Я пытаюсь построить кривую RO C для модели повышения градиента. Я сталкивался с этим постом, но он не работает для модели GBTclassifier. экстракт pyspark RO C кривая?
Я использую набор данных в блоках данных, и ниже приведен мой код. Выдает следующую ошибку
AttributeError: 'PipelineModel' object has no attribute 'summary'
%fs ls databricks-datasets/adult/adult.data
from pyspark.sql.functions import *
from pyspark.ml.classification import RandomForestClassifier, GBTClassifier
from pyspark.ml.feature import StringIndexer, OneHotEncoderEstimator, VectorAssembler, VectorSlicer
from pyspark.ml import Pipeline
from pyspark.ml.evaluation import BinaryClassificationEvaluator,MulticlassClassificationEvaluator
from pyspark.ml.linalg import Vectors
from pyspark.ml.tuning import ParamGridBuilder, TrainValidationSplit
import pandas as pd
dataset = spark.table("adult")
# spliting the train and test data frames
splits = dataset.randomSplit([0.7, 0.3])
train_df = splits[0]
test_df = splits[1]
def predictions(train_df,
target_col,
):
"""
#Function attributes
dataframe - training df
target - target varibale in the model
"""
# one hot encoding and assembling
encoding_var = [i[0] for i in train_df.dtypes if (i[1]=='string') & (i[0]!=target_col)]
num_var = [i[0] for i in train_df.dtypes if ((i[1]=='int') | (i[1]=='double')) & (i[0]!=target_col)]
string_indexes = [StringIndexer(inputCol = c, outputCol = 'IDX_' + c, handleInvalid = 'keep') for c in encoding_var]
onehot_indexes = [OneHotEncoderEstimator(inputCols = ['IDX_' + c], outputCols = ['OHE_' + c]) for c in encoding_var]
label_indexes = StringIndexer(inputCol = target_col, outputCol = 'label', handleInvalid = 'keep')
assembler = VectorAssembler(inputCols = num_var + ['OHE_' + c for c in encoding_var], outputCol = "features")
gbt = GBTClassifier(featuresCol = 'features', labelCol = 'label',
maxDepth = 5,
maxBins = 45,
maxIter = 20)
pipe = Pipeline(stages = string_indexes + onehot_indexes + [assembler, label_indexes, gbt])
model = pipe.fit(train_df)
return model
gbt_model = predictions(train_df = train_df,
target_col = 'income')
import matplotlib.pyplot as plt
plt.figure(figsize=(5,5))
plt.plot([0, 1], [0, 1], 'r--')
plt.plot(gbt_model.summary.roc.select('FPR').collect(),
gbt_model.summary.roc.select('TPR').collect())
plt.xlabel('FPR')
plt.ylabel('TPR')
plt.show()