.     td = si_model.transform(df)
    
33.     [training, test] = td.randomSplit([0.7, 0.3])
    
34. 
    
35.     lr = LogisticRegression(maxIter=100, regParam=0.3).setLabelCol("indexedLabel")
    
36.     lr.setElasticNetParam(0.8)
    
37. 
    
38.     # Fit the model
    
39.     lrModel = lr.fit(training)
    
40. 
    
41.     predictionAndLabels = lrModel.transform(test).select("prediction", "indexedLabel") \
    
42.         .map(lambda x: (x.prediction, x.indexedLabel))
    
43. 
    
44.     metrics = MulticlassMetrics(predictionAndLabels)
    
45.     print("weighted f-measure %.3f" % metrics.weightedFMeasure())
    
46.     print("precision %s" % metrics.precision())
    
47.     print("recall %s" % metrics.recall())
    
48. 
    
49.     sc.stop()

复制代码

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：regression Case study regressio logistic regress examples elastic python simple future