# encoding:utf-8 import os os.environ['HADOOP_HOME'] = 'D:\\system\\hadoop-common-2.6.0-bin-master' from pyspark.sql import SparkSession import pandas as pd spark = SparkSession.builder \ .appName("envTest")\ .getOrCreate() sc = spark.sparkContext data = pd.read_csv("E:\\data\\t_iris.csv",header=None) print(data) print(data[0:2]) # 取前两行数据 # 创建dataFrame data000002 = spark.createDataFrame(data, ["sepal_length","sepal_width","petal_length","petal_width", "iris_class"]) print(data000002.dtypes) print(data000002.take(2)) print(data000002.show(2)) from pyspark.ml.classification import DecisionTreeClassifier from pyspark.ml import Pipeline from Distributed.common import getEvaluationDF from Distributed.common import preProcessing def DT(label_data, label_col, features_col, test_data_pro=0.3, maxdepth=5, impurity="gini"): label_data, prePipel
机器学习pyspark使用决策树算法生成训练模型
最新推荐文章于 2024-08-18 09:56:22 发布
该博客介绍如何使用PySpark的决策树分类器进行机器学习模型训练。通过加载鸢尾花数据集,创建DataFrame,应用预处理,设置模型参数并训练决策树模型,最终评估模型性能并保存模型。
摘要由CSDN通过智能技术生成